diff options
Diffstat (limited to 'drivers/gpu/drm/msm/adreno')
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_catalog.c | 92 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 108 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gmu.h | 14 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 242 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gpu.h | 3 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c | 10 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_hfi.c | 34 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_preempt.c | 44 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/adreno_device.c | 13 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/adreno_gpu.c | 21 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/adreno_gpu.h | 1 |
11 files changed, 478 insertions, 104 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 d5d1271fce61..4c7f3c642f6a 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -1586,8 +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); @@ -1608,15 +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 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_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. |