diff options
Diffstat (limited to 'drivers/gpu/drm/msm/adreno')
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a3xx_gpu.c | 10 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a4xx_gpu.c | 10 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 261 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a5xx_gpu.h | 109 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a5xx_power.c | 9 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a5xx_preempt.c | 305 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/adreno_device.c | 78 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/adreno_gpu.c | 297 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/adreno_gpu.h | 66 |
9 files changed, 922 insertions, 223 deletions
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index 7791313405b5..4baef2738178 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -44,7 +44,7 @@ static bool a3xx_idle(struct msm_gpu *gpu); static bool a3xx_me_init(struct msm_gpu *gpu) { - struct msm_ringbuffer *ring = gpu->rb; + struct msm_ringbuffer *ring = gpu->rb[0]; OUT_PKT3(ring, CP_ME_INIT, 17); OUT_RING(ring, 0x000003f7); @@ -65,7 +65,7 @@ static bool a3xx_me_init(struct msm_gpu *gpu) OUT_RING(ring, 0x00000000); OUT_RING(ring, 0x00000000); - gpu->funcs->flush(gpu); + gpu->funcs->flush(gpu, ring); return a3xx_idle(gpu); } @@ -339,7 +339,7 @@ static void a3xx_destroy(struct msm_gpu *gpu) static bool a3xx_idle(struct msm_gpu *gpu) { /* wait for ringbuffer to drain: */ - if (!adreno_idle(gpu)) + if (!adreno_idle(gpu, gpu->rb[0])) return false; /* then wait for GPU to finish: */ @@ -444,9 +444,9 @@ static const struct adreno_gpu_funcs funcs = { .pm_suspend = msm_gpu_pm_suspend, .pm_resume = msm_gpu_pm_resume, .recover = a3xx_recover, - .last_fence = adreno_last_fence, .submit = adreno_submit, .flush = adreno_flush, + .active_ring = adreno_active_ring, .irq = a3xx_irq, .destroy = a3xx_destroy, #ifdef CONFIG_DEBUG_FS @@ -492,7 +492,7 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) adreno_gpu->registers = a3xx_registers; adreno_gpu->reg_offsets = a3xx_register_offsets; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) goto fail; diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index 58341ef6f15b..8199a4b9f2fa 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -116,7 +116,7 @@ static void a4xx_enable_hwcg(struct msm_gpu *gpu) static bool a4xx_me_init(struct msm_gpu *gpu) { - struct msm_ringbuffer *ring = gpu->rb; + struct msm_ringbuffer *ring = gpu->rb[0]; OUT_PKT3(ring, CP_ME_INIT, 17); OUT_RING(ring, 0x000003f7); @@ -137,7 +137,7 @@ static bool a4xx_me_init(struct msm_gpu *gpu) OUT_RING(ring, 0x00000000); OUT_RING(ring, 0x00000000); - gpu->funcs->flush(gpu); + gpu->funcs->flush(gpu, ring); return a4xx_idle(gpu); } @@ -337,7 +337,7 @@ static void a4xx_destroy(struct msm_gpu *gpu) static bool a4xx_idle(struct msm_gpu *gpu) { /* wait for ringbuffer to drain: */ - if (!adreno_idle(gpu)) + if (!adreno_idle(gpu, gpu->rb[0])) return false; /* then wait for GPU to finish: */ @@ -532,9 +532,9 @@ static const struct adreno_gpu_funcs funcs = { .pm_suspend = a4xx_pm_suspend, .pm_resume = a4xx_pm_resume, .recover = a4xx_recover, - .last_fence = adreno_last_fence, .submit = adreno_submit, .flush = adreno_flush, + .active_ring = adreno_active_ring, .irq = a4xx_irq, .destroy = a4xx_destroy, #ifdef CONFIG_DEBUG_FS @@ -574,7 +574,7 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) adreno_gpu->registers = a4xx_registers; adreno_gpu->reg_offsets = a4xx_register_offsets; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) goto fail; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 17c59d839e6f..a1f4eeeb73e2 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -26,8 +26,9 @@ static void a5xx_dump(struct msm_gpu *gpu); #define GPU_PAS_ID 13 -static int zap_shader_load_mdt(struct device *dev, const char *fwname) +static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname) { + struct device *dev = &gpu->pdev->dev; const struct firmware *fw; struct device_node *np; struct resource r; @@ -55,10 +56,10 @@ static int zap_shader_load_mdt(struct device *dev, const char *fwname) mem_size = resource_size(&r); /* Request the MDT file for the firmware */ - ret = request_firmware(&fw, fwname, dev); - if (ret) { + fw = adreno_request_fw(to_adreno_gpu(gpu), fwname); + if (IS_ERR(fw)) { DRM_DEV_ERROR(dev, "Unable to load %s\n", fwname); - return ret; + return PTR_ERR(fw); } /* Figure out how much memory we need */ @@ -75,9 +76,26 @@ static int zap_shader_load_mdt(struct device *dev, const char *fwname) goto out; } - /* Load the rest of the MDT */ - ret = qcom_mdt_load(dev, fw, fwname, GPU_PAS_ID, mem_region, mem_phys, - mem_size); + /* + * Load the rest of the MDT + * + * Note that we could be dealing with two different paths, since + * with upstream linux-firmware it would be in a qcom/ subdir.. + * adreno_request_fw() handles this, but qcom_mdt_load() does + * not. But since we've already gotten thru adreno_request_fw() + * we know which of the two cases it is: + */ + if (to_adreno_gpu(gpu)->fwloc == FW_LOCATION_LEGACY) { + ret = qcom_mdt_load(dev, fw, fwname, GPU_PAS_ID, + mem_region, mem_phys, mem_size); + } else { + char newname[strlen("qcom/") + strlen(fwname) + 1]; + + sprintf(newname, "qcom/%s", fwname); + + ret = qcom_mdt_load(dev, fw, newname, GPU_PAS_ID, + mem_region, mem_phys, mem_size); + } if (ret) goto out; @@ -95,14 +113,65 @@ out: return ret; } +static void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + uint32_t wptr; + unsigned long flags; + + spin_lock_irqsave(&ring->lock, flags); + + /* Copy the shadow to the actual register */ + ring->cur = ring->next; + + /* Make sure to wrap wptr if we need to */ + wptr = get_wptr(ring); + + spin_unlock_irqrestore(&ring->lock, flags); + + /* Make sure everything is posted before making a decision */ + mb(); + + /* Update HW if this is the current ring and we are not in preempt */ + if (a5xx_gpu->cur_ring == ring && !a5xx_in_preempt(a5xx_gpu)) + gpu_write(gpu, REG_A5XX_CP_RB_WPTR, wptr); +} + static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, struct msm_file_private *ctx) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); struct msm_drm_private *priv = gpu->dev->dev_private; - struct msm_ringbuffer *ring = gpu->rb; + struct msm_ringbuffer *ring = submit->ring; unsigned int i, ibs = 0; + OUT_PKT7(ring, CP_PREEMPT_ENABLE_GLOBAL, 1); + OUT_RING(ring, 0x02); + + /* Turn off protected mode to write to special registers */ + OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); + OUT_RING(ring, 0); + + /* Set the save preemption record for the ring/command */ + OUT_PKT4(ring, REG_A5XX_CP_CONTEXT_SWITCH_SAVE_ADDR_LO, 2); + OUT_RING(ring, lower_32_bits(a5xx_gpu->preempt_iova[submit->ring->id])); + OUT_RING(ring, upper_32_bits(a5xx_gpu->preempt_iova[submit->ring->id])); + + /* Turn back on protected mode */ + OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); + OUT_RING(ring, 1); + + /* Enable local preemption for finegrain preemption */ + OUT_PKT7(ring, CP_PREEMPT_ENABLE_GLOBAL, 1); + OUT_RING(ring, 0x02); + + /* Allow CP_CONTEXT_SWITCH_YIELD packets in the IB2 */ + OUT_PKT7(ring, CP_YIELD_ENABLE, 1); + OUT_RING(ring, 0x02); + + /* Submit the commands */ for (i = 0; i < submit->nr_cmds; i++) { switch (submit->cmd[i].type) { case MSM_SUBMIT_CMD_IB_TARGET_BUF: @@ -120,16 +189,54 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, } } + /* + * Write the render mode to NULL (0) to indicate to the CP that the IBs + * are done rendering - otherwise a lucky preemption would start + * replaying from the last checkpoint + */ + OUT_PKT7(ring, CP_SET_RENDER_MODE, 5); + OUT_RING(ring, 0); + OUT_RING(ring, 0); + OUT_RING(ring, 0); + OUT_RING(ring, 0); + OUT_RING(ring, 0); + + /* Turn off IB level preemptions */ + OUT_PKT7(ring, CP_YIELD_ENABLE, 1); + OUT_RING(ring, 0x01); + + /* Write the fence to the scratch register */ OUT_PKT4(ring, REG_A5XX_CP_SCRATCH_REG(2), 1); - OUT_RING(ring, submit->fence->seqno); + OUT_RING(ring, submit->seqno); + /* + * Execute a CACHE_FLUSH_TS event. This will ensure that the + * timestamp is written to the memory and then triggers the interrupt + */ OUT_PKT7(ring, CP_EVENT_WRITE, 4); OUT_RING(ring, CACHE_FLUSH_TS | (1 << 31)); - OUT_RING(ring, lower_32_bits(rbmemptr(adreno_gpu, fence))); - OUT_RING(ring, upper_32_bits(rbmemptr(adreno_gpu, fence))); - OUT_RING(ring, submit->fence->seqno); + OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence))); + OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence))); + OUT_RING(ring, submit->seqno); - gpu->funcs->flush(gpu); + /* Yield the floor on command completion */ + OUT_PKT7(ring, CP_CONTEXT_SWITCH_YIELD, 4); + /* + * If dword[2:1] are non zero, they specify an address for the CP to + * write the value of dword[3] to on preemption complete. Write 0 to + * skip the write + */ + OUT_RING(ring, 0x00); + OUT_RING(ring, 0x00); + /* Data value - not used if the address above is 0 */ + OUT_RING(ring, 0x01); + /* Set bit 0 to trigger an interrupt on preempt complete */ + OUT_RING(ring, 0x01); + + a5xx_flush(gpu, ring); + + /* Check to see if we need to start preemption */ + a5xx_preempt_trigger(gpu); } static const struct { @@ -245,7 +352,7 @@ void a5xx_set_hwcg(struct msm_gpu *gpu, bool state) static int a5xx_me_init(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); - struct msm_ringbuffer *ring = gpu->rb; + struct msm_ringbuffer *ring = gpu->rb[0]; OUT_PKT7(ring, CP_ME_INIT, 8); @@ -276,11 +383,54 @@ static int a5xx_me_init(struct msm_gpu *gpu) OUT_RING(ring, 0x00000000); OUT_RING(ring, 0x00000000); - gpu->funcs->flush(gpu); + gpu->funcs->flush(gpu, ring); + return a5xx_idle(gpu, ring) ? 0 : -EINVAL; +} + +static int a5xx_preempt_start(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + struct msm_ringbuffer *ring = gpu->rb[0]; + + if (gpu->nr_rings == 1) + return 0; + + /* Turn off protected mode to write to special registers */ + OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); + OUT_RING(ring, 0); + + /* Set the save preemption record for the ring/command */ + OUT_PKT4(ring, REG_A5XX_CP_CONTEXT_SWITCH_SAVE_ADDR_LO, 2); + OUT_RING(ring, lower_32_bits(a5xx_gpu->preempt_iova[ring->id])); + OUT_RING(ring, upper_32_bits(a5xx_gpu->preempt_iova[ring->id])); + + /* Turn back on protected mode */ + OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); + OUT_RING(ring, 1); + + OUT_PKT7(ring, CP_PREEMPT_ENABLE_GLOBAL, 1); + OUT_RING(ring, 0x00); + + OUT_PKT7(ring, CP_PREEMPT_ENABLE_LOCAL, 1); + OUT_RING(ring, 0x01); - return a5xx_idle(gpu) ? 0 : -EINVAL; + OUT_PKT7(ring, CP_YIELD_ENABLE, 1); + OUT_RING(ring, 0x01); + + /* Yield the floor on command completion */ + OUT_PKT7(ring, CP_CONTEXT_SWITCH_YIELD, 4); + OUT_RING(ring, 0x00); + OUT_RING(ring, 0x00); + OUT_RING(ring, 0x01); + OUT_RING(ring, 0x01); + + gpu->funcs->flush(gpu, ring); + + return a5xx_idle(gpu, ring) ? 0 : -EINVAL; } + static struct drm_gem_object *a5xx_ucode_load_bo(struct msm_gpu *gpu, const struct firmware *fw, u64 *iova) { @@ -381,7 +531,7 @@ static int a5xx_zap_shader_init(struct msm_gpu *gpu) return -ENODEV; } - ret = zap_shader_load_mdt(&pdev->dev, adreno_gpu->info->zapfw); + ret = zap_shader_load_mdt(gpu, adreno_gpu->info->zapfw); loaded = !ret; @@ -396,6 +546,7 @@ static int a5xx_zap_shader_init(struct msm_gpu *gpu) A5XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNC_OVERFLOW | \ A5XX_RBBM_INT_0_MASK_CP_HW_ERROR | \ A5XX_RBBM_INT_0_MASK_MISC_HANG_DETECT | \ + A5XX_RBBM_INT_0_MASK_CP_SW | \ A5XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS | \ A5XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS | \ A5XX_RBBM_INT_0_MASK_GPMU_VOLTAGE_DROOP) @@ -536,13 +687,14 @@ static int a5xx_hw_init(struct msm_gpu *gpu) REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000); gpu_write(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000); - /* Load the GPMU firmware before starting the HW init */ - a5xx_gpmu_ucode_init(gpu); - ret = adreno_hw_init(gpu); if (ret) return ret; + a5xx_preempt_hw_init(gpu); + + a5xx_gpmu_ucode_init(gpu); + ret = a5xx_ucode_init(gpu); if (ret) return ret; @@ -565,11 +717,11 @@ static int a5xx_hw_init(struct msm_gpu *gpu) * ticking correctly */ if (adreno_is_a530(adreno_gpu)) { - OUT_PKT7(gpu->rb, CP_EVENT_WRITE, 1); - OUT_RING(gpu->rb, 0x0F); + OUT_PKT7(gpu->rb[0], CP_EVENT_WRITE, 1); + OUT_RING(gpu->rb[0], 0x0F); - gpu->funcs->flush(gpu); - if (!a5xx_idle(gpu)) + gpu->funcs->flush(gpu, gpu->rb[0]); + if (!a5xx_idle(gpu, gpu->rb[0])) return -EINVAL; } @@ -582,11 +734,11 @@ static int a5xx_hw_init(struct msm_gpu *gpu) */ ret = a5xx_zap_shader_init(gpu); if (!ret) { - OUT_PKT7(gpu->rb, CP_SET_SECURE_MODE, 1); - OUT_RING(gpu->rb, 0x00000000); + OUT_PKT7(gpu->rb[0], CP_SET_SECURE_MODE, 1); + OUT_RING(gpu->rb[0], 0x00000000); - gpu->funcs->flush(gpu); - if (!a5xx_idle(gpu)) + gpu->funcs->flush(gpu, gpu->rb[0]); + if (!a5xx_idle(gpu, gpu->rb[0])) return -EINVAL; } else { /* Print a warning so if we die, we know why */ @@ -595,6 +747,9 @@ static int a5xx_hw_init(struct