Linaro-mm-sig November 2021

linaro-mm-sig@lists.linaro.org

17 participants
48 discussions

Re: [Linaro-mm-sig] [Freedreno] [PATCH v4 07/13] drm/msm: Track "seqno" fences by idr

by Rob Clark

On Thu, Nov 11, 2021 at 7:54 AM Akhil P Oommen <akhilpo(a)codeaurora.org> wrote: > > On 11/10/2021 10:25 PM, Rob Clark wrote: > > On Wed, Nov 10, 2021 at 7:28 AM Akhil P Oommen <akhilpo(a)codeaurora.org> wrote: > >> > >> On 7/28/2021 6:36 AM, Rob Clark wrote: > >>> From: Rob Clark <robdclark(a)chromium.org> > >>> > >>> Previously the (non-fd) fence returned from submit ioctl was a raw > >>> seqno, which is scoped to the ring. But from UABI standpoint, the > >>> ioctls related to seqno fences all specify a submitqueue. We can > >>> take advantage of that to replace the seqno fences with a cyclic idr > >>> handle. > >>> > >>> This is in preperation for moving to drm scheduler, at which point > >>> the submit ioctl will return after queuing the submit job to the > >>> scheduler, but before the submit is written into the ring (and > >>> therefore before a ring seqno has been assigned). Which means we > >>> need to replace the dma_fence that userspace may need to wait on > >>> with a scheduler fence. > >>> > >>> Signed-off-by: Rob Clark <robdclark(a)chromium.org> > >>> Acked-by: Christian König <christian.koenig(a)amd.com> > >>> --- > >>> drivers/gpu/drm/msm/msm_drv.c | 30 +++++++++++++++++-- > >>> drivers/gpu/drm/msm/msm_fence.c | 42 --------------------------- > >>> drivers/gpu/drm/msm/msm_fence.h | 3 -- > >>> drivers/gpu/drm/msm/msm_gem.h | 1 + > >>> drivers/gpu/drm/msm/msm_gem_submit.c | 23 ++++++++++++++- > >>> drivers/gpu/drm/msm/msm_gpu.h | 5 ++++ > >>> drivers/gpu/drm/msm/msm_submitqueue.c | 5 ++++ > >>> 7 files changed, 61 insertions(+), 48 deletions(-) > >>> > >>> diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c > >>> index 9b8fa2ad0d84..1594ae39d54f 100644 > >>> --- a/drivers/gpu/drm/msm/msm_drv.c > >>> +++ b/drivers/gpu/drm/msm/msm_drv.c > >>> @@ -911,6 +911,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, > >>> ktime_t timeout = to_ktime(args->timeout); > >>> struct msm_gpu_submitqueue *queue; > >>> struct msm_gpu *gpu = priv->gpu; > >>> + struct dma_fence *fence; > >>> int ret; > >>> > >>> if (args->pad) { > >>> @@ -925,10 +926,35 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, > >>> if (!queue) > >>> return -ENOENT; > >>> > >>> - ret = msm_wait_fence(gpu->rb[queue->prio]->fctx, args->fence, &timeout, > >>> - true); > >>> + /* > >>> + * Map submitqueue scoped "seqno" (which is actually an idr key) > >>> + * back to underlying dma-fence > >>> + * > >>> + * The fence is removed from the fence_idr when the submit is > >>> + * retired, so if the fence is not found it means there is nothing > >>> + * to wait for > >>> + */ > >>> + ret = mutex_lock_interruptible(&queue->lock); > >>> + if (ret) > >>> + return ret; > >>> + fence = idr_find(&queue->fence_idr, args->fence); > >>> + if (fence) > >>> + fence = dma_fence_get_rcu(fence); > >>> + mutex_unlock(&queue->lock); > >>> + > >>> + if (!fence) > >>> + return 0; > >>> > >>> + ret = dma_fence_wait_timeout(fence, true, timeout_to_jiffies(&timeout)); > >>> + if (ret == 0) { > >>> + ret = -ETIMEDOUT; > >>> + } else if (ret != -ERESTARTSYS) { > >>> + ret = 0; > >>> + } > >>> + > >>> + dma_fence_put(fence); > >>> msm_submitqueue_put(queue); > >>> + > >>> return ret; > >>> } > >>> > >>> diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c > >>> index b92a9091a1e2..f2cece542c3f 100644 > >>> --- a/drivers/gpu/drm/msm/msm_fence.c > >>> +++ b/drivers/gpu/drm/msm/msm_fence.c > >>> @@ -24,7 +24,6 @@ msm_fence_context_alloc(struct drm_device *dev, volatile uint32_t *fenceptr, > >>> strncpy(fctx->name, name, sizeof(fctx->name)); > >>> fctx->context = dma_fence_context_alloc(1); > >>> fctx->fenceptr = fenceptr; > >>> - init_waitqueue_head(&fctx->event); > >>> spin_lock_init(&fctx->spinlock); > >>> > >>> return fctx; > >>> @@ -45,53 +44,12 @@ static inline bool fence_completed(struct msm_fence_context *fctx, uint32_t fenc > >>> (int32_t)(*fctx->fenceptr - fence) >= 0; > >>> } > >>> > >>> -/* legacy path for WAIT_FENCE ioctl: */ > >>> -int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence, > >>> - ktime_t *timeout, bool interruptible) > >>> -{ > >>> - int ret; > >>> - > >>> - if (fence > fctx->last_fence) { > >>> - DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n", > >>> - fctx->name, fence, fctx->last_fence); > >>> - return -EINVAL; > >> > >> Rob, we changed this pre-existing behaviour in this patch. Now, when > >> userspace tries to wait on a future fence, we don't return an error. > >> > >> I just want to check if this was accidental or not? > > > > Hmm, perhaps we should do this to restore the previous behavior: > > > > ------------- > > diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c > > index 73e827641024..3dd6da56eae6 100644 > > --- a/drivers/gpu/drm/msm/msm_drv.c > > +++ b/drivers/gpu/drm/msm/msm_drv.c > > @@ -1000,8 +1000,12 @@ static int msm_ioctl_wait_fence(struct > > drm_device *dev, void *data, > > fence = dma_fence_get_rcu(fence); > > mutex_unlock(&queue->lock); > > > > - if (!fence) > > - return 0; > > + if (!fence) { > > + struct msm_fence_context *fctx = gpu->rb[queue->ring_nr]->fctx; > > + DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: > > %u (of %u)\n", > > + fctx->name, fence, fctx->last_fence); > > + return -EINVAL; > > + } > > With this, when userspace tries to wait on a fence which is already > retired, it gets -EINVAL instead of success. Will this break userspace? Oh, right, we definitely don't want that.. I guess that was the reason for the original logic. I have a different idea.. will send a patch in a bit. BR, -R > -Akhil. > > > > > ret = dma_fence_wait_timeout(fence, true, timeout_to_jiffies(&timeout)); > > if (ret == 0) { > > ------------- > > > > BR, > > -R > > > >> -Akhil. > >> > >>> - } > >>> - > >>> - if (!timeout) { > >>> - /* no-wait: */ > >>> - ret = fence_completed(fctx, fence) ? 0 : -EBUSY; > >>> - } else { > >>> - unsigned long remaining_jiffies = timeout_to_jiffies(timeout); > >>> - > >>> - if (interruptible) > >>> - ret = wait_event_interruptible_timeout(fctx->event, > >>> - fence_completed(fctx, fence), > >>> - remaining_jiffies); > >>> - else > >>> - ret = wait_event_timeout(fctx->event, > >>> - fence_completed(fctx, fence), > >>> - remaining_jiffies); > >>> - > >>> - if (ret == 0) { > >>> - DBG("timeout waiting for fence: %u (completed: %u)", > >>> - fence, fctx->completed_fence); > >>> - ret = -ETIMEDOUT; > >>> - } else if (ret != -ERESTARTSYS) { > >>> - ret = 0; > >>> - } > >>> - } > >>> - > >>> - return ret; > >>> -} > >>> - > >>> /* called from workqueue */ > >>> void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence) > >>> { > >>> spin_lock(&fctx->spinlock); > >>> fctx->completed_fence = max(fence, fctx->completed_fence); > >>> spin_unlock(&fctx->spinlock); > >>> - > >>> - wake_up_all(&fctx->event); > >>> } > >>> > >>> struct msm_fence { > >>> diff --git a/drivers/gpu/drm/msm/msm_fence.h b/drivers/gpu/drm/msm/msm_fence.h > >>> index 6ab97062ff1a..4783db528bcc 100644 > >>> --- a/drivers/gpu/drm/msm/msm_fence.h > >>> +++ b/drivers/gpu/drm/msm/msm_fence.h > >>> @@ -49,7 +49,6 @@ struct msm_fence_context { > >>> */ > >>> volatile uint32_t *fenceptr; > >>> > >>> - wait_queue_head_t event; > >>> spinlock_t spinlock; > >>> }; > >>> > >>> @@ -57,8 +56,6 @@ struct msm_fence_context * msm_fence_context_alloc(struct drm_device *dev, > >>> volatile uint32_t *fenceptr, const char *name); > >>> void msm_fence_context_free(struct msm_fence_context *fctx); > >>> > >>> -int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence, > >>> - ktime_t *timeout, bool interruptible); > >>> void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence); > >>> > >>> struct dma_fence * msm_fence_alloc(struct msm_fence_context *fctx); > >>> diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h > >>> index da3af702a6c8..e0579abda5b9 100644 > >>> --- a/drivers/gpu/drm/msm/msm_gem.h > >>> +++ b/drivers/gpu/drm/msm/msm_gem.h > >>> @@ -320,6 +320,7 @@ struct msm_gem_submit { > >>> struct ww_acquire_ctx ticket; > >>> uint32_t seqno; /* Sequence number of the submit on the ring */ > >>> struct dma_fence *fence; > >>> + int fence_id; /* key into queue->fence_idr */ > >>> struct msm_gpu_submitqueue *queue; > >>> struct pid *pid; /* submitting process */ > >>> bool fault_dumped; /* Limit devcoredump dumping to one per submit */ > >>> diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c > >>> index 4f02fa3c78f9..f6f595aae2c5 100644 > >>> --- a/drivers/gpu/drm/msm/msm_gem_submit.c > >>> +++ b/drivers/gpu/drm/msm/msm_gem_submit.c > >>> @@ -68,7 +68,14 @@ void __msm_gem_submit_destroy(struct kref *kref) > >>> container_of(kref, struct msm_gem_submit, ref); > >>> unsigned i; > >>> > >>> + if (submit->fence_id) { > >>> + mutex_lock(&submit->queue->lock); > >>> + idr_remove(&submit->queue->fence_idr, submit->fence_id); > >>> + mutex_unlock(&submit->queue->lock); > >>> + } > >>> + > >>> dma_fence_put(submit->fence); > >>> + > >>> put_pid(submit->pid); > >>> msm_submitqueue_put(submit->queue); > >>> > >>> @@ -872,6 +879,20 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, > >>> goto out; > >>> } > >>> > >>> + /* > >>> + * Allocate an id which can be used by WAIT_FENCE ioctl to map back > >>> + * to the underlying fence. > >>> + */ > >>> + mutex_lock(&queue->lock); > >>> + submit->fence_id = idr_alloc_cyclic(&queue->fence_idr, > >>> + submit->fence, 0, INT_MAX, GFP_KERNEL); > >>> + mutex_unlock(&queue->lock); > >>> + if (submit->fence_id < 0) { > >>> + ret = submit->fence_id = 0; > >>> + submit->fence_id = 0; > >>> + goto out; > >>> + } > >>> + > >>> if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) { > >>> struct sync_file *sync_file = sync_file_create(submit->fence); > >>> if (!sync_file) { > >>> @@ -886,7 +907,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, > >>> > >>> msm_gpu_submit(gpu, submit); > >>> > >>> - args->fence = submit->fence->seqno; > >>> + args->fence = submit->fence_id; > >>> > >>> msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs); > >>> msm_process_post_deps(post_deps, args->nr_out_syncobjs, > >>> diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h > >>> index 96efcb31e502..579627252540 100644 > >>> --- a/drivers/gpu/drm/msm/msm_gpu.h > >>> +++ b/drivers/gpu/drm/msm/msm_gpu.h > >>> @@ -263,6 +263,9 @@ struct msm_gpu_perfcntr { > >>> * which set of pgtables do submits jobs associated with the > >>> * submitqueue use) > >>> * @node: node in the context's list of submitqueues > >>> + * @fence_idr: maps fence-id to dma_fence for userspace visible fence > >>> + * seqno, protected by submitqueue lock > >>> + * @lock: submitqueue lock > >>> * @ref: reference count > >>> */ > >>> struct msm_gpu_submitqueue { > >>> @@ -272,6 +275,8 @@ struct msm_gpu_submitqueue { > >>> int faults; > >>> struct msm_file_private *ctx; > >>> struct list_head node; > >>> + struct idr fence_idr; > >>> + struct mutex lock; > >>> struct kref ref; > >>> }; > >>> > >>> diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c > >>> index 9e9fec61d629..66f8d0fb38b0 100644 > >>> --- a/drivers/gpu/drm/msm/msm_submitqueue.c > >>> +++ b/drivers/gpu/drm/msm/msm_submitqueue.c > >>> @@ -12,6 +12,8 @@ void msm_submitqueue_destroy(struct kref *kref) > >>> struct msm_gpu_submitqueue *queue = container_of(kref, > >>> struct msm_gpu_submitqueue, ref); > >>> > >>> + idr_destroy(&queue->fence_idr); > >>> + > >>> msm_file_private_put(queue->ctx); > >>> > >>> kfree(queue); > >>> @@ -89,6 +91,9 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx, > >>> if (id) > >>> *id = queue->id; > >>> > >>> + idr_init(&queue->fence_idr); > >>> + mutex_init(&queue->lock); > >>> + > >>> list_add_tail(&queue->node, &ctx->submitqueues); > >>> > >>> write_unlock(&ctx->queuelock); > >>> > >> >

