diff options
Diffstat (limited to 'drivers/gpu/drm/msm')
65 files changed, 1761 insertions, 1079 deletions
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c index 00e1afd46b81..44df6410bce1 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c @@ -913,6 +913,11 @@ static const struct adreno_info a6xx_gpus[] = { { /* sentinel */ }, }, }, + .speedbins = ADRENO_SPEEDBINS( + { 0, 0 }, + { 185, 0 }, + { 127, 1 }, + ), }, { .chip_ids = ADRENO_CHIP_IDS( 0x06030001, @@ -1024,6 +1029,11 @@ static const struct adreno_info a6xx_gpus[] = { .gmu_cgc_mode = 0x00020200, .prim_fifo_threshold = 0x00300200, }, + .speedbins = ADRENO_SPEEDBINS( + { 0, 0 }, + { 169, 0 }, + { 113, 1 }, + ), }, { .chip_ids = ADRENO_CHIP_IDS(0x06030500), .family = ADRENO_6XX_GEN4, @@ -1343,6 +1353,69 @@ static const uint32_t a7xx_pwrup_reglist_regs[] = { DECLARE_ADRENO_REGLIST_LIST(a7xx_pwrup_reglist); +/* Applicable for X185, A750 */ +static const u32 a750_ifpc_reglist_regs[] = { + REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(0), + REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(1), + REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(2), + REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(3), + REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(4), + REG_A6XX_TPL1_NC_MODE_CNTL, + REG_A6XX_SP_NC_MODE_CNTL, + REG_A6XX_CP_DBG_ECO_CNTL, + REG_A6XX_CP_PROTECT_CNTL, + REG_A6XX_CP_PROTECT(0), + REG_A6XX_CP_PROTECT(1), + REG_A6XX_CP_PROTECT(2), + REG_A6XX_CP_PROTECT(3), + REG_A6XX_CP_PROTECT(4), + REG_A6XX_CP_PROTECT(5), + REG_A6XX_CP_PROTECT(6), + REG_A6XX_CP_PROTECT(7), + REG_A6XX_CP_PROTECT(8), + REG_A6XX_CP_PROTECT(9), + REG_A6XX_CP_PROTECT(10), + REG_A6XX_CP_PROTECT(11), + REG_A6XX_CP_PROTECT(12), + REG_A6XX_CP_PROTECT(13), + REG_A6XX_CP_PROTECT(14), + REG_A6XX_CP_PROTECT(15), + REG_A6XX_CP_PROTECT(16), + REG_A6XX_CP_PROTECT(17), + REG_A6XX_CP_PROTECT(18), + REG_A6XX_CP_PROTECT(19), + REG_A6XX_CP_PROTECT(20), + REG_A6XX_CP_PROTECT(21), + REG_A6XX_CP_PROTECT(22), + REG_A6XX_CP_PROTECT(23), + REG_A6XX_CP_PROTECT(24), + REG_A6XX_CP_PROTECT(25), + REG_A6XX_CP_PROTECT(26), + REG_A6XX_CP_PROTECT(27), + REG_A6XX_CP_PROTECT(28), + REG_A6XX_CP_PROTECT(29), + REG_A6XX_CP_PROTECT(30), + REG_A6XX_CP_PROTECT(31), + REG_A6XX_CP_PROTECT(32), + REG_A6XX_CP_PROTECT(33), + REG_A6XX_CP_PROTECT(34), + REG_A6XX_CP_PROTECT(35), + REG_A6XX_CP_PROTECT(36), + REG_A6XX_CP_PROTECT(37), + REG_A6XX_CP_PROTECT(38), + REG_A6XX_CP_PROTECT(39), + REG_A6XX_CP_PROTECT(40), + REG_A6XX_CP_PROTECT(41), + REG_A6XX_CP_PROTECT(42), + REG_A6XX_CP_PROTECT(43), + REG_A6XX_CP_PROTECT(44), + REG_A6XX_CP_PROTECT(45), + REG_A6XX_CP_PROTECT(46), + REG_A6XX_CP_PROTECT(47), +}; + +DECLARE_ADRENO_REGLIST_LIST(a750_ifpc_reglist); + static const struct adreno_info a7xx_gpus[] = { { .chip_ids = ADRENO_CHIP_IDS(0x07000200), @@ -1432,14 +1505,27 @@ static const struct adreno_info a7xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV | - ADRENO_QUIRK_PREEMPTION, + ADRENO_QUIRK_PREEMPTION | + ADRENO_QUIRK_IFPC, .init = a6xx_gpu_init, .a6xx = &(const struct a6xx_info) { .hwcg = a740_hwcg, .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, + .ifpc_reglist = &a750_ifpc_reglist, .gmu_chipid = 0x7050001, .gmu_cgc_mode = 0x00020202, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(3), + .perfmode_bw = 16500000, + }, + { /* sentinel */ }, + }, }, .preempt_record_size = 4192 * SZ_1K, .speedbins = ADRENO_SPEEDBINS( @@ -1460,12 +1546,14 @@ static const struct adreno_info a7xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV | - ADRENO_QUIRK_PREEMPTION, + ADRENO_QUIRK_PREEMPTION | + ADRENO_QUIRK_IFPC, .init = a6xx_gpu_init, .zapfw = "gen70900_zap.mbn", .a6xx = &(const struct a6xx_info) { .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, + .ifpc_reglist = &a750_ifpc_reglist, .gmu_chipid = 0x7090100, .gmu_cgc_mode = 0x00020202, .bcms = (const struct a6xx_bcm[]) { diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 28e6705c6da6..fc62fef2fed8 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -93,14 +93,25 @@ bool a6xx_gmu_sptprac_is_on(struct a6xx_gmu *gmu) /* Check to see if the GX rail is still powered */ bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu) { + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; u32 val; /* This can be called from gpu state code so make sure GMU is valid */ if (!gmu->initialized) return false; + /* If GMU is absent, then GX power domain is ON as long as GPU is in active state */ + if (adreno_has_gmu_wrapper(adreno_gpu)) + return true; + val = gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS); + if (adreno_is_a7xx(adreno_gpu)) + return !(val & + (A7XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_GDSC_POWER_OFF | + A7XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_CLK_OFF)); + return !(val & (A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_GDSC_POWER_OFF | A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_CLK_OFF)); @@ -272,6 +283,8 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu) if (ret) DRM_DEV_ERROR(gmu->dev, "GMU firmware initialization timed out\n"); + set_bit(GMU_STATUS_FW_START, &gmu->status); + return ret; } @@ -403,7 +416,10 @@ int a6xx_sptprac_enable(struct a6xx_gmu *gmu) int ret; u32 val; - if (!gmu->legacy) + WARN_ON(!gmu->legacy); + + /* Nothing to do if GMU does the power management */ + if (gmu->idle_level > GMU_IDLE_STATE_ACTIVE) return 0; gmu_write(gmu, REG_A6XX_GMU_GX_SPTPRAC_POWER_CONTROL, 0x778000); @@ -518,6 +534,9 @@ static int a6xx_rpmh_start(struct a6xx_gmu *gmu) int ret; u32 val; + if (!test_and_clear_bit(GMU_STATUS_PDC_SLEEP, &gmu->status)) + return 0; + gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, BIT(1)); ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_RSCC_CONTROL_ACK, val, @@ -545,6 +564,9 @@ static void a6xx_rpmh_stop(struct a6xx_gmu *gmu) int ret; u32 val; + if (test_and_clear_bit(GMU_STATUS_FW_START, &gmu->status)) + return; + gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 1); ret = gmu_poll_timeout_rscc(gmu, REG_A6XX_GPU_RSCC_RSC_STATUS0_DRV0, @@ -553,6 +575,8 @@ static void a6xx_rpmh_stop(struct a6xx_gmu *gmu) DRM_DEV_ERROR(gmu->dev, "Unable to power off the GPU RSC\n"); gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 0); + + set_bit(GMU_STATUS_PDC_SLEEP, &gmu->status); } static inline void pdc_write(void __iomem *ptr, u32 offset, u32 value) @@ -681,8 +705,6 @@ setup_pdc: /* ensure no writes happen before the uCode is fully written */ wmb(); - a6xx_rpmh_stop(gmu); - err: if (!IS_ERR_OR_NULL(pdcptr)) iounmap(pdcptr); @@ -842,19 +864,15 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) else gmu_write(gmu, REG_A6XX_GMU_GENERAL_7, 1); - if (state == GMU_WARM_BOOT) { - ret = a6xx_rpmh_start(gmu); - if (ret) - return ret; - } else { + ret = a6xx_rpmh_start(gmu); + if (ret) + return ret; + + if (state == GMU_COLD_BOOT) { if (WARN(!adreno_gpu->fw[ADRENO_FW_GMU], "GMU firmware is not loaded\n")) return -ENOENT; - ret = a6xx_rpmh_start(gmu); - if (ret) - return ret; - ret = a6xx_gmu_fw_load(gmu); if (ret) return ret; @@ -925,10 +943,7 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) ret = a6xx_gmu_gfx_rail_on(gmu); if (ret) return ret; - } - /* Enable SPTP_PC if the CPU is responsible for it */ - if (gmu->idle_level < GMU_IDLE_STATE_SPTP) { ret = a6xx_sptprac_enable(gmu); if (ret) return ret; @@ -980,6 +995,22 @@ static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu) val, (val & 1), 100, 10000); 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)) + return; + + gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS4_DRV0_STATUS + seqmem_off, + val, (val & 1), 100, 10000); + gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS5_DRV0_STATUS + seqmem_off, + val, (val & 1), 100, 10000); + gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS6_DRV0_STATUS + seqmem_off, + val, (val & 1), 100, 10000); + gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS7_DRV0_STATUS + seqmem_off, + val, (val & 1), 100, 1000); + gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS8_DRV0_STATUS + seqmem_off, + val, (val & 1), 100, 10000); + gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS9_DRV0_STATUS + seqmem_off, + val, (val & 1), 100, 1000); } /* Force the GMU off in case it isn't responsive */ @@ -1023,6 +1054,8 @@ static void a6xx_gmu_force_off(struct a6xx_gmu *gmu) /* Reset GPU core blocks */ a6xx_gpu_sw_reset(gpu, true); + + a6xx_rpmh_stop(gmu); } static void a6xx_gmu_set_initial_freq(struct msm_gpu *gpu, struct a6xx_gmu *gmu) @@ -1128,6 +1161,11 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) /* Set the GPU to the current freq */ a6xx_gmu_set_initial_freq(gpu, gmu); + if (refcount_read(&gpu->sysprof_active) > 1) { + ret = a6xx_gmu_set_oob(gmu, GMU_OOB_PERFCOUNTER_SET); + if (!ret) + set_bit(GMU_STATUS_OOB_PERF_SET, &gmu->status); + } out: /* On failure, shut down the GMU to leave it in a good state */ if (ret) { @@ -1175,6 +1213,9 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); } + if (test_and_clear_bit(GMU_STATUS_OOB_PERF_SET, &gmu->status)) + a6xx_gmu_clear_oob(gmu, GMU_OOB_PERFCOUNTER_SET); + ret = a6xx_gmu_wait_for_idle(gmu); /* If the GMU isn't responding assume it is hung */ @@ -1318,8 +1359,6 @@ static int a6xx_gmu_memory_probe(struct drm_device *drm, struct a6xx_gmu *gmu) struct msm_mmu *mmu; mmu = msm_iommu_new(gmu->dev, 0); - if (!mmu) - return -ENODEV; if (IS_ERR(mmu)) return PTR_ERR(mmu); @@ -1692,6 +1731,7 @@ static int a6xx_gmu_acd_probe(struct a6xx_gmu *gmu) u32 val; freq = gmu->gpu_freqs[i]; + /* This is unlikely to fail because we are passing back a known freq */ opp = dev_pm_opp_find_freq_exact(&gpu->pdev->dev, freq, true); np = dev_pm_opp_get_of_node(opp); @@ -1790,6 +1830,35 @@ static int a6xx_gmu_get_irq(struct a6xx_gmu *gmu, struct platform_device *pdev, return irq; } +void a6xx_gmu_sysprof_setup(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 sysprof_active; + + /* Nothing to do if GPU is suspended. We will handle this during GMU resume */ + if (!pm_runtime_get_if_active(&gpu->pdev->dev)) + return; + + mutex_lock(&gmu->lock); + + sysprof_active = refcount_read(&gpu->sysprof_active); + + /* + * 'Perfcounter select' register values are lost during IFPC collapse. To avoid that, + * use the currently unused perfcounter oob vote to block IFPC when sysprof is active + */ + if ((sysprof_active > 1) && !test_and_set_bit(GMU_STATUS_OOB_PERF_SET, &gmu->status)) + a6xx_gmu_set_oob(gmu, GMU_OOB_PERFCOUNTER_SET); + else if ((sysprof_active == 1) && test_and_clear_bit(GMU_STATUS_OOB_PERF_SET, &gmu->status)) + a6xx_gmu_clear_oob(gmu, GMU_OOB_PERFCOUNTER_SET); + + mutex_unlock(&gmu->lock); + + pm_runtime_put(&gpu->pdev->dev); +} + void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu) { struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; @@ -1932,8 +2001,9 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) if (ret) return ret; - /* Fow now, don't do anything fancy until we get our feet under us */ - gmu->idle_level = GMU_IDLE_STATE_ACTIVE; + /* Set GMU idle level */ + gmu->idle_level = (adreno_gpu->info->quirks & ADRENO_QUIRK_IFPC) ? + GMU_IDLE_STATE_IFPC : GMU_IDLE_STATE_ACTIVE; pm_runtime_enable(gmu->dev); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h index d1ce11131ba6..06cfc294016f 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h @@ -50,6 +50,9 @@ struct a6xx_bcm { /* The GMU does not do any idle state management */ #define GMU_IDLE_STATE_ACTIVE 0 +/* Unknown power state. Not exposed by the firmware. For documentation purpose only */ +#define GMU_IDLE_STATE_RESERVED 1 + /* The GMU manages SPTP power collapse */ #define GMU_IDLE_STATE_SPTP 2 @@ -117,6 +120,14 @@ struct a6xx_gmu { struct qmp *qmp; struct a6xx_hfi_msg_bw_table *bw_table; + +/* To check if we can trigger sleep seq at PDC. Cleared in a6xx_rpmh_stop() */ +#define GMU_STATUS_FW_START 0 +/* To track if PDC sleep seq was done */ +#define GMU_STATUS_PDC_SLEEP 1 +/* To track Perfcounter OOB set status */ +#define GMU_STATUS_OOB_PERF_SET 2 + unsigned long status; }; static inline u32 gmu_read(struct a6xx_gmu *gmu, u32 offset) @@ -158,6 +169,9 @@ static inline u64 gmu_read64(struct a6xx_gmu *gmu, u32 lo, u32 hi) #define gmu_poll_timeout(gmu, addr, val, cond, interval, timeout) \ readl_poll_timeout((gmu)->mmio + ((addr) << 2), 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, \ + 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 45dd5fd1c2bf..b8f8ae940b55 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -16,6 +16,97 @@ #define GPU_PAS_ID 13 +static u64 read_gmu_ao_counter(struct a6xx_gpu *a6xx_gpu) +{ + u64 count_hi, count_lo, temp; + + do { + count_hi = gmu_read(&a6xx_gpu->gmu, REG_A6XX_GMU_ALWAYS_ON_COUNTER_H); + count_lo = gmu_read(&a6xx_gpu->gmu, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L); + temp = gmu_read(&a6xx_gpu->gmu, REG_A6XX_GMU_ALWAYS_ON_COUNTER_H); + } while (unlikely(count_hi != temp)); + + return (count_hi << 32) | count_lo; +} + +static bool fence_status_check(struct msm_gpu *gpu, u32 offset, u32 value, u32 status, u32 mask) +{ + /* Success if !writedropped0/1 */ + if (!(status & mask)) + return true; + + udelay(10); + + /* Try to update fenced register again */ + gpu_write(gpu, offset, value); + + /* We can't do a posted write here because the power domain could be + * in collapse state. So use the heaviest barrier instead + */ + mb(); + return false; +} + +static int fenced_write(struct a6xx_gpu *a6xx_gpu, u32 offset, u32 value, u32 mask) +{ + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + u32 status; + + gpu_write(gpu, offset, value); + + /* Nothing else to be done in the case of no-GMU */ + if (adreno_has_gmu_wrapper(adreno_gpu)) + return 0; + + /* We can't do a posted write here because the power domain could be + * in collapse state. So use the heaviest barrier instead + */ + mb(); + + if (!gmu_poll_timeout(gmu, REG_A6XX_GMU_AHB_FENCE_STATUS, status, + fence_status_check(gpu, offset, value, status, mask), 0, 1000)) + return 0; + + /* Try again for another 1ms before failing */ + gpu_write(gpu, offset, value); + mb(); + + if (!gmu_poll_timeout(gmu, REG_A6XX_GMU_AHB_FENCE_STATUS, status, + fence_status_check(gpu, offset, value, status, mask), 0, 1000)) { + /* + * The 'delay' warning is here because the pause to print this + * warning will allow gpu to move to power collapse which + * defeats the purpose of continuous polling for 2 ms + */ + dev_err_ratelimited(gmu->dev, "delay in fenced register write (0x%x)\n", + offset); + return 0; + } + + dev_err_ratelimited(gmu->dev, "fenced register write (0x%x) fail\n", + offset); + + return -ETIMEDOUT; +} + +int a6xx_fenced_write(struct a6xx_gpu *a6xx_gpu, u32 offset, u64 value, u32 mask, bool is_64b) +{ + int ret; + + ret = fenced_write(a6xx_gpu, offset, lower_32_bits(value), mask); + if (ret) + return ret; + + if (!is_64b) + return 0; + + ret = fenced_write(a6xx_gpu, offset + 1, upper_32_bits(value), mask); + + return ret; +} + static inline bool _a6xx_check_idle(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -86,7 +177,7 @@ static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *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); + a6xx_fenced_write(a6xx_gpu, REG_A6XX_CP_RB_WPTR, wptr, BIT(0), false); else ring->restore_wptr = true; } else { @@ -173,8 +264,8 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, * Needed for preemption */ OUT_PKT7(ring, CP_MEM_WRITE, 5); - OUT_RING(ring, CP_MEM_WRITE_0_ADDR_LO(lower_32_bits(memptr))); - OUT_RING(ring, CP_MEM_WRITE_1_ADDR_HI(upper_32_bits(memptr))); + OUT_RING(ring, A5XX_CP_MEM_WRITE_ADDR_LO(lower_32_bits(memptr))); + OUT_RING(ring, A5XX_CP_MEM_WRITE_ADDR_HI(upper_32_bits(memptr))); OUT_RING(ring, lower_32_bits(ttbr)); OUT_RING(ring, upper_32_bits(ttbr)); OUT_RING(ring, ctx->seqno); @@ -204,9 +295,9 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, */ 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_1_POLL_ADDR_LO( + OUT_RING(ring, CP_WAIT_REG_MEM_POLL_ADDR_LO( REG_A6XX_RBBM_PERFCTR_SRAM_INIT_STATUS)); - OUT_RING(ring, CP_WAIT_REG_MEM_2_POLL_ADDR_HI(0)); + 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)); @@ -298,8 +389,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence))); OUT_RING(ring, submit->seqno); - trace_msm_gpu_submit_flush(submit, - gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER)); + trace_msm_gpu_submit_flush(submit, read_gmu_ao_counter(a6xx_gpu)); a6xx_flush(gpu, ring); } @@ -499,8 +589,7 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) } - trace_msm_gpu_submit_flush(submit, - gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER)); + trace_msm_gpu_submit_flush(submit, read_gmu_ao_counter(a6xx_gpu)); a6xx_flush(gpu, ring); @@ -739,11 +828,10 @@ static void a7xx_patch_pwrup_reglist(struct msm_gpu *gpu) u32 *dest = (u32 *)&lock->regs[0]; int i; - reglist = adreno_gpu->info->a6xx->pwrup_reglist; - lock->gpu_req = lock->cpu_req = lock->turn = 0; - lock->ifpc_list_len = 0; - lock->preemption_list_len = reglist->count; + + reglist = adreno_gpu->info->a6xx->ifpc_reglist; + lock->ifpc_list_len = reglist->count; /* * For each entry in each of the lists, write the offset and the current @@ -754,6 +842,14 @@ static void a7xx_patch_pwrup_reglist(struct msm_gpu *gpu) *dest++ = gpu_read(gpu, reglist->regs[i]); } + reglist = adreno_gpu->info->a6xx->pwrup_reglist; + lock->preemption_list_len = reglist->count; + + for (i = 0; i < reglist->count; i++) { + *dest++ = reglist->regs[i]; + *dest++ = gpu_read(gpu, reglist->regs[i]); + } + /* * The overall register list is composed of * 1. Static IFPC-only registers @@ -1241,14 +1337,14 @@ static int hw_init(struct msm_gpu *gpu) /* Set weights for bicubic filtering */ if (adreno_is_a650_family(adreno_gpu) || adreno_is_x185(adreno_gpu)) { - gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_0, 0); - gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_1, + gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(0), 0); + gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(1), 0x3fe05ff4); - gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_2, + gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(2), 0x3fa0ebee); - gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_3, + gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(3), 0x3f5193ed); - gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_4, + gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(4), 0x3f0243f0); } @@ -1448,21 +1544,25 @@ static void a6xx_recover(struct msm_gpu *gpu) adreno_dump_info(gpu); - 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 (a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) { + /* 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); + if (hang_debug) + a6xx_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_A6XX_CP_SQE_CNTL, 3); + a6xx_gpu->hung = true; pm_runtime_dont_use_autosuspend(&gpu->pdev->dev); @@ -1693,8 +1793,6 @@ static void a6xx_cp_hw_err_irq(struct msm_gpu *gpu) static void a6xx_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); /* @@ -1706,13 +1804,6 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu) if (gpu_read(gpu, REG_A6XX_RBBM_STATUS3) & A6XX_RBBM_STATUS3_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 rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x\n", ring ? ring->id : -1, ring ? ring->fctx->last_fence : 0, @@ -1727,6 +1818,9 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu) /* Turn off the hangcheck timer to keep it from bothering us */ timer_delete(&gpu->hangcheck_timer); + /* Turn off interrupts to avoid triggering recovery again */ + gpu_write(gpu, REG_A6XX_RBBM_INT_0_MASK, 0); + kthread_queue_work(gpu->worker, &gpu->recover_work); } @@ -1751,9 +1845,49 @@ static void a7xx_sw_fuse_violation_irq(struct msm_gpu *gpu) } } +static void a6xx_gpu_keepalive_vote(struct msm_gpu *gpu, bool on) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + if (adreno_has_gmu_wrapper(adreno_gpu)) + return; + + gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, on); +} + +static int irq_poll_fence(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; + u32 status; + + if (adreno_has_gmu_wrapper(adreno_gpu)) + return 0; + + if (gmu_poll_timeout_atomic(gmu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, status, !status, 1, 100)) { + u32 rbbm_unmasked = gmu_read(gmu, REG_A6XX_GMU_RBBM_INT_UNMASKED_STATUS); + + dev_err_ratelimited(&gpu->pdev->dev, + "irq fence poll timeout, fence_ctrl=0x%x, unmasked_status=0x%x\n", + status, rbbm_unmasked); + return -ETIMEDOUT; + } + + return 0; +} + static irqreturn_t a6xx_irq(struct msm_gpu *gpu) { struct msm_drm_private *priv = gpu->dev->dev_private; + + /* Set keepalive vote to avoid power collapse after RBBM_INT_0_STATUS is read */ + a6xx_gpu_keepalive_vote(gpu, true); + + if (irq_poll_fence(gpu)) + goto done; + u32 status = gpu_read(gpu, REG_A6XX_RBBM_INT_0_STATUS); gpu_write(gpu, REG_A6XX_RBBM_INT_CLEAR_CMD, status); @@ -1790,6 +1924,9 @@ static irqreturn_t a6xx_irq(struct msm_gpu *gpu) if (status & A6XX_RBBM_INT_0_MASK_CP_SW) a6xx_preempt_irq(gpu); +done: + a6xx_gpu_keepalive_vote(gpu, false); + return IRQ_HANDLED; } @@ -2179,16 +2316,7 @@ 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); - 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_A6XX_CP_ALWAYS_ON_COUNTER); - - a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); - - mutex_unlock(&a6xx_gpu->gmu.lock); + *value = read_gmu_ao_counter(a6xx_gpu); return 0; } @@ -2298,18 +2426,36 @@ static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami) return a6xx_gpu->shadow[ring->id]; + /* + * This is true only on an A6XX_GEN1 with GMU, has IFPC enabled and a super old SQE firmware + * without 'whereami' support + */ + WARN_ONCE((to_adreno_gpu(gpu)->info->quirks & ADRENO_QUIRK_IFPC), + "Can't read CP_RB_RPTR register reliably\n"); + return ring->memptrs->rptr = gpu_read(gpu, REG_A6XX_CP_RB_RPTR); } static bool a6xx_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring) { - struct msm_cp_state cp_state = { + struct msm_cp_state cp_state; + bool progress; + + /* + * With IFPC, KMD doesn't know whether GX power domain is collapsed + * or not. So, we can't blindly read the below registers in GX domain. + * Lets trust the hang detection in HW and lie to the caller that + * there was progress. + */ + if (to_adreno_gpu(gpu)->info->quirks & ADRENO_QUIRK_IFPC) + return true; + + cp_state = (struct msm_cp_state) { .ib1_base = gpu_read64(gpu, REG_A6XX_CP_IB1_BASE), .ib2_base = gpu_read64(gpu, REG_A6XX_CP_IB2_BASE), .ib1_rem = gpu_read(gpu, REG_A6XX_CP_IB1_REM_SIZE), .ib2_rem = gpu_read(gpu, REG_A6XX_CP_IB2_REM_SIZE), }; - bool progress; /* * Adjust the remaining data to account for what has already been @@ -2408,6 +2554,7 @@ 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, }, .get_timestamp = a6xx_gmu_get_timestamp, }; @@ -2468,6 +2615,7 @@ 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, }, .get_timestamp = a6xx_gmu_get_timestamp, }; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index 6e71f617fc3d..0b17d36c36a9 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -45,6 +45,7 @@ struct a6xx_info { const struct adreno_reglist *hwcg; const struct adreno_protect *protect; const struct adreno_reglist_list *pwrup_reglist; + const struct adreno_reglist_list *ifpc_reglist; u32 gmu_chipid; u32 gmu_cgc_mode; u32 prim_fifo_threshold; @@ -254,6 +255,7 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state); int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node); int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node); void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu); +void a6xx_gmu_sysprof_setup(struct msm_gpu *gpu); void a6xx_preempt_init(struct msm_gpu *gpu); void a6xx_preempt_hw_init(struct msm_gpu *gpu); @@ -295,5 +297,6 @@ 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); #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 faca2a0243ab..4c7f3c642f6a 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -11,7 +11,7 @@ static const unsigned int *gen7_0_0_external_core_regs[] __always_unused; static const unsigned int *gen7_2_0_external_core_regs[] __always_unused; static const unsigned int *gen7_9_0_external_core_regs[] __always_unused; -static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused; +static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused; static const u32 gen7_9_0_cx_debugbus_blocks[] __always_unused; #include "adreno_gen7_0_0_snapshot.h" @@ -174,8 +174,15 @@ static int a6xx_crashdumper_run(struct msm_gpu *gpu, static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset, u32 *data) { - u32 reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) | - A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block); + u32 reg; + + if (to_adreno_gpu(gpu)->info->family >= ADRENO_7XX_GEN1) { + reg = A7XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) | + A7XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block); + } else { + reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) | + A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block); + } gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_A, reg); gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_B, reg); @@ -198,11 +205,18 @@ static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset, readl((ptr) + ((offset) << 2)) /* read a value from the CX debug bus */ -static int cx_debugbus_read(void __iomem *cxdbg, u32 block, u32 offset, +static int cx_debugbus_read(struct msm_gpu *gpu, void __iomem *cxdbg, u32 block, u32 offset, u32 *data) { - u32 reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | - A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block); + u32 reg; + + if (to_adreno_gpu(gpu)->info->family >= ADRENO_7XX_GEN1) { + reg = A7XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | + A7XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block); + } else { + reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | + A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block); + } cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_A, reg); cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_B, reg); @@ -315,7 +329,8 @@ static void a6xx_get_debugbus_block(struct msm_gpu *gpu, ptr += debugbus_read(gpu, block->id, i, ptr); } -static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg, +static void a6xx_get_cx_debugbus_block(struct msm_gpu *gpu, + void __iomem *cxdbg, struct a6xx_gpu_state *a6xx_state, const struct a6xx_debugbus_block *block, struct a6xx_gpu_state_obj *obj) @@ -330,7 +345,7 @@ static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg, obj->handle = block; for (ptr = obj->data, i = 0; i < block->count; i++) - ptr += cx_debugbus_read(cxdbg, block->id, i, ptr); + ptr += cx_debugbus_read(gpu, cxdbg, block->id, i, ptr); } static void a6xx_get_debugbus_blocks(struct msm_gpu *gpu, @@ -423,8 +438,9 @@ static void a7xx_get_debugbus_blocks(struct msm_gpu *gpu, a6xx_state, &a7xx_debugbus_blocks[gbif_debugbus_blocks[i]], &a6xx_state->debugbus[i + debugbus_blocks_count]); } - } + a6xx_state->nr_debugbus = total_debugbus_blocks; + } } static void a6xx_get_debugbus(struct msm_gpu *gpu, @@ -526,7 +542,8 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu, int i; for (i = 0; i < nr_cx_debugbus_blocks; i++) - a6xx_get_cx_debugbus_block(cxdbg, + a6xx_get_cx_debugbus_block(gpu, + cxdbg, a6xx_state, &cx_debugbus_blocks[i], &a6xx_state->cx_debugbus[i]); @@ -759,15 +776,15 @@ static void a7xx_get_cluster(struct msm_gpu *gpu, size_t datasize; int i, regcount = 0; - /* Some clusters need a selector register to be programmed too */ - if (cluster->sel) - in += CRASHDUMP_WRITE(in, cluster->sel->cd_reg, cluster->sel->val); - in += CRASHDUMP_WRITE(in, REG_A7XX_CP_APERTURE_CNTL_CD, A7XX_CP_APERTURE_CNTL_CD_PIPE(cluster->pipe_id) | A7XX_CP_APERTURE_CNTL_CD_CLUSTER(cluster->cluster_id) | A7XX_CP_APERTURE_CNTL_CD_CONTEXT(cluster->context_id)); + /* Some clusters need a selector register to be programmed too */ + if (cluster->sel) + in += CRASHDUMP_WRITE(in, cluster->sel->cd_reg, cluster->sel->val); + for (i = 0; cluster->regs[i] != UINT_MAX; i += 2) { int count = RANGE(cluster->regs, i); @@ -1569,8 +1586,7 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu) struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); struct a6xx_gpu_state *a6xx_state = kzalloc(sizeof(*a6xx_state), GFP_KERNEL); - bool stalled = !!