From: David Stevens stevensd@chromium.org
Allocate a new private stub fence in drm_syncobj_assign_null_handle, instead of using a static stub fence.
When userspace creates a fence with DRM_SYNCOBJ_CREATE_SIGNALED or when userspace signals a fence via DRM_IOCTL_SYNCOBJ_SIGNAL, the timestamp obtained when the fence is exported and queried with SYNC_IOC_FILE_INFO should match when the fence's status was changed from the perspective of userspace, which is during the respective ioctl.
When a static stub fence started being used in by these ioctls, this behavior changed. Instead, the timestamp returned by SYNC_IOC_FILE_INFO became the first time anything used the static stub fence, which has no meaning to userspace.
Signed-off-by: David Stevens stevensd@chromium.org --- drivers/dma-buf/dma-fence.c | 33 ++++++++++++++++++++++++++++++++- drivers/gpu/drm/drm_syncobj.c | 28 ++++++++++++++++++++-------- include/linux/dma-fence.h | 1 + 3 files changed, 53 insertions(+), 9 deletions(-)
diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index d64fc03929be..6081eb962490 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -26,6 +26,11 @@ EXPORT_TRACEPOINT_SYMBOL(dma_fence_signaled); static DEFINE_SPINLOCK(dma_fence_stub_lock); static struct dma_fence dma_fence_stub;
+struct drm_fence_private_stub { + struct dma_fence base; + spinlock_t lock; +}; + /* * fence context counter: each execution context should have its own * fence context, this allows checking if fences belong to the same @@ -123,7 +128,9 @@ static const struct dma_fence_ops dma_fence_stub_ops = { /** * dma_fence_get_stub - return a signaled fence * - * Return a stub fence which is already signaled. + * Return a stub fence which is already signaled. The fence's + * timestamp corresponds to the first time after boot this + * function is called. */ struct dma_fence *dma_fence_get_stub(void) { @@ -141,6 +148,30 @@ struct dma_fence *dma_fence_get_stub(void) } EXPORT_SYMBOL(dma_fence_get_stub);
+/** + * dma_fence_allocate_private_stub - return a private, signaled fence + * + * Return a newly allocated and signaled stub fence. + */ +struct dma_fence *dma_fence_allocate_private_stub(void) +{ + struct drm_fence_private_stub *fence; + + fence = kzalloc(sizeof(*fence), GFP_KERNEL); + if (fence == NULL) + return ERR_PTR(-ENOMEM); + + spin_lock_init(&fence->lock); + dma_fence_init(&fence->base, + &dma_fence_stub_ops, + &fence->lock, + 0, 0); + dma_fence_signal(&fence->base); + + return &fence->base; +} +EXPORT_SYMBOL(dma_fence_allocate_private_stub); + /** * dma_fence_context_alloc - allocate an array of fence contexts * @num: amount of contexts to allocate diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 349146049849..c6125e57ae37 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -350,12 +350,15 @@ EXPORT_SYMBOL(drm_syncobj_replace_fence); * * Assign a already signaled stub fence to the sync object. */ -static void drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj) +static int drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj) { - struct dma_fence *fence = dma_fence_get_stub(); + struct dma_fence *fence = dma_fence_allocate_private_stub(); + if (IS_ERR(fence)) + return PTR_ERR(fence);
- drm_syncobj_replace_fence(syncobj, fence); - dma_fence_put(fence); + drm_syncobj_replace_fence(syncobj, fence); + dma_fence_put(fence); + return 0; }
/* 5s default for wait submission */ @@ -469,6 +472,7 @@ EXPORT_SYMBOL(drm_syncobj_free); int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags, struct dma_fence *fence) { + int ret; struct drm_syncobj *syncobj;
syncobj = kzalloc(sizeof(struct drm_syncobj), GFP_KERNEL); @@ -479,8 +483,13 @@ int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags, INIT_LIST_HEAD(&syncobj->cb_list); spin_lock_init(&syncobj->lock);
- if (flags & DRM_SYNCOBJ_CREATE_SIGNALED) - drm_syncobj_assign_null_handle(syncobj); + if (flags & DRM_SYNCOBJ_CREATE_SIGNALED) { + ret = drm_syncobj_assign_null_handle(syncobj); + if (ret < 0) { + drm_syncobj_put(syncobj); + return ret; + } + }
if (fence) drm_syncobj_replace_fence(syncobj, fence); @@ -1322,8 +1331,11 @@ drm_syncobj_signal_ioctl(struct drm_device *dev, void *data, if (ret < 0) return ret;
- for (i = 0; i < args->count_handles; i++) - drm_syncobj_assign_null_handle(syncobjs[i]); + for (i = 0; i < args->count_handles; i++) { + ret = drm_syncobj_assign_null_handle(syncobjs[i]); + if (ret < 0) + break; + }
drm_syncobj_array_free(syncobjs, args->count_handles);
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 9f12efaaa93a..6ffb4b2c6371 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -587,6 +587,7 @@ static inline signed long dma_fence_wait(struct dma_fence *fence, bool intr) }
struct dma_fence *dma_fence_get_stub(void); +struct dma_fence *dma_fence_allocate_private_stub(void); u64 dma_fence_context_alloc(unsigned num);
#define DMA_FENCE_TRACE(f, fmt, args...) \
Sorry, I forgot to checkpatch this, I'll resend it momentarily.
-David
On Thu, Apr 8, 2021 at 6:34 PM David Stevens stevensd@chromium.org wrote:
Am 08.04.21 um 11:34 schrieb David Stevens:
You can drop this. The spinlock is only used when the fence is signaled to avoid races between signaling and adding a callback.
And for this the global spinlock should be perfectly sufficient. Apart from that looks good to me.
Regards, Christian.
On Thu, Apr 08, 2021 at 06:34:48PM +0900, David Stevens wrote:
Is there also an igt patch to enforce this in the drm_syncobj testcases? Would be really good to have that too. -Daniel
dri-devel@lists.freedesktop.org
-
Christian König -
Daniel Vetter -
David Stevens