msm_gpu *gpu) gpu_write(gpu, REG_A5XX_RBBM_SECVID_TRUST_CNTL, 0x0); } + /* Last step - yield the ringbuffer */ + a5xx_preempt_start(gpu); + return 0; } @@ -625,6 +780,8 @@ static void a5xx_destroy(struct msm_gpu *gpu) DBG("%s", gpu->name); + a5xx_preempt_fini(gpu); + if (a5xx_gpu->pm4_bo) { if (a5xx_gpu->pm4_iova) msm_gem_put_iova(a5xx_gpu->pm4_bo, gpu->aspace); @@ -660,18 +817,27 @@ static inline bool _a5xx_check_idle(struct msm_gpu *gpu) A5XX_RBBM_INT_0_MASK_MISC_HANG_DETECT); } -bool a5xx_idle(struct msm_gpu *gpu) +bool a5xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring) { + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + + if (ring != a5xx_gpu->cur_ring) { + WARN(1, "Tried to idle a non-current ringbuffer\n"); + return false; + } + /* wait for CP to drain ringbuffer: */ - if (!adreno_idle(gpu)) + if (!adreno_idle(gpu, ring)) return false; if (spin_until(_a5xx_check_idle(gpu))) { - DRM_ERROR("%s: %ps: timeout waiting for GPU to idle: status %8.8X irq %8.8X\n", + DRM_ERROR("%s: %ps: timeout waiting for GPU to idle: status %8.8X irq %8.8X rptr/wptr %d/%d\n", gpu->name, __builtin_return_address(0), gpu_read(gpu, REG_A5XX_RBBM_STATUS), - gpu_read(gpu, REG_A5XX_RBBM_INT_0_STATUS)); - + gpu_read(gpu, REG_A5XX_RBBM_INT_0_STATUS), + gpu_read(gpu, REG_A5XX_CP_RB_RPTR), + gpu_read(gpu, REG_A5XX_CP_RB_WPTR)); return false; } @@ -802,9 +968,10 @@ static void a5xx_fault_detect_irq(struct msm_gpu *gpu) { struct drm_device *dev = gpu->dev; struct msm_drm_private *priv = dev->dev_private; + struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu); - dev_err(dev->dev, "gpu fault fence %x status %8.8X rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x\n", - gpu->funcs->last_fence(gpu), + dev_err(dev->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->seqno : 0, gpu_read(gpu, REG_A5XX_RBBM_STATUS), gpu_read(gpu, REG_A5XX_CP_RB_RPTR), gpu_read(gpu, REG_A5XX_CP_RB_WPTR), @@ -854,8 +1021,13 @@ static irqreturn_t a5xx_irq(struct msm_gpu *gpu) if (status & A5XX_RBBM_INT_0_MASK_GPMU_VOLTAGE_DROOP) a5xx_gpmu_err_irq(gpu); - if (status & A5XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS) + if (status & A5XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS) { + a5xx_preempt_trigger(gpu); msm_gpu_retire(gpu); + } + + if (status & A5XX_RBBM_INT_0_MASK_CP_SW) + a5xx_preempt_irq(gpu); return IRQ_HANDLED; } @@ -985,6 +1157,14 @@ static void a5xx_show(struct msm_gpu *gpu, struct seq_file *m) } #endif +static struct msm_ringbuffer *a5xx_active_ring(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + + return a5xx_gpu->cur_ring; +} + static const struct adreno_gpu_funcs funcs = { .base = { .get_param = adreno_get_param, @@ -992,9 +1172,9 @@ static const struct adreno_gpu_funcs funcs = { .pm_suspend = a5xx_pm_suspend, .pm_resume = a5xx_pm_resume, .recover = a5xx_recover, - .last_fence = adreno_last_fence, .submit = a5xx_submit, - .flush = adreno_flush, + .flush = a5xx_flush, + .active_ring = a5xx_active_ring, .irq = a5xx_irq, .destroy = a5xx_destroy, #ifdef CONFIG_DEBUG_FS @@ -1030,7 +1210,7 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) a5xx_gpu->lm_leakage = 0x4E001A; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 4); if (ret) { a5xx_destroy(&(a5xx_gpu->base.base)); return ERR_PTR(ret); @@ -1039,5 +1219,8 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) if (gpu->aspace) msm_mmu_set_fault_handler(gpu->aspace->mmu, gpu, a5xx_fault_handler); + /* Set up the preemption specific bits and pieces for each ringbuffer */ + a5xx_preempt_init(gpu); + return gpu; } diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h index e94451685bf8..6fb8c2f9b9e4 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2016 The Linux Foundation. All rights reserved. +/* Copyright (c) 2016-2017 The Linux Foundation. All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 and @@ -35,10 +35,100 @@ struct a5xx_gpu { uint32_t gpmu_dwords; uint32_t lm_leakage; + + struct msm_ringbuffer *cur_ring; + struct msm_ringbuffer *next_ring; + + struct drm_gem_object *preempt_bo[MSM_GPU_MAX_RINGS]; + struct a5xx_preempt_record *preempt[MSM_GPU_MAX_RINGS]; + uint64_t preempt_iova[MSM_GPU_MAX_RINGS]; + + atomic_t preempt_state; + struct timer_list preempt_timer; }; #define to_a5xx_gpu(x) container_of(x, struct a5xx_gpu, base) +/* + * In order to do lockless preemption we use a simple state machine to progress + * through the process. + * + * PREEMPT_NONE - no preemption in progress. Next state START. + * PREEMPT_START - The trigger is evaulating if preemption is possible. Next + * states: TRIGGERED, NONE + * PREEMPT_ABORT - An intermediate state before moving back to NONE. Next + * state: NONE. + * PREEMPT_TRIGGERED: A preemption has been executed on the hardware. Next + * states: FAULTED, PENDING + * PREEMPT_FAULTED: A preemption timed out (never completed). This will trigger + * recovery. Next state: N/A + * PREEMPT_PENDING: Preemption complete interrupt fired - the callback is + * checking the success of the operation. Next state: FAULTED, NONE. + */ + +enum preempt_state { + PREEMPT_NONE = 0, + PREEMPT_START, + PREEMPT_ABORT, + PREEMPT_TRIGGERED, + PREEMPT_FAULTED, + PREEMPT_PENDING, +}; + +/* + * struct a5xx_preempt_record is a shared buffer between the microcode and the + * CPU to store the state for preemption. The record itself is much larger + * (64k) but most of that is used by the CP for storage. + * + * There is a preemption record assigned per ringbuffer. When the CPU triggers a + * preemption, it fills out the record with the useful information (wptr, ring + * base, etc) and the microcode uses that information to set up the CP following + * the preemption. When a ring is switched out, the CP will save the ringbuffer + * state back to the record. In this way, once the records are properly set up + * the CPU can quickly switch back and forth between ringbuffers by only + * updating a few registers (often only the wptr). + * + * These are the CPU aware registers in the record: + * @magic: Must always be 0x27C4BAFC + * @info: Type of the record - written 0 by the CPU, updated by the CP + * @data: Data field from SET_RENDER_MODE or a checkpoint. Written and used by + * the CP + * @cntl: Value of RB_CNTL written by CPU, save/restored by CP + * @rptr: Value of RB_RPTR written by CPU, save/restored by CP + * @wptr: Value of RB_WPTR written by CPU, save/restored by CP + * @rptr_addr: Value of RB_RPTR_ADDR written by CPU, save/restored by CP + * @rbase: Value of RB_BASE written by CPU, save/restored by CP + * @counter: GPU address of the storage area for the performance counters + */ +struct a5xx_preempt_record { + uint32_t magic; + uint32_t info; + uint32_t data; + uint32_t cntl; + uint32_t rptr; + uint32_t wptr; + uint64_t rptr_addr; + uint64_t rbase; + uint64_t counter; +}; + +/* Magic identifier for the preemption record */ +#define A5XX_PREEMPT_RECORD_MAGIC 0x27C4BAFCUL + +/* + * Even though the structure above is only a few bytes, we need a full 64k to + * store the entire preemption record from the CP + */ +#define A5XX_PREEMPT_RECORD_SIZE (64 * 1024) + +/* + * The preemption counter block is a storage area for the value of the + * preemption counters that are saved immediately before context switch. We + * append it on to the end of the allocation for the preemption record. + */ +#define A5XX_PREEMPT_COUNTER_SIZE (16 * 4) + + int a5xx_power_init(struct msm_gpu *gpu); void a5xx_gpmu_ucode_init(struct msm_gpu *gpu); @@ -55,7 +145,22 @@ static inline int spin_usecs(struct msm_gpu *gpu, uint32_t usecs, return -ETIMEDOUT; } -bool a5xx_idle(struct msm_gpu *gpu); +bool a5xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring); void a5xx_set_hwcg(struct msm_gpu *gpu, bool state); +void a5xx_preempt_init(struct msm_gpu *gpu); +void a5xx_preempt_hw_init(struct msm_gpu *gpu); +void a5xx_preempt_trigger(struct msm_gpu *gpu); +void a5xx_preempt_irq(struct msm_gpu *gpu); +void a5xx_preempt_fini(struct msm_gpu *gpu); + +/* Return true if we are in a preempt state */ +static inline bool a5xx_in_preempt(struct a5xx_gpu *a5xx_gpu) +{ + int preempt_state = atomic_read(&a5xx_gpu->preempt_state); + + return !(preempt_state == PREEMPT_NONE || + preempt_state == PREEMPT_ABORT); +} + #endif /* __A5XX_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c index 04aab1dcae2b..e5700bbf09dd 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_power.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c @@ -173,7 +173,7 @@ static int a5xx_gpmu_init(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); - struct msm_ringbuffer *ring = gpu->rb; + struct msm_ringbuffer *ring = gpu->rb[0]; if (!a5xx_gpu->gpmu_dwords) return 0; @@ -192,9 +192,9 @@ static int a5xx_gpmu_init(struct msm_gpu *gpu) OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); OUT_RING(ring, 1); - gpu->funcs->flush(gpu); + gpu->funcs->flush(gpu, ring); - if (!a5xx_idle(gpu)) { + if (!a5xx_idle(gpu, ring)) { DRM_ERROR("%s: Unable to load GPMU firmware. GPMU will not be active\n", gpu->name); return -EINVAL; @@ -264,7 +264,8 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu) return; /* Get the firmware */ - if (request_firmware(&fw, adreno_gpu->info->gpmufw, drm->dev)) { + fw = adreno_request_fw(adreno_gpu, adreno_gpu->info->gpmufw); + if (IS_ERR(fw)) { DRM_ERROR("%s: Could not get GPMU firmware. GPMU will not be active\n", gpu->name); return; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c new file mode 100644 index 000000000000..40f4840ef98e --- /dev/null +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -0,0 +1,305 @@ +/* Copyright (c) 2017 The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include "msm_gem.h" +#include "a5xx_gpu.h" + +/* + * Try to transition the preemption state from old to new. Return + * true on success or false if the original state wasn't 'old' + */ +static inline bool try_preempt_state(struct a5xx_gpu *a5xx_gpu, + enum preempt_state old, enum preempt_state new) +{ + enum preempt_state cur = atomic_cmpxchg(&a5xx_gpu->preempt_state, + old, new); + + return (cur == old); +} + +/* + * Force the preemption state to the specified state. This is used in cases + * where the current state is known and won't change + */ +static inline void set_preempt_state(struct a5xx_gpu *gpu, + enum preempt_state new) +{ + /* + * preempt_state may be read by other cores trying to trigger a + * preemption or in the interrupt handler so barriers are needed + * before... + */ + smp_mb__before_atomic(); + atomic_set(&gpu->preempt_state, new); + /* ... and after*/ + smp_mb__after_atomic(); +} + +/* 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) +{ + unsigned long flags; + uint32_t wptr; + + if (!ring) + return; + + spin_lock_irqsave(&ring->lock, flags); + wptr = get_wptr(ring); + spin_unlock_irqrestore(&ring->lock, flags); + + gpu_write(gpu, REG_A5XX_CP_RB_WPTR, wptr); +} + +/* Return the highest priority ringbuffer with something in it */ +static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu) +{ + unsigned long flags; + int i; + + for (i = 0; i < gpu->nr_rings; i++) { + bool empty; + struct msm_ringbuffer *ring = gpu->rb[i]; + + spin_lock_irqsave(&ring->lock, flags); + empty = (get_wptr(ring) == ring->memptrs->rptr); + spin_unlock_irqrestore(&ring->lock, flags); + + if (!empty) + return ring; + } + + return NULL; +} + +static void a5xx_preempt_timer(unsigned long data) +{ + struct a5xx_gpu *a5xx_gpu = (struct a5xx_gpu *) data; + struct msm_gpu *gpu = &a5xx_gpu->base.base; + struct drm_device *dev = gpu->dev; + struct msm_drm_private *priv = dev->dev_private; + + if (!try_preempt_state(a5xx_gpu, PREEMPT_TRIGGERED, PREEMPT_FAULTED)) + return; + + dev_err(dev->dev, "%s: preemption timed out\n", gpu->name); + queue_work(priv->wq, &gpu->recover_work); +} + +/* Try to trigger a preemption switch */ +void a5xx_preempt_trigger(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + unsigned long flags; + struct msm_ringbuffer *ring; + + if (gpu->nr_rings == 1) + return; + + /* + * Try to start preemption by moving from NONE to START. If + * unsuccessful, a preemption is already in flight + */ + if (!try_preempt_state(a5xx_gpu, PREEMPT_NONE, PREEMPT_START)) + return; + + /* Get the next ring to preempt to */ + ring = get_next_ring(gpu); + + /* + * If no ring is populated or the highest priority ring is the current + * one do nothing except to update the wptr to the latest and greatest + */ + if (!ring || (a5xx_gpu->cur_ring == ring)) { + /* + * Its possible that while a preemption request is in progress + * from an irq context, a user context trying to submit might + * fail to update the write pointer, because it determines + * that the preempt state is not PREEMPT_NONE. + * + * Close the race by introducing an intermediate + * state PREEMPT_ABORT to let the submit path + * know that the ringbuffer is not going to change + * and can safely update the write pointer. + */ + + set_preempt_state(a5xx_gpu, PREEMPT_ABORT); + update_wptr(gpu, a5xx_gpu->cur_ring); + set_preempt_state(a5xx_gpu, PREEMPT_NONE); + return; + } + + /* Make sure the wptr