(gpu_read(gpu, REG_A6XX_RBBM_STATUS3) & - A6XX_RBBM_STATUS3_SMMU_STALLED_ON_FAULT); + bool stalled; if (!a6xx_state) return ERR_PTR(-ENOMEM); @@ -1591,15 +1607,20 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu) } /* If GX isn't on the rest of the data isn't going to be accessible */ - if (!adreno_has_gmu_wrapper(adreno_gpu) && !a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) + if (!a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) return &a6xx_state->base; + /* Halt SQE first */ + gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3); + /* Get the banks of indexed registers */ if (adreno_is_a7xx(adreno_gpu)) a7xx_get_indexed_registers(gpu, a6xx_state); else a6xx_get_indexed_registers(gpu, a6xx_state); + stalled = !!(gpu_read(gpu, REG_A6XX_RBBM_STATUS3) & + A6XX_RBBM_STATUS3_SMMU_STALLED_ON_FAULT); /* * Try to initialize the crashdumper, if we are not dumping state * with the SMMU stalled. The crashdumper needs memory access to @@ -1796,6 +1817,7 @@ static void a7xx_show_shader(struct a6xx_gpu_state_obj *obj, print_name(p, " - type: ", a7xx_statetype_names[block->statetype]); print_name(p, " - pipe: ", a7xx_pipe_names[block->pipeid]); + drm_printf(p, " - location: %d\n", block->location); for (i = 0; i < block->num_sps; i++) { drm_printf(p, " - sp: %d\n", i); @@ -1873,6 +1895,7 @@ static void a7xx_show_dbgahb_cluster(struct a6xx_gpu_state_obj *obj, print_name(p, " - pipe: ", a7xx_pipe_names[dbgahb->pipe_id]); print_name(p, " - cluster-name: ", a7xx_cluster_names[dbgahb->cluster_id]); drm_printf(p, " - context: %d\n", dbgahb->context_id); + drm_printf(p, " - location: %d\n", dbgahb->location_id); a7xx_show_registers_indented(dbgahb->regs, obj->data, p, 4); } } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index 95d93ac6812a..1c18499b60bb 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -419,47 +419,47 @@ static const struct a6xx_indexed_registers a6xx_indexed_reglist[] = { REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL }, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + { "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR, + { "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR, REG_A6XX_CP_ROQ_DBG_DATA, 0, a6xx_get_cp_roq_size}, }; static const struct a6xx_indexed_registers a7xx_indexed_reglist[] = { { "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR, - REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL }, + REG_A6XX_CP_SQE_STAT_DATA, 0x40, NULL }, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + { "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR, - REG_A7XX_CP_BV_SQE_STAT_DATA, 0x33, NULL }, - { "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR, + { "CP_BV_SQE_STAT", REG_A7XX_CP_BV_SQE_STAT_ADDR, + REG_A7XX_CP_BV_SQE_STAT_DATA, 0x40, NULL }, + { "CP_BV_DRAW_STATE", REG_A7XX_CP_BV_DRAW_STATE_ADDR, REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, + { "CP_BV_SQE_UCODE_DBG", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR, - REG_A7XX_CP_SQE_AC_STAT_DATA, 0x33, NULL }, - { "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, + { "CP_SQE_AC_STAT", REG_A7XX_CP_SQE_AC_STAT_ADDR, + REG_A7XX_CP_SQE_AC_STAT_DATA, 0x40, NULL }, + { "CP_LPAC_DRAW_STATE", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, + { "CP_SQE_AC_UCODE_DBG", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, + { "CP_LPAC_FIFO_DBG", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x40, NULL }, - { "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR, + { "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR, REG_A6XX_CP_ROQ_DBG_DATA, 0, a7xx_get_cp_roq_size }, }; static const struct a6xx_indexed_registers a6xx_cp_mempool_indexed = { - "CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR, + "CP_MEM_POOL_DBG", REG_A6XX_CP_MEM_POOL_DBG_ADDR, REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2060, NULL, }; static const struct a6xx_indexed_registers a7xx_cp_bv_mempool_indexed[] = { - { "CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR, - REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2100, NULL }, - { "CP_BV_MEMPOOL", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR, - REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2100, NULL }, + { "CP_MEM_POOL_DBG", REG_A6XX_CP_MEM_POOL_DBG_ADDR, + REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2200, NULL }, + { "CP_BV_MEM_POOL_DBG", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR, + REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2200, NULL }, }; #define DEBUGBUS(_id, _count) { .id = _id, .name = #_id, .count = _count } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c index 8e69b1e84657..550de6ad68ef 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c @@ -21,6 +21,7 @@ static const char * const a6xx_hfi_msg_id[] = { HFI_MSG_ID(HFI_H2F_MSG_PERF_TABLE), HFI_MSG_ID(HFI_H2F_MSG_TEST), 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_GX_BW_PERF_VOTE), HFI_MSG_ID(HFI_H2F_MSG_PREPARE_SLUMBER), @@ -765,23 +766,40 @@ send: NULL, 0); } +static int a6xx_hfi_feature_ctrl_msg(struct a6xx_gmu *gmu, u32 feature, u32 enable, u32 data) +{ + struct a6xx_hfi_msg_feature_ctrl msg = { + .feature = feature, + .enable = enable, + .data = data, + }; + + return a6xx_hfi_send_msg(gmu, HFI_H2F_FEATURE_CTRL, &msg, sizeof(msg), NULL, 0); +} + +#define HFI_FEATURE_IFPC 9 +#define IFPC_LONG_HYST 0x1680 + +static int a6xx_hfi_enable_ifpc(struct a6xx_gmu *gmu) +{ + if (gmu->idle_level != GMU_IDLE_STATE_IFPC) + return 0; + + return a6xx_hfi_feature_ctrl_msg(gmu, HFI_FEATURE_IFPC, 1, IFPC_LONG_HYST); +} + #define HFI_FEATURE_ACD 12 static int a6xx_hfi_enable_acd(struct a6xx_gmu *gmu) { struct a6xx_hfi_acd_table *acd_table = &gmu->acd_table; - struct a6xx_hfi_msg_feature_ctrl msg = { - .feature = HFI_FEATURE_ACD, - .enable = 1, - .data = 0, - }; int ret; if (!acd_table->enable_by_level) return 0; /* Enable ACD feature at GMU */ - ret = a6xx_hfi_send_msg(gmu, HFI_H2F_FEATURE_CTRL, &msg, sizeof(msg), NULL, 0); + ret = a6xx_hfi_feature_ctrl_msg(gmu, HFI_FEATURE_ACD, 1, 0); if (ret) { DRM_DEV_ERROR(gmu->dev, "Unable to enable ACD (%d)\n", ret); return ret; @@ -898,6 +916,10 @@ int a6xx_hfi_start(struct a6xx_gmu *gmu, int boot_state) if (ret) return ret; + ret = a6xx_hfi_enable_ifpc(gmu); + if (ret) + return ret; + ret = a6xx_hfi_send_core_fw_start(gmu); if (ret) return ret; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_preempt.c b/drivers/gpu/drm/msm/adreno/a6xx_preempt.c index 6a12a35dabff..afc5f4aa3b17 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_preempt.c @@ -41,7 +41,7 @@ static inline void set_preempt_state(struct a6xx_gpu *gpu, } /* Write the most recent wptr for the given ring into the hardware */ -static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +static inline void update_wptr(struct a6xx_gpu *a6xx_gpu, struct msm_ringbuffer *ring) { unsigned long flags; uint32_t wptr; @@ -51,7 +51,7 @@ static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) if (ring->restore_wptr) { wptr = get_wptr(ring); - gpu_write(gpu, REG_A6XX_CP_RB_WPTR, wptr); + a6xx_fenced_write(a6xx_gpu, REG_A6XX_CP_RB_WPTR, wptr, BIT(0), false); ring->restore_wptr = false; } @@ -111,9 +111,9 @@ static void preempt_prepare_postamble(struct a6xx_gpu *a6xx_gpu) postamble[count++] = PKT7(CP_WAIT_REG_MEM, 6); postamble[count++] = CP_WAIT_REG_MEM_0_FUNCTION(WRITE_EQ); - postamble[count++] = CP_WAIT_REG_MEM_1_POLL_ADDR_LO( + postamble[count++] = CP_WAIT_REG_MEM_POLL_ADDR_LO( REG_A6XX_RBBM_PERFCTR_SRAM_INIT_STATUS); - postamble[count++] = CP_WAIT_REG_MEM_2_POLL_ADDR_HI(0); + postamble[count++] = CP_WAIT_REG_MEM_POLL_ADDR_HI(0); postamble[count++] = CP_WAIT_REG_MEM_3_REF(0x1); postamble[count++] = CP_WAIT_REG_MEM_4_MASK(0x1); postamble[count++] = CP_WAIT_REG_MEM_5_DELAY_LOOP_CYCLES(0); @@ -136,6 +136,21 @@ static void preempt_disable_postamble(struct a6xx_gpu *a6xx_gpu) a6xx_gpu->postamble_enabled = false; } +/* + * Set preemption keepalive vote. Please note that this vote is different from the one used in + * a6xx_irq() + */ +static void a6xx_preempt_keepalive_vote(struct msm_gpu *gpu, bool on) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + if (adreno_has_gmu_wrapper(adreno_gpu)) + return; + + gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_PWR_COL_PREEMPT_KEEPALIVE, on); +} + void a6xx_preempt_irq(struct msm_gpu *gpu) { uint32_t status; @@ -172,10 +187,12 @@ void a6xx_preempt_irq(struct msm_gpu *gpu) set_preempt_state(a6xx_gpu, PREEMPT_FINISH); - update_wptr(gpu, a6xx_gpu->cur_ring); + update_wptr(a6xx_gpu, a6xx_gpu->cur_ring); set_preempt_state(a6xx_gpu, PREEMPT_NONE); + a6xx_preempt_keepalive_vote(gpu, false); + trace_msm_gpu_preemption_irq(a6xx_gpu->cur_ring->id); /* @@ -268,7 +285,7 @@ void a6xx_preempt_trigger(struct msm_gpu *gpu) */ if (!ring || (a6xx_gpu->cur_ring == ring)) { set_preempt_state(a6xx_gpu, PREEMPT_FINISH); - update_wptr(gpu, a6xx_gpu->cur_ring); + update_wptr(a6xx_gpu, a6xx_gpu->cur_ring); set_preempt_state(a6xx_gpu, PREEMPT_NONE); spin_unlock_irqrestore(&a6xx_gpu->eval_lock, flags); return; @@ -302,13 +319,16 @@ void a6xx_preempt_trigger(struct msm_gpu *gpu) spin_unlock_irqrestore(&ring->preempt_lock, flags); - gpu_write64(gpu, - REG_A6XX_CP_CONTEXT_SWITCH_SMMU_INFO, - a6xx_gpu->preempt_smmu_iova[ring->id]); + /* Set the keepalive bit to keep the GPU ON until preemption is complete */ + a6xx_preempt_keepalive_vote(gpu, true); + + a6xx_fenced_write(a6xx_gpu, + REG_A6XX_CP_CONTEXT_SWITCH_SMMU_INFO, a6xx_gpu->preempt_smmu_iova[ring->id], + BIT(1), true); - gpu_write64(gpu, + a6xx_fenced_write(a6xx_gpu, REG_A6XX_CP_CONTEXT_SWITCH_PRIV_NON_SECURE_RESTORE_ADDR, - a6xx_gpu->preempt_iova[ring->id]); + a6xx_gpu->preempt_iova[ring->id], BIT(1), true); a6xx_gpu->next_ring = ring; @@ -328,7 +348,7 @@ void a6xx_preempt_trigger(struct msm_gpu *gpu) set_preempt_state(a6xx_gpu, PREEMPT_TRIGGERED); /* Trigger the preemption */ - gpu_write(gpu, REG_A6XX_CP_CONTEXT_SWITCH_CNTL, cntl); + a6xx_fenced_write(a6xx_gpu, REG_A6XX_CP_CONTEXT_SWITCH_CNTL, cntl, BIT(1), false); } static int preempt_init_ring(struct a6xx_gpu *a6xx_gpu, diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 50945bfe9b49..28f744f3caf7 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -24,6 +24,10 @@ bool disable_acd; MODULE_PARM_DESC(disable_acd, "Forcefully disable GPU ACD"); module_param_unsafe(disable_acd, bool, 0400); +static bool skip_gpu; +MODULE_PARM_DESC(no_gpu, "Disable GPU driver register (0=enable GPU driver register (default), 1=skip GPU driver register"); +module_param(skip_gpu, bool, 0400); + extern const struct adreno_gpulist a2xx_gpulist; extern const struct adreno_gpulist a3xx_gpulist; extern const struct adreno_gpulist a4xx_gpulist; @@ -184,6 +188,9 @@ bool adreno_has_gpu(struct device_node *node) uint32_t chip_id; int ret; + if (skip_gpu) + return false; + ret = find_chipid(node, &chip_id); if (ret) return false; @@ -404,10 +411,16 @@ static struct platform_driver adreno_driver = { void __init adreno_register(void) { + if (skip_gpu) + return; + platform_driver_register(&adreno_driver); } void __exit adreno_unregister(void) { + if (skip_gpu) + return; + platform_driver_unregister(&adreno_driver); } 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 cb66ece6606b..04b49d385f9d 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 @@ -81,7 +81,7 @@ static const u32 gen7_0_0_debugbus_blocks[] = { A7XX_DBGBUS_USPTP_7, }; -static struct gen7_shader_block gen7_0_0_shader_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}, @@ -668,12 +668,19 @@ static const u32 gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers), 8)); -/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_BR */ -static const u32 gen7_0_0_tpl1_noncontext_pipe_br_registers[] = { +/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_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, UINT_MAX, UINT_MAX, }; +static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_none_registers), 8)); + +/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_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 */ @@ -695,7 +702,7 @@ static const struct gen7_sel_reg gen7_0_0_rb_rbp_sel = { .val = 0x9, }; -static struct gen7_cluster_registers gen7_0_0_clusters[] = { +static const struct gen7_cluster_registers gen7_0_0_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, gen7_0_0_noncontext_pipe_br_registers, }, { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, @@ -764,7 +771,7 @@ static struct gen7_cluster_registers gen7_0_0_clusters[] = { gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, }; -static struct gen7_sptp_cluster_registers gen7_0_0_sptp_clusters[] = { +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, 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, @@ -914,7 +921,7 @@ static const u32 gen7_0_0_dpm_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_dpm_registers), 8)); -static struct gen7_reg_list gen7_0_0_reg_list[] = { +static const struct gen7_reg_list gen7_0_0_reg_list[] = { { gen7_0_0_gpu_registers, NULL }, { gen7_0_0_cx_misc_registers, NULL }, { gen7_0_0_dpm_registers, NULL }, 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 6f8ad50f32ce..772652eb61f3 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 @@ -95,7 +95,7 @@ static const u32 gen7_2_0_debugbus_blocks[] = { A7XX_DBGBUS_CCHE_2, }; -static struct gen7_shader_block gen7_2_0_shader_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}, @@ -489,7 +489,7 @@ static const struct gen7_sel_reg gen7_2_0_rb_rbp_sel = { .val = 0x9, }; -static struct gen7_cluster_registers gen7_2_0_clusters[] = { +static const struct gen7_cluster_registers gen7_2_0_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, gen7_2_0_noncontext_pipe_br_registers, }, { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, @@ -558,7 +558,7 @@ static struct gen7_cluster_registers gen7_2_0_clusters[] = { gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, }; -static struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = { +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, 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, @@ -573,6 +573,8 @@ static struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = { gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers, 0xaf80 }, { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_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, + gen7_0_0_tpl1_noncontext_pipe_none_registers, 0xb600 }, { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_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, @@ -737,7 +739,7 @@ static const u32 gen7_2_0_dpm_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_2_0_dpm_registers), 8)); -static struct gen7_reg_list gen7_2_0_reg_list[] = { +static const struct gen7_reg_list gen7_2_0_reg_list[] = { { gen7_2_0_gpu_registers, NULL }, { gen7_2_0_cx_misc_registers, NULL }, { gen7_2_0_dpm_registers, NULL }, 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 e02cabb39f19..0956dfca1f05 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 @@ -117,7 +117,7 @@ static const u32 gen7_9_0_cx_debugbus_blocks[] = { A7XX_DBGBUS_GBIF_CX, }; -static struct gen7_shader_block gen7_9_0_shader_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 }, @@ -1116,7 +1116,7 @@ static const struct gen7_sel_reg gen7_9_0_rb_rbp_sel = { .val = 0x9, }; -static struct gen7_cluster_registers gen7_9_0_clusters[] = { +static const struct gen7_cluster_registers gen7_9_0_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, gen7_9_0_non_context_pipe_br_registers, }, { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, @@ -1185,7 +1185,7 @@ static struct gen7_cluster_registers gen7_9_0_clusters[] = { gen7_9_0_vpc_pipe_bv_cluster_vpc_ps_registers, }, }; -static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = { +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, 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, @@ -1294,34 +1294,34 @@ static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = { gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000}, }; -static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = { +static const struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = { { "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR, REG_A6XX_CP_SQE_STAT_DATA, 0x00040}, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x00200}, - { "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR, + { "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR, REG_A6XX_CP_ROQ_DBG_DATA, 0x00800}, - { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + { "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x08000}, - { "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR, + { "CP_BV_DRAW_STATE", REG_A7XX_CP_BV_DRAW_STATE_ADDR, REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x00200}, - { "CP_BV_ROQ_DBG_ADDR", REG_A7XX_CP_BV_ROQ_DBG_ADDR, + { "CP_BV_ROQ_DBG", REG_A7XX_CP_BV_ROQ_DBG_ADDR, REG_A7XX_CP_BV_ROQ_DBG_DATA, 0x00800}, - { "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, + { "CP_BV_SQE_UCODE_DBG", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x08000}, - { "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR, + { "CP_BV_SQE_STAT", REG_A7XX_CP_BV_SQE_STAT_ADDR, REG_A7XX_CP_BV_SQE_STAT_DATA, 0x00040}, - { "CP_RESOURCE_TBL", REG_A7XX_CP_RESOURCE_TABLE_DBG_ADDR, + { "CP_RESOURCE_TABLE_DBG", REG_A7XX_CP_RESOURCE_TABLE_DBG_ADDR, REG_A7XX_CP_RESOURCE_TABLE_DBG_DATA, 0x04100}, - { "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, + { "CP_LPAC_DRAW_STATE", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x00200}, - { "CP_LPAC_ROQ", REG_A7XX_CP_LPAC_ROQ_DBG_ADDR, + { "CP_LPAC_ROQ_DBG", REG_A7XX_CP_LPAC_ROQ_DBG_ADDR, REG_A7XX_CP_LPAC_ROQ_DBG_DATA, 0x00200}, - { "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, + { "CP_SQE_AC_UCODE_DBG", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x08000}, - { "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR, + { "CP_SQE_AC_STAT", REG_A7XX_CP_SQE_AC_STAT_ADDR, REG_A7XX_CP_SQE_AC_STAT_DATA, 0x00040}, - { "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, + { "CP_LPAC_FIFO_DBG", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x00040}, { "CP_AQE_ROQ_0", REG_A7XX_CP_AQE_ROQ_DBG_ADDR_0, REG_A7XX_CP_AQE_ROQ_DBG_DATA_0, 0x00100}, @@ -1337,7 +1337,7 @@ static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = { REG_A7XX_CP_AQE_STAT_DATA_1, 0x00040}, }; -static struct gen7_reg_list gen7_9_0_reg_list[] = { +static const struct gen7_reg_list gen7_9_0_reg_list[] = { { gen7_9_0_gpu_registers, NULL}, { gen7_9_0_cx_misc_registers, NULL}, { gen7_9_0_cx_dbgc_registers, NULL}, diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index f1230465bf0d..afaa3cfefd35 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -10,7 +10,7 @@ #include <linux/interconnect.h> #include <linux/firmware/qcom/qcom_scm.h> #include <linux/kernel.h> -#include <linux/of_address.h> +#include <linux/of_reserved_mem.h> #include <linux/pm_opp.h> #include <linux/slab.h> #include <linux/soc/qcom/mdt_loader.h> @@ -33,7 +33,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname, struct device *dev = &gpu->pdev->dev; const struct firmware *fw; const char *signed_fwname = NULL; - struct device_node *np, *mem_np; + struct device_node *np; struct resource r; phys_addr_t mem_phys; ssize_t mem_size; @@ -51,18 +51,11 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname, return -ENODEV; } - mem_np = of_parse_phandle(np, "memory-region", 0); - of_node_put(np); - if (!mem_np) { + ret = of_reserved_mem_region_to_resource(np, 0, &r); + if (ret) { zap_available = false; - return -EINVAL; - } - - ret = of_address_to_resource(mem_np, 0, &r); - of_node_put(mem_np); - if (ret) return ret; - + } mem_phys = r.start; /* @@ -209,9 +202,7 @@ adreno_iommu_create_vm(struct msm_gpu *gpu, u64 start, size; mmu = msm_iommu_gpu_new(&pdev->dev, gpu, quirks); - if (!mmu) - return ERR_PTR(-ENODEV); - else if (IS_ERR_OR_NULL(mmu)) + if (IS_ERR(mmu)) return ERR_CAST(mmu); geometry = msm_iommu_get_geometry(mmu); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index 9dc93c247196..390fa6720d9b 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -59,6 +59,7 @@ enum adreno_family { #define ADRENO_QUIRK_HAS_CACHED_COHERENT BIT(4) #define ADRENO_QUIRK_PREEMPTION BIT(5) #define ADRENO_QUIRK_4GB_VA BIT(6) +#define ADRENO_QUIRK_IFPC BIT(7) /* Helper for formating the chip_id in the way that userspace tools like * crashdec expect. diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c index 0fb5789c60d0..13cc658065c5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c @@ -32,6 +32,26 @@ enum dpu_perf_mode { }; /** + * dpu_core_perf_adjusted_mode_clk - Adjust given mode clock rate according to + * the perf clock factor. + * @crtc_clk_rate - Unadjusted mode clock rate + * @perf_cfg: performance configuration + */ +u64 dpu_core_perf_adjusted_mode_clk(u64 mode_clk_rate, + const struct dpu_perf_cfg *perf_cfg) +{ + u32 clk_factor; + + clk_factor = perf_cfg->clk_inefficiency_factor; + if (clk_factor) { + mode_clk_rate *= clk_factor; + do_div(mode_clk_rate, 100); + } + + return mode_clk_rate; +} + +/** * _dpu_core_perf_calc_bw() - to calculate BW per crtc * @perf_cfg: performance configuration * @crtc: pointer to a crtc @@ -75,28 +95,21 @@ static u64 _dpu_core_perf_calc_clk(const struct dpu_perf_cfg *perf_cfg, struct drm_plane *plane; struct dpu_plane_state *pstate; struct drm_display_mode *mode; - u64 crtc_clk; - u32 clk_factor; + u64 mode_clk; mode = &state->adjusted_mode; - crtc_clk = (u64)mode->vtotal * mode->hdisplay * drm_mode_vrefresh(mode); + mode_clk = (u64)mode->vtotal * mode->hdisplay * drm_mode_vrefresh(mode); drm_atomic_crtc_for_each_plane(plane, crtc) { pstate = to_dpu_plane_state(plane->state); if (!pstate) continue; - crtc_clk = max(pstate->plane_clk, crtc_clk); - } - - clk_factor = perf_cfg->clk_inefficiency_factor; - if (clk_factor) { - crtc_clk *= clk_factor; - do_div(crtc_clk, 100); + mode_clk = max(pstate->plane_clk, mode_clk); } - return crtc_clk; + return dpu_core_perf_adjusted_mode_clk(mode_clk, perf_cfg); } static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h index d2f21d34e501..3740bc97422c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h @@ -54,6 +54,9 @@ struct dpu_core_perf { u32 fix_core_ab_vote; }; +u64 dpu_core_perf_adjusted_mode_clk(u64 clk_rate, + const struct dpu_perf_cfg *perf_cfg); + int dpu_core_perf_crtc_check(struct drm_crtc *crtc, struct drm_crtc_state *state); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index d4b545448d74..4b970a59deaf 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -377,11 +377,10 @@ static void _dpu_crtc_setup_blend_cfg(struct dpu_crtc_mixer *mixer, static void _dpu_crtc_program_lm_output_roi(struct drm_crtc *crtc) { struct dpu_crtc_state *crtc_state; - int lm_idx, lm_horiz_position; + int lm_idx; crtc_state = to_dpu_crtc_state(crtc->state); - lm_horiz_position = 0; for (lm_idx = 0; lm_idx < crtc_state->num_mixers; lm_idx++) { const struct drm_rect *lm_roi = &crtc_state->lm_bounds[lm_idx]; struct dpu_hw_mixer *hw_lm = crtc_state->mixers[lm_idx].hw_lm; @@ -392,7 +391,7 @@ static void _dpu_crtc_program_lm_output_roi(struct drm_crtc *crtc) cfg.out_width = drm_rect_width(lm_roi); cfg.out_height = drm_rect_height(lm_roi); - cfg.right_mixer = lm_horiz_position++; + cfg.right_mixer = lm_idx & 0x1; cfg.flags = 0; hw_lm->ops.setup_mixer_out(hw_lm, &cfg); } @@ -596,7 +595,7 @@ static void _dpu_crtc_complete_flip(struct drm_crtc *crtc) spin_lock_irqsave(&dev->event_lock, flags); if (dpu_crtc->event) { - DRM_DEBUG_VBL("%s: send event: %pK\n", dpu_crtc->name, + DRM_DEBUG_VBL("%s: send event: %p\n", dpu_crtc->name, dpu_crtc->event); trace_dpu_crtc_complete_flip(DRMID(crtc)); drm_crtc_send_vblank_event(crtc, dpu_crtc->event); @@ -1534,6 +1533,7 @@ static enum drm_mode_status dpu_crtc_mode_valid(struct drm_crtc *crtc, const struct drm_display_mode *mode) { struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc); + u64 adjusted_mode_clk; /* if there is no 3d_mux block we cannot merge LMs so we cannot * split the large layer into 2 LMs, filter out such modes @@ -1541,6 +1541,17 @@ static enum drm_mode_status dpu_crtc_mode_valid(struct drm_crtc *crtc, if (!dpu_kms->catalog->caps->has_3d_merge && mode->hdisplay > dpu_kms->catalog->caps->max_mixer_width) return MODE_BAD_HVALUE; + + adjusted_mode_clk = dpu_core_perf_adjusted_mode_clk(mode->clock, + dpu_kms->perf.perf_cfg); + + /* + * The given mode, adjusted for the perf clock factor, should not exceed + * the max core clock rate + */ + if (dpu_kms->perf.max_core_clk_rate < adjusted_mode_clk * 1000) + return MODE_CLOCK_HIGH; + /* * max crtc width is equal to the max mixer width * 2 and max height is 4K */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 05e5f3463e30..258edaa18fc0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -730,6 +730,8 @@ bool dpu_encoder_needs_modeset(struct drm_encoder *drm_enc, struct drm_atomic_st return false; conn_state = drm_atomic_get_new_connector_state(state, connector); + if (!conn_state) + return false; /** * These checks are duplicated from dpu_encoder_update_topology() since diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c index 56a5b596554d..46f348972a97 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c @@ -446,7 +446,7 @@ static void _dpu_encoder_phys_wb_handle_wbdone_timeout( static int dpu_encoder_phys_wb_wait_for_commit_done( struct dpu_encoder_phys *phys_enc) { - unsigned long ret; + int ret; struct dpu_encoder_wait_info wait_info; struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index e824cd64fd3f..6641455c4ec6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -338,7 +338,6 @@ static const struct dpu_sspp_sub_blks dpu_dma_sblk = _DMA_SBLK(); *************************************************************/ static const struct dpu_lm_sub_blks msm8998_lm_sblk = { - .