[v2,01/23] drm/msm: Pre-allocate hw_fence
Commit Message
From: Rob Clark <robdclark@chromium.org>
Avoid allocating memory in job_run() by pre-allocating the hw_fence.
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
drivers/gpu/drm/msm/msm_fence.c | 12 +++++++++---
drivers/gpu/drm/msm/msm_fence.h | 3 ++-
drivers/gpu/drm/msm/msm_gem_submit.c | 7 +++++++
drivers/gpu/drm/msm/msm_ringbuffer.c | 2 +-
4 files changed, 19 insertions(+), 5 deletions(-)
Comments
Am 20.03.23 um 15:43 schrieb Rob Clark:
> From: Rob Clark <robdclark@chromium.org>
>
> Avoid allocating memory in job_run() by pre-allocating the hw_fence.
>
> Signed-off-by: Rob Clark <robdclark@chromium.org>
> ---
> drivers/gpu/drm/msm/msm_fence.c | 12 +++++++++---
> drivers/gpu/drm/msm/msm_fence.h | 3 ++-
> drivers/gpu/drm/msm/msm_gem_submit.c | 7 +++++++
> drivers/gpu/drm/msm/msm_ringbuffer.c | 2 +-
> 4 files changed, 19 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
> index 56641408ea74..bab3d84f1686 100644
> --- a/drivers/gpu/drm/msm/msm_fence.c
> +++ b/drivers/gpu/drm/msm/msm_fence.c
> @@ -99,7 +99,7 @@ static const struct dma_fence_ops msm_fence_ops = {
> };
>
> struct dma_fence *
> -msm_fence_alloc(struct msm_fence_context *fctx)
> +msm_fence_alloc(void)
> {
> struct msm_fence *f;
>
> @@ -107,10 +107,16 @@ msm_fence_alloc(struct msm_fence_context *fctx)
> if (!f)
> return ERR_PTR(-ENOMEM);
>
> + return &f->base;
> +}
> +
> +void
> +msm_fence_init(struct dma_fence *fence, struct msm_fence_context *fctx)
> +{
> + struct msm_fence *f = to_msm_fence(fence);
> +
> f->fctx = fctx;
>
> dma_fence_init(&f->base, &msm_fence_ops, &fctx->spinlock,
> fctx->context, ++fctx->last_fence);
> -
> - return &f->base;
> }
> diff --git a/drivers/gpu/drm/msm/msm_fence.h b/drivers/gpu/drm/msm/msm_fence.h
> index 7f1798c54cd1..f913fa22d8fe 100644
> --- a/drivers/gpu/drm/msm/msm_fence.h
> +++ b/drivers/gpu/drm/msm/msm_fence.h
> @@ -61,7 +61,8 @@ void msm_fence_context_free(struct msm_fence_context *fctx);
> bool msm_fence_completed(struct msm_fence_context *fctx, uint32_t fence);
> void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence);
>
> -struct dma_fence * msm_fence_alloc(struct msm_fence_context *fctx);
> +struct dma_fence * msm_fence_alloc(void);
> +void msm_fence_init(struct dma_fence *fence, struct msm_fence_context *fctx);
>
> static inline bool
> fence_before(uint32_t a, uint32_t b)
> diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
> index be4bf77103cd..2570c018b0cb 100644
> --- a/drivers/gpu/drm/msm/msm_gem_submit.c
> +++ b/drivers/gpu/drm/msm/msm_gem_submit.c
> @@ -41,6 +41,13 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
> if (!submit)
> return ERR_PTR(-ENOMEM);
>
> + submit->hw_fence = msm_fence_alloc();
> + if (IS_ERR(submit->hw_fence)) {
> + ret = PTR_ERR(submit->hw_fence);
> + kfree(submit);
> + return ERR_PTR(ret);
> + }
> +
> ret = drm_sched_job_init(&submit->base, queue->entity, queue);
> if (ret) {
> kfree(submit);
You probably need some error handling here or otherwise leak
submit->hw_fence.
Apart from that looks good to me.
Christian.
> diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
> index 57a8e9564540..a62b45e5a8c3 100644
> --- a/drivers/gpu/drm/msm/msm_ringbuffer.c
> +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
> @@ -18,7 +18,7 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
> struct msm_gpu *gpu = submit->gpu;
> int i;
>
> - submit->hw_fence = msm_fence_alloc(fctx);
> + msm_fence_init(submit->hw_fence, fctx);
>
> for (i = 0; i < submit->nr_bos; i++) {
> struct drm_gem_object *obj = &submit->bos[i].obj->base;
On Mon, Mar 20, 2023 at 9:52 AM Christian König
<christian.koenig@amd.com> wrote:
>
>
>
> Am 20.03.23 um 15:43 schrieb Rob Clark:
> > From: Rob Clark <robdclark@chromium.org>
> >
> > Avoid allocating memory in job_run() by pre-allocating the hw_fence.