doesn't update while we're in motion */ + spin_lock_irqsave(&ring->lock, flags); + a5xx_gpu->preempt[ring->id]->wptr = get_wptr(ring); + spin_unlock_irqrestore(&ring->lock, flags); + + /* Set the address of the incoming preemption record */ + gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_RESTORE_ADDR_LO, + REG_A5XX_CP_CONTEXT_SWITCH_RESTORE_ADDR_HI, + a5xx_gpu->preempt_iova[ring->id]); + + a5xx_gpu->next_ring = ring; + + /* Start a timer to catch a stuck preemption */ + mod_timer(&a5xx_gpu->preempt_timer, jiffies + msecs_to_jiffies(10000)); + + /* Set the preemption state to triggered */ + set_preempt_state(a5xx_gpu, PREEMPT_TRIGGERED); + + /* Make sure everything is written before hitting the button */ + wmb(); + + /* And actually start the preemption */ + gpu_write(gpu, REG_A5XX_CP_CONTEXT_SWITCH_CNTL, 1); +} + +void a5xx_preempt_irq(struct msm_gpu *gpu) +{ + uint32_t status; + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + struct drm_device *dev = gpu->dev; + struct msm_drm_private *priv = dev->dev_private; + + if (!try_preempt_state(a5xx_gpu, PREEMPT_TRIGGERED, PREEMPT_PENDING)) + return; + + /* Delete the preemption watchdog timer */ + del_timer(&a5xx_gpu->preempt_timer); + + /* + * The hardware should be setting CP_CONTEXT_SWITCH_CNTL to zero before + * firing the interrupt, but there is a non zero chance of a hardware + * condition or a software race that could set it again before we have a + * chance to finish. If that happens, log and go for recovery + */ + status = gpu_read(gpu, REG_A5XX_CP_CONTEXT_SWITCH_CNTL); + if (unlikely(status)) { + set_preempt_state(a5xx_gpu, PREEMPT_FAULTED); + dev_err(dev->dev, "%s: Preemption failed to complete\n", + gpu->name); + queue_work(priv->wq, &gpu->recover_work); + return; + } + + a5xx_gpu->cur_ring = a5xx_gpu->next_ring; + a5xx_gpu->next_ring = NULL; + + update_wptr(gpu, a5xx_gpu->cur_ring); + + set_preempt_state(a5xx_gpu, PREEMPT_NONE); +} + +void a5xx_preempt_hw_init(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + int i; + + for (i = 0; i < gpu->nr_rings; i++) { + a5xx_gpu->preempt[i]->wptr = 0; + a5xx_gpu->preempt[i]->rptr = 0; + a5xx_gpu->preempt[i]->rbase = gpu->rb[i]->iova; + } + + /* Write a 0 to signal that we aren't switching pagetables */ + gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_LO, + REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_HI, 0); + + /* Reset the preemption state */ + set_preempt_state(a5xx_gpu, PREEMPT_NONE); + + /* Always come up on rb 0 */ + a5xx_gpu->cur_ring = gpu->rb[0]; +} + +static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu, + struct msm_ringbuffer *ring) +{ + struct adreno_gpu *adreno_gpu = &a5xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; + struct a5xx_preempt_record *ptr; + struct drm_gem_object *bo = NULL; + u64 iova = 0; + + ptr = msm_gem_kernel_new(gpu->dev, + A5XX_PREEMPT_RECORD_SIZE + A5XX_PREEMPT_COUNTER_SIZE, + MSM_BO_UNCACHED, gpu->aspace, &bo, &iova); + + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + a5xx_gpu->preempt_bo[ring->id] = bo; + a5xx_gpu->preempt_iova[ring->id] = iova; + a5xx_gpu->preempt[ring->id] = ptr; + + /* Set up the defaults on the preemption record */ + + ptr->magic = A5XX_PREEMPT_RECORD_MAGIC; + ptr->info = 0; + ptr->data = 0; + ptr->cntl = MSM_GPU_RB_CNTL_DEFAULT; + ptr->rptr_addr = rbmemptr(ring, rptr); + ptr->counter = iova + A5XX_PREEMPT_RECORD_SIZE; + + return 0; +} + +void a5xx_preempt_fini(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + int i; + + for (i = 0; i < gpu->nr_rings; i++) { + if (!a5xx_gpu->preempt_bo[i]) + continue; + + msm_gem_put_vaddr(a5xx_gpu->preempt_bo[i]); + + if (a5xx_gpu->preempt_iova[i]) + msm_gem_put_iova(a5xx_gpu->preempt_bo[i], gpu->aspace); + + drm_gem_object_unreference(a5xx_gpu->preempt_bo[i]); + a5xx_gpu->preempt_bo[i] = NULL; + } +} + +void a5xx_preempt_init(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + int i; + + /* No preemption if we only have one ring */ + if (gpu->nr_rings <= 1) + return; + + for (i = 0; i < gpu->nr_rings; i++) { + if (preempt_init_ring(a5xx_gpu, gpu->rb[i])) { + /* + * On any failure our adventure is over. Clean up and + * set nr_rings to 1 to force preemption off + */ + a5xx_preempt_fini(gpu); + gpu->nr_rings = 1; + + return; + } + } + + setup_timer(&a5xx_gpu->preempt_timer, a5xx_preempt_timer, + (unsigned long) a5xx_gpu); +} diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index c75c4df4bc39..05022ea2a007 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -125,51 +125,24 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev) { struct msm_drm_private *priv = dev->dev_private; struct platform_device *pdev = priv->gpu_pdev; - struct adreno_platform_config *config; - struct adreno_rev rev; - const struct adreno_info *info; - struct msm_gpu *gpu = NULL; + struct msm_gpu *gpu = platform_get_drvdata(priv->gpu_pdev); + int ret; - if (!pdev) { + if (!gpu) { dev_err(dev->dev, "no adreno device\n"); return NULL; } - config = pdev->dev.platform_data; - rev = config->rev; - info = adreno_info(config->rev); - - if (!info) { - dev_warn(dev->dev, "Unknown GPU revision: %u.%u.%u.%u\n", - rev.core, rev.major, rev.minor, rev.patchid); + pm_runtime_get_sync(&pdev->dev); + mutex_lock(&dev->struct_mutex); + ret = msm_gpu_hw_init(gpu); + mutex_unlock(&dev->struct_mutex); + pm_runtime_put_sync(&pdev->dev); + if (ret) { + dev_err(dev->dev, "gpu hw init failed: %d\n", ret); return NULL; } - DBG("Found GPU: %u.%u.%u.%u", rev.core, rev.major, - rev.minor, rev.patchid); - - gpu = info->init(dev); - if (IS_ERR(gpu)) { - dev_warn(dev->dev, "failed to load adreno gpu\n"); - gpu = NULL; - /* not fatal */ - } - - if (gpu) { - int ret; - - pm_runtime_get_sync(&pdev->dev); - mutex_lock(&dev->struct_mutex); - ret = msm_gpu_hw_init(gpu); - mutex_unlock(&dev->struct_mutex); - pm_runtime_put_sync(&pdev->dev); - if (ret) { - dev_err(dev->dev, "gpu hw init failed: %d\n", ret); - gpu->funcs->destroy(gpu); - gpu = NULL; - } - } - return gpu; } @@ -282,6 +255,9 @@ static int adreno_get_pwrlevels(struct device *dev, static int adreno_bind(struct device *dev, struct device *master, void *data) { static struct adreno_platform_config config = {}; + const struct adreno_info *info; + struct drm_device *drm = dev_get_drvdata(master); + struct msm_gpu *gpu; u32 val; int ret; @@ -302,13 +278,39 @@ static int adreno_bind(struct device *dev, struct device *master, void *data) return ret; dev->platform_data = &config; - set_gpu_pdev(dev_get_drvdata(master), to_platform_device(dev)); + set_gpu_pdev(drm, to_platform_device(dev)); + + info = adreno_info(config.rev); + + if (!info) { + dev_warn(drm->dev, "Unknown GPU revision: %u.