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .maxblendstages = 7, /* excluding base layer */ .blendstage_base = { /* offsets relative to mixer base */ 0x20, 0x50, 0x80, 0xb0, 0x230, @@ -347,7 +346,6 @@ static const struct dpu_lm_sub_blks msm8998_lm_sblk = { }; static const struct dpu_lm_sub_blks sdm845_lm_sblk = { - .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .maxblendstages = 11, /* excluding base layer */ .blendstage_base = { /* offsets relative to mixer base */ 0x20, 0x38, 0x50, 0x68, 0x80, 0x98, @@ -356,7 +354,6 @@ static const struct dpu_lm_sub_blks sdm845_lm_sblk = { }; static const struct dpu_lm_sub_blks sc7180_lm_sblk = { - .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .maxblendstages = 7, /* excluding base layer */ .blendstage_base = { /* offsets relative to mixer base */ 0x20, 0x38, 0x50, 0x68, 0x80, 0x98, 0xb0 @@ -364,7 +361,6 @@ static const struct dpu_lm_sub_blks sc7180_lm_sblk = { }; static const struct dpu_lm_sub_blks sm8750_lm_sblk = { - .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .maxblendstages = 11, /* excluding base layer */ .blendstage_base = { /* offsets relative to mixer base */ /* 0x40 + n*0x30 */ @@ -374,7 +370,6 @@ static const struct dpu_lm_sub_blks sm8750_lm_sblk = { }; static const struct dpu_lm_sub_blks qcm2290_lm_sblk = { - .maxwidth = DEFAULT_DPU_LINE_WIDTH, .maxblendstages = 4, /* excluding base layer */ .blendstage_base = { /* offsets relative to mixer base */ 0x20, 0x38, 0x50, 0x68 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 a78bb2c334e3..f0768f54e9b3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -307,7 +307,6 @@ struct dpu_sspp_sub_blks { * @blendstage_base: Blend-stage register base offset */ struct dpu_lm_sub_blks { - u32 maxwidth; u32 maxblendstages; u32 blendstage_base[MAX_BLOCKS]; }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c index 11fb1bc54fa9..54b20faa0b69 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c @@ -31,14 +31,14 @@ static void dpu_setup_dspp_pcc(struct dpu_hw_dspp *ctx, u32 base; if (!ctx) { - DRM_ERROR("invalid ctx %pK\n", ctx); + DRM_ERROR("invalid ctx %p\n", ctx); return; } base = ctx->cap->sblk->pcc.base; if (!base) { - DRM_ERROR("invalid ctx %pK pcc base 0x%x\n", ctx, base); + DRM_ERROR("invalid ctx %p pcc base 0x%x\n", ctx, base); return; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 12dcb32b4724..4e5a8ecd31f7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -1110,7 +1110,7 @@ static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms) { struct drm_gpuvm *vm; - vm = msm_kms_init_vm(dpu_kms->dev); + vm = msm_kms_init_vm(dpu_kms->dev, dpu_kms->dev->dev->parent); if (IS_ERR(vm)) return PTR_ERR(vm); @@ -1345,7 +1345,7 @@ static int dpu_kms_mmap_mdp5(struct dpu_kms *dpu_kms) dpu_kms->mmio = NULL; return ret; } - DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio); + DRM_DEBUG("mapped dpu address space @%p\n", dpu_kms->mmio); dpu_kms->vbif[VBIF_RT] = msm_ioremap_mdss(mdss_dev, dpu_kms->pdev, @@ -1380,7 +1380,7 @@ static int dpu_kms_mmap_dpu(struct dpu_kms *dpu_kms) dpu_kms->mmio = NULL; return ret; } - DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio); + DRM_DEBUG("mapped dpu address space @%p\n", dpu_kms->mmio); dpu_kms->vbif[VBIF_RT] = msm_ioremap(pdev, "vbif"); if (IS_ERR(dpu_kms->vbif[VBIF_RT])) { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 01171c535a27..f54cf0faa1c7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -922,6 +922,9 @@ static int dpu_plane_is_multirect_capable(struct dpu_hw_sspp *sspp, if (MSM_FORMAT_IS_YUV(fmt)) return false; + if (!sspp) + return true; + if (!test_bit(DPU_SSPP_SMART_DMA_V1, &sspp->cap->features) && !test_bit(DPU_SSPP_SMART_DMA_V2, &sspp->cap->features)) return false; @@ -1028,6 +1031,7 @@ static int dpu_plane_try_multirect_shared(struct dpu_plane_state *pstate, prev_pipe->multirect_mode != DPU_SSPP_MULTIRECT_NONE) return false; + /* Do not validate SSPP of current plane when it is not ready */ if (!dpu_plane_is_multirect_capable(pipe->sspp, pipe_cfg, fmt) || !dpu_plane_is_multirect_capable(prev_pipe->sspp, prev_pipe_cfg, prev_fmt)) return false; @@ -1129,7 +1133,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, struct drm_plane_state *old_plane_state = drm_atomic_get_old_plane_state(state, plane); struct dpu_plane_state *pstate = to_dpu_plane_state(plane_state); - struct drm_crtc_state *crtc_state; + struct drm_crtc_state *crtc_state = NULL; int ret; if (IS_ERR(plane_state)) @@ -1162,7 +1166,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, if (!old_plane_state || !old_plane_state->fb || old_plane_state->src_w != plane_state->src_w || old_plane_state->src_h != plane_state->src_h || - old_plane_state->src_w != plane_state->src_w || + old_plane_state->crtc_w != plane_state->crtc_w || old_plane_state->crtc_h != plane_state->crtc_h || msm_framebuffer_format(old_plane_state->fb) != msm_framebuffer_format(plane_state->fb)) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index 25382120cb1a..2c77c74fac0f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -865,6 +865,21 @@ void dpu_rm_release_all_sspp(struct dpu_global_state *global_state, ARRAY_SIZE(global_state->sspp_to_crtc_id), crtc_id); } +static char *dpu_hw_blk_type_name[] = { + [DPU_HW_BLK_TOP] = "TOP", + [DPU_HW_BLK_SSPP] = "SSPP", + [DPU_HW_BLK_LM] = "LM", + [DPU_HW_BLK_CTL] = "CTL", + [DPU_HW_BLK_PINGPONG] = "pingpong", + [DPU_HW_BLK_INTF] = "INTF", + [DPU_HW_BLK_WB] = "WB", + [DPU_HW_BLK_DSPP] = "DSPP", + [DPU_HW_BLK_MERGE_3D] = "merge_3d", + [DPU_HW_BLK_DSC] = "DSC", + [DPU_HW_BLK_CDM] = "CDM", + [DPU_HW_BLK_MAX] = "unknown", +}; + /** * dpu_rm_get_assigned_resources - Get hw resources of the given type that are * assigned to this encoder @@ -946,13 +961,13 @@ int dpu_rm_get_assigned_resources(struct dpu_rm *rm, } if (num_blks == blks_size) { - DPU_ERROR("More than %d resources assigned to crtc %d\n", - blks_size, crtc_id); + DPU_ERROR("More than %d %s assigned to crtc %d\n", + blks_size, dpu_hw_blk_type_name[type], crtc_id); break; } if (!hw_blks[i]) { - DPU_ERROR("Allocated resource %d unavailable to assign to crtc %d\n", - type, crtc_id); + DPU_ERROR("%s unavailable to assign to crtc %d\n", + dpu_hw_blk_type_name[type], crtc_id); break; } blks[num_blks++] = hw_blks[i]; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c index 8ff496082902..cd73468e369a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c @@ -80,7 +80,6 @@ static int dpu_wb_conn_atomic_check(struct drm_connector *connector, static const struct drm_connector_funcs dpu_wb_conn_funcs = { .reset = drm_atomic_helper_connector_reset, .fill_modes = drm_helper_probe_single_connector_modes, - .destroy = drm_connector_cleanup, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; @@ -131,12 +130,9 @@ int dpu_writeback_init(struct drm_device *dev, struct drm_encoder *enc, drm_connector_helper_add(&dpu_wb_conn->base.base, &dpu_wb_conn_helper_funcs); - /* DPU initializes the encoder and sets it up completely for writeback - * cases and hence should use the new API drm_writeback_connector_init_with_encoder - * to initialize the writeback connector - */ - rc = drm_writeback_connector_init_with_encoder(dev, &dpu_wb_conn->base, enc, - &dpu_wb_conn_funcs, format_list, num_formats); + rc = drmm_writeback_connector_init(dev, &dpu_wb_conn->base, + &dpu_wb_conn_funcs, enc, + format_list, num_formats); if (!rc) dpu_wb_conn->wb_enc = enc; diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c index 0952c7f18abd..809ca191e9de 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c @@ -391,11 +391,9 @@ static void read_mdp_hw_revision(struct mdp4_kms *mdp4_kms, static int mdp4_kms_init(struct drm_device *dev) { - struct platform_device *pdev = to_platform_device(dev->dev); struct msm_drm_private *priv = dev->dev_private; struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(priv->kms)); struct msm_kms *kms = NULL; - struct msm_mmu *mmu; struct drm_gpuvm *vm; int ret; u32 major, minor; @@ -458,29 +456,14 @@ static int mdp4_kms_init(struct drm_device *dev) mdp4_disable(mdp4_kms); mdelay(16); - mmu = msm_iommu_new(&pdev->dev, 0); - if (IS_ERR(mmu)) { - ret = PTR_ERR(mmu); + vm = msm_kms_init_vm(mdp4_kms->dev, NULL); + if (IS_ERR(vm)) { + ret = PTR_ERR(vm); goto fail; - } else if (!mmu) { - DRM_DEV_INFO(dev->dev, "no iommu, fallback to phys " - "contig buffers for scanout\n"); - vm = NULL; - } else { - vm = msm_gem_vm_create(dev, mmu, "mdp4", - 0x1000, 0x100000000 - 0x1000, - true); - - if (IS_ERR(vm)) { - if (!IS_ERR(mmu)) - mmu->funcs->destroy(mmu); - ret = PTR_ERR(vm); - goto fail; - } - - kms->vm = vm; } + kms->vm = vm; + ret = modeset_init(mdp4_kms); if (ret) { DRM_DEV_ERROR(dev->dev, "modeset_init failed: %d\n", ret); @@ -529,7 +512,7 @@ static int mdp4_probe(struct platform_device *pdev) mdp4_kms = devm_kzalloc(dev, sizeof(*mdp4_kms), GFP_KERNEL); if (!mdp4_kms) - return dev_err_probe(dev, -ENOMEM, "failed to allocate kms\n"); + return -ENOMEM; mdp4_kms->mmio = msm_ioremap(pdev, NULL); if (IS_ERR(mdp4_kms->mmio)) diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h index fb348583dc84..06458d4ee48c 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h @@ -202,6 +202,6 @@ static inline struct drm_encoder *mdp4_dsi_encoder_init(struct drm_device *dev) } #endif -struct clk *mpd4_get_lcdc_clock(struct drm_device *dev); +struct clk *mdp4_get_lcdc_clock(struct drm_device *dev); #endif /* __MDP4_KMS_H__ */ diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c index 06a307c1272d..1051873057f6 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c @@ -375,7 +375,7 @@ struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev) drm_encoder_helper_add(encoder, &mdp4_lcdc_encoder_helper_funcs); - mdp4_lcdc_encoder->lcdc_clk = mpd4_get_lcdc_clock(dev); + mdp4_lcdc_encoder->lcdc_clk = mdp4_get_lcdc_clock(dev); if (IS_ERR(mdp4_lcdc_encoder->lcdc_clk)) { DRM_DEV_ERROR(dev->dev, "failed to get lvds_clk\n"); return ERR_CAST(mdp4_lcdc_encoder->lcdc_clk); diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_pll.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_pll.c index fa2c29470510..04c49bf3d854 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_pll.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_pll.c @@ -54,7 +54,7 @@ static const struct pll_rate *find_rate(unsigned long rate) return &freqtbl[i-1]; } -static int mpd4_lvds_pll_enable(struct clk_hw *hw) +static int mdp4_lvds_pll_enable(struct clk_hw *hw) { struct mdp4_lvds_pll *lvds_pll = to_mdp4_lvds_pll(hw); struct mdp4_kms *mdp4_kms = get_kms(lvds_pll); @@ -80,7 +80,7 @@ static int mpd4_lvds_pll_enable(struct clk_hw *hw) return 0; } -static void mpd4_lvds_pll_disable(struct clk_hw *hw) +static void mdp4_lvds_pll_disable(struct clk_hw *hw) { struct mdp4_lvds_pll *lvds_pll = to_mdp4_lvds_pll(hw); struct mdp4_kms *mdp4_kms = get_kms(lvds_pll); @@ -91,21 +91,24 @@ static void mpd4_lvds_pll_disable(struct clk_hw *hw) mdp4_write(mdp4_kms, REG_MDP4_LVDS_PHY_PLL_CTRL_0, 0x0); } -static unsigned long mpd4_lvds_pll_recalc_rate(struct clk_hw *hw, +static unsigned long mdp4_lvds_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) { struct mdp4_lvds_pll *lvds_pll = to_mdp4_lvds_pll(hw); return lvds_pll->pixclk; } -static long mpd4_lvds_pll_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *parent_rate) +static int mdp4_lvds_pll_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { - const struct pll_rate *pll_rate = find_rate(rate); - return pll_rate->rate; + const struct pll_rate *pll_rate = find_rate(req->rate); + + req->rate = pll_rate->rate; + + return 0; } -static int mpd4_lvds_pll_set_rate(struct clk_hw *hw, unsigned long rate, +static int mdp4_lvds_pll_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { struct mdp4_lvds_pll *lvds_pll = to_mdp4_lvds_pll(hw); @@ -114,26 +117,26 @@ static int mpd4_lvds_pll_set_rate(struct clk_hw *hw, unsigned long rate, } -static const struct clk_ops mpd4_lvds_pll_ops = { - .enable = mpd4_lvds_pll_enable, - .disable = mpd4_lvds_pll_disable, - .recalc_rate = mpd4_lvds_pll_recalc_rate, - .round_rate = mpd4_lvds_pll_round_rate, - .set_rate = mpd4_lvds_pll_set_rate, +static const struct clk_ops mdp4_lvds_pll_ops = { + .enable = mdp4_lvds_pll_enable, + .disable = mdp4_lvds_pll_disable, + .recalc_rate = mdp4_lvds_pll_recalc_rate, + .determine_rate = mdp4_lvds_pll_determine_rate, + .set_rate = mdp4_lvds_pll_set_rate, }; -static const struct clk_parent_data mpd4_lvds_pll_parents[] = { +static const struct clk_parent_data mdp4_lvds_pll_parents[] = { { .fw_name = "pxo", .name = "pxo", }, }; static struct clk_init_data pll_init = { - .name = "mpd4_lvds_pll", - .ops = &mpd4_lvds_pll_ops, - .parent_data = mpd4_lvds_pll_parents, - .num_parents = ARRAY_SIZE(mpd4_lvds_pll_parents), + .name = "mdp4_lvds_pll", + .ops = &mdp4_lvds_pll_ops, + .parent_data = mdp4_lvds_pll_parents, + .num_parents = ARRAY_SIZE(mdp4_lvds_pll_parents), }; -static struct clk_hw *mpd4_lvds_pll_init(struct drm_device *dev) +static struct clk_hw *mdp4_lvds_pll_init(struct drm_device *dev) { struct mdp4_lvds_pll *lvds_pll; int ret; @@ -156,14 +159,14 @@ static struct clk_hw *mpd4_lvds_pll_init(struct drm_device *dev) return &lvds_pll->pll_hw; } -struct clk *mpd4_get_lcdc_clock(struct drm_device *dev) +struct clk *mdp4_get_lcdc_clock(struct drm_device *dev) { struct clk_hw *hw; struct clk *clk; /* TODO: do we need different pll in other cases? */ - hw = mpd4_lvds_pll_init(dev); + hw = mdp4_lvds_pll_init(dev); if (IS_ERR(hw)) { DRM_DEV_ERROR(dev->dev, "failed to register LVDS PLL\n"); return ERR_CAST(hw); diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c index 5b6ca8dd929e..61edf6864092 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c @@ -534,7 +534,7 @@ static int mdp5_kms_init(struct drm_device *dev) } mdelay(16); - vm = msm_kms_init_vm(mdp5_kms->dev); + vm = msm_kms_init_vm(mdp5_kms->dev, pdev->dev.parent); if (IS_ERR(vm)) { ret = PTR_ERR(vm); goto fail; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index 221f12db5f8b..4ea681130dba 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -5,6 +5,8 @@ #include <linux/clk-provider.h> #include <linux/platform_device.h> +#include <linux/pm_clock.h> +#include <linux/pm_runtime.h> #include <dt-bindings/phy/phy.h> #include "dsi_phy.h" @@ -511,30 +513,6 @@ int msm_dsi_cphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing, return 0; } -static int dsi_phy_enable_resource(struct msm_dsi_phy *phy) -{ - struct device *dev = &phy->pdev->dev; - int ret; - - ret = pm_runtime_resume_and_get(dev); - if (ret) - return ret; - - ret = clk_prepare_enable(phy->ahb_clk); - if (ret) { - DRM_DEV_ERROR(dev, "%s: can't enable ahb clk, %d\n", __func__, ret); - pm_runtime_put_sync(dev); - } - - return ret; -} - -static void dsi_phy_disable_resource(struct msm_dsi_phy *phy) -{ - clk_disable_unprepare(phy->ahb_clk); - pm_runtime_put(&phy->pdev->dev); -} - static const struct of_device_id dsi_phy_dt_match[] = { #ifdef CONFIG_DRM_MSM_DSI_28NM_PHY { .compatible = "qcom,dsi-phy-28nm-hpm", @@ -698,22 +676,20 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) if (ret) return ret; - phy->ahb_clk = msm_clk_get(pdev, "iface"); - if (IS_ERR(phy->ahb_clk)) - return dev_err_probe(dev, PTR_ERR(phy->ahb_clk), - "Unable to get ahb clk\n"); + platform_set_drvdata(pdev, phy); - ret = devm_pm_runtime_enable(&pdev->dev); + ret = devm_pm_runtime_enable(dev); if (ret) return ret; - /* PLL init will call into clk_register which requires - * register access, so we need to enable power and ahb clock. - */ - ret = dsi_phy_enable_resource(phy); + ret = devm_pm_clk_create(dev); if (ret) return ret; + ret = pm_clk_add(dev, "iface"); + if (ret < 0) + return dev_err_probe(dev, ret, "Unable to get iface clk\n"); + if (phy->cfg->ops.pll_init) { ret = phy->cfg->ops.pll_init(phy); if (ret) @@ -727,18 +703,19 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) return dev_err_probe(dev, ret, "Failed to register clk provider\n"); - dsi_phy_disable_resource(phy); - - platform_set_drvdata(pdev, phy); - return 0; } +static const struct dev_pm_ops dsi_phy_pm_ops = { + SET_RUNTIME_PM_OPS(pm_clk_suspend, pm_clk_resume, NULL) +}; + static struct platform_driver dsi_phy_platform_driver = { .probe = dsi_phy_driver_probe, .driver = { .name = "msm_dsi_phy", .of_match_table = dsi_phy_dt_match, + .pm = &dsi_phy_pm_ops, }, }; @@ -764,9 +741,9 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy, dev = &phy->pdev->dev; - ret = dsi_phy_enable_resource(phy); + ret = pm_runtime_resume_and_get(dev); if (ret) { - DRM_DEV_ERROR(dev, "%s: resource enable failed, %d\n", + DRM_DEV_ERROR(dev, "%s: resume failed, %d\n", __func__, ret); goto res_en_fail; } @@ -810,7 +787,7 @@ pll_restor_fail: phy_en_fail: regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies); reg_en_fail: - dsi_phy_disable_resource(phy); + pm_runtime_put(dev); res_en_fail: return ret; } @@ -823,7 +800,7 @@ void msm_dsi_phy_disable(struct msm_dsi_phy *phy) phy->cfg->ops.disable(phy); regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies); - dsi_phy_disable_resource(phy); + pm_runtime_put(&phy->pdev->dev); } void msm_dsi_phy_set_usecase(struct msm_dsi_phy *phy, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index c558f8df1684..e391505fdaf0 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -104,12 +104,12 @@ struct msm_dsi_phy { phys_addr_t lane_size; int id; - struct clk *ahb_clk; struct regulator_bulk_data *supplies; 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_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c index af2e30f3f842..ec486ff02c9b 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c @@ -444,21 +444,19 @@ static unsigned long dsi_pll_10nm_vco_recalc_rate(struct clk_hw *hw, return (unsigned long)vco_rate; } -static long dsi_pll_10nm_clk_round_rate(struct clk_hw *hw, - unsigned long rate, unsigned long *parent_rate) +static int dsi_pll_10nm_clk_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { struct dsi_pll_10nm *pll_10nm = to_pll_10nm(hw); - if (rate < pll_10nm->phy->cfg->min_pll_rate) - return pll_10nm->phy->cfg->min_pll_rate; - else if (rate > pll_10nm->phy->cfg->max_pll_rate) - return pll_10nm->phy->cfg->max_pll_rate; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, + pll_10nm->phy->cfg->min_pll_rate, pll_10nm->phy->cfg->max_pll_rate); + + return 0; } static const struct clk_ops clk_ops_dsi_pll_10nm_vco = { - .round_rate = dsi_pll_10nm_clk_round_rate, + .determine_rate = dsi_pll_10nm_clk_determine_rate, .set_rate = dsi_pll_10nm_vco_set_rate, .recalc_rate = dsi_pll_10nm_vco_recalc_rate, .prepare = dsi_pll_10nm_vco_prepare, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c index 3a1c8ece6657..fdefcbd9c284 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c @@ -578,21 +578,19 @@ static void dsi_pll_14nm_vco_unprepare(struct clk_hw *hw) pll_14nm->phy->pll_on = false; } -static long dsi_pll_14nm_clk_round_rate(struct clk_hw *hw, - unsigned long rate, unsigned long *parent_rate) +static int dsi_pll_14nm_clk_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { struct dsi_pll_14nm *pll_14nm = to_pll_14nm(hw); - if (rate < pll_14nm->phy->cfg->min_pll_rate) - return pll_14nm->phy->cfg->min_pll_rate; - else if (rate > pll_14nm->phy->cfg->max_pll_rate) - return pll_14nm->phy->cfg->max_pll_rate; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, + pll_14nm->phy->cfg->min_pll_rate, pll_14nm->phy->cfg->max_pll_rate); + + return 0; } static const struct clk_ops clk_ops_dsi_pll_14nm_vco = { - .round_rate = dsi_pll_14nm_clk_round_rate, + .determine_rate = dsi_pll_14nm_clk_determine_rate, .set_rate = dsi_pll_14nm_vco_set_rate, .recalc_rate = dsi_pll_14nm_vco_recalc_rate, .prepare = dsi_pll_14nm_vco_prepare, @@ -622,18 +620,20 @@ static unsigned long dsi_pll_14nm_postdiv_recalc_rate(struct clk_hw *hw, postdiv->flags, width); } -static long dsi_pll_14nm_postdiv_round_rate(struct clk_hw *hw, - unsigned long rate, - unsigned long *prate) +static int dsi_pll_14nm_postdiv_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { struct dsi_pll_14nm_postdiv *postdiv = to_pll_14nm_postdiv(hw); struct dsi_pll_14nm *pll_14nm = postdiv->pll; - DBG("DSI%d PLL parent rate=%lu", pll_14nm->phy->id, rate); + DBG("DSI%d PLL parent rate=%lu", pll_14nm->phy->id, req->rate); - return divider_round_rate(hw, rate, prate, NULL, - postdiv->width, - postdiv->flags); + req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, + NULL, + postdiv->width, + postdiv->flags); + + return 0; } static int dsi_pll_14nm_postdiv_set_rate(struct clk_hw *hw, unsigned long rate, @@ -680,7 +680,7 @@ static int dsi_pll_14nm_postdiv_set_rate(struct clk_hw *hw, unsigned long rate, static const struct clk_ops clk_ops_dsi_pll_14nm_postdiv = { .recalc_rate = dsi_pll_14nm_postdiv_recalc_rate, - .round_rate = dsi_pll_14nm_postdiv_round_rate, + .determine_rate = dsi_pll_14nm_postdiv_determine_rate, .set_rate = dsi_pll_14nm_postdiv_set_rate, }; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c index 90348a2af3e9..d00e415b9a99 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c @@ -533,21 +533,20 @@ static void dsi_pll_28nm_vco_unprepare(struct clk_hw *hw) pll_28nm->phy->pll_on = false; } -static long dsi_pll_28nm_clk_round_rate(struct clk_hw *hw, - unsigned long rate, unsigned long *parent_rate) +static int dsi_pll_28nm_clk_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); - if (rate < pll_28nm->phy->cfg->min_pll_rate) - return pll_28nm->phy->cfg->min_pll_rate; - else if (rate > pll_28nm->phy->cfg->max_pll_rate) - return pll_28nm->phy->cfg->max_pll_rate; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, + pll_28nm->phy->cfg->min_pll_rate, + pll_28nm->phy->cfg->max_pll_rate); + + return 0; } static const struct clk_ops clk_ops_dsi_pll_28nm_vco_hpm = { - .round_rate = dsi_pll_28nm_clk_round_rate, + .determine_rate = dsi_pll_28nm_clk_determine_rate, .set_rate = dsi_pll_28nm_clk_set_rate, .recalc_rate = dsi_pll_28nm_clk_recalc_rate, .prepare = dsi_pll_28nm_vco_prepare_hpm, @@ -556,7 +555,7 @@ static const struct clk_ops clk_ops_dsi_pll_28nm_vco_hpm = { }; static const struct clk_ops clk_ops_dsi_pll_28nm_vco_lp = { - .round_rate = dsi_pll_28nm_clk_round_rate, + .determine_rate = dsi_pll_28nm_clk_determine_rate, .set_rate = dsi_pll_28nm_clk_set_rate, .recalc_rate = dsi_pll_28nm_clk_recalc_rate, .prepare = dsi_pll_28nm_vco_prepare_lp, @@ -565,7 +564,7 @@ static const struct clk_ops clk_ops_dsi_pll_28nm_vco_lp = { }; static const struct clk_ops clk_ops_dsi_pll_28nm_vco_8226 = { - .round_rate = dsi_pll_28nm_clk_round_rate, + .determine_rate = dsi_pll_28nm_clk_determine_rate, .set_rate = dsi_pll_28nm_clk_set_rate, .recalc_rate = dsi_pll_28nm_clk_recalc_rate, .prepare = dsi_pll_28nm_vco_prepare_8226, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c index f3643320ff2f..8dcce9581dc3 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c @@ -231,21 +231,19 @@ static void dsi_pll_28nm_vco_unprepare(struct clk_hw *hw) pll_28nm->phy->pll_on = false; } -static long dsi_pll_28nm_clk_round_rate(struct clk_hw *hw, - unsigned long rate, unsigned long *parent_rate) +static int dsi_pll_28nm_clk_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); - if (rate < pll_28nm->phy->cfg->min_pll_rate) - return pll_28nm->phy->cfg->min_pll_rate; - else if (rate > pll_28nm->phy->cfg->max_pll_rate) - return pll_28nm->phy->cfg->max_pll_rate; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, + pll_28nm->phy->cfg->min_pll_rate, pll_28nm->phy->cfg->max_pll_rate); + + return 0; } static const struct clk_ops clk_ops_dsi_pll_28nm_vco = { - .round_rate = dsi_pll_28nm_clk_round_rate, + .determine_rate = dsi_pll_28nm_clk_determine_rate, .set_rate = dsi_pll_28nm_clk_set_rate, .recalc_rate = dsi_pll_28nm_clk_recalc_rate, .prepare = dsi_pll_28nm_vco_prepare, @@ -296,18 +294,20 @@ static unsigned int get_vco_mul_factor(unsigned long byte_clk_rate) return 8; } -static long clk_bytediv_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *prate) +static int clk_bytediv_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { unsigned long best_parent; unsigned int factor; - factor = get_vco_mul_factor(rate); + factor = get_vco_mul_factor(req->rate); + + best_parent = req->rate * factor; + req->best_parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw), best_parent); - best_parent = rate * factor; - *prate = clk_hw_round_rate(clk_hw_get_parent(hw), best_parent); + req->rate = req->best_parent_rate / factor; - return *prate / factor; + return 0; } static int clk_bytediv_set_rate(struct clk_hw *hw, unsigned long rate, @@ -328,7 +328,7 @@ static int clk_bytediv_set_rate(struct clk_hw *hw, unsigned long rate, /* Our special byte clock divider ops */ static const struct clk_ops clk_bytediv_ops = { - .round_rate = clk_bytediv_round_rate, + .determine_rate = clk_bytediv_determine_rate, .set_rate = clk_bytediv_set_rate, .recalc_rate = clk_bytediv_recalc_rate, }; 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 8c98f91a5930..32f06edd21a9 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -90,6 +90,13 @@ struct dsi_pll_7nm { /* protects REG_DSI_7nm_PHY_CMN_CLK_CFG1 register */ spinlock_t pclk_mux_lock; + /* + * protects REG_DSI_7nm_PHY_CMN_CTRL_0 register and pll_enable_cnt + * member + */ + spinlock_t pll_enable_lock; + int pll_enable_cnt; + struct pll_7nm_cached_state cached_state; struct dsi_pll_7nm *slave; @@ -103,6 +110,9 @@ struct dsi_pll_7nm { */ static struct dsi_pll_7nm *pll_7nm_list[DSI_MAX]; +static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll); +static void dsi_pll_disable_pll_bias(struct dsi_pll_7nm *pll); + static