> >
> > Signed-off-by: Rob Clark <robdclark@chromium.org>
> > ---
> > drivers/gpu/drm/msm/msm_fence.c | 12 +++++++++---
> > drivers/gpu/drm/msm/msm_fence.h | 3 ++-
> > drivers/gpu/drm/msm/msm_gem_submit.c | 7 +++++++
> > drivers/gpu/drm/msm/msm_ringbuffer.c | 2 +-
> > 4 files changed, 19 insertions(+), 5 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
> > index 56641408ea74..bab3d84f1686 100644
> > --- a/drivers/gpu/drm/msm/msm_fence.c
> > +++ b/drivers/gpu/drm/msm/msm_fence.c
> > @@ -99,7 +99,7 @@ static const struct dma_fence_ops msm_fence_ops = {
> > };
> >
> > struct dma_fence *
> > -msm_fence_alloc(struct msm_fence_context *fctx)
> > +msm_fence_alloc(void)
> > {
> > struct msm_fence *f;
> >
> > @@ -107,10 +107,16 @@ msm_fence_alloc(struct msm_fence_context *fctx)
> > if (!f)
> > return ERR_PTR(-ENOMEM);
> >
> > + return &f->base;
> > +}
> > +
> > +void
> > +msm_fence_init(struct dma_fence *fence, struct msm_fence_context *fctx)
> > +{
> > + struct msm_fence *f = to_msm_fence(fence);
> > +
> > f->fctx = fctx;
> >
> > dma_fence_init(&f->base, &msm_fence_ops, &fctx->spinlock,
> > fctx->context, ++fctx->last_fence);
> > -
> > - return &f->base;
> > }
> > diff --git a/drivers/gpu/drm/msm/msm_fence.h b/drivers/gpu/drm/msm/msm_fence.h
> > index 7f1798c54cd1..f913fa22d8fe 100644
> > --- a/drivers/gpu/drm/msm/msm_fence.h
> > +++ b/drivers/gpu/drm/msm/msm_fence.h
> > @@ -61,7 +61,8 @@ void msm_fence_context_free(struct msm_fence_context *fctx);
> > bool msm_fence_completed(struct msm_fence_context *fctx, uint32_t fence);
> > void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence);
> >
> > -struct dma_fence * msm_fence_alloc(struct msm_fence_context *fctx);
> > +struct dma_fence * msm_fence_alloc(void);
> > +void msm_fence_init(struct dma_fence *fence, struct msm_fence_context *fctx);
> >
> > static inline bool
> > fence_before(uint32_t a, uint32_t b)
> > diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
> > index be4bf77103cd..2570c018b0cb 100644
> > --- a/drivers/gpu/drm/msm/msm_gem_submit.c
> > +++ b/drivers/gpu/drm/msm/msm_gem_submit.c
> > @@ -41,6 +41,13 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
> > if (!submit)
> > return ERR_PTR(-ENOMEM);
> >
> > + submit->hw_fence = msm_fence_alloc();
> > + if (IS_ERR(submit->hw_fence)) {
> > + ret = PTR_ERR(submit->hw_fence);
> > + kfree(submit);
> > + return ERR_PTR(ret);
> > + }
> > +
> > ret = drm_sched_job_init(&submit->base, queue->entity, queue);
> > if (ret) {
> > kfree(submit);
>
> You probably need some error handling here or otherwise leak
> submit->hw_fence.
ah, right.. thx
BR,
-R
> Apart from that looks good to me.
>
> Christian.
>
> > diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
> > index 57a8e9564540..a62b45e5a8c3 100644
> > --- a/drivers/gpu/drm/msm/msm_ringbuffer.c
> > +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
> > @@ -18,7 +18,7 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
> > struct msm_gpu *gpu = submit->gpu;
> > int i;
> >
> > - submit->hw_fence = msm_fence_alloc(fctx);
> > + msm_fence_init(submit->hw_fence, fctx);
> >
> > for (i = 0; i < submit->nr_bos; i++) {
> > struct drm_gem_object *obj = &submit->bos[i].obj->base;
>
@@ -99,7 +99,7 @@ static const struct dma_fence_ops msm_fence_ops = {
};
struct dma_fence *
-msm_fence_alloc(struct msm_fence_context *fctx)
+msm_fence_alloc(void)
{
struct msm_fence *f;
@@ -107,10 +107,16 @@ msm_fence_alloc(struct msm_fence_context *fctx)
if (!f)
return ERR_PTR(-ENOMEM);
+ return &f->base;
+}
+
+void
+msm_fence_init(struct dma_fence *fence, struct msm_fence_context *fctx)
+{
+ struct msm_fence *f = to_msm_fence(fence);
+
f->fctx = fctx;
dma_fence_init(&f->base, &msm_fence_ops, &fctx->spinlock,
fctx->context, ++fctx->last_fence);
-
- return &f->base;
}
@@ -61,7 +61,8 @@ void msm_fence_context_free(struct msm_fence_context *fctx);
bool msm_fence_completed(struct msm_fence_context *fctx, uint32_t fence);
void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence);
-struct dma_fence * msm_fence_alloc(struct msm_fence_context *fctx);
+struct dma_fence * msm_fence_alloc(void);
+void msm_fence_init(struct dma_fence *fence, struct msm_fence_context *fctx);
static inline bool
fence_before(uint32_t a, uint32_t b)
@@ -41,6 +41,13 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
if (!submit)
return ERR_PTR(-ENOMEM);
+ submit->hw_fence = msm_fence_alloc();
+ if (IS_ERR(submit->hw_fence)) {
+ ret = PTR_ERR(submit->hw_fence);
+ kfree(submit);
+ return ERR_PTR(ret);
+ }
+
ret = drm_sched_job_init(&submit->base, queue->entity, queue);
if (ret) {
kfree(submit);
@@ -18,7 +18,7 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
struct msm_gpu *gpu = submit->gpu;
int i;
- submit->hw_fence = msm_fence_alloc(fctx);
+ msm_fence_init(submit->hw_fence, fctx);
for (i = 0; i < submit->nr_bos; i++) {
struct drm_gem_object *obj = &submit->bos[i].obj->base;