/*
* Copyright 2009 Jerome Glisse.
* All Rights Reserved.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the
* "Software"), to deal in the Software without restriction, including
* without limitation the rights to use, copy, modify, merge, publish,
* distribute, sub license, and/or sell copies of the Software, and to
* permit persons to whom the Software is furnished to do so, subject to
* the following conditions:
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
* THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
* DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
* OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
* USE OR OTHER DEALINGS IN THE SOFTWARE.
*
* The above copyright notice and this permission notice (including the
* next paragraph) shall be included in all copies or substantial portions
* of the Software.
*
*/
/*
* Authors:
* Jerome Glisse <glisse@freedesktop.org>
* Dave Airlie
*/
#include <linux/seq_file.h>
#include <linux/atomic.h>
#include <linux/wait.h>
#include <linux/kref.h>
#include <linux/slab.h>
#include <linux/firmware.h>
#include <linux/pm_runtime.h>
#include <drm/drm_drv.h>
#include "amdgpu.h"
#include "amdgpu_trace.h"
#include "amdgpu_reset.h"
/*
* Fences mark an event in the GPUs pipeline and are used
* for GPU/CPU synchronization. When the fence is written,
* it is expected that all buffers associated with that fence
* are no longer in use by the associated ring on the GPU and
* that the relevant GPU caches have been flushed.
*/
struct amdgpu_fence {
struct dma_fence base;
/* RB, DMA, etc. */
struct amdgpu_ring *ring;
ktime_t start_timestamp;
};
static struct kmem_cache *amdgpu_fence_slab;
int amdgpu_fence_slab_init(void)
{
amdgpu_fence_slab = KMEM_CACHE(amdgpu_fence, SLAB_HWCACHE_ALIGN);
if (!amdgpu_fence_slab)
return -ENOMEM;
return 0;
}
void amdgpu_fence_slab_fini(void)
{
rcu_barrier();
kmem_cache_destroy(amdgpu_fence_slab);
}
/*
* Cast helper
*/
static const struct dma_fence_ops amdgpu_fence_ops;
static const struct dma_fence_ops amdgpu_job_fence_ops;
static inline struct amdgpu_fence *to_amdgpu_fence(struct dma_fence *f)
{
struct amdgpu_fence *__f = container_of(f, struct amdgpu_fence, base);
if (__f->base.ops == &amdgpu_fence_ops ||
__f->base.ops == &amdgpu_job_fence_ops)
return __f;
return NULL;
}
/**
* amdgpu_fence_write - write a fence value
*
* @ring: ring the fence is associated with
* @seq: sequence number to write
*
* Writes a fence value to memory (all asics).
*/
static void amdgpu_fence_write(struct amdgpu_ring *ring, u32 seq)
{
struct amdgpu_fence_driver *drv = &ring->fence_drv;
if (drv->cpu_addr)
*drv->cpu_addr = cpu_to_le32(seq);
}
/**
* amdgpu_fence_read - read a fence value
*
* @ring: ring the fence is associated with
*
* Reads a fence value from memory (all asics).
* Returns the value of the fence read from memory.
*/
static u32 amdgpu_fence_read(struct amdgpu_ring *ring)
{
struct amdgpu_fence_driver *drv = &ring->fence_drv;
u32 seq = 0;
if (drv->cpu_addr)
seq = le32_to_cpu(*drv->cpu_addr);
else
seq = atomic_read(&drv->last_seq);
return seq;
}
/**
* amdgpu_fence_emit - emit a fence on the requested ring
*
* @ring: ring the fence is associated with
* @f: resulting fence object
* @job: job the fence is embedded in
* @flags: flags to pass into the subordinate .emit_fence() call
*
* Emits a fence command on the requested ring (all asics).
* Returns 0 on success, -ENOMEM on failure.
*/
int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amdgpu_job *job,
unsigned int flags)
{
struct amdgpu_device *adev = ring->adev;
struct dma_fence *fence;
struct amdgpu_fence *am_fence;
struct dma_fence __rcu **ptr;
uint32_t seq;
int r;
if (job == NULL) {
/* create a sperate hw fence */
am_fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_ATOMIC);
if (am_fence == NULL)
return -ENOMEM;
fence = &am_fence->base;
am_fence->ring = ring;
} else {
/* take use of job-embedded fence */
fence = &job->hw_fence;
}
seq = ++ring->fence_drv.sync_seq;
if (job && job->job_run_counter) {
/* reinit seq for resubmitted jobs */
fence->seqno = seq;
/* TO be inline with external fence creation and other drivers */
dma_fence_get(fence);
} else {
if (job) {
dma_fence_init(fence, &amdgpu_job_fence_ops,
&ring->fence_drv.lock,
adev->fence_context + ring->idx, seq);
/* Against remove in amdgpu_job_{free, free_cb} */
dma_fence_get(fence);
} else {
dma_fence_init(fence, &amdgpu_fence_ops,
&ring