void dsi_pll_setup_config(struct dsi_pll_config *config) { config->ssc_freq = 31500; @@ -340,6 +350,7 @@ static int dsi_pll_7nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, struct dsi_pll_7nm *pll_7nm = to_pll_7nm(hw); struct dsi_pll_config config; + dsi_pll_enable_pll_bias(pll_7nm); DBG("DSI PLL%d rate=%lu, parent's=%lu", pll_7nm->phy->id, rate, parent_rate); @@ -357,6 +368,7 @@ static int dsi_pll_7nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, dsi_pll_ssc_commit(pll_7nm, &config); + dsi_pll_disable_pll_bias(pll_7nm); /* flush, ensure all register writes are done*/ wmb(); @@ -385,19 +397,47 @@ static int dsi_pll_7nm_lock_status(struct dsi_pll_7nm *pll) static void dsi_pll_disable_pll_bias(struct dsi_pll_7nm *pll) { - u32 data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + unsigned long flags; + u32 data; + spin_lock_irqsave(&pll->pll_enable_lock, flags); + --pll->pll_enable_cnt; + if (pll->pll_enable_cnt < 0) { + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); + DRM_DEV_ERROR_RATELIMITED(&pll->phy->pdev->dev, + "bug: imbalance in disabling PLL bias\n"); + return; + } else if (pll->pll_enable_cnt > 0) { + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); + return; + } /* else: == 0 */ + + data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + data &= ~DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB; writel(0, pll->phy->pll_base + REG_DSI_7nm_PHY_PLL_SYSTEM_MUXES); - writel(data & ~BIT(5), pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + writel(data, pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); ndelay(250); } static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll) { - u32 data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + unsigned long flags; + 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; + } + + data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + data |= DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB; + writel(data, pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); - writel(data | BIT(5), pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); writel(0xc0, pll->phy->pll_base + REG_DSI_7nm_PHY_PLL_SYSTEM_MUXES); + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); ndelay(250); } @@ -491,6 +531,10 @@ static int dsi_pll_7nm_vco_prepare(struct clk_hw *hw) if (pll_7nm->slave) dsi_pll_enable_global_clk(pll_7nm->slave); + writel(0x1, pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_RBUF_CTRL); + if (pll_7nm->slave) + writel(0x1, pll_7nm->slave->phy->base + REG_DSI_7nm_PHY_CMN_RBUF_CTRL); + error: return rc; } @@ -534,6 +578,7 @@ static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw, u32 dec; u64 pll_freq, tmp64; + dsi_pll_enable_pll_bias(pll_7nm); dec = readl(base + REG_DSI_7nm_PHY_PLL_DECIMAL_DIV_START_1); dec &= 0xff; @@ -558,24 +603,24 @@ static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw, DBG("DSI PLL%d returning vco rate = %lu, dec = %x, frac = %x", pll_7nm->phy->id, (unsigned long)vco_rate, dec, frac); + dsi_pll_disable_pll_bias(pll_7nm); + return (unsigned long)vco_rate; } -static long dsi_pll_7nm_clk_round_rate(struct clk_hw *hw, - unsigned long rate, unsigned long *parent_rate) +static int dsi_pll_7nm_clk_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { struct dsi_pll_7nm *pll_7nm = to_pll_7nm(hw); - if (rate < pll_7nm->phy->cfg->min_pll_rate) - return pll_7nm->phy->cfg->min_pll_rate; - else if (rate > pll_7nm->phy->cfg->max_pll_rate) - return pll_7nm->phy->cfg->max_pll_rate; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, + pll_7nm->phy->cfg->min_pll_rate, pll_7nm->phy->cfg->max_pll_rate); + + return 0; } static const struct clk_ops clk_ops_dsi_pll_7nm_vco = { - .round_rate = dsi_pll_7nm_clk_round_rate, + .determine_rate = dsi_pll_7nm_clk_determine_rate, .set_rate = dsi_pll_7nm_vco_set_rate, .recalc_rate = dsi_pll_7nm_vco_recalc_rate, .prepare = dsi_pll_7nm_vco_prepare, @@ -593,6 +638,7 @@ static void dsi_7nm_pll_save_state(struct msm_dsi_phy *phy) void __iomem *phy_base = pll_7nm->phy->base; u32 cmn_clk_cfg0, cmn_clk_cfg1; + dsi_pll_enable_pll_bias(pll_7nm); cached->pll_out_div = readl(pll_7nm->phy->pll_base + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE); cached->pll_out_div &= 0x3; @@ -604,6 +650,7 @@ static void dsi_7nm_pll_save_state(struct msm_dsi_phy *phy) cmn_clk_cfg1 = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); cached->pll_mux = FIELD_GET(DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL__MASK, cmn_clk_cfg1); + dsi_pll_disable_pll_bias(pll_7nm); DBG("DSI PLL%d outdiv %x bit_clk_div %x pix_clk_div %x pll_mux %x", pll_7nm->phy->id, cached->pll_out_div, cached->bit_clk_div, cached->pix_clk_div, cached->pll_mux); @@ -826,8 +873,10 @@ static int dsi_pll_7nm_init(struct msm_dsi_phy *phy) spin_lock_init(&pll_7nm->postdiv_lock); spin_lock_init(&pll_7nm->pclk_mux_lock); + 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) { @@ -839,6 +888,12 @@ static int dsi_pll_7nm_init(struct msm_dsi_phy *phy) /* TODO: Remove this when we have proper display handover support */ msm_dsi_phy_pll_save_state(phy); + /* + * Store also proper vco_current_rate, because its value will be used in + * dsi_7nm_pll_restore_state(). + */ + if (!dsi_pll_7nm_vco_recalc_rate(&pll_7nm->clk_hw, VCO_REF_CLK_RATE)) + pll_7nm->vco_current_rate = pll_7nm->phy->cfg->min_pll_rate; return 0; } @@ -910,8 +965,10 @@ 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; @@ -1033,9 +1090,13 @@ 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 = BIT(6) | BIT(5); + 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); @@ -1148,7 +1209,9 @@ 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(""); @@ -1175,8 +1238,12 @@ 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/hdmi/hdmi_phy_8996.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c index 8c8d80b59573..36e928b0fd5a 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c @@ -629,16 +629,12 @@ static int hdmi_8996_pll_prepare(struct clk_hw *hw) return 0; } -static long hdmi_8996_pll_round_rate(struct clk_hw *hw, - unsigned long rate, - unsigned long *parent_rate) +static int hdmi_8996_pll_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { - if (rate < HDMI_PCLK_MIN_FREQ) - return HDMI_PCLK_MIN_FREQ; - else if (rate > HDMI_PCLK_MAX_FREQ) - return HDMI_PCLK_MAX_FREQ; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, HDMI_PCLK_MIN_FREQ, HDMI_PCLK_MAX_FREQ); + + return 0; } static unsigned long hdmi_8996_pll_recalc_rate(struct clk_hw *hw, @@ -684,7 +680,7 @@ static int hdmi_8996_pll_is_enabled(struct clk_hw *hw) static const struct clk_ops hdmi_8996_pll_ops = { .set_rate = hdmi_8996_pll_set_clk_rate, - .round_rate = hdmi_8996_pll_round_rate, + .determine_rate = hdmi_8996_pll_determine_rate, .recalc_rate = hdmi_8996_pll_recalc_rate, .prepare = hdmi_8996_pll_prepare, .unprepare = hdmi_8996_pll_unprepare, diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c index 33bb48ae58a2..a86ff3706369 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c @@ -646,16 +646,12 @@ static int hdmi_8998_pll_prepare(struct clk_hw *hw) return 0; } -static long hdmi_8998_pll_round_rate(struct clk_hw *hw, - unsigned long rate, - unsigned long *parent_rate) +static int hdmi_8998_pll_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { - if (rate < HDMI_PCLK_MIN_FREQ) - return HDMI_PCLK_MIN_FREQ; - else if (rate > HDMI_PCLK_MAX_FREQ) - return HDMI_PCLK_MAX_FREQ; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, HDMI_PCLK_MIN_FREQ, HDMI_PCLK_MAX_FREQ); + + return 0; } static unsigned long hdmi_8998_pll_recalc_rate(struct clk_hw *hw, @@ -688,7 +684,7 @@ static int hdmi_8998_pll_is_enabled(struct clk_hw *hw) static const struct clk_ops hdmi_8998_pll_ops = { .set_rate = hdmi_8998_pll_set_clk_rate, - .round_rate = hdmi_8998_pll_round_rate, + .determine_rate = hdmi_8998_pll_determine_rate, .recalc_rate = hdmi_8998_pll_recalc_rate, .prepare = hdmi_8998_pll_prepare, .unprepare = hdmi_8998_pll_unprepare, diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c b/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c index 83c8781fcc3f..6ba6bbdb7e05 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c @@ -373,12 +373,14 @@ static unsigned long hdmi_pll_recalc_rate(struct clk_hw *hw, return pll->pixclk; } -static long hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *parent_rate) +static int hdmi_pll_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { - const struct pll_rate *pll_rate = find_rate(rate); + const struct pll_rate *pll_rate = find_rate(req->rate); + + req->rate = pll_rate->rate; - return pll_rate->rate; + return 0; } static int hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate, @@ -402,7 +404,7 @@ static const struct clk_ops hdmi_pll_ops = { .enable = hdmi_pll_enable, .disable = hdmi_pll_disable, .recalc_rate = hdmi_pll_recalc_rate, - .round_rate = hdmi_pll_round_rate, + .determine_rate = hdmi_pll_determine_rate, .set_rate = hdmi_pll_set_rate, }; diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c index bbda865addae..97dc70876442 100644 --- a/drivers/gpu/drm/msm/msm_debugfs.c +++ b/drivers/gpu/drm/msm/msm_debugfs.c @@ -325,25 +325,28 @@ static struct drm_info_list msm_debugfs_list[] = { static int late_init_minor(struct drm_minor *minor) { - struct drm_device *dev = minor->dev; - struct msm_drm_private *priv = dev->dev_private; + struct drm_device *dev; + struct msm_drm_private *priv; int ret; if (!minor) return 0; + dev = minor->dev; + priv = dev->dev_private; + if (!priv->gpu_pdev) return 0; ret = msm_rd_debugfs_init(minor); if (ret) { - DRM_DEV_ERROR(minor->dev->dev, "could not install rd debugfs\n"); + DRM_DEV_ERROR(dev->dev, "could not install rd debugfs\n"); return ret; } ret = msm_perf_debugfs_init(minor); if (ret) { - DRM_DEV_ERROR(minor->dev->dev, "could not install perf debugfs\n"); + DRM_DEV_ERROR(dev->dev, "could not install perf debugfs\n"); return ret; } diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 9dcc7a596a11..7e977fec4100 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -826,6 +826,7 @@ static const struct file_operations fops = { #define DRIVER_FEATURES_KMS ( \ DRIVER_GEM | \ + DRIVER_GEM_GPUVA | \ DRIVER_ATOMIC | \ DRIVER_MODESET | \ 0 ) diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 985db9febd98..6d847d593f1a 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -229,7 +229,7 @@ void msm_crtc_disable_vblank(struct drm_crtc *crtc); int msm_register_mmu(struct drm_device *dev, struct msm_mmu *mmu); void msm_unregister_mmu(struct drm_device *dev, struct msm_mmu *mmu); -struct drm_gpuvm *msm_kms_init_vm(struct drm_device *dev); +struct drm_gpuvm *msm_kms_init_vm(struct drm_device *dev, struct device *mdss_dev); bool msm_use_mmu(struct drm_device *dev); int msm_ioctl_gem_submit(struct drm_device *dev, void *data, diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 7ff994d4f91a..07d8cdd6bb2e 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -95,7 +95,6 @@ void msm_gem_vma_get(struct drm_gem_object *obj) void msm_gem_vma_put(struct drm_gem_object *obj) { struct msm_drm_private *priv = obj->dev->dev_private; - struct drm_exec exec; if (atomic_dec_return(&to_msm_bo(obj)->vma_ref)) return; @@ -103,9 +102,13 @@ void msm_gem_vma_put(struct drm_gem_object *obj) if (!priv->kms) return; +#ifdef CONFIG_DRM_MSM_KMS + struct drm_exec exec; + msm_gem_lock_vm_and_obj(&exec, obj, priv->kms->vm); put_iova_spaces(obj, priv->kms->vm, true, "vma_put"); drm_exec_fini(&exec); /* drop locks */ +#endif } /* @@ -188,7 +191,7 @@ static struct page **get_pages(struct drm_gem_object *obj) if (!msm_obj->pages) { struct drm_device *dev = obj->dev; struct page **p; - int npages = obj->size >> PAGE_SHIFT; + size_t npages = obj->size >> PAGE_SHIFT; p = drm_gem_get_pages(obj); @@ -663,9 +666,13 @@ int msm_gem_set_iova(struct drm_gem_object *obj, static bool is_kms_vm(struct drm_gpuvm *vm) { +#ifdef CONFIG_DRM_MSM_KMS struct msm_drm_private *priv = vm->drm->dev_private; return priv->kms && (priv->kms->vm == vm); +#else + return false; +#endif } /* @@ -1113,10 +1120,12 @@ static void msm_gem_free_object(struct drm_gem_object *obj) put_pages(obj); } - if (msm_obj->flags & MSM_BO_NO_SHARE) { + if (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); } @@ -1139,7 +1148,7 @@ static int msm_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct /* convenience method to construct a GEM buffer object, and userspace handle */ int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file, - uint32_t size, uint32_t flags, uint32_t *handle, + size_t size, uint32_t flags, uint32_t *handle, char *name) { struct drm_gem_object *obj; @@ -1205,9 +1214,8 @@ static const struct drm_gem_object_funcs msm_gem_object_funcs = { .vm_ops = &vm_ops, }; -static int msm_gem_new_impl(struct drm_device *dev, - uint32_t size, uint32_t flags, - struct drm_gem_object **obj) +static int msm_gem_new_impl(struct drm_device *dev, uint32_t flags, + struct drm_gem_object **obj) { struct msm_drm_private *priv = dev->dev_private; struct msm_gem_object *msm_obj; @@ -1241,7 +1249,7 @@ static int msm_gem_new_impl(struct drm_device *dev, return 0; } -struct drm_gem_object *msm_gem_new(struct drm_device *dev, uint32_t size, uint32_t flags) +struct drm_gem_object *msm_gem_new(struct drm_device *dev, size_t size, uint32_t flags) { struct msm_drm_private *priv = dev->dev_private; struct msm_gem_object *msm_obj; @@ -1256,7 +1264,7 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev, uint32_t size, uint32 if (size == 0) return ERR_PTR(-EINVAL); - ret = msm_gem_new_impl(dev, size, flags, &obj); + ret = msm_gem_new_impl(dev, flags, &obj); if (ret) return ERR_PTR(ret); @@ -1296,12 +1304,12 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev, struct msm_drm_private *priv = dev->dev_private; struct msm_gem_object *msm_obj; struct drm_gem_object *obj; - uint32_t size; - int ret, npages; + size_t size, npages; + int ret; size = PAGE_ALIGN(dmabuf->size); - ret = msm_gem_new_impl(dev, size, MSM_BO_WC, &obj); + ret = msm_gem_new_impl(dev, MSM_BO_WC, &obj); if (ret) return ERR_PTR(ret); @@ -1344,7 +1352,7 @@ fail: return ERR_PTR(ret); } -void *msm_gem_kernel_new(struct drm_device *dev, uint32_t size, uint32_t flags, +void *msm_gem_kernel_new(struct drm_device *dev, size_t size, uint32_t flags, struct drm_gpuvm *vm, struct drm_gem_object **bo, uint64_t *iova) { diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index 88239da1cd72..a4cf31853c50 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -100,7 +100,7 @@ struct msm_gem_vm { * * Only used for kernel managed VMs, unused for user managed VMs. * - * Protected by @mm_lock. + * Protected by vm lock. See msm_gem_lock_vm_and_obj(), for ex. */ struct drm_mm mm; @@ -297,10 +297,10 @@ bool msm_gem_active(struct drm_gem_object *obj); int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout); int msm_gem_cpu_fini(struct drm_gem_object *obj); int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file, - uint32_t size, uint32_t flags, uint32_t *handle, char *name); + size_t size, uint32_t flags, uint32_t *handle, char *name); struct drm_gem_object *msm_gem_new(struct drm_device *dev, - uint32_t size, uint32_t flags); -void *msm_gem_kernel_new(struct drm_device *dev, uint32_t size, uint32_t flags, + size_t size, uint32_t flags); +void *msm_gem_kernel_new(struct drm_device *dev, size_t size, uint32_t flags, struct drm_gpuvm *vm, struct drm_gem_object **bo, uint64_t *iova); void msm_gem_kernel_put(struct drm_gem_object *bo, struct drm_gpuvm *vm); diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c index c0a33ac839cb..036d34c674d9 100644 --- a/drivers/gpu/drm/msm/msm_gem_prime.c +++ b/drivers/gpu/drm/msm/msm_gem_prime.c @@ -15,7 +15,7 @@ struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj) { struct msm_gem_object *msm_obj = to_msm_bo(obj); - int npages = obj->size >> PAGE_SHIFT; + size_t npages = obj->size >> PAGE_SHIFT; if (msm_obj->flags & MSM_BO_NO_SHARE) return ERR_PTR(-EINVAL); diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 5f8e939a5906..3ab3b27134f9 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -271,32 +271,37 @@ out: return ret; } -/* This is where we make sure all the bo's are reserved and pin'd: */ -static int submit_lock_objects(struct msm_gem_submit *submit) +static int submit_lock_objects_vmbind(struct msm_gem_submit *submit) { - unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT; + unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT | DRM_EXEC_IGNORE_DUPLICATES; struct drm_exec *exec = &submit->exec; - int ret; + int ret = 0; - if (msm_context_is_vmbind(submit->queue->ctx)) { - flags |= DRM_EXEC_IGNORE_DUPLICATES; + drm_exec_init(&submit->exec, flags, submit->nr_bos); - drm_exec_init(&submit->exec, flags, submit->nr_bos); + drm_exec_until_all_locked (&submit->exec) { + ret = drm_gpuvm_prepare_vm(submit->vm, exec, 1); + drm_exec_retry_on_contention(exec); + if (ret) + break; - drm_exec_until_all_locked (&submit->exec) { - ret = drm_gpuvm_prepare_vm(submit->vm, exec, 1); - drm_exec_retry_on_contention(exec); - if (ret) - return ret; + ret = drm_gpuvm_prepare_objects(submit->vm, exec, 1); + drm_exec_retry_on_contention(exec); + if (ret) + break; + } - ret = drm_gpuvm_prepare_objects(submit->vm, exec, 1); - drm_exec_retry_on_contention(exec); - if (ret) - return ret; - } + return ret; +} - return 0; - } +/* This is where we make sure all the bo's are reserved and pin'd: */ +static int submit_lock_objects(struct msm_gem_submit *submit) +{ + unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT; + int ret = 0; + + if (msm_context_is_vmbind(submit->queue->ctx)) + return submit_lock_objects_vmbind(submit); drm_exec_init(&submit->exec, flags, submit->nr_bos); @@ -305,17 +310,17 @@ static int submit_lock_objects(struct msm_gem_submit *submit) drm_gpuvm_resv_obj(submit->vm)); drm_exec_retry_on_contention(&submit->exec); if (ret) - return ret; + break; for (unsigned i = 0; i < submit->nr_bos; i++) { struct drm_gem_object *obj = submit->bos[i].obj; ret = drm_exec_prepare_obj(&submit->exec, obj, 1); drm_exec_retry_on_contention(&submit->exec); if (ret) - return ret; + break; } } - return 0; + return ret; } static int submit_fence_sync(struct msm_gem_submit *submit) @@ -514,14 +519,15 @@ out: */ static void submit_cleanup(struct msm_gem_submit *submit, bool error) { + if (error) + submit_unpin_objects(submit); + if (submit->exec.objects) drm_exec_fini(&submit->exec); - if (error) { - submit_unpin_objects(submit); - /* job wasn't enqueued to scheduler, so early retirement: */ + /* if job wasn't enqueued to scheduler, early retirement: */ + if (error) msm_submit_retire(submit); - } } void msm_submit_retire(struct msm_gem_submit *submit) @@ -769,12 +775,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (ret == 0 && args->flags & MSM_SUBMIT_FENCE_FD_OUT) { sync_file = sync_file_create(submit->user_fence); - if (!sync_file) { + if (!sync_file) ret = -ENOMEM; - } else { - fd_install(out_fence_fd, sync_file->file); - args->fence_fd = out_fence_fd; - } } if (ret) @@ -812,10 +814,14 @@ out: out_unlock: mutex_unlock(&queue->lock); out_post_unlock: - if (ret && (out_fence_fd >= 0)) { - put_unused_fd(out_fence_fd); + if (ret) { + if (out_fence_fd >= 0) + put_unused_fd(out_fence_fd); if (sync_file) fput(sync_file->file); + } else if (sync_file) { + fd_install(out_fence_fd, sync_file->file); + args->fence_fd = out_fence_fd; } if (!IS_ERR_OR_NULL(submit)) { diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c index 3cd8562a5109..8316af1723c2 100644 --- a/drivers/gpu/drm/msm/msm_gem_vma.c +++ b/drivers/gpu/drm/msm/msm_gem_vma.c @@ -319,13 +319,10 @@ msm_gem_vma_map(struct drm_gpuva *vma, int prot, struct sg_table *sgt) mutex_lock(&vm->mmu_lock); /* - * NOTE: iommu/io-pgtable can allocate pages, so we cannot hold + * NOTE: if not using pgtable preallocation, we cannot hold * a lock across map/unmap which is also used in the job_run() * path, as this can cause deadlock in job_run() vs shrinker/ * reclaim. - * - * Revisit this if we can come up with a scheme to pre-alloc pages - * for the pgtable in map/unmap ops. */ ret = vm_map_op(vm, &(struct msm_vm_map_op){ .iova = vma->va.addr, @@ -399,7 +396,14 @@ msm_gem_vma_new(struct drm_gpuvm *gpuvm, struct drm_gem_object *obj, if (obj) GEM_WARN_ON((range_end - range_start) > obj->size); - drm_gpuva_init(&vma->base, range_start, range_end - range_start, obj, offset); + struct drm_gpuva_op_map op_map = { + .va.addr = range_start, + .va.range = range_end - range_start, + .gem.obj = obj, + .gem.offset = offset, + }; + + drm_gpuva_init_from_op(&vma->base, &op_map); vma->mapped = false; ret = drm_gpuva_insert(&vm->base, &vma->base); @@ -454,6 +458,8 @@ msm_gem_vm_bo_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec) struct op_arg { unsigned flags; struct msm_vm_bind_job *job; + const struct msm_vm_bind_op *op; + bool kept; }; static void @@ -475,14 +481,18 @@ vma_from_op(struct op_arg *arg, struct drm_gpuva_op_map *op) } static int -msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *arg) +msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg) { - struct msm_vm_bind_job *job = ((struct op_arg *)arg)->job; + struct op_arg *arg = _arg; + struct msm_vm_bind_job *job = arg->job; struct drm_gem_object *obj = op->map.gem.obj; struct drm_gpuva *vma; struct sg_table *sgt; unsigned prot; + if (arg->kept) + return 0; + vma = vma_from_op(arg, &op->map); if (WARN_ON(IS_ERR(vma))) return PTR_ERR(vma); @@ -602,15 +612,41 @@ msm_gem_vm_sm_step_remap(struct drm_gpuva_op *op, void *arg) } static int -msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *arg) +msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *_arg) { - struct msm_vm_bind_job *job = ((struct op_arg *)arg)->job; + struct op_arg *arg = _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); vm_dbg("%p:%p:%p: %016llx %016llx", vma->vm, vma, vma->gem.obj, vma->va.addr, vma->va.range); + /* + * Detect in-place remap. Turnip does this to change the vma flags, + * in particular MSM_VMA_DUMP. In this case we want to avoid actually + * touching the page tables, as that would require synchronization + * against SUBMIT jobs running on the GPU. + */ + if (op->unmap.keep && + (arg->op->op == MSM_VM_BIND_OP_MAP) && + (vma->gem.obj == arg->op->obj) && + (vma->gem.offset == arg->op->obj_offset) && + (vma->va.addr == arg->op->iova) && + (vma->va.range == arg->op->range)) { + /* We are only expecting a single in-place unmap+map cb pair: */ + WARN_ON(arg->kept); + + /* Leave the existing VMA in place, but signal that to the map cb: */ + arg->kept = true; + + /* Only flags are changing, so update that in-place: */ + unsigned orig_flags = vma->flags & (DRM_GPUVA_USERBITS - 1); + vma->flags = orig_flags | arg->flags; + + return 0; + } + if (!msm_vma->mapped) goto out_close; @@ -994,6 +1030,7 @@ vm_bind_job_lookup_ops(struct msm_vm_bind_job *job, struct drm_msm_vm_bind *args struct drm_device *dev = job->vm->drm; int ret = 0; int cnt = 0; + int i = -1; if (args->nr_ops == 1) { /* Single op case, the op is inlined: */ @@ -1027,11 +1064,12 @@ vm_bind_job_lookup_ops(struct msm_vm_bind_job *job, struct drm_msm_vm_bind *args spin_lock(&file->table_lock); - for (unsigned i = 0; i < args->nr_ops; i++) { + for (i = 0; i < args->nr_ops; i++) { + struct msm_vm_bind_op *op = &job->ops[i]; struct drm_gem_object *obj; - if (!job->ops[i].handle) { - job->ops[i].obj = NULL; + if (!op->handle) { + op->obj = NULL; continue; } @@ -1039,16 +1077,22 @@ vm_bind_job_lookup_ops(struct msm_vm_bind_job *job, struct drm_msm_vm_bind *args * normally use drm_gem_object_lookup(), but for bulk lookup * all under single table_lock just hit object_idr directly: */ - obj = idr_find(&file->object_idr, job->ops[i].handle); + obj = idr_find(&file->object_idr, op->handle); if (!obj) { - ret = UERR(EINVAL, dev, "invalid handle %u at index %u\n", job->ops[i].handle, i); + ret = UERR(EINVAL, dev, "invalid handle %u at index %u\n", op->handle, i); goto out_unlock; } drm_gem_object_get(obj); - job->ops[i].obj = obj; + op->obj = obj; cnt++; + + if ((op->range + op->obj_offset) > obj->size) { + ret = UERR(EINVAL, dev, "invalid range: %016llx + %016llx > %016zx\n", + op->range, op->obj_offset, obj->size); + goto out_unlock; + } } *nr_bos = cnt; @@ -1056,6 +1100,17 @@ vm_bind_job_lookup_ops(struct msm_vm_bind_job *job, struct drm_msm_vm_bind *args out_unlock: spin_unlock(&file->table_lock); + if (ret) { + for (; i >= 0; i--) { + struct msm_vm_bind_op *op = &job->ops[i]; + + if (!op->obj) + continue; + + drm_gem_object_put(op->obj); + op->obj = NULL; + } + } out: return ret; } @@ -1171,11 +1226,17 @@ vm_bind_job_lock_objects(struct msm_vm_bind_job *job, struct drm_exec *exec) op->obj_offset); break; case MSM_VM_BIND_OP_MAP: - case MSM_VM_BIND_OP_MAP_NULL: - ret = drm_gpuvm_sm_map_exec_lock(job->vm, exec, 1, - op->iova, op->range, - op->obj, op->obj_offset); + case MSM_VM_BIND_OP_MAP_NULL: { + struct drm_gpuvm_map_req map_req = { + .map.va.addr = op->iova, + .map.va.range = op->range, + .map.gem.obj = op->obj, + .map.gem.offset = op->obj_offset, + }; + + ret = drm_gpuvm_sm_map_exec_lock(job->vm, exec, 1, &map_req); break; + } default: /* * lookup_op() should have already thrown an error for @@ -1271,6 +1332,7 @@ vm_bind_job_prepare(struct msm_vm_bind_job *job) const struct msm_vm_bind_op *op = &job->ops[i]; struct op_arg arg = { .job = job, + .op = op, }; switch (op->op) { @@ -1282,10 +1344,17 @@ vm_bind_job_prepare(struct msm_vm_bind_job *job) if (op->flags & MSM_VM_BIND_OP_DUMP) arg.flags |= MSM_VMA_DUMP; fallthrough; - case MSM_VM_BIND_OP_MAP_NULL: - ret = drm_gpuvm_sm_map(job->vm, &arg, op->iova, - op->range, op->obj, op->obj_offset); + case MSM_VM_BIND_OP_MAP_NULL: { + struct drm_gpuvm_map_req map_req = { + .map.va.addr = op->iova, + .map.va.range = op->range, + .map.gem.obj = op->obj, + .map.gem.offset = op->obj_offset, + }; + + ret = drm_gpuvm_sm_map(job->vm, &arg, &map_req); break; + } default: /* * lookup_op() should have already thrown an error for @@ -1460,12 +1529,8 @@ msm_ioctl_vm_bind(struct drm_device *dev, void *data, struct drm_file *file) if (args->flags & MSM_VM_BIND_FENCE_FD_OUT) { sync_file = sync_file_create(job->fence); - if (!sync_file) { + if (!sync_file) ret = -ENOMEM; - } else { - fd_install(out_fence_fd, sync_file->file); - args->fence_fd = out_fence_fd; - } } if (ret) @@ -1494,10 +1559,14 @@ out: out_unlock: mutex_unlock(&queue->lock); out_post_unlock: - if (ret && (out_fence_fd >= 0)) { - put_unused_fd(out_fence_fd); + if (ret) { + if (out_fence_fd >= 0) + put_unused_fd(out_fence_fd); if (sync_file) fput(sync_file->file); + } else