%u.%u.%u\n", + config.rev.core, config.rev.major, + config.rev.minor, config.rev.patchid); + return -ENXIO; + } + + DBG("Found GPU: %u.%u.%u.%u", config.rev.core, config.rev.major, + config.rev.minor, config.rev.patchid); + + gpu = info->init(drm); + if (IS_ERR(gpu)) { + dev_warn(drm->dev, "failed to load adreno gpu\n"); + return PTR_ERR(gpu); + } + + dev_set_drvdata(dev, gpu); + return 0; } static void adreno_unbind(struct device *dev, struct device *master, void *data) { + struct msm_gpu *gpu = dev_get_drvdata(dev); + + gpu->funcs->pm_suspend(gpu); + gpu->funcs->destroy(gpu); + set_gpu_pdev(dev_get_drvdata(master), NULL); } diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index c8b4ac254bb5..e2ffecce59a3 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -21,8 +21,6 @@ #include "msm_gem.h" #include "msm_mmu.h" -#define RB_SIZE SZ_32K -#define RB_BLKSIZE 32 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value) { @@ -58,72 +56,181 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value) return ret; } return -EINVAL; + case MSM_PARAM_NR_RINGS: + *value = gpu->nr_rings; + return 0; default: DBG("%s: invalid param: %u", gpu->name, param); return -EINVAL; } } +const struct firmware * +adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname) +{ + struct drm_device *drm = adreno_gpu->base.dev; + const struct firmware *fw = NULL; + char newname[strlen("qcom/") + strlen(fwname) + 1]; + int ret; + + sprintf(newname, "qcom/%s", fwname); + + /* + * Try first to load from qcom/$fwfile using a direct load (to avoid + * a potential timeout waiting for usermode helper) + */ + if ((adreno_gpu->fwloc == FW_LOCATION_UNKNOWN) || + (adreno_gpu->fwloc == FW_LOCATION_NEW)) { + + ret = request_firmware_direct(&fw, newname, drm->dev); + if (!ret) { + dev_info(drm->dev, "loaded %s from new location\n", + newname); + adreno_gpu->fwloc = FW_LOCATION_NEW; + return fw; + } else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) { + dev_err(drm->dev, "failed to load %s: %d\n", + newname, ret); + return ERR_PTR(ret); + } + } + + /* + * Then try the legacy location without qcom/ prefix + */ + if ((adreno_gpu->fwloc == FW_LOCATION_UNKNOWN) || + (adreno_gpu->fwloc == FW_LOCATION_LEGACY)) { + + ret = request_firmware_direct(&fw, fwname, drm->dev); + if (!ret) { + dev_info(drm->dev, "loaded %s from legacy location\n", + newname); + adreno_gpu->fwloc = FW_LOCATION_LEGACY; + return fw; + } else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) { + dev_err(drm->dev, "failed to load %s: %d\n", + fwname, ret); + return ERR_PTR(ret); + } + } + + /* + * Finally fall back to request_firmware() for cases where the + * usermode helper is needed (I think mainly android) + */ + if ((adreno_gpu->fwloc == FW_LOCATION_UNKNOWN) || + (adreno_gpu->fwloc == FW_LOCATION_HELPER)) { + + ret = request_firmware(&fw, newname, drm->dev); + if (!ret) { + dev_info(drm->dev, "loaded %s with helper\n", + newname); + adreno_gpu->fwloc = FW_LOCATION_HELPER; + return fw; + } else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) { + dev_err(drm->dev, "failed to load %s: %d\n", + newname, ret); + return ERR_PTR(ret); + } + } + + dev_err(drm->dev, "failed to load %s\n", fwname); + return ERR_PTR(-ENOENT); +} + +static int adreno_load_fw(struct adreno_gpu *adreno_gpu) +{ + const struct firmware *fw; + + if (adreno_gpu->pm4) + return 0; + + fw = adreno_request_fw(adreno_gpu, adreno_gpu->info->pm4fw); + if (IS_ERR(fw)) + return PTR_ERR(fw); + adreno_gpu->pm4 = fw; + + fw = adreno_request_fw(adreno_gpu, adreno_gpu->info->pfpfw); + if (IS_ERR(fw)) { + release_firmware(adreno_gpu->pm4); + adreno_gpu->pm4 = NULL; + return PTR_ERR(fw); + } + adreno_gpu->pfp = fw; + + return 0; +} + int adreno_hw_init(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); - int ret; + int ret, i; DBG("%s", gpu->name); - ret = msm_gem_get_iova(gpu->rb->bo, gpu->aspace, &gpu->rb_iova); - if (ret) { - gpu->rb_iova = 0; - dev_err(gpu->dev->dev, "could not map ringbuffer: %d\n", ret); + ret = adreno_load_fw(adreno_gpu); + if (ret) return ret; - } - /* reset ringbuffer: */ - gpu->rb->cur = gpu->rb->start; + for (i = 0; i < gpu->nr_rings; i++) { + struct msm_ringbuffer *ring = gpu->rb[i]; + + if (!ring) + continue; + + ret = msm_gem_get_iova(ring->bo, gpu->aspace, &ring->iova); + if (ret) { + ring->iova = 0; + dev_err(gpu->dev->dev, + "could not map ringbuffer %d: %d\n", i, ret); + return ret; + } + + ring->cur = ring->start; + ring->next = ring->start; - /* reset completed fence seqno: */ - adreno_gpu->memptrs->fence = gpu->fctx->completed_fence; - adreno_gpu->memptrs->rptr = 0; + /* reset completed fence seqno: */ + ring->memptrs->fence = ring->seqno; + ring->memptrs->rptr = 0; + } - /* Setup REG_CP_RB_CNTL: */ + /* + * Setup REG_CP_RB_CNTL. The same value is used across targets (with + * the excpetion of A430 that disables the RPTR shadow) - the cacluation + * for the ringbuffer size and block size is moved to msm_gpu.h for the + * pre-processor to deal with and the A430 variant is ORed in here + */ adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_CNTL, - /* size is log2(quad-words): */ - AXXX_CP_RB_CNTL_BUFSZ(ilog2(gpu->rb->size / 8)) | - AXXX_CP_RB_CNTL_BLKSZ(ilog2(RB_BLKSIZE / 8)) | - (adreno_is_a430(adreno_gpu) ? AXXX_CP_RB_CNTL_NO_UPDATE : 0)); + MSM_GPU_RB_CNTL_DEFAULT | + (adreno_is_a430(adreno_gpu) ? AXXX_CP_RB_CNTL_NO_UPDATE : 0)); - /* Setup ringbuffer address: */ + /* Setup ringbuffer address - use ringbuffer[0] for GPU init */ adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_BASE, - REG_ADRENO_CP_RB_BASE_HI, gpu->rb_iova); + REG_ADRENO_CP_RB_BASE_HI, gpu->rb[0]->iova); if (!adreno_is_a430(adreno_gpu)) { adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_RPTR_ADDR, REG_ADRENO_CP_RB_RPTR_ADDR_HI, - rbmemptr(adreno_gpu, rptr)); + rbmemptr(gpu->rb[0], rptr)); } return 0; } -static uint32_t get_wptr(struct msm_ringbuffer *ring) -{ - return ring->cur - ring->start; -} - /* Use this helper to read rptr, since a430 doesn't update rptr in memory */ -static uint32_t get_rptr(struct adreno_gpu *adreno_gpu) +static uint32_t get_rptr(struct adreno_gpu *adreno_gpu, + struct msm_ringbuffer *ring) { if (adreno_is_a430(adreno_gpu)) - return adreno_gpu->memptrs->rptr = adreno_gpu_read( + return ring->memptrs->rptr = adreno_gpu_read( adreno_gpu, REG_ADRENO_CP_RB_RPTR); else - return adreno_gpu->memptrs->rptr; + return ring->memptrs->rptr; } -uint32_t