3 years, 1 month

Re: [Linaro-mm-sig] [PATCH v4 07/13] drm/msm: Track "seqno" fences by idr

by Rob Clark

On Wed, Nov 10, 2021 at 7:28 AM Akhil P Oommen <akhilpo(a)codeaurora.org> wrote: > > On 7/28/2021 6:36 AM, Rob Clark wrote: > > From: Rob Clark <robdclark(a)chromium.org> > > > > Previously the (non-fd) fence returned from submit ioctl was a raw > > seqno, which is scoped to the ring. But from UABI standpoint, the > > ioctls related to seqno fences all specify a submitqueue. We can > > take advantage of that to replace the seqno fences with a cyclic idr > > handle. > > > > This is in preperation for moving to drm scheduler, at which point > > the submit ioctl will return after queuing the submit job to the > > scheduler, but before the submit is written into the ring (and > > therefore before a ring seqno has been assigned). Which means we > > need to replace the dma_fence that userspace may need to wait on > > with a scheduler fence. > > > > Signed-off-by: Rob Clark <robdclark(a)chromium.org> > > Acked-by: Christian König <christian.koenig(a)amd.com> > > --- > > drivers/gpu/drm/msm/msm_drv.c | 30 +++++++++++++++++-- > > drivers/gpu/drm/msm/msm_fence.c | 42 --------------------------- > > drivers/gpu/drm/msm/msm_fence.h | 3 -- > > drivers/gpu/drm/msm/msm_gem.h | 1 + > > drivers/gpu/drm/msm/msm_gem_submit.c | 23 ++++++++++++++- > > drivers/gpu/drm/msm/msm_gpu.h | 5 ++++ > > drivers/gpu/drm/msm/msm_submitqueue.c | 5 ++++ > > 7 files changed, 61 insertions(+), 48 deletions(-) > > > > diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c > > index 9b8fa2ad0d84..1594ae39d54f 100644 > > --- a/drivers/gpu/drm/msm/msm_drv.c > > +++ b/drivers/gpu/drm/msm/msm_drv.c > > @@ -911,6 +911,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, > > ktime_t timeout = to_ktime(args->timeout); > > struct msm_gpu_submitqueue *queue; > > struct msm_gpu *gpu = priv->gpu; > > + struct dma_fence *fence; > > int ret; > > > > if (args->pad) { > > @@ -925,10 +926,35 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, > > if (!queue) > > return -ENOENT; > > > > - ret = msm_wait_fence(gpu->rb[queue->prio]->fctx, args->fence, &timeout, > > - true); > > + /* > > + * Map submitqueue scoped "seqno" (which is actually an idr key) > > + * back to underlying dma-fence > > + * > > + * The fence is removed from the fence_idr when the submit is > > + * retired, so if the fence is not found it means there is nothing > > + * to wait for > > + */ > > + ret = mutex_lock_interruptible(&queue->lock); > > + if (ret) > > + return ret; > > + fence = idr_find(&queue->fence_idr, args->fence); > > + if (fence) > > + fence = dma_fence_get_rcu(fence); > > + mutex_unlock(&queue->lock); > > + > > + if (!fence) > > + return 0; > > > > + ret = dma_fence_wait_timeout(fence, true, timeout_to_jiffies(&timeout)); > > + if (ret == 0) { > > + ret = -ETIMEDOUT; > > + } else if (ret != -ERESTARTSYS) { > > + ret = 0; > > + } > > + > > + dma_fence_put(fence); > > msm_submitqueue_put(queue); > > + > > return ret; > > } > > > > diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c > > index b92a9091a1e2..f2cece542c3f 100644 > > --- a/drivers/gpu/drm/msm/msm_fence.c > > +++ b/drivers/gpu/drm/msm/msm_fence.c > > @@ -24,7 +24,6 @@ msm_fence_context_alloc(struct drm_device *dev, volatile uint32_t *fenceptr, > > strncpy(fctx->name, name, sizeof(fctx->name)); > > fctx->context = dma_fence_context_alloc(1); > > fctx->fenceptr = fenceptr; > > - init_waitqueue_head(&fctx->event); > > spin_lock_init(&fctx->spinlock); > > > > return fctx; > > @@ -45,53 +44,12 @@ static inline bool fence_completed(struct msm_fence_context *fctx, uint32_t fenc > > (int32_t)(*fctx->fenceptr - fence) >= 0; > > } > > > > -/* legacy path for WAIT_FENCE ioctl: */ > > -int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence, > > - ktime_t *timeout, bool interruptible) > > -{ > > - int ret; > > - > > - if (fence > fctx->last_fence) { > > - DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n", > > - fctx->name, fence, fctx->last_fence); > > - return -EINVAL; > > Rob, we changed this pre-existing behaviour in this patch. Now, when > userspace tries to wait on a future fence, we don't return an error. > > I just want to check if this was accidental or not? Hmm, perhaps we should do this to restore the previous behavior: ------------- diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 73e827641024..3dd6da56eae6 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -1000,8 +1000,12 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, fence = dma_fence_get_rcu(fence); mutex_unlock(&queue->lock); - if (!fence) - return 0; + if (!fence) { + struct msm_fence_context *fctx = gpu->rb[queue->ring_nr]->fctx; + DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n", + fctx->name, fence, fctx->last_fence); + return -EINVAL; + } ret = dma_fence_wait_timeout(fence, true, timeout_to_jiffies(&timeout)); if (ret == 0) { ------------- BR, -R > -Akhil. > > > - } > > - > > - if (!timeout) { > > - /* no-wait: */ > > - ret = fence_completed(fctx, fence) ? 