if (sync_file) { + fd_install(out_fence_fd, sync_file->file); + args->fence_fd = out_fence_fd; } if (!IS_ERR_OR_NULL(job)) { diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index c317b25a8162..17759abc46d7 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -304,7 +304,7 @@ static void crashstate_get_bos(struct msm_gpu_state *state, struct msm_gem_submi sizeof(struct msm_gpu_state_bo), GFP_KERNEL); for (int i = 0; state->bos && i < submit->nr_bos; i++) { - struct drm_gem_object *obj = submit->bos[i].obj;; + struct drm_gem_object *obj = submit->bos[i].obj; bool dump = rd_full || (submit->bos[i].flags & MSM_SUBMIT_BO_DUMP); msm_gem_lock(obj); @@ -465,6 +465,7 @@ static void recover_worker(struct kthread_work *work) struct msm_gem_submit *submit; struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu); char *comm = NULL, *cmd = NULL; + struct task_struct *task; int i; mutex_lock(&gpu->lock); @@ -482,16 +483,20 @@ static void recover_worker(struct kthread_work *work) /* Increment the fault counts */ submit->queue->faults++; - if (submit->vm) { + + task = get_pid_task(submit->pid, PIDTYPE_PID); + if (!task) + gpu->global_faults++; + else { struct msm_gem_vm *vm = to_msm_vm(submit->vm); vm->faults++; /* * If userspace has opted-in to VM_BIND (and therefore userspace - * management of the VM), faults mark the VM as unusuable. This + * management of the VM), faults mark the VM as unusable. This * matches vulkan expectations (vulkan is the main target for - * VM_BIND) + * VM_BIND). */ if (!vm->managed) msm_gem_vm_unusable(submit->vm); @@ -553,8 +558,15 @@ static void recover_worker(struct kthread_work *work) unsigned long flags; spin_lock_irqsave(&ring->submit_lock, flags); - list_for_each_entry(submit, &ring->submits, node) + list_for_each_entry(submit, &ring->submits, node) { + /* + * If the submit uses an unusable vm make sure + * we don't actually run it + */ + if (to_msm_vm(submit->vm)->unusable) + submit->nr_cmds = 0; gpu->funcs->submit(gpu, submit); + } spin_unlock_irqrestore(&ring->submit_lock, flags); } } diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index b2a96544f92a..a597f2bee30b 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -16,6 +16,7 @@ #include "msm_drv.h" #include "msm_fence.h" +#include "msm_gpu_trace.h" #include "msm_ringbuffer.h" #include "msm_gem.h" @@ -91,6 +92,7 @@ struct msm_gpu_funcs { * for cmdstream that is buffered in this FIFO upstream of the CP fw. */ bool (*progress)(struct msm_gpu *gpu, struct msm_ringbuffer *ring); + void (*sysprof_setup)(struct msm_gpu *gpu); }; /* Additional state for iommu faults: */ @@ -613,16 +615,19 @@ struct msm_gpu_state { static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data) { + trace_msm_gpu_regaccess(reg); writel(data, gpu->mmio + (reg << 2)); } static inline u32 gpu_read(struct msm_gpu *gpu, u32 reg) { + trace_msm_gpu_regaccess(reg); return readl(gpu->mmio + (reg << 2)); } static inline void gpu_rmw(struct msm_gpu *gpu, u32 reg, u32 mask, u32 or) { + trace_msm_gpu_regaccess(reg); msm_rmw(gpu->mmio + (reg << 2), mask, or); } @@ -644,7 +649,9 @@ static inline u64 gpu_read64(struct msm_gpu *gpu, u32 reg) * when the lo is read, so make sure to read the lo first to trigger * that */ + trace_msm_gpu_regaccess(reg); val = (u64) readl(gpu->mmio + (reg << 2)); + trace_msm_gpu_regaccess(reg+1); val |= ((u64) readl(gpu->mmio + ((reg + 1) << 2)) << 32); return val; @@ -652,8 +659,10 @@ static inline u64 gpu_read64(struct msm_gpu *gpu, u32 reg) static inline void gpu_write64(struct msm_gpu *gpu, u32 reg, u64 val) { + trace_msm_gpu_regaccess(reg); /* Why not a writeq here? Read the screed above */ writel(lower_32_bits(val), gpu->mmio + (reg << 2)); + trace_msm_gpu_regaccess(reg+1); writel(upper_32_bits(val), gpu->mmio + ((reg + 1) << 2)); } diff --git a/drivers/gpu/drm/msm/msm_gpu_trace.h b/drivers/gpu/drm/msm/msm_gpu_trace.h index 781bbe5540bd..5417f8d389a3 100644 --- a/drivers/gpu/drm/msm/msm_gpu_trace.h +++ b/drivers/gpu/drm/msm/msm_gpu_trace.h @@ -219,6 +219,18 @@ TRACE_EVENT(msm_mmu_prealloc_cleanup, TP_printk("count=%u, remaining=%u", __entry->count, __entry->remaining) ); +TRACE_EVENT(msm_gpu_regaccess, + TP_PROTO(u32 offset), + TP_ARGS(offset), + TP_STRUCT__entry( + __field(u32, offset) + ), + TP_fast_assign( + __entry->offset = offset; + ), + TP_printk("offset=0x%x", __entry->offset) +); + #endif #undef TRACE_INCLUDE_PATH diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 55c29f49b788..0e18619f96cb 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -14,7 +14,9 @@ struct msm_iommu { struct msm_mmu base; struct iommu_domain *domain; - atomic_t pagetables; + + struct mutex init_lock; /* protects pagetables counter and prr_page */ + int pagetables; struct page *prr_page; struct kmem_cache *pt_cache; @@ -227,7 +229,8 @@ static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu) * If this is the last attached pagetable for the parent, * disable TTBR0 in the arm-smmu driver */ - if (atomic_dec_return(&iommu->pagetables) == 0) { + mutex_lock(&iommu->init_lock); + if (--iommu->pagetables == 0) { adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, NULL); if (adreno_smmu->set_prr_bit) { @@ -236,6 +239,7 @@ static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu) iommu->prr_page = NULL; } } + mutex_unlock(&iommu->init_lock); free_io_pgtable_ops(pagetable->pgtbl_ops); kfree(pagetable); @@ -568,9 +572,12 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent, bool kernel_m * If this is the first pagetable that we've allocated, send it back to * the arm-smmu driver as a trigger to set up TTBR0 */ - if (atomic_inc_return(&iommu->pagetables) == 1) { + mutex_lock(&iommu->init_lock); + if (iommu->pagetables++ == 0) { ret = adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, &ttbr0_cfg); if (ret) { + iommu->pagetables--; + mutex_unlock(&iommu->init_lock); free_io_pgtable_ops(pagetable->pgtbl_ops); kfree(pagetable); return ERR_PTR(ret); @@ -595,6 +602,7 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent, bool kernel_m adreno_smmu->set_prr_bit(adreno_smmu->cookie, true); } } + mutex_unlock(&iommu->init_lock); /* Needed later for TLB flush */ pagetable->parent = parent; @@ -713,7 +721,7 @@ struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) int ret; if (!device_iommu_mapped(dev)) - return NULL; + return ERR_PTR(-ENODEV); domain = iommu_paging_domain_alloc(dev); if (IS_ERR(domain)) @@ -730,7 +738,7 @@ struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) iommu->domain = domain; msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU); - atomic_set(&iommu->pagetables, 0); + mutex_init(&iommu->init_lock); ret = iommu_attach_device(iommu->domain, dev); if (ret) { @@ -748,7 +756,7 @@ struct msm_mmu *msm_iommu_disp_new(struct device *dev, unsigned long quirks) struct msm_mmu *mmu; mmu = msm_iommu_new(dev, quirks); - if (IS_ERR_OR_NULL(mmu)) + if (IS_ERR(mmu)) return mmu; iommu = to_msm_iommu(mmu); @@ -764,11 +772,11 @@ struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsig struct msm_mmu *mmu; mmu = msm_iommu_new(dev, quirks); - if (IS_ERR_OR_NULL(mmu)) + if (IS_ERR(mmu)) return mmu; iommu = to_msm_iommu(mmu); - if (adreno_smmu && adreno_smmu->cookie) { + if (adreno_smmu->cookie) { const struct io_pgtable_cfg *cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie); size_t tblsz = get_tblsz(cfg); diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c index 6889f1c1e721..6e5e94f5c9a7 100644 --- a/drivers/gpu/drm/msm/msm_kms.c +++ b/drivers/gpu/drm/msm/msm_kms.c @@ -177,12 +177,11 @@ static int msm_kms_fault_handler(void *arg, unsigned long iova, int flags, void return -ENOSYS; } -struct drm_gpuvm *msm_kms_init_vm(struct drm_device *dev) +struct drm_gpuvm *msm_kms_init_vm(struct drm_device *dev, struct device *mdss_dev) { struct drm_gpuvm *vm; struct msm_mmu *mmu; struct device *mdp_dev = dev->dev; - struct device *mdss_dev = mdp_dev->parent; struct msm_drm_private *priv = dev->dev_private; struct msm_kms *kms = priv->kms; struct device *iommu_dev; @@ -193,18 +192,17 @@ struct drm_gpuvm *msm_kms_init_vm(struct drm_device *dev) */ if (device_iommu_mapped(mdp_dev)) iommu_dev = mdp_dev; - else + else if (mdss_dev && device_iommu_mapped(mdss_dev)) iommu_dev = mdss_dev; + else { + drm_info(dev, "no IOMMU, bailing out\n"); + return ERR_PTR(-ENODEV); + } mmu = msm_iommu_disp_new(iommu_dev, 0); if (IS_ERR(mmu)) return ERR_CAST(mmu); - if (!mmu) { - drm_info(dev, "no IOMMU, fallback to phys contig buffers for scanout\n"); - return NULL; - } - vm = msm_gem_vm_create(dev, mmu, "mdp_kms", 0x1000, 0x100000000 - 0x1000, true); if (IS_ERR(vm)) { @@ -275,6 +273,12 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv) if (ret) return ret; + ret = msm_disp_snapshot_init(ddev); + if (ret) { + DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret); + return ret; + } + ret = priv->kms_init(ddev); if (ret) { DRM_DEV_ERROR(dev, "failed to load kms\n"); @@ -327,10 +331,6 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv) goto err_msm_uninit; } - ret = msm_disp_snapshot_init(ddev); - if (ret) - DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret); - drm_mode_config_reset(ddev); return 0; diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index 1f5fe7811e01..2d0e3e784c04 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -154,8 +154,7 @@ static int _msm_mdss_irq_domain_add(struct msm_mdss *msm_mdss) dev = msm_mdss->dev; - domain = irq_domain_create_linear(of_fwnode_handle(dev->of_node), 32, - &msm_mdss_irqdomain_ops, msm_mdss); + domain = irq_domain_create_linear(dev_fwnode(dev), 32, &msm_mdss_irqdomain_ops, msm_mdss); if (!domain) { dev_err(dev, "failed to add irq_domain\n"); return -EINVAL; @@ -423,7 +422,7 @@ static struct msm_mdss *msm_mdss_init(struct platform_device *pdev, bool is_mdp5 if (IS_ERR(msm_mdss->mmio)) return ERR_CAST(msm_mdss->mmio); - dev_dbg(&pdev->dev, "mapped mdss address space @%pK\n", msm_mdss->mmio); + dev_dbg(&pdev->dev, "mapped mdss address space @%p\n", msm_mdss->mmio); ret = msm_mdss_parse_data_bus_icc_path(&pdev->dev, msm_mdss); if (ret) diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index 8617a82cd6b3..d53dfad16bde 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -40,6 +40,10 @@ int msm_context_set_sysprof(struct msm_context *ctx, struct msm_gpu *gpu, int sy break; } + /* Some gpu families require additional setup for sysprof */ + if (gpu->funcs->sysprof_setup) + gpu->funcs->sysprof_setup(gpu); + ctx->sysprof = sysprof; return 0; diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml index d860fd94feae..9459b6038217 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml @@ -594,10 +594,14 @@ by a particular renderpass/blit. <reg32 offset="0x0600" name="DBGC_CFG_DBGBUS_SEL_A"/> <reg32 offset="0x0601" name="DBGC_CFG_DBGBUS_SEL_B"/> <reg32 offset="0x0602" name="DBGC_CFG_DBGBUS_SEL_C"/> - <reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D"> + <reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D" variants="A6XX"> <bitfield high="7" low="0" name="PING_INDEX"/> <bitfield high="15" low="8" name="PING_BLK_SEL"/> </reg32> + <reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D" variants="A7XX-"> + <bitfield high="7" low="0" name="PING_INDEX"/> + <bitfield high="24" low="16" name="PING_BLK_SEL"/> + </reg32> <reg32 offset="0x0604" name="DBGC_CFG_DBGBUS_CNTLT"> <bitfield high="5" low="0" name="TRACEEN"/> <bitfield high="14" low="12" name="GRANU"/> @@ -810,7 +814,7 @@ by a particular renderpass/blit. <bitfield name="Y" low="16" high="29" type="uint"/> </bitset> - <reg32 offset="0x8000" name="GRAS_CL_CNTL" usage="rp_blit"> + <bitset name="a6xx_gras_cl_cntl" inline="yes"> <bitfield name="CLIP_DISABLE" pos="0" type="boolean"/> <bitfield name="ZNEAR_CLIP_DISABLE" pos="1" type="boolean"/> <bitfield name="ZFAR_CLIP_DISABLE" pos="2" type="boolean"/> @@ -822,18 +826,20 @@ by a particular renderpass/blit. <bitfield name="VP_CLIP_CODE_IGNORE" pos="7" type="boolean"/> <bitfield name="VP_XFORM_DISABLE" pos="8" type="boolean"/> <bitfield name="PERSP_DIVISION_DISABLE" pos="9" type="boolean"/> - </reg32> + </bitset> + + <reg32 offset="0x8000" name="GRAS_CL_CNTL" type="a6xx_gras_cl_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <bitset name="a6xx_gras_xs_clip_cull_distance" inline="yes"> <bitfield name="CLIP_MASK" low="0" high="7"/> <bitfield name="CULL_MASK" low="8" high="15"/> </bitset> - <reg32 offset="0x8001" name="GRAS_CL_VS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit"/> - <reg32 offset="0x8002" name="GRAS_CL_DS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit"/> - <reg32 offset="0x8003" name="GRAS_CL_GS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit"/> - <reg32 offset="0x8004" name="GRAS_CL_ARRAY_SIZE" low="0" high="10" type="uint" usage="rp_blit"/> + <reg32 offset="0x8001" name="GRAS_CL_VS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit" variants="A6XX-A7XX" /> + <reg32 offset="0x8002" name="GRAS_CL_DS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit" variants="A6XX-A7XX" /> + <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="0x8005" name="GRAS_CL_INTERP_CNTL" usage="rp_blit"> + <bitset name="a6xx_gras_cl_interp_cntl" inline="yes"> <!-- see also RB_INTERP_CNTL --> <bitfield name="IJ_PERSP_PIXEL" pos="0" type="boolean"/> <bitfield name="IJ_PERSP_CENTROID" pos="1" type="boolean"/> @@ -844,26 +850,69 @@ by a particular renderpass/blit. <bitfield name="COORD_MASK" low="6" high="9" type="hex"/> <bitfield name="UNK10" pos="10" type="boolean" variants="A7XX-"/> <bitfield name="UNK11" pos="11" type="boolean" variants="A7XX-"/> - </reg32> - <reg32 offset="0x8006" name="GRAS_CL_GUARDBAND_CLIP_ADJ" usage="rp_blit"> + </bitset> + + <reg32 offset="0x8005" name="GRAS_CL_INTERP_CNTL" type="a6xx_gras_cl_interp_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_gras_cl_guardband_clip_adj" inline="true"> <bitfield name="HORZ" low="0" high="8" type="uint"/> <bitfield name="VERT" low="10" high="18" type="uint"/> - </reg32> + </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="0x8008" name="GRAS_UNKNOWN_8008" variants="A7XX-" usage="cmd"/> + <!-- the scale/offset is per view, with up to 6 views --> + <bitset name="a6xx_gras_bin_foveat" inline="yes"> + <bitfield name="BINSCALEEN" pos="6" type="boolean"/> + <enum name="a7xx_bin_scale"> + <value value="0" name="NOSCALE"/> + <value value="1" name="SCALE2X"/> + <value value="2" name="SCALE4X"/> + </enum> + <bitfield name="XSCALE_0" low="8" high="9" type="a7xx_bin_scale"/> + <bitfield name="YSCALE_0" low="10" high="11" type="a7xx_bin_scale"/> + <bitfield name="XSCALE_1" low="12" high="13" type="a7xx_bin_scale"/> + <bitfield name="YSCALE_1" low="14" high="15" type="a7xx_bin_scale"/> + <bitfield name="XSCALE_2" low="16" high="17" type="a7xx_bin_scale"/> + <bitfield name="YSCALE_2" low="18" high="19" type="a7xx_bin_scale"/> + <bitfield name="XSCALE_3" low="20" high="21" type="a7xx_bin_scale"/> + <bitfield name="YSCALE_3" low="22" high="23" type="a7xx_bin_scale"/> + <bitfield name="XSCALE_4" low="24" high="25" type="a7xx_bin_scale"/> + <bitfield name="YSCALE_4" low="26" high="27" type="a7xx_bin_scale"/> + <bitfield name="XSCALE_5" low="28" high="29" type="a7xx_bin_scale"/> + <bitfield name="YSCALE_5" low="30" high="31" type="a7xx_bin_scale"/> + </bitset> - <reg32 offset="0x8009" name="GRAS_UNKNOWN_8009" variants="A7XX-" usage="cmd"/> - <reg32 offset="0x800a" name="GRAS_UNKNOWN_800A" variants="A7XX-" usage="cmd"/> - <reg32 offset="0x800b" name="GRAS_UNKNOWN_800B" variants="A7XX-" usage="cmd"/> - <reg32 offset="0x800c" name="GRAS_UNKNOWN_800C" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x8008" name="GRAS_BIN_FOVEAT" type="a6xx_gras_bin_foveat" variants="A7XX" 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"/> + <bitfield name="XOFFSET_1" low="10" high="19" shr="2" type="uint"/> + <bitfield name="XOFFSET_2" low="20" high="29" shr="2" type="uint"/> + </reg32> + <reg32 offset="0x800a" name="GRAS_BIN_FOVEAT_OFFSET_1" variants="A7XX-" usage="cmd"> + <bitfield name="XOFFSET_3" low="0" high="9" shr="2" type="uint"/> + <bitfield name="XOFFSET_4" low="10" high="19" shr="2" type="uint"/> + <bitfield name="XOFFSET_5" low="20" high="29" shr="2" type="uint"/> + </reg32> + <reg32 offset="0x800b" name="GRAS_BIN_FOVEAT_OFFSET_2" variants="A7XX-" usage="cmd"> + <bitfield name="YOFFSET_0" low="0" high="9" shr="2" type="uint"/> + <bitfield name="YOFFSET_1" low="10" high="19" shr="2" type="uint"/> + <bitfield name="YOFFSET_2" low="20" high="29" shr="2" type="uint"/> + </reg32> + <reg32 offset="0x800c" name="GRAS_BIN_FOVEAT_OFFSET_3" variants="A7XX-" usage="cmd"> + <bitfield name="YOFFSET_3" low="0" high="9" shr="2" type="uint"/> + <bitfield name="YOFFSET_4" low="10" high="19" shr="2" type="uint"/> + <bitfield name="YOFFSET_5" low="20" high="29" shr="2" type="uint"/> + </reg32> <!-- <reg32 offset="0x80f0" name="GRAS_UNKNOWN_80F0" type="a6xx_reg_xy"/> --> <!-- 0x8006-0x800f invalid --> - <array offset="0x8010" name="GRAS_CL_VIEWPORT" stride="6" length="16" usage="rp_blit"> + <array offset="0x8010" name="GRAS_CL_VIEWPORT" stride="6" length="16" variants="A6XX-A7XX" usage="rp_blit"> <reg32 offset="0" name="XOFFSET" type="float"/> <reg32 offset="1" name="XSCALE" type="float"/> <reg32 offset="2" name="YOFFSET" type="float"/> @@ -871,12 +920,13 @@ by a particular renderpass/blit. <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" usage="rp_blit"> + + <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> - <reg32 offset="0x8090" name="GRAS_SU_CNTL" usage="rp_blit"> + <bitset name="a6xx_gras_su_cntl" varset="chip"> <bitfield name="CULL_FRONT" pos="0" type="boolean"/> <bitfield name="CULL_BACK" pos="1" type="boolean"/> <bitfield name="FRONT_CW" pos="2" type="boolean"/> @@ -886,39 +936,66 @@ by a particular renderpass/blit. <bitfield name="LINE_MODE" pos="13" type="a5xx_line_mode"/> <bitfield name="UNK15" low="15" high="16"/> <!-- - On gen1 only MULTIVIEW_ENABLE exists. On gen3 we have - the ability to add the view index to either the RT array - index or the viewport index, and it seems that - MULTIVIEW_ENABLE doesn't do anything, instead we need to - set at least one of RENDERTARGETINDEXINCR or - VIEWPORTINDEXINCR to enable multiview. The blob still - sets MULTIVIEW_ENABLE regardless. - TODO: what about gen2 (a640)? + On gen1 only MULTIVIEW_ENABLE exists. On gen3 we have + the ability to add the view index to either the RT array + index or the viewport index, and it seems that + MULTIVIEW_ENABLE doesn't do anything, instead we need to + set at least one of RENDERTARGETINDEXINCR or + VIEWPORTINDEXINCR to enable multiview. The blob still + sets MULTIVIEW_ENABLE regardless. + TODO: what about gen2 (a640)? --> <bitfield name="MULTIVIEW_ENABLE" pos="17" type="boolean"/> - <bitfield name="RENDERTARGETINDEXINCR" pos="18" type="boolean"/> - <bitfield name="VIEWPORTINDEXINCR" pos="19" type="boolean"/> - <bitfield name="UNK20" low="20" high="22"/> - </reg32> - <reg32 offset="0x8091" name="GRAS_SU_POINT_MINMAX" usage="rp_blit"> + <bitfield name="RENDERTARGETINDEXINCR" pos="18" type="boolean" variants="A6XX-A7XX"/> + <bitfield name="VIEWPORTINDEXINCR" pos="19" type="boolean" variants="A6XX-A7XX"/> + <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"/> + + <bitset name="a6xx_gras_su_point_minmax" inline="yes"> <bitfield name="MIN" low="0" high="15" type="ufixed" radix="4"/> <bitfield name="MAX" low="16" high="31" type="ufixed" radix="4"/> - </reg32> - <reg32 offset="0x8092" name="GRAS_SU_POINT_SIZE" low="0" high="15" type="fixed" radix="4" usage="rp_blit"/> + </bitset> + + <reg32 offset="0x8091" name="GRAS_SU_POINT_MINMAX" type="a6xx_gras_su_point_minmax" variants="A6XX-A7XX" 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"/> + + <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"/> + + <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"/> + + <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"/> + <!-- 0x8093 invalid --> - <reg32 offset="0x8094" name="GRAS_SU_DEPTH_PLANE_CNTL" usage="rp_blit"> + <bitset name="a6xx_depth_plane_cntl" inline="yes"> <bitfield name="Z_MODE" low="0" high="1" type="a6xx_ztest_mode"/> - </reg32> - <reg32 offset="0x8095" name="GRAS_SU_POLY_OFFSET_SCALE" type="float" usage="rp_blit"/> - <reg32 offset="0x8096" name="GRAS_SU_POLY_OFFSET_OFFSET" type="float" usage="rp_blit"/> - <reg32 offset="0x8097" name="GRAS_SU_POLY_OFFSET_OFFSET_CLAMP" type="float" usage="rp_blit"/> - <!-- duplicates RB_DEPTH_BUFFER_INFO: --> - <reg32 offset="0x8098" name="GRAS_SU_DEPTH_BUFFER_INFO" usage="rp_blit"> + </bitset> + + <reg32 offset="0x8094" name="GRAS_SU_DEPTH_PLANE_CNTL" type="a6xx_depth_plane_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8095" name="GRAS_SU_POLY_OFFSET_SCALE" type="float" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8096" name="GRAS_SU_POLY_OFFSET_OFFSET" type="float" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8097" name="GRAS_SU_POLY_OFFSET_OFFSET_CLAMP" type="float" variants="A6XX-A7XX" 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"/> - </reg32> + </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="0x8099" name="GRAS_SU_CONSERVATIVE_RAS_CNTL" usage="cmd"> + <bitset name="a6xx_gras_su_conservative_ras_cntl" inline="yes"> <bitfield name="CONSERVATIVERASEN" pos="0" type="boolean"/> <enum name="a6xx_shift_amount"> <value value="0" name="NO_SHIFT"/> @@ -928,7 +1005,10 @@ by a particular renderpass/blit. <bitfield name="SHIFTAMOUNT" low="1" high="2" type="a6xx_shift_amount"/> <bitfield name="INNERCONSERVATIVERASEN" pos="3" type="boolean"/> <bitfield name="UNK4" low="4" high="5"/> - </reg32> + </bitset> + + <reg32 offset="0x8099" name="GRAS_SU_CONSERVATIVE_RAS_CNTL" type="a6xx_gras_su_conservative_ras_cntl" variants="A6XX-A7XX" usage="cmd"/> + <reg32 offset="0x809a" name="GRAS_SU_PATH_RENDERING_CNTL"> <bitfield name="UNK0" pos="0" type="boolean"/> <bitfield name="LINELENGTHEN" pos="1" type="boolean"/> @@ -938,10 +1018,13 @@ by a particular renderpass/blit. <bitfield name="WRITES_LAYER" pos="0" type="boolean"/> <bitfield name="WRITES_VIEW" pos="1" type="boolean"/> </bitset> - <reg32 offset="0x809b" name="GRAS_SU_VS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" usage="rp_blit"/> - <reg32 offset="0x809c" name="GRAS_SU_GS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" usage="rp_blit"/> - <reg32 offset="0x809d" name="GRAS_SU_DS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" usage="rp_blit"/> - <!-- 0x809e/0x809f invalid --> + <reg32 offset="0x809b" name="GRAS_SU_VS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_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"/> + + <bitset name="a6xx_rast_cntl" inline="yes"> + <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> + </bitset> <enum name="a6xx_sequenced_thread_dist"> <value value="0x0" name="DIST_SCREEN_COORD"/> @@ -989,7 +1072,7 @@ by a particular renderpass/blit. <value value="0x3" name="RB_BT"/> </enum> - <reg32 offset="0x80a0" name="GRAS_SC_CNTL" usage="rp_blit"> + <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"/> @@ -999,7 +1082,9 @@ by a particular renderpass/blit. <bitfield name="UNK9" pos="9" type="boolean"/> <bitfield name="ROTATION" low="10" high="11" type="uint"/> <bitfield name="EARLYVIZOUTEN" pos="12" type="boolean"/> - </reg32> + </bitset> + + <reg32 offset="0x80a0" name="GRAS_SC_CNTL" type="a6xx_gras_sc_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <enum name="a6xx_render_mode"> <value value="0x0" name="RENDERING_PASS"/> @@ -1020,7 +1105,7 @@ by a particular renderpass/blit. <value value="0x4" name="LRZ_FEEDBACK_LATE_Z"/> </enum> - <reg32 offset="0x80a1" name="GRAS_SC_BIN_CNTL" usage="rp_blit"> + <bitset name="a6xx_bin_cntl" inline="yes"> <bitfield name="BINW" low="0" high="5" shr="5" type="uint"/> <bitfield name="BINH" low="8" high="14" shr="4" type="uint"/> <bitfield name="RENDER_MODE" low="18" high="20" type="a6xx_render_mode"/> @@ -1033,18 +1118,25 @@ by a particular renderpass/blit. In sysmem mode GRAS_LRZ_CNTL.LRZ_WRITE is not considered. </doc> <bitfield name="LRZ_FEEDBACK_ZMODE_MASK" low="24" high="26" type="a6xx_lrz_feedback_mask"/> - <bitfield name="UNK27" pos="27"/> - </reg32> + <bitfield name="FORCE_LRZ_DIS" pos="27" type="boolean"/> + </bitset> + + <reg32 offset="0x80a1" name="GRAS_SC_BIN_CNTL" type="a6xx_bin_cntl" variants="A6XX-A7XX" usage="rp_blit"/> - <reg32 offset="0x80a2" name="GRAS_SC_RAS_MSAA_CNTL" usage="rp_blit"> + <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"/> <bitfield name="UNK3" pos="3"/> - </reg32> - <reg32 offset="0x80a3" name="GRAS_SC_DEST_MSAA_CNTL" usage="rp_blit"> + </bitset> + + <reg32 offset="0x80a2" name="GRAS_SC_RAS_MSAA_CNTL" type="a6xx_gras_sc_ras_msaa_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_gras_sc_dest_msaa_cntl" inline="yes"> <bitfield name="SAMPLES" low="0" high="1" type="a3xx_msaa_samples"/> <bitfield name="MSAA_DISABLE" pos="2" type="boolean"/> - </reg32> + </bitset> + + <reg32 offset="0x80a3" name="GRAS_SC_DEST_MSAA_CNTL" type="a6xx_gras_sc_dest_msaa_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <bitset name="a6xx_msaa_sample_pos_cntl" inline="yes"> <bitfield name="UNK0" pos="0"/> @@ -1062,30 +1154,35 @@ by a particular renderpass/blit. <bitfield name="SAMPLE_3_Y" low="28" high="31" radix="4" type="fixed"/> </bitset> - <reg32 offset="0x80a4" name="GRAS_SC_MSAA_SAMPLE_POS_CNTL" type="a6xx_msaa_sample_pos_cntl" usage="rp_blit"/> - <reg32 offset="0x80a5" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_0" type="a6xx_programmable_msaa_pos" usage="rp_blit"/> - <reg32 offset="0x80a6" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_1" type="a6xx_programmable_msaa_pos" usage="rp_blit"/> + <reg32 offset="0x80a4" name="GRAS_SC_MSAA_SAMPLE_POS_CNTL" type="a6xx_msaa_sample_pos_cntl" variants="A6XX-A7XX" usage="rp_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="0x80a7" name="GRAS_UNKNOWN_80A7" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x80a7" name="GRAS_ROTATION_CNTL" variants="A7XX" usage="cmd"/> - <!