search for: sync_obj

...new_mem); @@ -1151,8 +1152,9 @@ nouveau_bo_vm_cleanup(struct ttm_buffer_object *bo, { struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct drm_device *dev = drm->dev; + struct fence *fence = reservation_object_get_excl(bo->resv); - nv10_bo_put_tile_region(dev, *old_tile, bo->sync_obj); + nv10_bo_put_tile_region(dev, *old_tile, fence); *old_tile = new_tile; } @@ -1423,47 +1425,14 @@ nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm) ttm_pool_unpopulate(ttm); } -static void -nouveau_bo_fence_unref(void **sync_obj) -{ - nouveau_fence_unref((struct nouveau_fence **)sync_obj);...

...new_mem); @@ -1151,8 +1152,9 @@ nouveau_bo_vm_cleanup(struct ttm_buffer_object *bo, { struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct drm_device *dev = drm->dev; + struct fence *fence = reservation_object_get_excl(bo->resv); - nv10_bo_put_tile_region(dev, *old_tile, bo->sync_obj); + nv10_bo_put_tile_region(dev, *old_tile, fence); *old_tile = new_tile; } @@ -1423,47 +1425,14 @@ nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm) ttm_pool_unpopulate(ttm); } -static void -nouveau_bo_fence_unref(void **sync_obj) -{ - nouveau_fence_unref((struct nouveau_fence **)sync_obj);...

...rue, intr, no_wait_gpu); - spin_unlock(&bo->bdev->fence_lock); if (ret == 0) ret = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem); @@ -1425,26 +1423,19 @@ nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm) ttm_pool_unpopulate(ttm); } +static void +nouveau_bo_fence_unref(void **sync_obj) +{ + nouveau_fence_unref((struct nouveau_fence **)sync_obj); +} + void nouveau_bo_fence(struct nouveau_bo *nvbo, struct nouveau_fence *fence) { - struct nouveau_fence *new_fence = nouveau_fence_ref(fence); - struct nouveau_fence *old_fence = NULL; - lockdep_assert_held(&nvbo->bo.resv-&...

This series depends on the previously posted reservation api patches. 2 of them are not yet in for-next-fences branch of git://git.linaro.org/people/sumit.semwal/linux-3.x.git The missing patches are still in my vmwgfx_wip branch at git://people.freedesktop.org/~mlankhorst/linux All ttm drivers are converted to the fence api, fence_lock is removed and rcu is used in its place. qxl is the first

fence_is_signaled callback should support being run in atomic context, but not in irq context. Signed-off-by: Maarten Lankhorst <maarten.lankhorst at canonical.com> --- include/linux/fence.h | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/include/linux/fence.h b/include/linux/fence.h index d174585b874b..c1a4519ba2f5 100644 ---

This series applies on top of the driver-core-next branch of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git Before converting ttm to the new fence interface I had to fix some drivers to require a reservation before poking with fence_obj. After flipping the switch RCU becomes available instead, and the extra reservations can be dropped again. :-) I've done at least basic

...ed_at; void (*work)(void *priv, bool signalled); void *priv; @@ -172,6 +173,7 @@ nouveau_fence_emit(struct nouveau_fence *fence) } OUT_RING (chan, fence->sequence); FIRE_RING(chan); + fence->emitted_at = jiffies; return 0; } @@ -230,7 +232,8 @@ __nouveau_fence_signalled(void *sync_obj, void *sync_arg) int __nouveau_fence_wait(void *sync_obj, void *sync_arg, bool lazy, bool intr) { - unsigned long timeout = jiffies + (3 * DRM_HZ); + struct nouveau_fence *fence = nouveau_fence(sync_obj); + unsigned long timeout = fence->emitted_at + 3 * DRM_HZ; unsigned long sleep_time = N...

...+ rcu_read_lock(); + fobj = rcu_dereference(bo->tbo.resv->fence); + rel = fobj ? fobj->shared_count : 0; + rcu_read_unlock(); + seq_printf(m, "size %ld, pc %d, sync obj %p, num releases %d\n", (unsigned long)bo->gem_base.size, bo->pin_count, - bo->tbo.sync_obj, bo->fence.num_active_releases); + bo->tbo.sync_obj, rel); } + spin_unlock(&qdev->release_lock); return 0; } diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index 36ed40ba773f..d547cbdebeb4 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/...

...u_bo.c index db0ed4c..8afc17e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -35,6 +35,70 @@ #include <linux/log2.h> +int +nouveau_bo_wait(struct ttm_buffer_object *bo, struct nouveau_channel *chan) +{ + int ret = 0; + + if (likely(!bo->sync_obj)) + return 0; + + spin_lock(&bo->lock); + if (chan) { + struct nouveau_fence *new_fence; + struct nouveau_channel *waited_chan; + + do { + struct nouveau_fence *prev_fence; + prev_fence = bo->sync_obj; + + waited_chan = nouveau_fence_channel(prev_fence); + if (likely(!waited_c...

...drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 4ab9f7171c4f..d7d34336f108 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -502,17 +502,6 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo, if (ret) return ret; - /* - * remove sync_obj with ttm_bo_wait, the wait should be - * finished, and no new wait object should have been added. - */ - spin_lock(&bdev->fence_lock); - ret = ttm_bo_wait(bo, false, false, true); - WARN_ON(ret); - spin_unlock(&bdev->fence_lock); - if (ret) - return ret; - spin_lock(&amp...

