drm/msm/a6xx: Serialize GMU communication

I've seen some crashes in our crash reporting that *look* like multiple
threads stomping on each other while communicating with GMU.  So wrap
all those paths in a lock.

Signed-off-by: Rob Clark <robdclark@chromium.org>
This commit is contained in:
Rob Clark 2021-09-27 11:00:04 -07:00
parent 654e9c18df
commit f6f59072e8
3 changed files with 43 additions and 6 deletions

View File

@ -296,6 +296,8 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
u32 val;
int request, ack;
WARN_ON_ONCE(!mutex_is_locked(&gmu->lock));
if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits))
return -EINVAL;
@ -337,6 +339,8 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
{
int bit;
WARN_ON_ONCE(!mutex_is_locked(&gmu->lock));
if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits))
return;
@ -1482,6 +1486,8 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
if (!pdev)
return -ENODEV;
mutex_init(&gmu->lock);
gmu->dev = &pdev->dev;
of_dma_configure(gmu->dev, node, true);

View File

@ -44,6 +44,9 @@ struct a6xx_gmu_bo {
struct a6xx_gmu {
struct device *dev;
/* For serializing communication with the GMU: */
struct mutex lock;
struct msm_gem_address_space *aspace;
void * __iomem mmio;

View File

@ -881,7 +881,7 @@ static int a6xx_zap_shader_init(struct msm_gpu *gpu)
A6XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS | \
A6XX_RBBM_INT_0_MASK_UCHE_TRAP_INTR)
static int a6xx_hw_init(struct msm_gpu *gpu)
static int hw_init(struct msm_gpu *gpu)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
@ -1135,6 +1135,19 @@ out:
return ret;
}
static int a6xx_hw_init(struct msm_gpu *gpu)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
int ret;
mutex_lock(&a6xx_gpu->gmu.lock);
ret = hw_init(gpu);
mutex_unlock(&a6xx_gpu->gmu.lock);
return ret;
}
static void a6xx_dump(struct msm_gpu *gpu)
{
DRM_DEV_INFO(&gpu->pdev->dev, "status: %08x\n",
@ -1509,7 +1522,9 @@ static int a6xx_pm_resume(struct msm_gpu *gpu)
trace_msm_gpu_resume(0);
mutex_lock(&a6xx_gpu->gmu.lock);
ret = a6xx_gmu_resume(a6xx_gpu);
mutex_unlock(&a6xx_gpu->gmu.lock);
if (ret)
return ret;
@ -1532,7 +1547,9 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
msm_devfreq_suspend(gpu);
mutex_lock(&a6xx_gpu->gmu.lock);
ret = a6xx_gmu_stop(a6xx_gpu);
mutex_unlock(&a6xx_gpu->gmu.lock);
if (ret)
return ret;
@ -1547,18 +1564,19 @@ static int a6xx_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);
static DEFINE_MUTEX(perfcounter_oob);
mutex_lock(&perfcounter_oob);
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_LO,
REG_A6XX_CP_ALWAYS_ON_COUNTER_HI);
REG_A6XX_CP_ALWAYS_ON_COUNTER_HI);
a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
mutex_unlock(&perfcounter_oob);
mutex_unlock(&a6xx_gpu->gmu.lock);
return 0;
}
@ -1622,6 +1640,16 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
return (unsigned long)busy_time;
}
void a6xx_gpu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
{
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);
a6xx_gmu_set_freq(gpu, opp);
mutex_unlock(&a6xx_gpu->gmu.lock);
}
static struct msm_gem_address_space *
a6xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev)
{
@ -1766,7 +1794,7 @@ static const struct adreno_gpu_funcs funcs = {
#endif
.gpu_busy = a6xx_gpu_busy,
.gpu_get_freq = a6xx_gmu_get_freq,
.gpu_set_freq = a6xx_gmu_set_freq,
.gpu_set_freq = a6xx_gpu_set_freq,
#if defined(CONFIG_DRM_MSM_GPU_STATE)
.gpu_state_get = a6xx_gpu_state_get,
.gpu_state_put = a6xx_gpu_state_put,