-- 0x80a7-0x80ae invalid --> - <reg32 offset="0x80af" name="GRAS_UNKNOWN_80AF" pos="0" 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"/> <bitset name="a6xx_scissor_xy" inline="yes"> <bitfield name="X" low="0" high="15" type="uint"/> <bitfield name="Y" low="16" high="31" type="uint"/> </bitset> - <array offset="0x80b0" name="GRAS_SC_SCREEN_SCISSOR" stride="2" length="16" usage="rp_blit"> + + <array offset="0x80b0" name="GRAS_SC_SCREEN_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="0x80d0" name="GRAS_SC_VIEWPORT_SCISSOR" stride="2" length="16" usage="rp_blit"> + + <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> - <reg32 offset="0x80f0" name="GRAS_SC_WINDOW_SCISSOR_TL" type="a6xx_reg_xy" usage="rp_blit"/> - <reg32 offset="0x80f1" name="GRAS_SC_WINDOW_SCISSOR_BR" type="a6xx_reg_xy" usage="rp_blit"/> + <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"/> <enum name="a6xx_fsr_combiner"> <value value="0" name="FSR_COMBINER_OP_KEEP"/> @@ -1095,7 +1192,7 @@ by a particular renderpass/blit. <value value="4" name="FSR_COMBINER_OP_MUL"/> </enum> - <reg32 offset="0x80f4" name="GRAS_VRS_CONFIG" variants="A7XX-" usage="rp_blit"> + <bitset name="a6xx_gras_vrs_config"> <bitfield name="PIPELINE_FSR_ENABLE" pos="0" type="boolean"/> <bitfield name="FRAG_SIZE_X" low="1" high="2" type="uint"/> <bitfield name="FRAG_SIZE_Y" low="3" high="4" type="uint"/> @@ -1103,20 +1200,32 @@ by a particular renderpass/blit. <bitfield name="COMBINER_OP_2" low="8" high="10" type="a6xx_fsr_combiner"/> <bitfield name="ATTACHMENT_FSR_ENABLE" pos="13" type="boolean"/> <bitfield name="PRIMITIVE_FSR_ENABLE" pos="20" type="boolean"/> - </reg32> - <reg32 offset="0x80f5" name="GRAS_QUALITY_BUFFER_INFO" variants="A7XX-" usage="rp_blit"> + </bitset> + + <reg32 offset="0x80f4" name="GRAS_VRS_CONFIG" type="a6xx_gras_vrs_config" variants="A7XX" usage="rp_blit"/> + + <bitset name="a6xx_gras_quality_buffer_info" inline="yes"> <bitfield name="LAYERED" pos="0" type="boolean"/> <bitfield name="TILE_MODE" low="1" high="2" type="a6xx_tile_mode"/> - </reg32> - <reg32 offset="0x80f6" name="GRAS_QUALITY_BUFFER_DIMENSION" variants="A7XX-" usage="rp_blit"> + </bitset> + + <reg32 offset="0x80f5" name="GRAS_QUALITY_BUFFER_INFO" type="a6xx_gras_quality_buffer_info" variants="A7XX" usage="rp_blit"/> + + <bitset name="a6xx_gras_quality_buffer_dimension" inline="yes"> <bitfield name="WIDTH" low="0" high="15" type="uint"/> <bitfield name="HEIGHT" low="16" high="31" type="uint"/> - </reg32> - <reg64 offset="0x80f8" name="GRAS_QUALITY_BUFFER_BASE" variants="A7XX-" type="waddress" usage="rp_blit"/> - <reg32 offset="0x80fa" name="GRAS_QUALITY_BUFFER_PITCH" variants="A7XX-" usage="rp_blit"> + </bitset> + + <reg32 offset="0x80f6" name="GRAS_QUALITY_BUFFER_DIMENSION" type="a6xx_gras_quality_buffer_dimension" variants="A7XX" usage="rp_blit"/> + + <reg64 offset="0x80f8" name="GRAS_QUALITY_BUFFER_BASE" variants="A7XX" 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"/> <bitfield name="ARRAY_PITCH" shr="6" low="10" high="28" type="uint"/> - </reg32> + </bitset> + + <reg32 offset="0x80fa" name="GRAS_QUALITY_BUFFER_PITCH" type="a6xx_gras_quality_buffer_pitch" variants="A7XX" usage="rp_blit"/> <enum name="a6xx_lrz_dir_status"> <value value="0x1" name="LRZ_DIR_LE"/> @@ -1124,7 +1233,7 @@ by a particular renderpass/blit. <value value="0x3" name="LRZ_DIR_INVALID"/> </enum> - <reg32 offset="0x8100" name="GRAS_LRZ_CNTL" usage="rp_blit"> + <bitset name="a6xx_gras_lrz_cntl" inline="yes"> <bitfield name="ENABLE" pos="0" type="boolean"/> <doc>LRZ write also disabled for blend/etc.</doc> <bitfield name="LRZ_WRITE" pos="1" type="boolean"/> @@ -1151,26 +1260,36 @@ by a particular renderpass/blit. </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-"/> - </reg32> + </bitset> + + <reg32 offset="0x8100" name="GRAS_LRZ_CNTL" type="a6xx_gras_lrz_cntl" usage="rp_blit" variants="A6XX-A7XX"/> <enum name="a6xx_fragcoord_sample_mode"> <value value="0" name="FRAGCOORD_CENTER"/> <value value="3" name="FRAGCOORD_SAMPLE"/> </enum> - <reg32 offset="0x8101" name="GRAS_LRZ_PS_INPUT_CNTL" low="0" high="2" usage="rp_blit"> + <bitset name="a6xx_gras_lrz_ps_input_cntl" inline="yes"> <bitfield name="SAMPLEID" pos="0" type="boolean"/> <bitfield name="FRAGCOORDSAMPLEMODE" low="1" high="2" type="a6xx_fragcoord_sample_mode"/> - </reg32> + </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_MRT_BUFFER_INFO_0" usage="rp_blit"> + <bitset name="a6xx_gras_lrz_mrt_buffer_info_0" inline="yes"> <bitfield name="COLOR_FORMAT" low="0" high="7" type="a6xx_format"/> - </reg32> - <reg64 offset="0x8103" name="GRAS_LRZ_BUFFER_BASE" align="256" type="waddress" usage="rp_blit"/> - <reg32 offset="0x8105" name="GRAS_LRZ_BUFFER_PITCH" usage="rp_blit"> + </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"/> + + <reg64 offset="0x8103" name="GRAS_LRZ_BUFFER_BASE" align="256" type="waddress" usage="rp_blit" variants="A6XX-A7XX"/> + + <bitset name="a6xx_gras_lrz_buffer_pitch" inline="yes"> <bitfield name="PITCH" low="0" high="7" shr="5" type="uint"/> <bitfield name="ARRAY_PITCH" low="10" high="28" shr="8" type="uint"/> - </reg32> + </bitset> + + <reg32 offset="0x8105" name="GRAS_LRZ_BUFFER_PITCH" type="a6xx_gras_lrz_buffer_pitch" usage="rp_blit" variants="A6XX-A7XX"/> <!-- The LRZ "fast clear" buffer is initialized to zero's by blob, and @@ -1203,7 +1322,6 @@ by a particular renderpass/blit. not. --> <reg64 offset="0x8106" name="GRAS_LRZ_FAST_CLEAR_BUFFER_BASE" align="64" type="waddress" usage="rp_blit"/> - <!-- 0x8108 invalid --> <reg32 offset="0x8109" name="GRAS_LRZ_PS_SAMPLEFREQ_CNTL" usage="rp_blit"> <bitfield name="PER_SAMP_MODE" pos="0" type="boolean"/> </reg32> @@ -1228,19 +1346,20 @@ by a particular renderpass/blit. <!-- 0x810c-0x810f invalid --> - <reg32 offset="0x8110" name="GRAS_UNKNOWN_8110" low="0" high="1" usage="cmd"/> + <reg32 offset="0x8110" name="GRAS_MODE_CNTL" low="0" high="1" variants="A6XX-A7XX" 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="0x8111" name="GRAS_LRZ_DEPTH_CLEAR" type="float" variants="A7XX"/> - <reg32 offset="0x8113" name="GRAS_LRZ_DEPTH_BUFFER_INFO" variants="A7XX-" usage="rp_blit"> + <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"/> - </reg32> + </bitset> + + <reg32 offset="0x8113" name="GRAS_LRZ_DEPTH_BUFFER_INFO" type="a6xx_gras_lrz_depth_buffer_info" variants="A7XX" usage="rp_blit"/> - <!-- Always written together and always equal 09510840 00000a62 --> - <reg32 offset="0x8120" name="GRAS_UNKNOWN_8120" variants="A7XX-" usage="cmd"/> - <reg32 offset="0x8121" name="GRAS_UNKNOWN_8121" variants="A7XX-" usage="cmd"/> + <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"/> <!-- 0x8112-0x83ff invalid --> @@ -1265,28 +1384,29 @@ by a particular renderpass/blit. <bitfield name="D24S8" pos="19" type="boolean"/> <!-- some sort of channel mask, disabled channels are set to zero ? --> <bitfield name="MASK" low="20" high="23"/> - <bitfield name="IFMT" low="24" high="28" type="a6xx_2d_ifmt"/> + <bitfield name="IFMT" low="24" high="26" type="a6xx_2d_ifmt"/> + <bitfield name="UNK27" pos="27" type="boolean"/> + <bitfield name="UNK28" pos="28" type="boolean"/> <bitfield name="RASTER_MODE" pos="29" type="a6xx_raster_mode"/> - <bitfield name="UNK30" pos="30" type="boolean" variants="A7XX-"/> + <bitfield name="COPY" pos="30" type="boolean" variants="A7XX-"/> </bitset> - <reg32 offset="0x8400" name="GRAS_A2D_BLT_CNTL" type="a6xx_a2d_bit_cntl" usage="rp_blit"/> + <reg32 offset="0x8400" name="GRAS_A2D_BLT_CNTL" type="a6xx_a2d_bit_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? --> - <reg32 offset="0x8401" name="GRAS_A2D_SRC_XMIN" low="8" high="24" type="int" usage="rp_blit"/> - <reg32 offset="0x8402" name="GRAS_A2D_SRC_XMAX" low="8" high="24" type="int" usage="rp_blit"/> - <reg32 offset="0x8403" name="GRAS_A2D_SRC_YMIN" low="8" high="24" type="int" usage="rp_blit"/> - <reg32 offset="0x8404" name="GRAS_A2D_SRC_YMAX" low="8" high="24" type="int" usage="rp_blit"/> - <reg32 offset="0x8405" name="GRAS_A2D_DEST_TL" type="a6xx_reg_xy" usage="rp_blit"/> - <reg32 offset="0x8406" name="GRAS_A2D_DEST_BR" type="a6xx_reg_xy" usage="rp_blit"/> + <reg32 offset="0x8401" name="GRAS_A2D_SRC_XMIN" low="8" high="24" type="int" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8402" name="GRAS_A2D_SRC_XMAX" low="8" high="24" type="int" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8403" name="GRAS_A2D_SRC_YMIN" low="8" high="24" type="int" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8404" name="GRAS_A2D_SRC_YMAX" low="8" high="24" type="int" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8405" name="GRAS_A2D_DEST_TL" type="a6xx_reg_xy" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8406" name="GRAS_A2D_DEST_BR" type="a6xx_reg_xy" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x8407" name="GRAS_2D_UNKNOWN_8407" low="0" high="31"/> <reg32 offset="0x8408" name="GRAS_2D_UNKNOWN_8408" low="0" high="31"/> <reg32 offset="0x8409" name="GRAS_2D_UNKNOWN_8409" low="0" high="31"/> - <reg32 offset="0x840a" name="GRAS_A2D_SCISSOR_TL" type="a6xx_reg_xy" usage="rp_blit"/> - <reg32 offset="0x840b" name="GRAS_A2D_SCISSOR_BR" type="a6xx_reg_xy" usage="rp_blit"/> - <!-- 0x840c-0x85ff invalid --> + <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"/> <!-- always 0x880 ? (and 0 in a640/a650 traces?) --> <reg32 offset="0x8600" name="GRAS_DBG_ECO_CNTL" usage="cmd"> @@ -1304,22 +1424,7 @@ by a particular renderpass/blit. --> <!-- same as GRAS_BIN_CONTROL, but without bit 27: --> - <reg32 offset="0x8800" name="RB_CNTL" variants="A6XX" usage="rp_blit"> - <bitfield name="BINW" low="0" high="5" shr="5" type="uint"/> - <bitfield name="BINH" low="8" high="14" shr="4" type="uint"/> - <bitfield name="RENDER_MODE" low="18" high="20" type="a6xx_render_mode"/> - <bitfield name="FORCE_LRZ_WRITE_DIS" pos="21" type="boolean"/> - <bitfield name="BUFFERS_LOCATION" low="22" high="23" type="a6xx_buffers_location"/> - <bitfield name="LRZ_FEEDBACK_ZMODE_MASK" low="24" high="26" type="a6xx_lrz_feedback_mask"/> - </reg32> - - <reg32 offset="0x8800" name="RB_CNTL" variants="A7XX-" usage="rp_blit"> - <bitfield name="BINW" low="0" high="5" shr="5" type="uint"/> - <bitfield name="BINH" low="8" high="14" shr="4" type="uint"/> - <bitfield name="RENDER_MODE" low="18" high="20" type="a6xx_render_mode"/> - <bitfield name="FORCE_LRZ_WRITE_DIS" pos="21" type="boolean"/> - <bitfield name="LRZ_FEEDBACK_ZMODE_MASK" low="24" high="26" type="a6xx_lrz_feedback_mask"/> - </reg32> + <reg32 offset="0x8800" name="RB_CNTL" variants="A6XX-A7XX" type="a6xx_bin_cntl" usage="rp_blit"/> <reg32 offset="0x8801" name="RB_RENDER_CNTL" variants="A6XX" usage="rp_blit"> <bitfield name="CCUSINGLECACHELINESIZE" low="3" high="5"/> @@ -1343,9 +1448,6 @@ by a particular renderpass/blit. <bitfield name="CONSERVATIVERASEN" pos="11" type="boolean"/> <bitfield name="INNERCONSERVATIVERASEN" pos="12" type="boolean"/> </reg32> - <reg32 offset="0x8116" name="GRAS_SU_RENDER_CNTL" variants="A7XX-" usage="rp_blit"> - <bitfield name="FS_DISABLE" pos="7" type="boolean"/> - </reg32> <reg32 offset="0x8802" name="RB_RAS_MSAA_CNTL" usage="rp_blit"> <bitfield name="SAMPLES" low="0" high="1" type="a3xx_msaa_samples"/> @@ -1512,9 +1614,7 @@ by a particular renderpass/blit. <bitfield name="SAMPLE_MASK" low="16" high="31"/> </reg32> <!-- 0x8866-0x886f invalid --> - <reg32 offset="0x8870" name="RB_DEPTH_PLANE_CNTL" usage="rp_blit"> - <bitfield name="Z_MODE" low="0" high="1" type="a6xx_ztest_mode"/> - </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"> <bitfield name="Z_TEST_ENABLE" pos="0" type="boolean"/> @@ -1528,14 +1628,9 @@ by a particular renderpass/blit. <bitfield name="Z_READ_ENABLE" pos="6" type="boolean"/> <bitfield name="Z_BOUNDS_ENABLE" pos="7" type="boolean"/> </reg32> - <reg32 offset="0x8114" name="GRAS_SU_DEPTH_CNTL" usage="rp_blit"> - <bitfield name="Z_TEST_ENABLE" pos="0" type="boolean"/> - </reg32> + <!-- duplicates GRAS_SU_DEPTH_BUFFER_INFO: --> - <reg32 offset="0x8872" name="RB_DEPTH_BUFFER_INFO" variants="A6XX" usage="rp_blit"> - <bitfield name="DEPTH_FORMAT" low="0" high="2" type="a6xx_depth_format"/> - <bitfield name="UNK3" low="3" high="4"/> - </reg32> + <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"/> @@ -1571,9 +1666,7 @@ by a particular renderpass/blit. <bitfield name="ZPASS_BF" low="26" high="28" type="adreno_stencil_op"/> <bitfield name="ZFAIL_BF" low="29" high="31" type="adreno_stencil_op"/> </reg32> - <reg32 offset="0x8115" name="GRAS_SU_STENCIL_CNTL" usage="rp_blit"> - <bitfield name="STENCIL_ENABLE" pos="0" type="boolean"/> - </reg32> + <reg32 offset="0x8881" name="RB_STENCIL_BUFFER_INFO" variants="A6XX" usage="rp_blit"> <bitfield name="SEPARATE_STENCIL" pos="0" type="boolean"/> <bitfield name="UNK1" pos="1" type="boolean"/> @@ -1612,8 +1705,9 @@ by a particular renderpass/blit. <reg32 offset="0x8899" name="RB_UNKNOWN_8899" variants="A7XX-" usage="cmd"/> <!-- 0x8899-0x88bf invalid --> <!-- clamps depth value for depth test/write --> - <reg32 offset="0x88c0" name="RB_VIEWPORT_ZCLAMP_MIN" type="float" usage="rp_blit"/> - <reg32 offset="0x88c1" name="RB_VIEWPORT_ZCLAMP_MAX" type="float" usage="rp_blit"/> + <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"/> + <!-- 0x88c2-0x88cf invalid--> <reg32 offset="0x88d0" name="RB_RESOLVE_CNTL_0" usage="rp_blit"> <bitfield name="UNK0" low="0" high="12"/> @@ -1622,7 +1716,7 @@ by a particular renderpass/blit. <reg32 offset="0x88d1" name="RB_RESOLVE_CNTL_1" type="a6xx_reg_xy" usage="rp_blit"/> <reg32 offset="0x88d2" name="RB_RESOLVE_CNTL_2" type="a6xx_reg_xy" usage="rp_blit"/> <!-- weird to duplicate other regs from same block?? --> - <reg32 offset="0x88d3" name="RB_RESOLVE_CNTL_3" usage="rp_blit"> + <reg32 offset="0x88d3" name="RB_RESOLVE_CNTL_3" variants="A6XX-A7XX" usage="rp_blit"> <bitfield name="BINW" low="0" high="5" shr="5" type="uint"/> <bitfield name="BINH" low="8" high="14" shr="4" type="uint"/> </reg32> @@ -1646,10 +1740,13 @@ by a particular renderpass/blit. <!-- array-pitch is size of layer --> <reg32 offset="0x88db" name="RB_RESOLVE_SYSTEM_BUFFER_ARRAY_PITCH" low="0" high="28" shr="6" type="uint" usage="rp_blit"/> <reg64 offset="0x88dc" name="RB_RESOLVE_SYSTEM_FLAG_BUFFER_BASE" type="waddress" align="64" usage="rp_blit"/> - <reg32 offset="0x88de" name="RB_RESOLVE_SYSTEM_FLAG_BUFFER_PITCH" usage="rp_blit"> + + <bitset name="a6xx_flag_buffer_pitch" inline="yes"> <bitfield name="PITCH" low="0" high="10" shr="6" type="uint"/> - <bitfield name="ARRAY_PITCH" low="11" high="27" shr="7" type="uint"/> - </reg32> + <bitfield name="ARRAY_PITCH" low="11" high="28" shr="7" type="uint"/> + </bitset> + + <reg32 offset="0x88de" name="RB_RESOLVE_SYSTEM_FLAG_BUFFER_PITCH" type="a6xx_flag_buffer_pitch" usage="rp_blit"/> <reg32 offset="0x88df" name="RB_RESOLVE_CLEAR_COLOR_DW0" usage="rp_blit"/> <reg32 offset="0x88e0" name="RB_RESOLVE_CLEAR_COLOR_DW1" usage="rp_blit"/> @@ -1722,10 +1819,7 @@ by a particular renderpass/blit. <reg32 offset="0x88f0" name="RB_UNKNOWN_88F0" low="0" high="11" 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"> - <bitfield name="PITCH" low="0" high="10" shr="6" type="uint"/> - <bitfield name="ARRAY_PITCH" low="11" high="23" shr="7" type="uint"/> - </reg32> + <reg32 offset="0x88f3" name="RB_UNK_FLAG_BUFFER_PITCH" type="a6xx_flag_buffer_pitch"/> <reg32 offset="0x88f4" name="RB_VRS_CONFIG" usage="rp_blit"> <bitfield name="UNK2" pos="2" type="boolean"/> @@ -1733,8 +1827,9 @@ by a particular renderpass/blit. <bitfield name="ATTACHMENT_FSR_ENABLE" pos="5" type="boolean"/> <bitfield name="PRIMITIVE_FSR_ENABLE" pos="18" type="boolean"/> </reg32> - <!-- Connected to VK_EXT_fragment_density_map? --> - <reg32 offset="0x88f5" name="RB_UNKNOWN_88F5" variants="A7XX-"/> + <reg32 offset="0x88f5" name="RB_BIN_FOVEAT" variants="A7XX-" usage="cmd"> + <bitfield name="BINSCALEEN" pos="6" type="boolean"/> + </reg32> <!-- 0x88f6-0x88ff invalid --> <reg64 offset="0x8900" name="RB_DEPTH_FLAG_BUFFER_BASE" type="waddress" align="64" usage="rp_blit"/> <reg32 offset="0x8902" name="RB_DEPTH_FLAG_BUFFER_PITCH" usage="rp_blit"> @@ -1743,12 +1838,10 @@ by a particular renderpass/blit. <bitfield name="UNK8" low="8" high="10"/> <bitfield name="ARRAY_PITCH" low="11" high="27" shr="7" type="uint"/> </reg32> + <array offset="0x8903" name="RB_COLOR_FLAG_BUFFER" stride="3" length="8" usage="rp_blit"> <reg64 offset="0" name="ADDR" type="waddress" align="64"/> - <reg32 offset="2" name="PITCH"> - <bitfield name="PITCH" low="0" high="10" shr="6" type="uint"/> - <bitfield name="ARRAY_PITCH" low="11" high="28" shr="7" type="uint"/> - </reg32> + <reg32 offset="2" name="PITCH" type="a6xx_flag_buffer_pitch"/> </array> <!-- 0x891b-0x8926 invalid --> <doc> @@ -1811,7 +1904,7 @@ by a particular renderpass/blit. <reg64 offset="0x8c1e" name="RB_A2D_DEST_BUFFER_BASE_2" type="waddress" align="64" usage="rp_blit"/> <reg64 offset="0x8c20" name="RB_A2D_DEST_FLAG_BUFFER_BASE" type="waddress" align="64" usage="rp_blit"/> - <reg32 offset="0x8c22" name="RB_A2D_DEST_FLAG_BUFFER_PITCH" low="0" high="7" shr="6" type="uint" usage="rp_blit"/> + <reg32 offset="0x8c22" name="RB_A2D_DEST_FLAG_BUFFER_PITCH" type="a6xx_flag_buffer_pitch" usage="rp_blit"/> <!-- this is a guess but seems likely (for NV12 with UBWC): --> <reg64 offset="0x8c23" name="RB_A2D_DEST_FLAG_BUFFER_BASE_1" type="waddress" align="64" usage="rp_blit"/> <reg32 offset="0x8c25" name="RB_A2D_DEST_FLAG_BUFFER_PITCH_1" low="0" high="7" shr="6" type="uint" usage="rp_blit"/> @@ -1917,13 +2010,13 @@ by a particular renderpass/blit. <bitfield name="CLIP_DIST_03_LOC" low="8" high="15" type="uint"/> <bitfield name="CLIP_DIST_47_LOC" low="16" high="23" type="uint"/> </bitset> - <reg32 offset="0x9101" name="VPC_VS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <reg32 offset="0x9102" name="VPC_GS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <reg32 offset="0x9103" name="VPC_DS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> + <reg32 offset="0x9101" name="VPC_VS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" variants="A6XX-A7XX" usage="rp_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="0x9311" name="VPC_VS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <reg32 offset="0x9312" name="VPC_GS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <reg32 offset="0x9313" name="VPC_DS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> + <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"/> <bitset name="a6xx_vpc_xs_siv_cntl" inline="yes"> <bitfield name="LAYERLOC" low="0" high="7" type="uint"/> @@ -1931,23 +2024,33 @@ by a particular renderpass/blit. <bitfield name="SHADINGRATELOC" low="16" high="23" type="uint" variants="A7XX-"/> </bitset> - <reg32 offset="0x9104" name="VPC_VS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> - <reg32 offset="0x9105" name="VPC_GS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> - <reg32 offset="0x9106" name="VPC_DS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> + <reg32 offset="0x9104" name="VPC_VS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_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="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"/> + <reg32 offset="0x9316" name="VPC_DS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_vpc_rast_stream_cntl" inline="yes"> + <!-- which stream to send to GRAS --> + <bitfield name="STREAM" low="0" high="1" type="uint"/> + <!-- discard primitives before rasterization --> + <bitfield name="DISCARD" pos="2" type="boolean"/> + </bitset> - <reg32 offset="0x9314" name="VPC_VS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> - <reg32 offset="0x9315" name="VPC_GS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> - <reg32 offset="0x9316" name="VPC_DS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> + <reg32 offset="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="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"> <!-- this mirrors VPC_RAST_STREAM_CNTL::DISCARD, although it seems it's unused --> <bitfield name="RASTER_DISCARD" pos="0" type="boolean"/> <bitfield name="UNK2" pos="2" type="boolean"/> </reg32> - <reg32 offset="0x9108" name="VPC_RAST_CNTL" usage="rp_blit"> - <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> - </reg32> + <reg32 offset="0x9108" name="VPC_RAST_CNTL" type="a6xx_rast_cntl" variants="A6XX-A7XX" 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"/> @@ -1987,10 +2090,10 @@ by a particular renderpass/blit. <bitfield name="VIEWS" low="2" high="6" type="uint"/> </bitset> - <reg32 offset="0x9109" name="VPC_PC_CNTL" type="a6xx_pc_cntl" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0x910a" name="VPC_GS_PARAM_0" type="a6xx_gs_param_0" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0x910b" name="VPC_STEREO_RENDERING_VIEWMASK" type="hex" low="0" high="15" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0x910c" name="VPC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0x9109" name="VPC_PC_CNTL" type="a6xx_pc_cntl" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x910a" name="VPC_GS_PARAM_0" type="a6xx_gs_param_0" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x910b" name="VPC_STEREO_RENDERING_VIEWMASK" type="hex" low="0" high="15" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x910c" name="VPC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" variants="A7XX" usage="rp_blit"/> <enum name="a6xx_varying_interp_mode"> <value value="0" name="INTERP_SMOOTH"/> @@ -2007,11 +2110,11 @@ by a particular renderpass/blit. </enum> <!-- 0x9109-0x91ff invalid --> - <array offset="0x9200" name="VPC_VARYING_INTERP_MODE" stride="1" length="8" usage="rp_blit"> + <array offset="0x9200" name="VPC_VARYING_INTERP_MODE" stride="1" length="8" variants="A6XX-A7XX" usage="rp_blit"> <doc>Packed array of a6xx_varying_interp_mode</doc> <reg32 offset="0x0" name="MODE"/> </array> - <array offset="0x9208" name="VPC_VARYING_REPLACE_MODE_0" stride="1" length="8" usage="rp_blit"> + <array offset="0x9208" name="VPC_VARYING_REPLACE_MODE" stride="1" length="8" variants="A6XX-A7XX" usage="rp_blit"> <doc>Packed array of a6xx_varying_ps_repl_mode</doc> <reg32 offset="0x0" name="MODE"/> </array> @@ -2020,12 +2123,12 @@ by a particular renderpass/blit. <reg32 offset="0x9210" name="VPC_UNKNOWN_9210" low="0" high="31" variants="A6XX" usage="cmd"/> <reg32 offset="0x9211" name="VPC_UNKNOWN_9211" low="0" high="31" variants="A6XX" usage="cmd"/> - <array offset="0x9212" name="VPC_VARYING_LM_TRANSFER_CNTL_0" stride="1" length="4" usage="rp_blit"> + <array offset="0x9212" name="VPC_VARYING_LM_TRANSFER_CNTL" stride="1" length="4" variants="A6XX-A7XX" usage="rp_blit"> <!-- one bit per varying component: --> <reg32 offset="0" name="DISABLE"/> </array> - <reg32 offset="0x9216" name="VPC_SO_MAPPING_WPTR" usage="rp_blit"> + <bitset name="a6xx_vpc_so_mapping_wptr" inline="yes"> <!-- Choose which DWORD to write to. There is an array of (4 * 64) DWORD's, dumped in the devcoredump at @@ -2052,20 +2155,25 @@ by a particular renderpass/blit. <bitfield name="ADDR" low="0" high="7" type="hex"/> <!-- clear all A_EN and B_EN bits for all DWORD's --> <bitfield name="RESET" pos="16" type="boolean"/> - </reg32> - <!-- special register, write multiple times to load SO program (not readable) --> - <reg32 offset="0x9217" name="VPC_SO_MAPPING_PORT" usage="rp_blit"> + </bitset> + + <reg32 offset="0x9216" name="VPC_SO_MAPPING_WPTR" type="a6xx_vpc_so_mapping_wptr" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_vpc_so_mapping_port" inline="yes"> <bitfield name="A_BUF" low="0" high="1" type="uint"/> <bitfield name="A_OFF" low="2" high="10" shr="2" type="uint"/> <bitfield name="A_EN" pos="11" type="boolean"/> <bitfield name="B_BUF" low="12" high="13" type="uint"/> <bitfield name="B_OFF" low="14" high="22" shr="2" type="uint"/> <bitfield name="B_EN" pos="23" type="boolean"/> - </reg32> + </bitset> + + <!-- 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"/> - <reg64 offset="0x9218" name="VPC_SO_QUERY_BASE" type="waddress" align="32" usage="cmd"/> + <reg64 offset="0x9218" name="VPC_SO_QUERY_BASE" type="waddress" align="32" variants="A6XX-A7XX" usage="cmd"/> - <array offset="0x921a" name="VPC_SO" stride="7" length="4" 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"/> <reg32 offset="2" name="BUFFER_SIZE" low="2" high="31" shr="2"/> <reg32 offset="3" name="BUFFER_STRIDE" low="0" high="9" shr="2"/> @@ -2073,12 +2181,13 @@ by a particular renderpass/blit. <reg64 offset="5" name="FLUSH_BASE" type="waddress" align="32"/> </array> - <reg32 offset="0x9236" name="VPC_REPLACE_MODE_CNTL" usage="cmd"> + <bitset name="a6xx_vpc_replace_mode_cntl" inline="yes"> <bitfield name="INVERT" pos="0" type="boolean"/> - </reg32> - <!-- 0x9237-0x92ff invalid --> - <!-- always 0x0 ? --> - <reg32 offset="0x9300" name="VPC_UNKNOWN_9300" low="0" high="2" usage="cmd"/> + </bitset> + + <reg32 offset="0x9236" name="VPC_REPLACE_MODE_CNTL" type="a6xx_vpc_replace_mode_cntl" variants="A6XX-A7XX" usage="cmd"/> + + <reg32 offset="0x9300" name="VPC_ROTATION_CNTL" low="0" high="2" variants="A6XX-A7XX" usage="cmd"/> <bitset name="a6xx_vpc_xs_cntl" inline="yes"> <doc> @@ -2097,11 +2206,12 @@ by a particular renderpass/blit. </doc> </bitfield> </bitset> - <reg32 offset="0x9301" name="VPC_VS_CNTL" type="a6xx_vpc_xs_cntl" usage="rp_blit"/> - <reg32 offset="0x9302" name="VPC_GS_CNTL" type="a6xx_vpc_xs_cntl" usage="rp_blit"/> - <reg32 offset="0x9303" name="VPC_DS_CNTL" type="a6xx_vpc_xs_cntl" usage="rp_blit"/> - <reg32 offset="0x9304" name="VPC_PS_CNTL" usage="rp_blit"> + <reg32 offset="0x9301" name="VPC_VS_CNTL" type="a6xx_vpc_xs_cntl" variants="A6XX-A7XX" usage="rp_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"/> + + <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 --> <bitfield name="PRIMIDLOC" low="8" high="15" type="uint"/> @@ -2118,9 +2228,11 @@ by a particular renderpass/blit. ViewID through the VS. </doc> </bitfield> - </reg32> + </bitset> + + <reg32 offset="0x9304" name="VPC_PS_CNTL" type="a6xx_vpc_ps_cntl" variants="A6XX-A7XX" usage="rp_blit"/> - <reg32 offset="0x9305" name="VPC_SO_CNTL" usage="rp_blit"> + <bitset name="a6xx_vpc_so_cntl" inline="yes"> <!-- It's offset by 1, and 0 means "disabled" --> @@ -2129,22 +2241,28 @@ by a particular renderpass/blit. <bitfield name="BUF2_STREAM" low="6" high="8" type="uint"/> <bitfield name="BUF3_STREAM" low="9" high="11" type="uint"/> <bitfield name="STREAM_ENABLE" low="15" high="18" type="hex"/> - </reg32> - <reg32 offset="0x9306" name="VPC_SO_OVERRIDE" usage="rp_blit"> + </bitset> + + <reg32 offset="0x9305" name="VPC_SO_CNTL" type="a6xx_vpc_so_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_so_override" inline="yes"> <bitfield name="DISABLE" pos="0" type="boolean"/> - </reg32> - <reg32 offset="0x9307" name="VPC_PS_RAST_CNTL" variants="A6XX-" usage="rp_blit"> <!