...ged, 26 insertions(+), 52 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c index 4a36bb1dc525..f15718cc631d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c @@ -792,15 +792,12 @@ static int vmw_sync_obj_flush(void *sync_obj) static bool vmw_sync_obj_signaled(void *sync_obj) { - return vmw_fence_obj_signaled((struct vmw_fence_obj *) sync_obj, - DRM_VMW_FENCE_FLAG_EXEC); - + return vmw_fence_obj_signaled((struct vmw_fence_obj *) sync_obj); } static int vmw_sync_obj_wait(void *sync_...

...u_bo.c index 028719f..2da6acf 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -35,6 +35,70 @@ #include <linux/log2.h> +int +nouveau_bo_wait(struct ttm_buffer_object *bo, struct nouveau_channel *chan) +{ + int ret = 0; + + if (likely(!bo->sync_obj)) + return 0; + + spin_lock(&bo->lock); + if (chan) { + struct nouveau_fence *new_fence; + struct nouveau_channel *waited_chan; + + do { + struct nouveau_fence *prev_fence; + prev_fence = bo->sync_obj; + + waited_chan = nouveau_fence_channel(prev_fence); + if (likely(!waited_c...

...ence->entry, &chan->fence.pending); - spin_unlock_irqrestore(&chan->fence.lock, flags); + spin_unlock(&chan->fence.lock); BEGIN_RING(chan, NvSubSw, USE_REFCNT ? 0x0050 : 0x0150, 1); OUT_RING(chan, fence->sequence); @@ -173,14 +172,11 @@ nouveau_fence_signalled(void *sync_obj, void *sync_arg) { struct nouveau_fence *fence = nouveau_fence(sync_obj); struct nouveau_channel *chan = fence->channel; - unsigned long flags; if (fence->signalled) return true; - spin_lock_irqsave(&chan->fence.lock, flags); nouveau_fence_update(chan); - spin_unlock_ir...

...0 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -959,7 +959,7 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr, } mutex_lock_nested(&chan->cli->mutex, SINGLE_DEPTH_NESTING); - ret = nouveau_fence_sync(bo->sync_obj, chan); + ret = nouveau_fence_sync(nouveau_bo(bo), chan); if (ret == 0) { ret = drm->ttm.move(chan, bo, &bo->mem, new_mem); if (ret == 0) { @@ -1432,10 +1432,12 @@ nouveau_bo_fence_unref(void **sync_obj) void nouveau_bo_fence(struct nouveau_bo *nvbo, struct nouveau_fence *fence)...

...(struct nouveau_bo *nvbo, struct nouveau_fence *fence) struct nouveau_fence *new_fence = nouveau_fence_ref(fence); struct nouveau_fence *old_fence = NULL; + lockdep_assert_held(&nvbo->bo.resv->lock.base); + spin_lock(&nvbo->bo.bdev->fence_lock); old_fence = nvbo->bo.sync_obj; nvbo->bo.sync_obj = new_fence; diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index da764a4ed958..61b8c3375135 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -716,6 +716,9 @@ nouveau...

http://bugs.freedesktop.org/show_bug.cgi?id=25806 Summary: NV40 vertex corruption (kernel BO deletion too early?) Product: Mesa Version: git Platform: Other OS/Version: All Status: NEW Severity: normal Priority: medium Component: Drivers/DRI/nouveau AssignedTo: nouveau at lists.freedesktop.org

...nlock(&glob->lru_lock); - ttm_eu_list_ref_sub(list); -err_fini: - if (ticket) { - ww_acquire_done(ticket); - ww_acquire_fini(ticket); - } - return ret; } EXPORT_SYMBOL(ttm_eu_reserve_buffers); @@ -229,7 +188,6 @@ void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket, bo->sync_obj = driver->sync_obj_ref(sync_obj); ttm_bo_add_to_lru(bo); __ttm_bo_unreserve(bo); - entry->reserved = false; } spin_unlock(&bdev->fence_lock); spin_unlock(&glob->lru_lock); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c...

...evice *dev, unsigned offset) diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 59f92e9..8c973ab 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -233,17 +233,22 @@ int __nouveau_fence_wait(void *sync_obj, void *sync_arg, bool lazy, bool intr) { struct nouveau_fence *fence = nouveau_fence(sync_obj); + struct drm_device *dev = fence->channel->dev; unsigned long timeout = fence->emitted_at + 3 * DRM_HZ; unsigned long sleep_time = NSEC_PER_MSEC / 1000; ktime_t t; int ret = 0; + if...

...t seems that the current model is wrong, and the current fence should only be used to determine whether the pushbuffer itself can be reused. It seems that, after figuring out where the GPU writes the value and how to use the mechanism properly, this should be used by the kernel driver as the bo->sync_obj implementation. This will delay destruction of the buffers, and thus prevent reallocation of them, and artifacts, without synchronizing rendering. I'm not sure why this hasn't been noticed before though. Is everyone getting randomly misrendered OpenGL or is my machine somehow more prone to...

...mp;nvbo->bo.bdev->fence_lock); + ret = ttm_bo_reserve(&nvbo->bo, true, false, false, 0); + if (!ret) { + spin_lock(&nvbo->bo.bdev->fence_lock); + ret = ttm_bo_wait(&nvbo->bo, true, true, true); + if (!no_wait && ret) + fence = nouveau_fence_ref(nvbo->bo.sync_obj); + spin_unlock(&nvbo->bo.bdev->fence_lock); + + ttm_bo_unreserve(&nvbo->bo); + } drm_gem_object_unreference_unlocked(gem); + + if (fence) { + ret = nouveau_fence_wait(fence, true, no_wait); + nouveau_fence_unref(&fence); + } + return ret; }