0 : -EBUSY; > > - } else { > > - unsigned long remaining_jiffies = timeout_to_jiffies(timeout); > > - > > - if (interruptible) > > - ret = wait_event_interruptible_timeout(fctx->event, > > - fence_completed(fctx, fence), > > - remaining_jiffies); > > - else > > - ret = wait_event_timeout(fctx->event, > > - fence_completed(fctx, fence), > > - remaining_jiffies); > > - > > - if (ret == 0) { > > - DBG("timeout waiting for fence: %u (completed: %u)", > > - fence, fctx->completed_fence); > > - ret = -ETIMEDOUT; > > - } else if (ret != -ERESTARTSYS) { > > - ret = 0; > > - } > > - } > > - > > - return ret; > > -} > > - > > /* called from workqueue */ > > void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence) > > { > > spin_lock(&fctx->spinlock); > > fctx->completed_fence = max(fence, fctx->completed_fence); > > spin_unlock(&fctx->spinlock); > > - > > - wake_up_all(&fctx->event); > > } > > > > struct msm_fence { > > diff --git a/drivers/gpu/drm/msm/msm_fence.h b/drivers/gpu/drm/msm/msm_fence.h > > index 6ab97062ff1a..4783db528bcc 100644 > > --- a/drivers/gpu/drm/msm/msm_fence.h > > +++ b/drivers/gpu/drm/msm/msm_fence.h > > @@ -49,7 +49,6 @@ struct msm_fence_context { > > */ > > volatile uint32_t *fenceptr; > > > > - wait_queue_head_t event; > > spinlock_t spinlock; > > }; > > > > @@ -57,8 +56,6 @@ struct msm_fence_context * msm_fence_context_alloc(struct drm_device *dev, > > volatile uint32_t *fenceptr, const char *name); > > void msm_fence_context_free(struct msm_fence_context *fctx); > > > > -int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence, > > - ktime_t *timeout, bool interruptible); > > void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence); > > > > struct dma_fence * msm_fence_alloc(struct msm_fence_context *fctx); > > diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h > > index da3af702a6c8..e0579abda5b9 100644 > > --- a/drivers/gpu/drm/msm/msm_gem.h > > +++ b/drivers/gpu/drm/msm/msm_gem.h > > @@ -320,6 +320,7 @@ struct msm_gem_submit { > > struct ww_acquire_ctx ticket; > > uint32_t seqno; /* Sequence number of the submit on the ring */ > > struct dma_fence *fence; > > + int fence_id; /* key into queue->fence_idr */ > > struct msm_gpu_submitqueue *queue; > > struct pid *pid; /* submitting process */ > > bool fault_dumped; /* Limit devcoredump dumping to one per submit */ > > diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c > > index 4f02fa3c78f9..f6f595aae2c5 100644 > > --- a/drivers/gpu/drm/msm/msm_gem_submit.c > > +++ b/drivers/gpu/drm/msm/msm_gem_submit.c > > @@ -68,7 +68,14 @@ void __msm_gem_submit_destroy(struct kref *kref) > > container_of(kref, struct msm_gem_submit, ref); > > unsigned i; > > > > + if (submit->fence_id) { > > + mutex_lock(&submit->queue->lock); > > + idr_remove(&submit->queue->fence_idr, submit->fence_id); > > + mutex_unlock(&submit->queue->lock); > > + } > > + > > dma_fence_put(submit->fence); > > + > > put_pid(submit->pid); > > msm_submitqueue_put(submit->queue); > > > > @@ -872,6 +879,20 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, > > goto out; > > } > > > > + /* > > + * Allocate an id which can be used by WAIT_FENCE ioctl to map back > > + * to the underlying fence. > > + */ > > + mutex_lock(&queue->lock); > > + submit->fence_id = idr_alloc_cyclic(&queue->fence_idr, > > + submit->fence, 0, INT_MAX, GFP_KERNEL); > > + mutex_unlock(&queue->lock); > > + if (submit->fence_id < 0) { > > + ret = submit->fence_id = 0; > > + submit->fence_id = 0; > > + goto out; > > + } > > + > > if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) { > > struct sync_file *sync_file = sync_file_create(submit->fence); > > if (!sync_file) { > > @@ -886,7 +907,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, > > > > msm_gpu_submit(gpu, submit); > > > > - args->fence = submit->fence->seqno; > > + args->fence = submit->fence_id; > > > > msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs); > > msm_process_post_deps(post_deps, args->nr_out_syncobjs, > > diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h > > index 96efcb31e502..579627252540 100644 > > --- a/drivers/gpu/drm/msm/msm_gpu.h > > +++ b/drivers/gpu/drm/msm/msm_gpu.h > > @@ -263,6 +263,9 @@ struct msm_gpu_perfcntr { > > * which set of pgtables do submits jobs associated with the > > * submitqueue use) > > * @node: node in the context's list of submitqueues > > + * @fence_idr: maps fence-id to dma_fence for userspace visible fence > > + * seqno, protected by submitqueue lock > > + * @lock: submitqueue lock > > * @ref: reference count > > */ > > struct msm_gpu_submitqueue { > > @@ -272,6 +275,8 @@ struct msm_gpu_submitqueue { > > int faults; > > struct msm_file_private *ctx; > > struct list_head node; > > + struct idr fence_idr; > > + struct mutex lock; > > struct kref ref; > > }; > > > > diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c > > index 9e9fec61d629..66f8d0fb38b0 100644 > > --- a/drivers/gpu/drm/msm/msm_submitqueue.c > > +++ b/drivers/gpu/drm/msm/msm_submitqueue.c > > @@ -12,6 +12,8 @@ void msm_submitqueue_destroy(struct kref *kref) > > struct msm_gpu_submitqueue *queue = container_of(kref, > > struct msm_gpu_submitqueue, ref); > > > > + idr_destroy(&queue->fence_idr); > > + > > msm_file_private_put(queue->ctx); > > > > kfree(queue); > > @@ -89,6 +91,9 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx, > > if (id) > > *id = queue->id; > > > > + idr_init(&queue->fence_idr); > > + mutex_init(&queue->lock); > > + > > list_add_tail(&queue->node, &ctx->submitqueues); > > > > write_unlock(&ctx->queuelock); > > >