-- A702 + A7xx --> - <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> - </reg32> - <reg32 offset="0x9308" name="VPC_ATTR_BUF_GMEM_SIZE" variants="A7XX-" usage="rp_blit"> - <bitfield name="SIZE_GMEM" low="0" high="31"/> - </reg32> - <reg32 offset="0x9309" name="VPC_ATTR_BUF_GMEM_BASE" variants="A7XX-" usage="rp_blit"> - <bitfield name="BASE_GMEM" low="0" high="31"/> - </reg32> - <reg32 offset="0x9b09" name="PC_ATTR_BUF_GMEM_SIZE" variants="A7XX-" usage="rp_blit"> - <bitfield name="SIZE_GMEM" low="0" high="31"/> - </reg32> + </bitset> + + <reg32 offset="0x9306" name="VPC_SO_OVERRIDE" type="a6xx_so_override" variants="A6XX-A7XX" usage="rp_blit"/> + + <reg32 offset="0x9807" name="PC_DGEN_SO_OVERRIDE" type="a6xx_so_override" variants="A7XX" usage="rp_blit"/> + + <reg32 offset="0x9307" name="VPC_PS_RAST_CNTL" type="a6xx_rast_cntl" variants="A6XX-A7XX" 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="0x9b09" name="PC_ATTR_BUF_GMEM_SIZE" variants="A7XX" type="uint" usage="rp_blit"/> + + <reg32 offset="0x930a" name="VPC_UNKNOWN_930A" variants="A7XX"/> + + <reg32 offset="0x960a" name="VPC_FLATSHADE_MODE_CNTL" variants="A7XX"/> <!-- 0x9307-0x95ff invalid --> @@ -2159,52 +2277,62 @@ by a particular renderpass/blit. <!-- TODO: regs from 0x9624-0x963a --> <!-- 0x963b-0x97ff invalid --> - <reg32 offset="0x9800" name="PC_HS_PARAM_0" low="0" high="5" type="uint" usage="rp_blit"/> + <reg32 offset="0x9800" name="PC_HS_PARAM_0" low="0" high="5" type="uint" variants="A6XX-A7XX" usage="rp_blit"/> - <!-- always 0x0 ? --> - <reg32 offset="0x9801" name="PC_HS_PARAM_1" usage="rp_blit"> + <bitset name="a6xx_pc_hs_param_1" inline="yes"> <bitfield name="SIZE" low="0" high="10" type="uint"/> <bitfield name="UNK13" pos="13"/> - </reg32> + </bitset> - <reg32 offset="0x9802" name="PC_DS_PARAM" usage="rp_blit"> + <reg32 offset="0x9801" name="PC_HS_PARAM_1" type="a6xx_pc_hs_param_1" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_pc_ds_param" inline="yes"> <bitfield name="SPACING" low="0" high="1" type="a6xx_tess_spacing"/> <bitfield name="OUTPUT" low="2" high="3" type="a6xx_tess_output"/> - </reg32> + </bitset> + + <reg32 offset="0x9802" name="PC_DS_PARAM" type="a6xx_pc_ds_param" variants="A6XX-A7XX" usage="rp_blit"/> - <reg32 offset="0x9803" name="PC_RESTART_INDEX" low="0" high="31" type="uint" usage="rp_blit"/> - <reg32 offset="0x9804" name="PC_MODE_CNTL" low="0" high="7" usage="rp_blit"/> + <reg32 offset="0x9803" name="PC_RESTART_INDEX" low="0" high="31" type="uint" variants="A6XX-A7XX" usage="rp_blit"/> + + <reg32 offset="0x9804" name="PC_MODE_CNTL" low="0" high="7" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x9805" name="PC_POWER_CNTL" low="0" high="2" usage="rp_blit"/> - <reg32 offset="0x9806" name="PC_PS_CNTL" usage="rp_blit"> + <bitset name="a6xx_pc_ps_cntl" inline="yes"> <bitfield name="PRIMITIVEIDEN" pos="0" type="boolean"/> - </reg32> + </bitset> - <!-- New in a6xx gen3+ --> - <reg32 offset="0x9808" name="PC_DGEN_SO_CNTL" usage="rp_blit"> + <reg32 offset="0x9806" name="PC_PS_CNTL" type="a6xx_pc_ps_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_pc_dgen_so_cntl" inline="yes"> <bitfield name="STREAM_ENABLE" low="15" high="18" type="hex"/> - </reg32> + </bitset> - <reg32 offset="0x980a" name="PC_DGEN_SU_CONSERVATIVE_RAS_CNTL"> + <!-- New in a6xx gen3+ --> + <reg32 offset="0x9808" name="PC_DGEN_SO_CNTL" type="a6xx_pc_dgen_so_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_pc_dgen_su_conservative_ras_cntl" inline="yes"> <bitfield name="CONSERVATIVERASEN" pos="0" type="boolean"/> - </reg32> - <!-- 0x980b-0x983f invalid --> + </bitset> + + <reg32 offset="0x980a" name="PC_DGEN_SU_CONSERVATIVE_RAS_CNTL" type="a6xx_pc_dgen_su_conservative_ras_cntl" variants="A6XX-A7XX"/> <!-- 0x9840 - 0x9842 are not readable --> - <reg32 offset="0x9840" name="PC_DRAW_INITIATOR"> + <bitset name="a6xx_draw_initiator" inline="yes"> <bitfield name="STATE_ID" low="0" high="7"/> - </reg32> + </bitset> - <reg32 offset="0x9841" name="PC_KERNEL_INITIATOR"> - <bitfield name="STATE_ID" low="0" high="7"/> - </reg32> + <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="0x9842" name="PC_EVENT_INITIATOR"> + <bitset name="a6xx_event_initiator" inline="yes"> <!-- I think only the low bit is actually used? --> <bitfield name="STATE_ID" low="16" high="23"/> <bitfield name="EVENT" low="0" high="6" type="vgt_event_type"/> - </reg32> + </bitset> + + <reg32 offset="0x9842" name="PC_EVENT_INITIATOR" type="a6xx_event_initiator" variants="A6XX-A7XX"/> <!-- 0x9880 written in a lot of places by SQE, same value gets written @@ -2215,45 +2343,21 @@ by a particular renderpass/blit. <!-- 0x9843-0x997f invalid --> - <reg32 offset="0x9981" name="PC_DGEN_RAST_CNTL" variants="A6XX" usage="rp_blit"> - <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> - </reg32> - <reg32 offset="0x9809" name="PC_DGEN_RAST_CNTL" variants="A7XX-" usage="rp_blit"> - <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> - </reg32> - - <reg32 offset="0x9980" name="VPC_RAST_STREAM_CNTL" variants="A6XX" usage="rp_blit"> - <!-- which stream to send to GRAS --> - <bitfield name="STREAM" low="0" high="1" type="uint"/> - <!-- discard primitives before rasterization --> - <bitfield name="DISCARD" pos="2" type="boolean"/> - </reg32> - <!-- VPC_RAST_STREAM_CNTL --> - <reg32 offset="0x9107" name="VPC_RAST_STREAM_CNTL" variants="A7XX-" usage="rp_blit"> - <!-- which stream to send to GRAS --> - <bitfield name="STREAM" low="0" high="1" type="uint"/> - <!-- discard primitives before rasterization --> - <bitfield name="DISCARD" pos="2" type="boolean"/> - </reg32> - <reg32 offset="0x9317" name="VPC_RAST_STREAM_CNTL_V2" variants="A7XX-" usage="rp_blit"> - <!-- which stream to send to GRAS --> - <bitfield name="STREAM" low="0" high="1" type="uint"/> - <!-- discard primitives before rasterization --> - <bitfield name="DISCARD" pos="2" type="boolean"/> - </reg32> + <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"/> <!-- 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="0x9885" name="PC_HS_BUFFER_SIZE" variants="A7XX" usage="cmd"/> <!-- Blob adds a bit more space {0x10, 0x20, 0x30, 0x40} bytes, but the meaning of this additional space is not known. --> - <reg32 offset="0x9886" name="PC_TF_BUFFER_SIZE" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x9886" name="PC_TF_BUFFER_SIZE" variants="A7XX" usage="cmd"/> <!-- 0x9982-0x9aff invalid --> - <reg32 offset="0x9b00" name="PC_CNTL" type="a6xx_pc_cntl" usage="rp_blit"/> + <reg32 offset="0x9b00" name="PC_CNTL" type="a6xx_pc_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <bitset name="a6xx_pc_xs_cntl" inline="yes"> <doc> @@ -2266,18 +2370,18 @@ by a particular renderpass/blit. <bitfield name="LAYER" pos="9" type="boolean"/> <bitfield name="VIEW" pos="10" type="boolean"/> <!-- note: PC_VS_CNTL doesn't have the PRIMITIVE_ID bit --> + <!-- since HS can't output anything, only PRIMITIVE_ID is valid --> <bitfield name="PRIMITIVE_ID" pos="11" type="boolean"/> <bitfield name="CLIP_MASK" low="16" high="23" type="uint"/> <bitfield name="SHADINGRATE" pos="24" type="boolean" variants="A7XX-"/> </bitset> - <reg32 offset="0x9b01" name="PC_VS_CNTL" type="a6xx_pc_xs_cntl" usage="rp_blit"/> - <reg32 offset="0x9b02" name="PC_GS_CNTL" type="a6xx_pc_xs_cntl" usage="rp_blit"/> - <!-- since HS can't output anything, only PRIMITIVE_ID is valid --> - <reg32 offset="0x9b03" name="PC_HS_CNTL" type="a6xx_pc_xs_cntl" usage="rp_blit"/> - <reg32 offset="0x9b04" name="PC_DS_CNTL" type="a6xx_pc_xs_cntl" usage="rp_blit"/> + <reg32 offset="0x9b01" name="PC_VS_CNTL" type="a6xx_pc_xs_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b02" name="PC_GS_CNTL" type="a6xx_pc_xs_cntl" variants="A6XX-A7XX" usage="rp_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="0x9b05" name="PC_GS_PARAM_0" type="a6xx_gs_param_0" usage="rp_blit"/> + <reg32 offset="0x9b05" name="PC_GS_PARAM_0" type="a6xx_gs_param_0" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x9b06" name="PC_PRIMITIVE_CNTL_6" variants="A6XX" usage="rp_blit"> <doc> @@ -2286,9 +2390,9 @@ by a particular renderpass/blit. <bitfield name="STRIDE_IN_VPC" low="0" high="10" type="uint"/> </reg32> - <reg32 offset="0x9b07" name="PC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" usage="rp_blit"/> + <reg32 offset="0x9b07" name="PC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" variants="A6XX-A7XX" 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" usage="rp_blit"/> + <reg32 offset="0x9b08" name="PC_STEREO_RENDERING_VIEWMASK" type="hex" low="0" high="15" variants="A6XX-A7XX" 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) --> @@ -2299,34 +2403,39 @@ by a particular renderpass/blit. <!-- TODO: 0x9e00-0xa000 range incomplete --> <reg32 offset="0x9e00" name="PC_DBG_ECO_CNTL"/> <reg32 offset="0x9e01" name="PC_ADDR_MODE_CNTL" type="a5xx_address_mode"/> - <reg64 offset="0x9e04" name="PC_DMA_BASE"/> - <reg32 offset="0x9e06" name="PC_DMA_OFFSET" type="uint"/> - <reg32 offset="0x9e07" name="PC_DMA_SIZE" type="uint"/> + <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="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="0x9810" name="PC_TESS_BASE" variants="A7XX" type="waddress" align="32" usage="cmd"/> - <reg32 offset="0x9e0b" name="PC_DRAWCALL_CNTL" type="vgt_draw_initiator_a4xx"> + <reg32 offset="0x9e0b" name="PC_DRAWCALL_CNTL" type="vgt_draw_initiator_a4xx" variants="A6XX-A7XX"> <doc> Possibly not really "initiating" the draw but the layout is similar to VGT_DRAW_INITIATOR on older gens </doc> </reg32> - <reg32 offset="0x9e0c" name="PC_DRAWCALL_INSTANCE_NUM" type="uint"/> - <reg32 offset="0x9e0d" name="PC_DRAWCALL_SIZE" type="uint"/> + <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"/> <!-- These match the contents of CP_SET_BIN_DATA (not written directly) --> - <reg32 offset="0x9e11" name="PC_VIS_STREAM_CNTL"> + <bitset name="a6xx_pc_vis_stream_cntl" inline="yes"> <bitfield name="UNK0" low="0" high="15"/> <bitfield name="VSC_SIZE" low="16" high="21" type="uint"/> <bitfield name="VSC_N" low="22" high="26" type="uint"/> - </reg32> - <reg64 offset="0x9e12" name="PC_PVIS_STREAM_BIN_BASE" type="waddress" align="32"/> - <reg64 offset="0x9e14" name="PC_DVIS_STREAM_BIN_BASE" type="waddress" align="32"/> + </bitset> + + <reg32 offset="0x9e11" name="PC_VIS_STREAM_CNTL" type="a6xx_pc_vis_stream_cntl" variants="A6XX-A7XX"/> + <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="0x9e1c" name="PC_DRAWCALL_CNTL_OVERRIDE"> + <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"/> - </reg32> + </bitset> + + <reg32 offset="0x9e1c" name="PC_DRAWCALL_CNTL_OVERRIDE" type="a6xx_pc_drawcall_cntl_override" variants="A6XX-A7XX"/> <reg32 offset="0x9e24" name="PC_UNKNOWN_9E24" variants="A7XX-" usage="cmd"/> @@ -2932,7 +3041,7 @@ by a particular renderpass/blit. <reg32 offset="0xa9b3" name="SP_CS_PROGRAM_COUNTER_OFFSET" type="uint" usage="cmd"/> <reg64 offset="0xa9b4" name="SP_CS_BASE" type="address" align="32" usage="cmd"/> <reg32 offset="0xa9b6" name="SP_CS_PVT_MEM_PARAM" type="a6xx_sp_xs_pvt_mem_param" usage="cmd"/> - <reg64 offset="0xa9b7" name="SP_CS_PVT_MEM_BASE" align="32" usage="cmd"/> + <reg64 offset="0xa9b7" name="SP_CS_PVT_MEM_BASE" type="waddress" align="32" usage="cmd"/> <reg32 offset="0xa9b9" name="SP_CS_PVT_MEM_SIZE" type="a6xx_sp_xs_pvt_mem_size" usage="cmd"/> <reg32 offset="0xa9ba" name="SP_CS_TSIZE" low="0" high="7" type="uint" usage="cmd"/> <reg32 offset="0xa9bb" name="SP_CS_CONFIG" type="a6xx_sp_xs_config" usage="cmd"/> @@ -3017,7 +3126,7 @@ by a particular renderpass/blit. UAV state for compute shader: --> <reg64 offset="0xa9f2" name="SP_CS_UAV_BASE" type="address" align="16" variants="A6XX"/> - <reg64 offset="0xa9f8" name="SP_CS_UAV_BASE" type="address" align="16" variants="A7XX"/> + <reg64 offset="0xa9f8" name="SP_CS_UAV_BASE" type="address" align="16" variants="A7XX-"/> <reg32 offset="0xaa00" name="SP_CS_USIZE" low="0" high="6" type="uint"/> <!-- Correlated with avgs/uvgs usage in FS --> @@ -3100,14 +3209,19 @@ by a particular renderpass/blit. instructions VS/HS/DS/GS/FS. See SP_CS_UAV_BASE_* for compute shaders. --> <reg64 offset="0xab1a" name="SP_GFX_UAV_BASE" type="address" align="16" usage="cmd"/> - <reg32 offset="0xab20" name="SP_GFX_USIZE" low="0" high="6" type="uint" usage="cmd"/> + <reg32 offset="0xab20" name="SP_GFX_USIZE" low="0" high="6" type="uint" variants="A6XX-A7XX" usage="cmd"/> - <reg32 offset="0xab22" name="SP_UNKNOWN_AB22" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xab22" name="SP_UNKNOWN_AB22" variants="A7XX" usage="cmd"/> + + <enum name="a6xx_sp_a2d_output_ifmt_type"> + <value name="OUTPUT_IFMT_2D_FLOAT" value="0"/> + <value name="OUTPUT_IFMT_2D_SINT" value="1"/> + <value name="OUTPUT_IFMT_2D_UINT" value="2"/> + </enum> <bitset name="a6xx_sp_a2d_output_info" inline="yes"> - <bitfield name="NORM" pos="0" type="boolean"/> - <bitfield name="SINT" pos="1" type="boolean"/> - <bitfield name="UINT" pos="2" type="boolean"/> + <bitfield name="HALF_PRECISION" pos="0" type="boolean"/> + <bitfield name="IFMT_TYPE" low="1" high="2" type="a6xx_sp_a2d_output_ifmt_type"/> <!-- looks like HW only cares about the base type of this format, which matches the ifmt? --> <bitfield name="COLOR_FORMAT" low="3" high="10" type="a6xx_format"/> @@ -3152,7 +3266,7 @@ by a particular renderpass/blit. <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="0xae6d" name="SP_READ_SEL" variants="A7XX-"> - <bitfield name="LOCATION" low="18" high="19" type="a7xx_state_location"/> + <bitfield name="LOCATION" low="18" high="20" type="a7xx_state_location"/> <bitfield name="PIPE" low="16" high="17" type="a7xx_pipe"/> <bitfield name="STATETYPE" low="8" high="15" type="a7xx_statetype_id"/> <bitfield name="USPTP" low="4" high="7"/> @@ -3188,7 +3302,7 @@ 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" usage="rp_blit"/> + <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="0xb307" name="TPL1_WINDOW_OFFSET" type="a6xx_reg_xy" usage="rp_blit"/> @@ -3228,12 +3342,12 @@ by a particular renderpass/blit. </reg32> <reg32 offset="0xb2c0" name="TPL1_A2D_SRC_TEXTURE_INFO" type="a6xx_a2d_src_texture_info" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xb2c1" name="TPL1_A2D_SRC_TEXTURE_SIZE" variants="A7XX"> + <reg32 offset="0xb2c1" name="TPL1_A2D_SRC_TEXTURE_SIZE" variants="A7XX-"> <bitfield name="WIDTH" low="0" high="14" type="uint"/> <bitfield name="HEIGHT" low="15" high="29" type="uint"/> </reg32> <reg64 offset="0xb2c2" name="TPL1_A2D_SRC_TEXTURE_BASE" type="address" align="16" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xb2c4" name="TPL1_A2D_SRC_TEXTURE_PITCH" variants="A7XX"> + <reg32 offset="0xb2c4" name="TPL1_A2D_SRC_TEXTURE_PITCH" variants="A7XX-"> <!-- Bits from 3..9 must be zero unless 'TPL1_A2D_BLT_CNTL::TYPE' is A6XX_TEX_IMG_BUFFER, which allows for lower alignment. @@ -3266,13 +3380,13 @@ by a particular renderpass/blit. <reg32 offset="0xb2ce" name="SP_PS_UNKNOWN_B4CE" low="0" high="31" variants="A7XX"/> <reg32 offset="0xb2cf" name="SP_PS_UNKNOWN_B4CF" low="0" high="30" variants="A7XX"/> <reg32 offset="0xb2d0" name="SP_PS_UNKNOWN_B4D0" low="0" high="29" variants="A7XX"/> - <reg32 offset="0xb2d1" name="TPL1_A2D_WINDOW_OFFSET" type="a6xx_reg_xy" variants="A7XX"/> + <reg32 offset="0xb2d1" name="TPL1_A2D_WINDOW_OFFSET" type="a6xx_reg_xy" variants="A7XX-"/> <reg32 offset="0xb2d2" name="TPL1_A2D_BLT_CNTL" variants="A7XX-" usage="rp_blit"> <bitfield name="RAW_COPY" pos="0" type="boolean"/> <bitfield name="START_OFFSET_TEXELS" low="16" high="21"/> <bitfield name="TYPE" low="29" high="31" type="a6xx_tex_type"/> </reg32> - <reg32 offset="0xab21" name="SP_WINDOW_OFFSET" type="a6xx_reg_xy" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xab21" name="SP_WINDOW_OFFSET" type="a6xx_reg_xy" variants="A7XX" usage="rp_blit"/> <!-- always 0x100000 or 0x1000000? --> <reg32 offset="0xb600" name="TPL1_DBG_ECO_CNTL" low="0" high="25" usage="cmd"/> @@ -3292,17 +3406,13 @@ by a particular renderpass/blit. </reg32> <reg32 offset="0xb605" name="TPL1_UNKNOWN_B605" low="0" high="7" type="uint" variants="A6XX" usage="cmd"/> <!-- always 0x0 or 0x44 ? --> - <reg32 offset="0xb608" name="TPL1_BICUBIC_WEIGHTS_TABLE_0" low="0" high="29" variants="A6XX"/> - <reg32 offset="0xb609" name="TPL1_BICUBIC_WEIGHTS_TABLE_1" low="0" high="29" variants="A6XX"/> - <reg32 offset="0xb60a" name="TPL1_BICUBIC_WEIGHTS_TABLE_2" low="0" high="29" variants="A6XX"/> - <reg32 offset="0xb60b" name="TPL1_BICUBIC_WEIGHTS_TABLE_3" low="0" high="29" variants="A6XX"/> - <reg32 offset="0xb60c" name="TPL1_BICUBIC_WEIGHTS_TABLE_4" low="0" high="29" variants="A6XX"/> + <array offset="0xb608" name="TPL1_BICUBIC_WEIGHTS_TABLE" stride="1" length="5" variants="A6XX"> + <reg32 offset="0" name="REG" low="0" high="29"/> + </array> - <reg32 offset="0xb608" name="TPL1_BICUBIC_WEIGHTS_TABLE_0" low="0" high="29" variants="A7XX" usage="cmd"/> - <reg32 offset="0xb609" name="TPL1_BICUBIC_WEIGHTS_TABLE_1" low="0" high="29" variants="A7XX" usage="cmd"/> - <reg32 offset="0xb60a" name="TPL1_BICUBIC_WEIGHTS_TABLE_2" low="0" high="29" variants="A7XX" usage="cmd"/> - <reg32 offset="0xb60b" name="TPL1_BICUBIC_WEIGHTS_TABLE_3" low="0" high="29" variants="A7XX" usage="cmd"/> - <reg32 offset="0xb60c" name="TPL1_BICUBIC_WEIGHTS_TABLE_4" low="0" high="29" variants="A7XX" usage="cmd"/> + <array offset="0xb608" name="TPL1_BICUBIC_WEIGHTS_TABLE" stride="1" length="5" variants="A7XX"> + <reg32 offset="0" name="REG" low="0" high="29" usage="cmd"/> + </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"/> @@ -3634,7 +3744,7 @@ by a particular renderpass/blit. <reg32 offset="0xbb10" name="SP_PS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A6XX" usage="rp_blit"/> <reg32 offset="0xab03" name="SP_PS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A7XX-" usage="rp_blit"/> - <array offset="0xab40" name="SP_SHARED_CONSTANT_GFX_0" stride="1" length="64" variants="A7XX-"/> + <array offset="0xab40" name="SP_SHARED_CONSTANT_GFX" stride="1" length="64" variants="A7XX"/> <reg32 offset="0xbb11" name="HLSQ_SHARED_CONSTS" variants="A6XX" usage="cmd"> <doc> @@ -3796,6 +3906,14 @@ by a particular renderpass/blit. <reg32 offset="0x0030" name="CFG_DBGBUS_TRACE_BUF2"/> </domain> +<domain name="A7XX_CX_DBGC" width="32" varset="chip"> + <!-- Bitfields shifted, but otherwise the same: --> + <reg32 offset="0x0000" name="CFG_DBGBUS_SEL_A" variants="A7XX-"> + <bitfield high="7" low="0" name="PING_INDEX"/> + <bitfield high="24" low="16" name="PING_BLK_SEL"/> + </reg32> +</domain> + <domain name="A6XX_CX_MISC" width="32" prefix="variant" varset="chip"> <reg32 offset="0x0001" name="SYSTEM_CACHE_CNTL_0"/> <reg32 offset="0x0002" name="SYSTEM_CACHE_CNTL_1"/> diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_descriptors.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_descriptors.xml index 307d43dda8a2..56cfaff614a4 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx_descriptors.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_descriptors.xml @@ -9,38 +9,6 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <domain name="A6XX_TEX_SAMP" width="32"> <doc>Texture sampler dwords</doc> - <enum name="a6xx_tex_filter"> <!-- same as a4xx? --> - <value name="A6XX_TEX_NEAREST" value="0"/> - <value name="A6XX_TEX_LINEAR" value="1"/> - <value name="A6XX_TEX_ANISO" value="2"/> - <value name="A6XX_TEX_CUBIC" value="3"/> <!-- a650 only --> - </enum> - <enum name="a6xx_tex_clamp"> <!-- same as a4xx? --> - <value name="A6XX_TEX_REPEAT" value="0"/> - <value name="A6XX_TEX_CLAMP_TO_EDGE" value="1"/> - <value name="A6XX_TEX_MIRROR_REPEAT" value="2"/> - <value name="A6XX_TEX_CLAMP_TO_BORDER" value="3"/> - <value name="A6XX_TEX_MIRROR_CLAMP" value="4"/> - </enum> - <enum name="a6xx_tex_aniso"> <!-- same as a4xx? --> - <value name="A6XX_TEX_ANISO_1" value="0"/> - <value name="A6XX_TEX_ANISO_2" value="1"/> - <value name="A6XX_TEX_ANISO_4" value="2"/> - <value name="A6XX_TEX_ANISO_8" value="3"/> - <value name="A6XX_TEX_ANISO_16" value="4"/> - </enum> - <enum name="a6xx_reduction_mode"> - <value name="A6XX_REDUCTION_MODE_AVERAGE" value="0"/> - <value name="A6XX_REDUCTION_MODE_MIN" value="1"/> - <value name="A6XX_REDUCTION_MODE_MAX" value="2"/> - </enum> - <enum name="a6xx_fast_border_color"> - <!-- R B G A --> - <value name="A6XX_BORDER_COLOR_0_0_0_0" value="0"/> - <value name="A6XX_BORDER_COLOR_0_0_0_1" value="1"/> - <value name="A6XX_BORDER_COLOR_1_1_1_0" value="2"/> - <value name="A6XX_BORDER_COLOR_1_1_1_1" value="3"/> - </enum> <reg32 offset="0" name="0"> <bitfield name="MIPFILTER_LINEAR_NEAR" pos="0" type="boolean"/> @@ -79,14 +47,6 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <domain name="A6XX_TEX_CONST" width="32" varset="chip"> <doc>Texture constant dwords</doc> - <enum name="a6xx_tex_swiz"> <!-- same as a4xx? --> - <value name="A6XX_TEX_X" value="0"/> - <value name="A6XX_TEX_Y" value="1"/> - <value name="A6XX_TEX_Z" value="2"/> - <value name="A6XX_TEX_W" value="3"/> - <value name="A6XX_TEX_ZERO" value="4"/> - <value name="A6XX_TEX_ONE" value="5"/> - </enum> <reg32 offset="0" name="0"> <bitfield name="TILE_MODE" low="0" high="1" type="a6xx_tile_mode"/> <bitfield name="SRGB" pos="2" type="boolean"/> diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml index 665539b098c6..4e42f055b85f 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml @@ -320,14 +320,14 @@ to upconvert to 32b float internally? 16b float: 3 --> <enum name="a6xx_2d_ifmt"> - <value value="0x10" name="R2D_UNORM8"/> <value value="0x7" name="R2D_INT32"/> <value value="0x6" name="R2D_INT16"/> <value value="0x5" name="R2D_INT8"/> <value value="0x4" name="R2D_FLOAT32"/> <value value="0x3" name="R2D_FLOAT16"/> + <value value="0x2" name="R2D_SNORM8"/> <value value="0x1" name="R2D_UNORM8_SRGB"/> - <value value="0x0" name="R2D_RAW"/> + <value value="0x0" name="R2D_UNORM8"/> </enum> <enum name="a6xx_tex_type"> @@ -380,4 +380,50 @@ to upconvert to 32b float internally? <value value="0x3" name="TESS_CCW_TRIS"/> </enum> +<enum name="a6xx_tex_filter"> <!-- same as a4xx? --> + <value name="A6XX_TEX_NEAREST" value="0"/> + <value name="A6XX_TEX_LINEAR" value="1"/> + <value name="A6XX_TEX_ANISO" value="2"/> + <value name="A6XX_TEX_CUBIC" value="3"/> <!-- a650 only --> +</enum> + +<enum name="a6xx_tex_clamp"> <!-- same as a4xx? --> + <value name="A6XX_TEX_REPEAT" value="0"/> + <value name="A6XX_TEX_CLAMP_TO_EDGE" value="1"/> + <value name="A6XX_TEX_MIRROR_REPEAT" value="2"/> + <value name="A6XX_TEX_CLAMP_TO_BORDER" value="3"/> + <value name="A6XX_TEX_MIRROR_CLAMP" value="4"/> +</enum> + +<enum name="a6xx_tex_aniso"> <!-- same as a4xx? --> + <value name="A6XX_TEX_ANISO_1" value="0"/> + <value name="A6XX_TEX_ANISO_2" value="1"/> + <value name="A6XX_TEX_ANISO_4" value="2"/> + <value name="A6XX_TEX_ANISO_8" value="3"/> + <value name="A6XX_TEX_ANISO_16" value="4"/> +</enum> + +<enum name="a6xx_reduction_mode"> + <value name="A6XX_REDUCTION_MODE_AVERAGE" value="0"/> + <value name="A6XX_REDUCTION_MODE_MIN" value="1"/> + <value name="A6XX_REDUCTION_MODE_MAX" value="2"/> +</enum> + +<enum name="a6xx_fast_border_color"> + <!-- R B G A --> + <value name="A6XX_BORDER_COLOR_0_0_0_0" value="0"/> + <value name="A6XX_BORDER_COLOR_0_0_0_1" value="1"/> + <value name="A6XX_BORDER_COLOR_1_1_1_0" value="2"/> + <value name="A6XX_BORDER_COLOR_1_1_1_1" value="3"/> +</enum> + +<enum name="a6xx_tex_swiz"> <!-- same as a4xx? --> + <value name="A6XX_TEX_X" value="0"/> + <value name="A6XX_TEX_Y" value="1"/> + <value name="A6XX_TEX_Z" value="2"/> + <value name="A6XX_TEX_W" value="3"/> + <value name="A6XX_TEX_ZERO" value="4"/> + <value name="A6XX_TEX_ONE" value="5"/> +</enum> + </database> diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml index 3d2cc339b8f1..b15a242d974d 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml @@ -99,6 +99,10 @@ 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"> + <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"> <bitfield name="HW_NAP_ENABLE" pos="0"/> <bitfield name="SID" low="4" high="8"/> @@ -127,6 +131,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <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"/> @@ -228,6 +233,12 @@ 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"/> </domain> </database> diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml index 7abc08635495..0e10e1c6d263 100644 --- a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml +++ b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml @@ -120,12 +120,12 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <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="UNK_40" value="40" variants="A7XX"/> + <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="UNK_2C" value="44" variants="A5XX-"/> - <value name="UNK_2D" value="45" variants="A5XX-"/> + <value name="VSC_BINNING_START" value="44" variants="A5XX-"/> + <value name="VSC_BINNING_END" value="45" variants="A5XX-"/> <!-- a6xx events --> <doc> @@ -523,7 +523,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <!-- Seems to set the mode flags which control which CP_SET_DRAW_STATE packets are executed, based on their ENABLE_MASK values - + CP_SET_MODE w/ payload of 0x1 seems to cause CP_SET_DRAW_STATE packets w/ ENABLE_MASK & 0x6 to execute immediately --> @@ -640,8 +640,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value name="CP_BV_BR_COUNT_OPS" value="0x1b" variants="A7XX-"/> <doc> Clears, adds to local, or adds to global timestamp </doc> <value name="CP_MODIFY_TIMESTAMP" value="0x1c" variants="A7XX-"/> - <!-- similar to CP_CONTEXT_REG_BUNCH, but discards first two dwords?? --> - <value name="CP_CONTEXT_REG_BUNCH2" value="0x5d" variants="A7XX-"/> + <value name="CP_NON_CONTEXT_REG_BUNCH" value="0x5d" variants="A7XX-"/> <doc> Write to a scratch memory that is read by CP_REG_TEST with SOURCE_SCRATCH_MEM set. It's not the same scratch as scratch registers. @@ -918,12 +917,6 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </reg32> <stripe varset="chip" variants="A5XX-"> - <reg32 offset="4" name="4"> - <bitfield name="INDX_BASE_LO" low="0" high="31"/> - </reg32> - <reg32 offset="5" name="5"> - <bitfield name="INDX_BASE_HI" low="0" high="31"/> - </reg32> <reg64 offset="4" name="INDX_BASE" type="address"/> <reg32 offset="6" name="6"> <!-- max # of elements in index buffer --> @@ -1099,8 +1092,10 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="BINNING" pos="20" varset="chip" variants="A6XX-" type="boolean"/> <bitfield name="GMEM" pos="21" varset="chip" variants="A6XX-" type="boolean"/> <bitfield name="SYSMEM" pos="22" varset="chip" variants="A6XX-" type="boolean"/> - <bitfield name="GROUP_ID" low="24" high="28" type="uint"/> + <!-- high bit is 28 until a750: --> + <bitfield name="GROUP_ID" low="24" high="29" type="uint"/> </reg32> + <reg64 offset="1" name="ADDR" type="address"/> <reg32 offset="1" name="1"> <bitfield name="ADDR_LO" low="0" high="31" type="hex"/> </reg32> @@ -1166,26 +1161,11 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </reg32> <stripe varset="a7xx_abs_mask_mode" variants="NO_ABS_MASK"> <!