adreno_last_fence(struct msm_gpu *gpu) +struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu) { - struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); - return adreno_gpu->memptrs->fence; + return gpu->rb[0]; } void adreno_recover(struct msm_gpu *gpu) @@ -149,7 +256,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct msm_drm_private *priv = gpu->dev->dev_private; - struct msm_ringbuffer *ring = gpu->rb; + struct msm_ringbuffer *ring = submit->ring; unsigned i; for (i = 0; i < submit->nr_cmds; i++) { @@ -164,7 +271,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, case MSM_SUBMIT_CMD_BUF: OUT_PKT3(ring, adreno_is_a430(adreno_gpu) ? CP_INDIRECT_BUFFER_PFE : CP_INDIRECT_BUFFER_PFD, 2); - OUT_RING(ring, submit->cmd[i].iova); + OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); OUT_RING(ring, submit->cmd[i].size); OUT_PKT2(ring); break; @@ -172,7 +279,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, } OUT_PKT0(ring, REG_AXXX_CP_SCRATCH_REG2, 1); - OUT_RING(ring, submit->fence->seqno); + OUT_RING(ring, submit->seqno); if (adreno_is_a3xx(adreno_gpu) || adreno_is_a4xx(adreno_gpu)) { /* Flush HLSQ lazy updates to make sure there is nothing @@ -188,8 +295,8 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, OUT_PKT3(ring, CP_EVENT_WRITE, 3); OUT_RING(ring, CACHE_FLUSH_TS); - OUT_RING(ring, rbmemptr(adreno_gpu, fence)); - OUT_RING(ring, submit->fence->seqno); + OUT_RING(ring, rbmemptr(ring, fence)); + OUT_RING(ring, submit->seqno); /* we could maybe be clever and only CP_COND_EXEC the interrupt: */ OUT_PKT3(ring, CP_INTERRUPT, 1); @@ -215,20 +322,23 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, } #endif - gpu->funcs->flush(gpu); + gpu->funcs->flush(gpu, ring); } -void adreno_flush(struct msm_gpu *gpu) +void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); uint32_t wptr; + /* Copy the shadow to the actual register */ + ring->cur = ring->next; + /* * Mask wptr value that we calculate to fit in the HW range. This is * to account for the possibility that the last command fit exactly into * the ringbuffer and rb->next hasn't wrapped to zero yet */ - wptr = get_wptr(gpu->rb) & ((gpu->rb->size / 4) - 1); + wptr = get_wptr(ring); /* ensure writes to ringbuffer have hit system memory: */ mb(); @@ -236,17 +346,19 @@ void adreno_flush(struct msm_gpu *gpu) adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_WPTR, wptr); } -bool adreno_idle(struct msm_gpu *gpu) +bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); - uint32_t wptr = get_wptr(gpu->rb); + uint32_t wptr = get_wptr(ring); /* wait for CP to drain ringbuffer: */ - if (!spin_until(get_rptr(adreno_gpu) == wptr)) + if (!spin_until(get_rptr(adreno_gpu, ring) == wptr)) return true; /* TODO maybe we need to reset GPU here to recover from hang? */ - DRM_ERROR("%s: timeout waiting to drain ringbuffer!\n", gpu->name); + DRM_ERROR("%s: timeout waiting to drain ringbuffer %d rptr/wptr = %X/%X\n", + gpu->name, ring->id, get_rptr(adreno_gpu, ring), wptr); + return false; } @@ -261,10 +373,16 @@ void adreno_show(struct msm_gpu *gpu, struct seq_file *m) adreno_gpu->rev.major, adreno_gpu->rev.minor, adreno_gpu->rev.patchid); - seq_printf(m, "fence: %d/%d\n", adreno_gpu->memptrs->fence, - gpu->fctx->last_fence); - seq_printf(m, "rptr: %d\n", get_rptr(adreno_gpu)); - seq_printf(m, "rb wptr: %d\n", get_wptr(gpu->rb)); + for (i = 0; i < gpu->nr_rings; i++) { + struct msm_ringbuffer *ring = gpu->rb[i]; + + seq_printf(m, "rb %d: fence: %d/%d\n", i, + ring->memptrs->fence, ring->seqno); + + seq_printf(m, " rptr: %d\n", + get_rptr(adreno_gpu, ring)); + seq_printf(m, "rb wptr: %d\n", get_wptr(ring)); + } /* dump these out in a form that can be parsed by demsm: */ seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name); @@ -290,16 +408,23 @@ void adreno_show(struct msm_gpu *gpu, struct seq_file *m) void adreno_dump_info(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + int i; printk("revision: %d (%d.%d.%d.%d)\n", adreno_gpu->info->revn, adreno_gpu->rev.core, adreno_gpu->rev.major, adreno_gpu->rev.minor, adreno_gpu->rev.patchid); - printk("fence: %d/%d\n", adreno_gpu->memptrs->fence, - gpu->fctx->last_fence); - printk("rptr: %d\n", get_rptr(adreno_gpu)); - printk("rb wptr: %d\n", get_wptr(gpu->rb)); + for (i = 0; i < gpu->nr_rings; i++) { + struct msm_ringbuffer *ring = gpu->rb[i]; + + printk("rb %d: fence: %d/%d\n", i, + ring->memptrs->fence, + ring->seqno); + + printk("rptr: %d\n", get_rptr(adreno_gpu, ring)); + printk("rb wptr: %d\n", get_wptr(ring)); + } } /* would be nice to not have to duplicate the _show() stuff with printk(): */ @@ -322,28 +447,31 @@ void adreno_dump(struct msm_gpu *gpu) } } -static uint32_t ring_freewords(struct msm_gpu *gpu) +static uint32_t ring_freewords(struct msm_ringbuffer *ring) { - struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); - uint32_t size = gpu->rb->size / 4; - uint32_t wptr = get_wptr(gpu->rb); - uint32_t rptr = get_rptr(adreno_gpu); + struct adreno_gpu *adreno_gpu = to_adreno_gpu(ring->gpu); + uint32_t size = MSM_GPU_RINGBUFFER_SZ >> 2; + /* Use ring->next to calculate free size */ + uint32_t wptr = ring->next - ring->start; + uint32_t rptr = get_rptr(adreno_gpu, ring); return (rptr + (size - 1) - wptr) % size; } -void adreno_wait_ring(struct msm_gpu *gpu, uint32_t ndwords) +void adreno_wait_ring(struct msm_ringbuffer *ring, uint32_t ndwords) { - if (spin_until(ring_freewords(gpu) >= ndwords)) - DRM_ERROR("%s: timeout waiting for ringbuffer space\n", gpu->name); + if (spin_until(ring_freewords(ring) >= ndwords)) + DRM_DEV_ERROR(ring->gpu->dev->dev, + "timeout waiting for space in ringubffer %d\n", + ring->id); } int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, - struct adreno_gpu *adreno_gpu, const struct adreno_gpu_funcs *funcs) + struct adreno_gpu *adreno_gpu, + const struct adreno_gpu_funcs *funcs, int nr_rings) { struct adreno_platform_config *config = pdev->dev.platform_data; struct msm_gpu_config adreno_gpu_config = { 0 }; struct msm_gpu *gpu = &adreno_gpu->base; - int ret; adreno_gpu->funcs = funcs; adreno_gpu->info = adreno_info(config->rev); @@ -366,59 +494,20 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, adreno_gpu_config.va_start = SZ_16M; adreno_gpu_config.va_end = 0xffffffff; - adreno_gpu_config.ringsz = RB_SIZE; + adreno_gpu_config.nr_rings = nr_rings; pm_runtime_set_autosuspend_delay(&pdev->dev, DRM_MSM_INACTIVE_PERIOD); pm_runtime_use_autosuspend(&pdev->dev); pm_runtime_enable(&pdev->dev); - ret = msm_gpu_init(drm, pdev, &adreno_gpu->base, &funcs->base, + return msm_gpu_init(drm, pdev, &adreno_gpu->base, &funcs->base, adreno_gpu->info->name, &adreno_gpu_config); - if (ret) - return ret; - - ret = request_firmware(&adreno_gpu->pm4, adreno_gpu->info->pm4fw, drm->dev); - if (ret) { - dev_err(drm->dev, "failed to load %s PM4 firmware: %d\n", - adreno_gpu->info->pm4fw, ret); - return ret; - } - - ret = request_firmware(&adreno_gpu->pfp, adreno_gpu->info->pfpfw, drm->dev); - if (ret) { - dev_err(drm->dev, "failed to load %s PFP firmware: %d\n", - adreno_gpu->info->pfpfw, ret); - return ret; - } - - adreno_gpu->memptrs = msm_gem_kernel_new(drm, - sizeof(*adreno_gpu->memptrs), MSM_BO_UNCACHED, gpu->aspace, - &adreno_gpu->memptrs_bo, &adreno_gpu->memptrs_iova); - - if (IS_ERR(adreno_gpu->memptrs)) { - ret = PTR_ERR(adreno_gpu->memptrs); - adreno_gpu->memptrs = NULL; - dev_err(drm->dev, "could not allocate memptrs: %d\n", ret); - } - - return ret; } void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu) { - struct msm_gpu *gpu = &adreno_gpu->base; - - if (adreno_gpu->memptrs_bo) { - if (adreno_gpu->memptrs) - msm_gem_put_vaddr(adreno_gpu->memptrs_bo); - - if (adreno_gpu->memptrs_iova) - msm_gem_put_iova(adreno_gpu->memptrs_bo, gpu->aspace); - - drm_gem_object_unreference_unlocked(adreno_gpu->memptrs_bo); - } release_firmware(adreno_gpu->pm4); release_firmware(adreno_gpu->pfp); - msm_gpu_cleanup(gpu); + msm_gpu_cleanup(&adreno_gpu->base); } diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index 4d9165f29f43..28e3de6e5f94 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -2,7 +2,7 @@ * Copyright (C) 2013 Red Hat * Author: Rob Clark <robdclark@gmail.com> * - * Copyright (c) 2014 The Linux Foundation. All rights reserved. + * Copyright (c) 2014,2017 The Linux Foundation. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published by @@ -82,14 +82,6 @@ struct adreno_info { const struct adreno_info *adreno_info(struct adreno_rev rev); -#define rbmemptr(adreno_gpu, member) \ - ((adreno_gpu)->memptrs_iova + offsetof(struct adreno_rbmemptrs, member)) - -struct adreno_rbmemptrs { - volatile uint32_t rptr; - volatile uint32_t fence; -}; - struct adreno_gpu { struct msm_gpu base; struct adreno_rev rev; @@ -101,16 +93,30 @@ struct adreno_gpu { /* interesting register offsets to dump: */ const unsigned int *registers; + /* + * Are we loading fw from legacy path? Prior to addition + * of gpu firmware to linux-firmware, the fw files were + * placed in toplevel firmware directory, following qcom's + * android kernel. But linux-firmware preferred they be + * placed in a 'qcom' subdirectory. + * + * For backwards compatibility, we try first to load from + * the new path, using request_firmware_direct() to avoid + * any potential timeout waiting for usermode helper, then + * fall back to the old path (with direct load). And + * finally fall back to request_firmware() with the new + * path to allow the usermode helper. + */ + enum { + FW_LOCATION_UNKNOWN = 0, + FW_LOCATION_NEW, /* /lib/firmware/qcom/$fwfile */ + FW_LOCATION_LEGACY, /* /lib/firmware/$fwfile */ + FW_LOCATION_HELPER, + } fwloc; + /* firmware: */ const struct firmware *pm4, *pfp; - /* ringbuffer rptr/wptr: */ - // TODO should this be in msm_ringbuffer? I think it would be - // different for z180.. - struct adreno_rbmemptrs *memptrs; - struct drm_gem_object *memptrs_bo; - uint64_t memptrs_iova; - /* * Register offsets are different between some GPUs. * GPU specific offsets will be exported by GPU specific @@ -196,22 +202,25 @@ static inline int adreno_is_a530(struct adreno_gpu *gpu) } int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value); +const struct firmware *adreno_request_fw(struct adreno_gpu *adreno_gpu, + const char *fwname); int adreno_hw_init(struct msm_gpu *gpu); -uint32_t adreno_last_fence(struct msm_gpu *gpu); void adreno_recover(struct msm_gpu *gpu); void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, struct msm_file_private *ctx); -void adreno_flush(struct msm_gpu *gpu); -bool adreno_idle(struct msm_gpu *gpu); +void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring); +bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring); #ifdef CONFIG_DEBUG_FS void adreno_show(struct msm_gpu *gpu, struct seq_file *m); #endif void adreno_dump_info(struct msm_gpu *gpu); void adreno_dump(struct msm_gpu *gpu); -void adreno_wait_ring(struct msm_gpu *gpu, uint32_t ndwords); +void adreno_wait_ring(struct msm_ringbuffer *ring, uint32_t ndwords); +struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu); int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, - struct adreno_gpu *gpu, const struct adreno_gpu_funcs *funcs); + struct adreno_gpu *gpu, const struct adreno_gpu_funcs *funcs, + int nr_rings); void adreno_gpu_cleanup(struct adreno_gpu *gpu); @@ -220,7 +229,7 @@ void adreno_gpu_cleanup(struct adreno_gpu *gpu); static inline void OUT_PKT0(struct msm_ringbuffer *ring, uint16_t regindx, uint16_t cnt) { - adreno_wait_ring(ring->gpu, cnt+1); + adreno_wait_ring(ring, cnt+1); OUT_RING(ring, CP_TYPE0_PKT | ((cnt-1) << 16) | (regindx & 0x7FFF)); } @@ -228,14 +237,14 @@ OUT_PKT0(struct msm_ringbuffer *ring, uint16_t regindx, uint16_t cnt) static inline void OUT_PKT2(struct msm_ringbuffer *ring) { - adreno_wait_ring(ring->gpu, 1); + adreno_wait_ring(ring, 1); OUT_RING(ring, CP_TYPE2_PKT); } static inline void OUT_PKT3(struct msm_ringbuffer *ring, uint8_t opcode, uint16_t cnt) { - adreno_wait_ring(ring->gpu, cnt+1); + adreno_wait_ring(ring, cnt+1); OUT_RING(ring, CP_TYPE3_PKT | ((cnt-1) << 16) | ((opcode & 0xFF) << 8)); } @@ -257,14 +266,14 @@ static inline u32 PM4_PARITY(u32 val) static inline void OUT_PKT4(struct msm_ringbuffer *ring, uint16_t regindx, uint16_t cnt) { - adreno_wait_ring(ring->gpu, cnt + 1); + adreno_wait_ring(ring, cnt + 1); OUT_RING(ring, PKT4(regindx, cnt)); } static inline void OUT_PKT7(struct msm_ringbuffer *ring, uint8_t opcode, uint16_t cnt) { - adreno_wait_ring(ring->gpu, cnt + 1); + adreno_wait_ring(ring, cnt + 1); OUT_RING(ring, CP_TYPE7_PKT | (cnt << 0) | (PM4_PARITY(cnt) << 15) | ((opcode & 0x7F) << 16) | (PM4_PARITY(opcode) << 23)); } @@ -323,6 +332,11 @@ static inline void adreno_gpu_write64(struct adreno_gpu *gpu, adreno_gpu_write(gpu, hi, upper_32_bits(data)); } +static inline uint32_t get_wptr(struct msm_ringbuffer *ring) +{ + return (ring->cur - ring->start) % (MSM_GPU_RINGBUFFER_SZ >> 2); +} + /* * Given a register and a count, return a value to program into * REG_CP_PROTECT_REG(n) - this will block both reads and writes for _len |