3 years, 1 month

Re: [Linaro-mm-sig] AUTOSEL series truncated was -- Re: [PATCH AUTOSEL 5.15 001/146] dma-buf: WARN on dmabuf release with pending attachments

by Christian König

Hi Pavel, Am 09.11.21 um 08:54 schrieb Pavel Machek: > Hi! > > This series is truncated .. I only got first patches. Similary, 5.10 > series is truncated, [PATCH AUTOSEL 5.10 035/101] media: s5p-mfc: Add > checking to s5p_mfc_probe... is last one I got. > > I got all the patches before that, so I believe it is not problem on > my side, but I'd not mind someone confirming they are seeing the same > problem... It could of course be a different issue, but I've been experiencing similar problems since a couple of weeks now, especially with mailing lists hosted on the freedesktop.org servers and long series of mails. The symptons are that individual mails are missing from a series. I'm usually registered with two completely separated mail accounts (private and work) on those lists and if a mail is missing it is always missing on both accounts. The interesting thing is that if it is a patch set then patchwork (https://patchwork.freedesktop.org/) always seems to get all mails. No idea what's going on here and so far it was to rarely to complain, but with this series it is totally obvious that something is wrong. Regards, Christian. > > Best regards, > Pavel >

3 years, 1 month

[PATCH AUTOSEL 5.4 01/74] dma-buf: WARN on dmabuf release with pending attachments