-- BIN_DATA_ADDR -> VSC_PIPE[p].DATA_ADDRESS --> - <reg32 offset="1" name="1"> - <bitfield name="BIN_DATA_ADDR_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="BIN_DATA_ADDR_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="1" name="BIN_DATA_ADDR" type="address"/> <!-- BIN_SIZE_ADDRESS -> VSC_SIZE_ADDRESS + (p * 4)--> - <reg32 offset="3" name="3"> - <bitfield name="BIN_SIZE_ADDRESS_LO" low="0" high="31"/> - </reg32> - <reg32 offset="4" name="4"> - <bitfield name="BIN_SIZE_ADDRESS_HI" low="0" high="31"/> - </reg32> + <reg64 offset="3" name="BIN_SIZE_ADDR" type="address"/> <!-- new on a6xx, where BIN_DATA_ADDR is the DRAW_STRM: --> - <reg32 offset="5" name="5"> - <bitfield name="BIN_PRIM_STRM_LO" low="0" high="31"/> - </reg32> - <reg32 offset="6" name="6"> - <bitfield name="BIN_PRIM_STRM_HI" low="0" high="31"/> - </reg32> + <reg64 offset="5" name="BIN_PRIM_STRM" type="address"/> <!-- a7xx adds a few more addresses to the end of the pkt --> @@ -1195,26 +1175,11 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <stripe varset="a7xx_abs_mask_mode" variants="ABS_MASK"> <reg32 offset="1" name="ABS_MASK"/> <!-- BIN_DATA_ADDR -> VSC_PIPE[p].DATA_ADDRESS --> - <reg32 offset="2" name="2"> - <bitfield name="BIN_DATA_ADDR_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="3" name="3"> - <bitfield name="BIN_DATA_ADDR_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="2" name="BIN_DATA_ADDR" type="address"/> <!-- BIN_SIZE_ADDRESS -> VSC_SIZE_ADDRESS + (p * 4)--> - <reg32 offset="4" name="4"> - <bitfield name="BIN_SIZE_ADDRESS_LO" low="0" high="31"/> - </reg32> - <reg32 offset="5" name="5"> - <bitfield name="BIN_SIZE_ADDRESS_HI" low="0" high="31"/> - </reg32> + <reg64 offset="4" name="BIN_SIZE_ADDR" type="address"/> <!-- new on a6xx, where BIN_DATA_ADDR is the DRAW_STRM: --> - <reg32 offset="6" name="6"> - <bitfield name="BIN_PRIM_STRM_LO" low="0" high="31"/> - </reg32> - <reg32 offset="7" name="7"> - <bitfield name="BIN_PRIM_STRM_HI" low="0" high="31"/> - </reg32> + <reg64 offset="6" name="BIN_PRIM_STRM" type="address"/> <!-- a7xx adds a few more addresses to the end of the pkt --> @@ -1300,7 +1265,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </reg32> </domain> -<domain name="CP_REG_TO_MEM" width="32"> +<domain name="CP_REG_TO_MEM" width="32" prefix="chip"> <reg32 offset="0" name="0"> <bitfield name="REG" low="0" high="17" type="hex"/> <!-- number of registers/dwords copied is max(CNT, 1). --> @@ -1308,12 +1273,12 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="64B" pos="30" type="boolean"/> <bitfield name="ACCUMULATE" pos="31" type="boolean"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="DEST" low="0" high="31"/> - </reg32> - <reg32 offset="2" name="2" varset="chip" variants="A5XX-"> - <bitfield name="DEST_HI" low="0" high="31"/> - </reg32> + <stripe varset="chip" variants="A2XX-A4XX"> + <reg32 offset="1" name="DEST" type="address"/> + </stripe> + <stripe varset="chip" variants="A5XX-"> + <reg64 offset="1" name="DEST" type="address"/> + </stripe> </domain> <domain name="CP_REG_TO_MEM_OFFSET_REG" width="32"> @@ -1329,12 +1294,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="64B" pos="30" type="boolean"/> <bitfield name="ACCUMULATE" pos="31" type="boolean"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="DEST" low="0" high="31"/> - </reg32> - <reg32 offset="2" name="2" varset="chip" variants="A5XX-"> - <bitfield name="DEST_HI" low="0" high="31"/> - </reg32> + <reg64 offset="1" name="DEST" type="waddress"/> <reg32 offset="3" name="3"> <bitfield name="OFFSET0" low="0" high="17" type="hex"/> <bitfield name="OFFSET0_SCRATCH" pos="19" type="boolean"/> @@ -1354,18 +1314,8 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="64B" pos="30" type="boolean"/> <bitfield name="ACCUMULATE" pos="31" type="boolean"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="DEST" low="0" high="31"/> - </reg32> - <reg32 offset="2" name="2" varset="chip" variants="A5XX-"> - <bitfield name="DEST_HI" low="0" high="31"/> - </reg32> - <reg32 offset="3" name="3"> - <bitfield name="OFFSET_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="4" name="4"> - <bitfield name="OFFSET_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="1" name="DEST" type="waddress"/> + <reg64 offset="3" name="OFFSET" type="waddress"/> </domain> <domain name="CP_MEM_TO_REG" width="32"> @@ -1378,12 +1328,12 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <!-- does the same thing as CP_MEM_TO_MEM::UNK31 --> <bitfield name="UNK31" pos="31" type="boolean"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="SRC" low="0" high="31"/> - </reg32> - <reg32 offset="2" name="2" varset="chip" variants="A5XX-"> - <bitfield name="SRC_HI" low="0" high="31"/> - </reg32> + <stripe varset="chip" variants="A2XX-A4XX"> + <reg32 offset="1" name="SRC" type="address"/> + </stripe> + <stripe varset="chip" variants="A5XX-"> + <reg64 offset="1" name="SRC" type="address"/> + </stripe> </domain> <domain name="CP_MEM_TO_MEM" width="32"> @@ -1403,6 +1353,10 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <!-- some other kind of wait --> <bitfield name="UNK31" pos="31" type="boolean"/> </reg32> + <reg64 offset="1" name="DST" type="waddress"/> + <reg64 offset="3" name="SRC_A" type="address"/> + <reg64 offset="5" name="SRC_B" type="address"/> + <reg64 offset="7" name="SRC_C" type="address"/> <!-- followed by sequence of addresses.. the first is the destination and the rest are N src addresses which are @@ -1461,12 +1415,12 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </domain> <domain name="CP_MEM_WRITE" width="32"> - <reg32 offset="0" name="0"> - <bitfield name="ADDR_LO" low="0" high="31"/> - </reg32> - <reg32 offset="1" name="1"> - <bitfield name="ADDR_HI" low="0" high="31"/> - </reg32> + <stripe varset="chip" variants="A2XX-A4XX"> + <reg32 offset="0" name="ADDR" type="address"/> + </stripe> + <stripe varset="chip" variants="A5XX-"> + <reg64 offset="0" name="ADDR" type="address"/> + </stripe> <!-- followed by the DWORDs to write --> </domain> @@ -1518,24 +1472,14 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="POLL" low="4" high="5" type="poll_memory_type"/> <bitfield name="WRITE_MEMORY" pos="8" type="boolean"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="POLL_ADDR_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="POLL_ADDR_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="1" name="POLL_ADDR" type="address"/> <reg32 offset="3" name="3"> <bitfield name="REF" low="0" high="31"/> </reg32> <reg32 offset="4" name="4"> <bitfield name="MASK" low="0" high="31"/> </reg32> - <reg32 offset="5" name="5"> - <bitfield name="WRITE_ADDR_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="6" name="6"> - <bitfield name="WRITE_ADDR_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="5" name="WRITE_ADDR" type="waddress"/> <reg32 offset="7" name="7"> <bitfield name="WRITE_DATA" low="0" high="31"/> </reg32> @@ -1550,12 +1494,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <!-- Reserved for flags, presumably? Unused in FW --> <bitfield name="RESERVED" low="0" high="31" type="hex"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="POLL_ADDR_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="POLL_ADDR_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="1" name="POLL_ADDR" type="address"/> <reg32 offset="3" name="3"> <bitfield name="REF" low="0" high="31"/> </reg32> @@ -1573,12 +1512,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="POLL" low="4" high="5" type="poll_memory_type"/> <bitfield name="WRITE_MEMORY" pos="8" type="boolean"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="POLL_ADDR_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="POLL_ADDR_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="1" name="POLL_ADDR" type="address"/> <reg32 offset="3" name="3"> <bitfield name="REF" low="0" high="31"/> </reg32> @@ -1712,12 +1646,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) TODO what is gpuaddr for, seems to be all 0's.. maybe needed for context switch? --> - <reg32 offset="1" name="1"> - <bitfield name="ADDR_0_LO" low="0" high="31"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="ADDR_0_HI" low="0" high="31"/> - </reg32> + <reg64 offset="1" name="ADDR" type="waddress"/> <reg32 offset="3" name="3"> <!-- ??? --> </reg32> @@ -1832,9 +1761,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <reg32 offset="0" name="0"> </reg32> <stripe varset="chip" variants="A4XX"> - <reg32 offset="1" name="1"> - <bitfield name="ADDR" low="0" high="31"/> - </reg32> + <reg32 offset="1" name="ADDR" type="address"/> <reg32 offset="2" name="2"> <!-- localsize is value minus one: --> <bitfield name="LOCALSIZEX" low="2" high="11" type="uint"/> @@ -1843,12 +1770,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </reg32> </stripe> <stripe varset="chip" variants="A5XX-"> - <reg32 offset="1" name="1"> - <bitfield name="ADDR_LO" low="0" high="31"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="ADDR_HI" low="0" high="31"/> - </reg32> + <reg64 offset="1" name="ADDR" type="address"/> <reg32 offset="3" name="3"> <!-- localsize is value minus one: --> <bitfield name="LOCALSIZEX" low="2" high="11" type="uint"/> @@ -2161,12 +2083,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </doc> </value> </enum> - <reg32 offset="0" name="0"> - <bitfield name="ADDR_LO" low="0" high="31"/> - </reg32> - <reg32 offset="1" name="1"> - <bitfield name="ADDR_HI" low="0" high="31"/> - </reg32> + <reg64 offset="0" name="ADDR" type="address"/> <reg32 offset="2" name="2"> <bitfield name="DWORDS" low="0" high="19" type="uint"/> <bitfield name="TYPE" low="20" high="21" type="amble_type"/> diff --git a/drivers/gpu/drm/msm/registers/display/dsi.xml b/drivers/gpu/drm/msm/registers/display/dsi.xml index 501ffc585a9f..c7a7b633d747 100644 --- a/drivers/gpu/drm/msm/registers/display/dsi.xml +++ b/drivers/gpu/drm/msm/registers/display/dsi.xml @@ -159,28 +159,28 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="RGB_SWAP" low="12" high="14" type="dsi_rgb_swap"/> </reg32> <reg32 offset="0x00020" name="ACTIVE_H"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00024" name="ACTIVE_V"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00028" name="TOTAL"> - <bitfield name="H_TOTAL" low="0" high="11" type="uint"/> - <bitfield name="V_TOTAL" low="16" high="27" type="uint"/> + <bitfield name="H_TOTAL" low="0" high="15" type="uint"/> + <bitfield name="V_TOTAL" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x0002c" name="ACTIVE_HSYNC"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00030" name="ACTIVE_VSYNC_HPOS"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00034" name="ACTIVE_VSYNC_VPOS"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00038" name="CMD_DMA_CTRL"> @@ -209,8 +209,8 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="WORD_COUNT" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00058" name="CMD_MDP_STREAM0_TOTAL"> - <bitfield name="H_TOTAL" low="0" high="11" type="uint"/> - <bitfield name="V_TOTAL" low="16" high="27" type="uint"/> + <bitfield name="H_TOTAL" low="0" high="15" type="uint"/> + <bitfield name="V_TOTAL" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x0005c" name="CMD_MDP_STREAM1_CTRL"> <bitfield name="DATA_TYPE" low="0" high="5" type="uint"/> diff --git a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml index 4e5ac0f25dea..f41516dd0567 100644 --- a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml +++ b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml @@ -22,7 +22,16 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <reg32 offset="0x00018" name="GLBL_CTRL"/> <reg32 offset="0x0001c" name="RBUF_CTRL"/> <reg32 offset="0x00020" name="VREG_CTRL_0"/> - <reg32 offset="0x00024" name="CTRL_0"/> + <reg32 offset="0x00024" name="CTRL_0"> + <bitfield name="CLKSL_SHUTDOWNB" pos="7" type="boolean"/> + <bitfield name="DIGTOP_PWRDN_B" pos="6" type="boolean"/> + <bitfield name="PLL_SHUTDOWNB" pos="5" type="boolean"/> + <bitfield name="DLN3_SHUTDOWNB" pos="4" type="boolean"/> + <bitfield name="DLN2_SHUTDOWNB" pos="3" type="boolean"/> + <bitfield name="CLK_SHUTDOWNB" pos="2" type="boolean"/> + <bitfield name="DLN1_SHUTDOWNB" pos="1" type="boolean"/> + <bitfield name="DLN0_SHUTDOWNB" pos="0" type="boolean"/> + </reg32> <reg32 offset="0x00028" name="CTRL_1"/> <reg32 offset="0x0002c" name="CTRL_2"/> <reg32 offset="0x00030" name="CTRL_3"/> diff --git a/drivers/gpu/drm/msm/registers/gen_header.py b/drivers/gpu/drm/msm/registers/gen_header.py index a409404627c7..1d603dadfabd 100644 --- a/drivers/gpu/drm/msm/registers/gen_header.py +++ b/drivers/gpu/drm/msm/registers/gen_header.py @@ -11,7 +11,6 @@ import collections import argparse import time import datetime -import re class Error(Exception): def __init__(self, message): @@ -31,7 +30,7 @@ class Enum(object): def names(self): return [n for (n, value) in self.values] - def dump(self): + def dump(self, is_deprecated): use_hex = False for (name, value) in self.values: if value > 0x1000: @@ -45,7 +44,7 @@ class Enum(object): print("\t%s = %d," % (name, value)) print("};\n") - def dump_pack_struct(self): + def dump_pack_struct(self, is_deprecated): pass class Field(object): @@ -70,11 +69,11 @@ class Field(object): raise parser.error("booleans should be 1 bit fields") elif self.type == "float" and not (high - low == 31 or high - low == 15): raise parser.error("floats should be 16 or 32 bit fields") - elif not self.type in builtin_types and not self.type in parser.enums: + elif self.type not in builtin_types and self.type not in parser.enums: raise parser.error("unknown type '%s'" % self.type) def ctype(self, var_name): - if self.type == None: + if self.type is None: type = "uint32_t" val = var_name elif self.type == "boolean": @@ -124,7 +123,7 @@ def field_name(reg, f): name = f.name.lower() else: # We hit this path when a reg is defined with no bitset fields, ie. - # <reg32 offset="0x88db" name="RB_BLIT_DST_ARRAY_PITCH" low="0" high="28" shr="6" type="uint"/> + # <reg32 offset="0x88db" name="RB_RESOLVE_SYSTEM_BUFFER_ARRAY_PITCH" low="0" high="28" shr="6" type="uint"/> name = reg.name.lower() if (name in [ "double", "float", "int" ]) or not (name[0].isalpha()): @@ -146,10 +145,23 @@ def indices_strides(indices): "%s(i%d)" % (offset, idx) for (idx, (ctype, stride, offset)) in enumerate(indices)]) +def is_number(str): + try: + int(str) + return True + except ValueError: + return False + +def sanitize_variant(variant): + if variant and "-" in variant: + return variant[:variant.index("-")] + return variant + class Bitset(object): def __init__(self, name, template): self.name = name self.inline = False + self.reg = None if template: self.fields = template.fields[:] else: @@ -175,11 +187,7 @@ class Bitset(object): print("#endif\n") print(" return (struct fd_reg_pair) {") - if reg.array: - print(" .reg = REG_%s(__i)," % reg.full_name) - else: - print(" .reg = REG_%s," % reg.full_name) - + print(" .reg = (uint32_t)%s," % reg.reg_offset()) print(" .value =") for f in self.fields: if f.type in [ "address", "waddress" ]: @@ -204,7 +212,7 @@ class Bitset(object): print(" };") - def dump_pack_struct(self, reg=None): + def dump_pack_struct(self, is_deprecated, reg=None): if not reg: return @@ -229,12 +237,15 @@ class Bitset(object): tab_to(" uint32_t", "dword;") print("};\n") + depcrstr = "" + if is_deprecated: + depcrstr = " FD_DEPRECATED" if reg.array: - print("static inline struct fd_reg_pair\npack_%s(uint32_t __i, struct %s fields)\n{" % - (prefix, prefix)) + print("static inline%s struct fd_reg_pair\npack_%s(uint32_t __i, struct %s fields)\n{" % + (depcrstr, prefix, prefix)) else: - print("static inline struct fd_reg_pair\npack_%s(struct %s fields)\n{" % - (prefix, prefix)) + print("static inline%s struct fd_reg_pair\npack_%s(struct %s fields)\n{" % + (depcrstr, prefix, prefix)) self.dump_regpair_builder(reg) @@ -253,18 +264,23 @@ class Bitset(object): (prefix, prefix, prefix, skip)) - def dump(self, prefix=None): - if prefix == None: + def dump(self, is_deprecated, prefix=None): + if prefix is None: prefix = self.name + if self.reg and self.reg.bit_size == 64: + 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) + print("\treturn val;\n}") for f in self.fields: if f.name: name = prefix + "_" + f.name else: name = prefix - if not f.name and f.low == 0 and f.shr == 0 and not f.type in ["float", "fixed", "ufixed"]: + if not f.name and f.low == 0 and f.shr == 0 and f.type not in ["float", "fixed", "ufixed"]: pass - elif f.type == "boolean" or (f.type == None and f.low == f.high): + 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)) @@ -286,6 +302,7 @@ class Array(object): self.domain = domain self.variant = variant self.parent = parent + self.children = [] if self.parent: self.name = self.parent.name + "_" + self.local_name else: @@ -337,12 +354,15 @@ class Array(object): offset += self.parent.total_offset() return offset - def dump(self): + def dump(self, is_deprecated): + depcrstr = "" + if is_deprecated: + depcrstr = " FD_DEPRECATED" proto = indices_varlist(self.indices()) strides = indices_strides(self.indices()) array_offset = self.total_offset() if self.fixed_offsets: - print("static inline uint32_t __offset_%s(%s idx)" % (self.local_name, self.index_ctype())) + print("static inline%s uint32_t __offset_%s(%s idx)" % (depcrstr, self.local_name, self.index_ctype())) print("{\n\tswitch (idx) {") if self.index_type: for val, offset in zip(self.index_type.names(), self.offsets): @@ -357,7 +377,7 @@ class Array(object): else: tab_to("#define REG_%s_%s(%s)" % (self.domain, self.name, proto), "(0x%08x + %s )\n" % (array_offset, strides)) - def dump_pack_struct(self): + def dump_pack_struct(self, is_deprecated): pass def dump_regpair_builder(self): @@ -373,6 +393,7 @@ class Reg(object): self.bit_size = bit_size if array: self.name = array.name + "_" + self.name + array.children.append(self) self.full_name = self.domain + "_" + self.name if "stride" in attrs: self.stride = int(attrs["stride"], 0) @@ -397,25 +418,34 @@ class Reg(object): else: return self.offset - def dump(self): + def reg_offset(self): + if self.array: + offset = self.array.offset + self.offset + return "(0x%08x + 0x%x*__i)" % (offset, self.array.stride) + return "0x%08x" % self.offset + + def dump(self, is_deprecated): + depcrstr = "" + if is_deprecated: + depcrstr = " FD_DEPRECATED " proto = indices_prototype(self.indices()) strides = indices_strides(self.indices()) offset = self.total_offset() if proto == '': tab_to("#define REG_%s" % self.full_name, "0x%08x" % offset) else: - print("static inline uint32_t REG_%s(%s) { return 0x%08x + %s; }" % (self.full_name, proto, offset, strides)) + 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(self.full_name) + self.bitset.dump(is_deprecated, self.full_name) + print("") - def dump_pack_struct(self): + def dump_pack_struct(self, is_deprecated): if self.bitset.inline: - self.bitset.dump_pack_struct(self) + self.bitset.dump_pack_struct(is_deprecated, self) def dump_regpair_builder(self): - if self.bitset.inline: - self.bitset.dump_regpair_builder(self) + self.bitset.dump_regpair_builder(self) def dump_py(self): print("\tREG_%s = 0x%08x" % (self.full_name, self.offset)) @@ -444,9 +474,6 @@ class Parser(object): self.variants = set() self.file = [] self.xml_files = [] - self.copyright_year = None - self.authors = [] - self.license = None def error(self, message): parser, filename = self.stack[-1] @@ -454,7 +481,7 @@ class Parser(object): def prefix(self, variant=None): if self.current_prefix_type == "variant" and variant: - return variant + return sanitize_variant(variant) elif self.current_stripe: return self.current_stripe + "_" + self.current_domain elif self.current_prefix: @@ -500,15 +527,22 @@ class Parser(object): return varset def parse_variants(self, attrs): - if not "variants" in attrs: + if "variants" not in attrs: return None - variant = attrs["variants"].split(",")[0] - if "-" in variant: - variant = variant[:variant.index("-")] + variant = attrs["variants"].split(",")[0] varset = self.parse_varset(attrs) - assert varset.has_name(variant) + if "-" in variant: + # if we have a range, validate that both the start and end + # of the range are valid enums: + start = variant[:variant.index("-")] + end = variant[variant.index("-") + 1:] + assert varset.has_name(start) + if end != "": + assert varset.has_name(end) + else: + assert varset.has_name(variant) return variant @@ -572,9 +606,6 @@ class Parser(object): error_str = str(xmlschema.error_log.filter_from_errors()[0]) raise self.error("Schema validation failed for: " + filename + "\n" + error_str) except ImportError as e: - if self.validate: - raise e - print("lxml not found, skipping validation", file=sys.stderr) def do_parse(self, filename): @@ -620,6 +651,7 @@ class Parser(object): self.current_reg = Reg(attrs, self.prefix(variant), self.current_array, bit_size) self.current_reg.bitset = self.current_bitset + self.current_bitset.reg = self.current_reg if len(self.stack) == 1: self.file.append(self.current_reg) @@ -643,7 +675,7 @@ class Parser(object): elif name == "domain": self.current_domain = attrs["name"] if "prefix" in attrs: - self.current_prefix = self.parse_variants(attrs) + self.current_prefix = sanitize_variant(self.parse_variants(attrs)) self.current_prefix_type = attrs["prefix"] else: self.current_prefix = None @@ -651,7 +683,7 @@ class Parser(object): if "varset" in attrs: self.current_varset = self.enums[attrs["varset"]] elif name == "stripe": - self.current_stripe = self.parse_variants(attrs) + self.current_stripe = sanitize_variant(self.parse_variants(attrs)) elif name == "enum": self.current_enum_value = 0 self.current_enum = Enum(attrs["name"]) @@ -686,10 +718,6 @@ class Parser(object): self.parse_field(attrs["name"], attrs) elif name == "database": self.do_validate(attrs["xsi:schemaLocation"]) - elif name == "copyright": - self.copyright_year = attrs["year"] - elif name == "author": - self.authors.append(attrs["name"] + " <" + attrs["email"] + "> " + attrs["name"]) def end_element(self, name): if name == "domain": @@ -703,11 +731,16 @@ class Parser(object): elif name == "reg32": self.current_reg = None elif name == "array": + # if the array has no Reg children, push an implicit reg32: + if len(self.current_array.children) == 0: + attrs = { + "name": "REG", + "offset": "0", + } + self.parse_reg(attrs, 32) self.current_array = self.current_array.parent elif name == "enum": self.current_enum = None - elif name == "license": - self.license = self.cdata def character_data(self, data): self.cdata += data @@ -720,10 +753,10 @@ class Parser(object): if variants: for variant, vreg in variants.items(): if reg == vreg: - d[(usage, variant)].append(reg) + d[(usage, sanitize_variant(variant))].append(reg) else: for variant in self.variants: - d[(usage, variant)].append(reg) + d[(usage, sanitize_variant(variant))].append(reg) print("#ifdef __cplusplus") @@ -753,6 +786,9 @@ class Parser(object): print("#endif") + def has_variants(self, reg): + return reg.name in self.variant_regs and not is_number(reg.name) and not is_number(reg.name[1:]) + def dump(self): enums = [] bitsets = [] @@ -766,7 +802,7 @@ class Parser(object): regs.append(e) for e in enums + bitsets + regs: - e.dump() + e.dump(self.has_variants(e)) self.dump_reg_usages() @@ -782,8 +818,7 @@ class Parser(object): def dump_reg_variants(self, regname, variants): - # Don't bother for things that only have a single variant: - if len(variants) == 1: + if is_number(regname) or is_number(regname[1:]): return print("#ifdef __cplusplus") print("struct __%s {" % regname) @@ -834,11 +869,20 @@ class Parser(object): xtravar = "__i, " print("__%s(%sstruct __%s fields) {" % (regname, xtra, regname)) for variant in variants.keys(): - print(" if (%s == %s) {" % (varenum.upper(), variant)) + if "-" in variant: + start = variant[:variant.index("-")] + end = variant[variant.index("-") + 1:] + if end != "": + print(" if ((%s >= %s) && (%s <= %s)) {" % (varenum.upper(), start, varenum.upper(), end)) + else: + print(" if (%s >= %s) {" % (varenum.upper(), start)) + else: + print(" if (%s == %s) {" % (varenum.upper(), variant)) reg = variants[variant] reg.dump_regpair_builder() print(" } else") print(" assert(!\"invalid variant\");") + print(" return (struct fd_reg_pair){};") print("}") if bit_size == 64: @@ -851,7 +895,7 @@ class Parser(object): def dump_structs(self): for e in self.file: - e.dump_pack_struct() + e.dump_pack_struct(self.has_variants(e)) for regname in self.variant_regs: self.dump_reg_variants(regname, self.variant_regs[regname]) @@ -868,33 +912,7 @@ def dump_c(args, guard, func): print("#ifndef %s\n#define %s\n" % (guard, guard)) - print("""/* Autogenerated file, DO NOT EDIT manually! - -This file was generated by the rules-ng-ng gen_header.py tool in this git repository: -http://gitlab.freedesktop.org/mesa/mesa/ -git clone https://gitlab.freedesktop.org/mesa/mesa.git - -The rules-ng-ng source files this header was generated from are: -""") - maxlen = 0 - for filepath in p.xml_files: - new_filepath = re.sub("^.+drivers","drivers",filepath) - maxlen = max(maxlen, len(new_filepath)) - for filepath in p.xml_files: - pad = " " * (maxlen - len(new_filepath)) - filesize = str(os.path.getsize(filepath)) - filesize = " " * (7 - len(filesize)) + filesize - filetime = time.ctime(os.path.getmtime(filepath)) - print("- " + new_filepath + pad + " (" + filesize + " bytes, from <stripped>)") - if p.copyright_year: - current_year = str(datetime.date.today().year) - print() - print("Copyright (C) %s-%s by the following authors:" % (p.copyright_year, current_year)) - for author in p.authors: - print("- " + author) - if p.license: - print(p.license) - print("*/") + print("/* Autogenerated file, DO NOT EDIT manually! */") print() print("#ifdef __KERNEL__") @@ -912,9 +930,20 @@ The rules-ng-ng source files this header was generated from are: print("#endif") print() + print("#ifndef FD_NO_DEPRECATED_PACK") + print("#define FD_DEPRECATED __attribute__((deprecated))") + print("#else") + print("#define FD_DEPRECATED") + print("#endif") + print() + func(p) - print("\n#endif /* %s */" % guard) + print() + print("#undef FD_DEPRECATED") + print() + + print("#endif /* %s */" % guard) def dump_c_defines(args): @@ -931,7 +960,7 @@ def dump_py_defines(args): p = Parser() try: - p.parse(args.rnn, args.xml) + p.parse(args.rnn, args.xml, args.validate) except Error as e: print(e, file=sys.stderr) exit(1) |