diff options
Diffstat (limited to 'drivers/gpu/drm/msm/adreno/a5xx_preempt.c')
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a5xx_preempt.c | 101 |
1 files changed, 65 insertions, 36 deletions
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index 3d62310a535f..e4924b5e1c48 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -1,14 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0-only /* 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" @@ -54,9 +45,9 @@ static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) if (!ring) return; - spin_lock_irqsave(&ring->lock, flags); + spin_lock_irqsave(&ring->preempt_lock, flags); wptr = get_wptr(ring); - spin_unlock_irqrestore(&ring->lock, flags); + spin_unlock_irqrestore(&ring->preempt_lock, flags); gpu_write(gpu, REG_A5XX_CP_RB_WPTR, wptr); } @@ -64,6 +55,8 @@ static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) /* Return the highest priority ringbuffer with something in it */ static struct msm_ringbuffer *get_next_ring(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; int i; @@ -71,9 +64,11 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu) 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); + spin_lock_irqsave(&ring->preempt_lock, flags); + empty = (get_wptr(ring) == gpu->funcs->get_rptr(gpu, ring)); + if (!empty && ring == a5xx_gpu->cur_ring) + empty = ring->memptrs->fence == a5xx_gpu->last_seqno[i]; + spin_unlock_irqrestore(&ring->preempt_lock, flags); if (!empty) return ring; @@ -84,16 +79,16 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu) static void a5xx_preempt_timer(struct timer_list *t) { - struct a5xx_gpu *a5xx_gpu = from_timer(a5xx_gpu, t, preempt_timer); + struct a5xx_gpu *a5xx_gpu = timer_container_of(a5xx_gpu, t, + preempt_timer); 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; DRM_DEV_ERROR(dev->dev, "%s: preemption timed out\n", gpu->name); - queue_work(priv->wq, &gpu->recover_work); + kthread_queue_work(gpu->worker, &gpu->recover_work); } /* Try to trigger a preemption switch */ @@ -108,11 +103,18 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu) return; /* + * Serialize preemption start to ensure that we always make + * decision on latest state. Otherwise we can get stuck in + * lower priority or empty ring. + */ + spin_lock_irqsave(&a5xx_gpu->preempt_start_lock, flags); + + /* * 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; + goto out; /* Get the next ring to preempt to */ ring = get_next_ring(gpu); @@ -137,17 +139,18 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu) set_preempt_state(a5xx_gpu, PREEMPT_ABORT); update_wptr(gpu, a5xx_gpu->cur_ring); set_preempt_state(a5xx_gpu, PREEMPT_NONE); - return; + goto out; } + spin_unlock_irqrestore(&a5xx_gpu->preempt_start_lock, flags); + /* Make sure the wptr doesn't update while we're in motion */ - spin_lock_irqsave(&ring->lock, flags); + spin_lock_irqsave(&ring->preempt_lock, flags); a5xx_gpu->preempt[ring->id]->wptr = get_wptr(ring); - spin_unlock_irqrestore(&ring->lock, flags); + spin_unlock_irqrestore(&ring->preempt_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; @@ -163,6 +166,10 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu) /* And actually start the preemption */ gpu_write(gpu, REG_A5XX_CP_CONTEXT_SWITCH_CNTL, 1); + return; + +out: + spin_unlock_irqrestore(&a5xx_gpu->preempt_start_lock, flags); } void a5xx_preempt_irq(struct msm_gpu *gpu) @@ -171,13 +178,12 @@ void a5xx_preempt_irq(struct msm_gpu *gpu) 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); + timer_delete(&a5xx_gpu->preempt_timer); /* * The hardware should be setting CP_CONTEXT_SWITCH_CNTL to zero before @@ -190,7 +196,7 @@ void a5xx_preempt_irq(struct msm_gpu *gpu) set_preempt_state(a5xx_gpu, PREEMPT_FAULTED); DRM_DEV_ERROR(dev->dev, "%s: Preemption failed to complete\n", gpu->name); - queue_work(priv->wq, &gpu->recover_work); + kthread_queue_work(gpu->worker, &gpu->recover_work); return; } @@ -200,6 +206,12 @@ void a5xx_preempt_irq(struct msm_gpu *gpu) update_wptr(gpu, a5xx_gpu->cur_ring); set_preempt_state(a5xx_gpu, PREEMPT_NONE); + + /* + * Try to trigger preemption again in case there was a submit or + * retire during ring switch + */ + a5xx_preempt_trigger(gpu); } void a5xx_preempt_hw_init(struct msm_gpu *gpu) @@ -216,14 +228,16 @@ void a5xx_preempt_hw_init(struct msm_gpu *gpu) return; for (i = 0; i < gpu->nr_rings; i++) { + a5xx_gpu->preempt[i]->data = 0; + a5xx_gpu->preempt[i]->info = 0; a5xx_gpu->preempt[i]->wptr = 0; a5xx_gpu->preempt[i]->rptr = 0; a5xx_gpu->preempt[i]->rbase = gpu->rb[i]->iova; + a5xx_gpu->preempt[i]->rptr_addr = shadowptr(a5xx_gpu, gpu->rb[i]); } /* 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); + gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_LO, 0); /* Reset the preemption state */ set_preempt_state(a5xx_gpu, PREEMPT_NONE); @@ -235,19 +249,31 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu, 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; + void *counters; + struct drm_gem_object *bo = NULL, *counters_bo = NULL; + u64 iova = 0, counters_iova = 0; ptr = msm_gem_kernel_new(gpu->dev, A5XX_PREEMPT_RECORD_SIZE + A5XX_PREEMPT_COUNTER_SIZE, - MSM_BO_UNCACHED, gpu->aspace, &bo, &iova); + MSM_BO_WC | MSM_BO_MAP_PRIV, gpu->vm, &bo, &iova); if (IS_ERR(ptr)) return PTR_ERR(ptr); + /* The buffer to store counters needs to be unprivileged */ + counters = msm_gem_kernel_new(gpu->dev, + A5XX_PREEMPT_COUNTER_SIZE, + MSM_BO_WC, gpu->vm, &counters_bo, &counters_iova); + if (IS_ERR(counters)) { + msm_gem_kernel_put(bo, gpu->vm); + return PTR_ERR(counters); + } + msm_gem_object_set_name(bo, "preempt"); + msm_gem_object_set_name(counters_bo, "preempt_counters"); a5xx_gpu->preempt_bo[ring->id] = bo; + a5xx_gpu->preempt_counters_bo[ring->id] = counters_bo; a5xx_gpu->preempt_iova[ring->id] = iova; a5xx_gpu->preempt[ring->id] = ptr; @@ -256,9 +282,9 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu, 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; + ptr->cntl = MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE; + + ptr->counter = counters_iova; return 0; } @@ -269,8 +295,10 @@ void a5xx_preempt_fini(struct msm_gpu *gpu) struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); int i; - for (i = 0; i < gpu->nr_rings; i++) - msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace, true); + for (i = 0; i < gpu->nr_rings; i++) { + msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->vm); + msm_gem_kernel_put(a5xx_gpu->preempt_counters_bo[i], gpu->vm); + } } void a5xx_preempt_init(struct msm_gpu *gpu) @@ -296,5 +324,6 @@ void a5xx_preempt_init(struct msm_gpu *gpu) } } + spin_lock_init(&a5xx_gpu->preempt_start_lock); timer_setup(&a5xx_gpu->preempt_timer, a5xx_preempt_timer, 0); } |