On 2023-06-15 07:56, Christian König wrote:
> This reverts commit 8ee3a52e3f35e064a3bf82f21dc74ddaf9843648.
>
> The new amdgpu_ctx_mgr_entity_fini() was never called, so it was pure
> coincident that this patch didn't cause a crash. Since the workaround
> shouldn't be needed any more just mostly revert the changes to amdgpu.
>
> Signed-off-by: Christian König <christian.koenig@xxxxxxx>
Add a fixes-tag,
Fixes: 8ee3a52e3f35e0 ("drm/gpu-sched: fix force APP kill hang(v4)")
Acked-by: Luben Tuikov <luben.tuikov@xxxxxxx>
Regards,
Luben
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 59 ++-----------------------
> drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h | 1 -
> drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 2 +-
> 3 files changed, 5 insertions(+), 57 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
> index d2139ac12159..1445e030d788 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
> @@ -267,7 +267,7 @@ static ktime_t amdgpu_ctx_fini_entity(struct amdgpu_ctx_entity *entity)
> res = ktime_add(res, amdgpu_ctx_fence_time(entity->fences[i]));
> dma_fence_put(entity->fences[i]);
> }
> -
> + drm_sched_entity_destroy(&entity->entity);
> kfree(entity);
> return res;
> }
> @@ -476,24 +476,6 @@ static int amdgpu_ctx_alloc(struct amdgpu_device *adev,
> return r;
> }
>
> -static void amdgpu_ctx_do_release(struct kref *ref)
> -{
> - struct amdgpu_ctx *ctx;
> - u32 i, j;
> -
> - ctx = container_of(ref, struct amdgpu_ctx, refcount);
> - for (i = 0; i < AMDGPU_HW_IP_NUM; ++i) {
> - for (j = 0; j < amdgpu_ctx_num_entities[i]; ++j) {
> - if (!ctx->entities[i][j])
> - continue;
> -
> - drm_sched_entity_destroy(&ctx->entities[i][j]->entity);
> - }
> - }
> -
> - amdgpu_ctx_fini(ref);
> -}
> -
> static int amdgpu_ctx_free(struct amdgpu_fpriv *fpriv, uint32_t id)
> {
> struct amdgpu_ctx_mgr *mgr = &fpriv->ctx_mgr;
> @@ -502,7 +484,7 @@ static int amdgpu_ctx_free(struct amdgpu_fpriv *fpriv, uint32_t id)
> mutex_lock(&mgr->lock);
> ctx = idr_remove(&mgr->ctx_handles, id);
> if (ctx)
> - kref_put(&ctx->refcount, amdgpu_ctx_do_release);
> + kref_put(&ctx->refcount, amdgpu_ctx_fini);
> mutex_unlock(&mgr->lock);
> return ctx ? 0 : -EINVAL;
> }
> @@ -712,7 +694,7 @@ int amdgpu_ctx_put(struct amdgpu_ctx *ctx)
> if (ctx == NULL)
> return -EINVAL;
>
> - kref_put(&ctx->refcount, amdgpu_ctx_do_release);
> + kref_put(&ctx->refcount, amdgpu_ctx_fini);
> return 0;
> }
>
> @@ -881,45 +863,12 @@ long amdgpu_ctx_mgr_entity_flush(struct amdgpu_ctx_mgr *mgr, long timeout)
> return timeout;
> }
>
> -void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
> -{
> - struct amdgpu_ctx *ctx;
> - struct idr *idp;
> - uint32_t id, i, j;
> -
> - idp = &mgr->ctx_handles;
> -
> - idr_for_each_entry(idp, ctx, id) {
> - if (kref_read(&ctx->refcount) != 1) {
> - DRM_ERROR("ctx %p is still alive\n", ctx);
> - continue;
> - }
> -
> - for (i = 0; i < AMDGPU_HW_IP_NUM; ++i) {
> - for (j = 0; j < amdgpu_ctx_num_entities[i]; ++j) {
> - struct drm_sched_entity *entity;
> -
> - if (!ctx->entities[i][j])
> - continue;
> -
> - entity = &ctx->entities[i][j]->entity;
> - drm_sched_entity_fini(entity);
> - }
> - }
> - }
> -}
> -
> void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr)
> {
> struct amdgpu_ctx *ctx;
> - struct idr *idp;
> uint32_t id;
>
> - amdgpu_ctx_mgr_entity_fini(mgr);
> -
> - idp = &mgr->ctx_handles;
> -
> - idr_for_each_entry(idp, ctx, id) {
> + idr_for_each_entry(&mgr->ctx_handles, ctx, id) {
> if (kref_put(&ctx->refcount, amdgpu_ctx_fini) != 1)
> DRM_ERROR("ctx %p is still alive\n", ctx);
> }
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
> index 0fa0e56daf67..729cf479d71d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
> @@ -91,7 +91,6 @@ int amdgpu_ctx_wait_prev_fence(struct amdgpu_ctx *ctx,
>
> void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr,
> struct amdgpu_device *adev);
> -void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr);
> long amdgpu_ctx_mgr_entity_flush(struct amdgpu_ctx_mgr *mgr, long timeout);
> void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr);
> void amdgpu_ctx_mgr_usage(struct amdgpu_ctx_mgr *mgr,
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> index 0efb38539d70..50c36c95556d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> @@ -1278,6 +1278,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
> return;
>
> pm_runtime_get_sync(dev->dev);
> + amdgpu_ctx_mgr_fini(&fpriv->ctx_mgr);
>
> if (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_UVD) != NULL)
> amdgpu_uvd_free_handles(adev, file_priv);
> @@ -1299,7 +1300,6 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
> amdgpu_bo_unreserve(pd);
> }
>
> - amdgpu_ctx_mgr_fini(&fpriv->ctx_mgr);
> amdgpu_vm_fini(adev, &fpriv->vm);
>
> if (pasid)