by Sasha Levin

From: Charan Teja Reddy <charante(a)codeaurora.org> [ Upstream commit f492283b157053e9555787262f058ae33096f568 ] It is expected from the clients to follow the below steps on an imported dmabuf fd: a) dmabuf = dma_buf_get(fd) // Get the dmabuf from fd b) dma_buf_attach(dmabuf); // Clients attach to the dmabuf o Here the kernel does some slab allocations, say for dma_buf_attachment and may be some other slab allocation in the dmabuf->ops->attach(). c) Client may need to do dma_buf_map_attachment(). d) Accordingly dma_buf_unmap_attachment() should be called. e) dma_buf_detach () // Clients detach to the dmabuf. o Here the slab allocations made in b) are freed. f) dma_buf_put(dmabuf) // Can free the dmabuf if it is the last reference. Now say an erroneous client failed at step c) above thus it directly called dma_buf_put(), step f) above. Considering that it may be the last reference to the dmabuf, buffer will be freed with pending attachments left to the dmabuf which can show up as the 'memory leak'. This should at least be reported as the WARN(). Signed-off-by: Charan Teja Reddy <charante(a)codeaurora.org> Reviewed-by: Christian König <christian.koenig(a)amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/1627043468-16381-1-git-send-e… Signed-off-by: Christian König <christian.koenig(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/dma-buf/dma-buf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 758de0e9b2ddc..16bbc9bc9e6d1 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -79,6 +79,7 @@ static void dma_buf_release(struct dentry *dentry) if (dmabuf->resv == (struct dma_resv *)&dmabuf[1]) dma_resv_fini(dmabuf->resv); + WARN_ON(!list_empty(&dmabuf->attachments)); module_put(dmabuf->owner); kfree(dmabuf->name); kfree(dmabuf); -- 2.33.0

3 years, 1 month

[PATCH AUTOSEL 5.10 001/101] dma-buf: WARN on dmabuf release with pending attachments

by Sasha Levin

From: Charan Teja Reddy <charante(a)codeaurora.org> [ Upstream commit f492283b157053e9555787262f058ae33096f568 ] It is expected from the clients to follow the below steps on an imported dmabuf fd: a) dmabuf = dma_buf_get(fd) // Get the dmabuf from fd b) dma_buf_attach(dmabuf); // Clients attach to the dmabuf o Here the kernel does some slab allocations, say for dma_buf_attachment and may be some other slab allocation in the dmabuf->ops->attach(). c) Client may need to do dma_buf_map_attachment(). d) Accordingly dma_buf_unmap_attachment() should be called. e) dma_buf_detach () // Clients detach to the dmabuf. o Here the slab allocations made in b) are freed. f) dma_buf_put(dmabuf) // Can free the dmabuf if it is the last reference. Now say an erroneous client failed at step c) above thus it directly called dma_buf_put(), step f) above. Considering that it may be the last reference to the dmabuf, buffer will be freed with pending attachments left to the dmabuf which can show up as the 'memory leak'. This should at least be reported as the WARN(). Signed-off-by: Charan Teja Reddy <charante(a)codeaurora.org> Reviewed-by: Christian König <christian.koenig(a)amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/1627043468-16381-1-git-send-e… Signed-off-by: Christian König <christian.koenig(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/dma-buf/dma-buf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 922416b3aaceb..93e9bf7382595 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -79,6 +79,7 @@ static void dma_buf_release(struct dentry *dentry) if (dmabuf->resv == (struct dma_resv *)&dmabuf[1]) dma_resv_fini(dmabuf->resv); + WARN_ON(!list_empty(&dmabuf->attachments)); module_put(dmabuf->owner); kfree(dmabuf->name); kfree(dmabuf); -- 2.33.0

3 years, 1 month

[PATCH AUTOSEL 5.14 001/138] dma-buf: WARN on dmabuf release with pending attachments

by Sasha Levin

From: Charan Teja Reddy <charante(a)codeaurora.org> [ Upstream commit f492283b157053e9555787262f058ae33096f568 ] It is expected from the clients to follow the below steps on an imported dmabuf fd: a) dmabuf = dma_buf_get(fd) // Get the dmabuf from fd b) dma_buf_attach(dmabuf); // Clients attach to the dmabuf o Here the kernel does some slab allocations, say for dma_buf_attachment and may be some other slab allocation in the dmabuf->ops->attach(). c) Client may need to do dma_buf_map_attachment(). d) Accordingly dma_buf_unmap_attachment() should be called. e) dma_buf_detach () // Clients detach to the dmabuf. o Here the slab allocations made in b) are freed. f) dma_buf_put(dmabuf) // Can free the dmabuf if it is the last reference. Now say an erroneous client failed at step c) above thus it directly called dma_buf_put(), step f) above. Considering that it may be the last reference to the dmabuf, buffer will be freed with pending attachments left to the dmabuf which can show up as the 'memory leak'. This should at least be reported as the WARN(). Signed-off-by: Charan Teja Reddy <charante(a)codeaurora.org> Reviewed-by: Christian König <christian.koenig(a)amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/1627043468-16381-1-git-send-e… Signed-off-by: Christian König <christian.koenig(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/dma-buf/dma-buf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 511fe0d217a08..733c8b1c8467c 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -79,6 +79,7 @@ static void dma_buf_release(struct dentry *dentry) if (dmabuf->resv == (struct dma_resv *)&dmabuf[1]) dma_resv_fini(dmabuf->resv); + WARN_ON(!list_empty(&dmabuf->attachments)); module_put(dmabuf->owner); kfree(dmabuf->name); kfree(dmabuf); -- 2.33.0

3 years, 1 month

[PATCH AUTOSEL 5.15 001/146] dma-buf: WARN on dmabuf release with pending attachments

by Sasha Levin

From: Charan Teja Reddy <charante(a)codeaurora.org> [ Upstream commit f492283b157053e9555787262f058ae33096f568 ] It is expected from the clients to follow the below steps on an imported dmabuf fd: a) dmabuf = dma_buf_get(fd) // Get the dmabuf from fd b) dma_buf_attach(dmabuf); // Clients attach to the dmabuf o Here the kernel does some slab allocations, say for dma_buf_attachment and may be some other slab allocation in the dmabuf->ops->attach(). c) Client may need to do dma_buf_map_attachment(). d) Accordingly dma_buf_unmap_attachment() should be called. e) dma_buf_detach () // Clients detach to the dmabuf. o Here the slab allocations made in b) are freed. f) dma_buf_put(dmabuf) // Can free the dmabuf if it is the last reference. Now say an erroneous client failed at step c) above thus it directly called dma_buf_put(), step f) above. Considering that it may be the last reference to the dmabuf, buffer will be freed with pending attachments left to the dmabuf which can show up as the 'memory leak'. This should at least be reported as the WARN(). Signed-off-by: Charan Teja Reddy <charante(a)codeaurora.org> Reviewed-by: Christian König <christian.koenig(a)amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/1627043468-16381-1-git-send-e… Signed-off-by: Christian König <christian.koenig(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/dma-buf/dma-buf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 63d32261b63ff..474de2d988ca7 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -82,6 +82,7 @@ static void dma_buf_release(struct dentry *dentry) if (dmabuf->resv == (struct dma_resv *)&dmabuf[1]) dma_resv_fini(dmabuf->resv); + WARN_ON(!list_empty(&dmabuf->attachments)); module_put(dmabuf->owner); kfree(dmabuf->name); kfree(dmabuf); -- 2.33.0

3 years, 1 month

[PATCH] dma-buf/poll: Get a file reference for outstanding fence callbacks

by Michel Dänzer

From: Michel Dänzer <mdaenzer(a)redhat.com> This makes sure we don't hit the BUG_ON(dmabuf->cb_in.active || dmabuf->cb_out.active); in dma_buf_release, which could be triggered by user space closing the dma-buf file description while there are outstanding fence callbacks from dma_buf_poll. Cc: stable(a)vger.kernel.org Signed-off-by: Michel Dänzer <mdaenzer(a)redhat.com> --- drivers/dma-buf/dma-buf.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 6c520c9bd93c..ec25498a971f 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -65,12 +65,9 @@ static void dma_buf_release(struct dentry *dentry) BUG_ON(dmabuf->vmapping_counter); /* - * Any fences that a dma-buf poll can wait on should be signaled - * before releasing dma-buf. This is the responsibility of each - * driver that uses the reservation objects. - * - * If you hit this BUG() it means someone dropped their ref to the - * dma-buf while still having pending operation to the buffer. + * If you hit this BUG() it could mean: + * * There's a file reference imbalance in dma_buf_poll / dma_buf_poll_cb or somewhere else + * * dmabuf->cb_in/out.active are non-0 despite no pending fence callback */ BUG_ON(dmabuf->cb_in.active || dmabuf->cb_out.active); @@ -196,6 +193,7 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb) { struct dma_buf_poll_cb_t *dcb = (struct dma_buf_poll_cb_t *)cb; + struct dma_buf *dmabuf = container_of(dcb->poll, struct dma_buf, poll); unsigned long flags; spin_lock_irqsave(&dcb->poll->lock, flags); @@ -203,6 +201,8 @@ static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb) dcb->active = 0; spin_unlock_irqrestore(&dcb->poll->lock, flags); dma_fence_put(fence); + /* Paired with get_file in dma_buf_poll */ + fput(dmabuf->file); } static bool dma_buf_poll_shared(struct dma_resv *resv, @@ -278,6 +278,9 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) spin_unlock_irq(&dmabuf->poll.lock); if (events & EPOLLOUT) { + /* Paired with fput in dma_buf_poll_cb */ + get_file(dmabuf->file); + if (!dma_buf_poll_shared(resv, dcb) && !dma_buf_poll_excl(resv, dcb)) /* No callback queued, wake up any other waiters */ @@ -299,6 +302,9 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) spin_unlock_irq(&dmabuf->poll.lock); if (events & EPOLLIN) { + /* Paired with fput in dma_buf_poll_cb */ + get_file(dmabuf->file); + if (!dma_buf_poll_excl(resv, dcb)) /* No callback queued, wake up any other waiters */ dma_buf_poll_cb(NULL, &dcb->cb); -- 2.32.0

3 years, 1 month

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

Linaro-mm-sig November 2021