diff options
author | Chunming Zhou <david1.zhou@amd.com> | 2019-04-01 12:50:57 +0300 |
---|---|---|
committer | Christian König <christian.koenig@amd.com> | 2019-04-01 13:06:11 +0300 |
commit | 01d6c357837918d8186b9f520e167d98e3d560cc (patch) | |
tree | 1d691c84d55e6f25060ab6c40788c312197bded3 /drivers/gpu/drm/drm_syncobj.c | |
parent | 44f8a1396e83f1030eaf18591b3f106235118a64 (diff) | |
download | linux-01d6c357837918d8186b9f520e167d98e3d560cc.tar.xz |
drm/syncobj: add support for timeline point wait v8
points array is one-to-one match with syncobjs array.
v2:
add seperate ioctl for timeline point wait, otherwise break uapi.
v3:
userspace can specify two kinds waits::
a. Wait for time point to be completed.
b. and wait for time point to become available
v4:
rebase
v5:
add comment for xxx_WAIT_AVAILABLE
v6: rebase and rework on new container
v7: drop _WAIT_COMPLETED, it is the default anyway
v8: correctly handle garbage collected fences
Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Cc: Tobias Hector <Tobias.Hector@amd.com>
Cc: Jason Ekstrand <jason@jlekstrand.net>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/295782/?series=58813&rev=1
Diffstat (limited to 'drivers/gpu/drm/drm_syncobj.c')
-rw-r--r-- | drivers/gpu/drm/drm_syncobj.c | 153 |
1 files changed, 124 insertions, 29 deletions
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index dbe4a1c75fbc..b1262e92011c 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -61,6 +61,7 @@ struct syncobj_wait_entry { struct task_struct *task; struct dma_fence *fence; struct dma_fence_cb fence_cb; + u64 point; }; static void syncobj_wait_syncobj_func(struct drm_syncobj *syncobj, @@ -95,6 +96,8 @@ EXPORT_SYMBOL(drm_syncobj_find); static void drm_syncobj_fence_add_wait(struct drm_syncobj *syncobj, struct syncobj_wait_entry *wait) { + struct dma_fence *fence; + if (wait->fence) return; @@ -103,11 +106,15 @@ static void drm_syncobj_fence_add_wait(struct drm_syncobj *syncobj, * have the lock, try one more time just to be sure we don't add a * callback when a fence has already been set. */ - if (syncobj->fence) - wait->fence = dma_fence_get( - rcu_dereference_protected(syncobj->fence, 1)); - else + fence = dma_fence_get(rcu_dereference_protected(syncobj->fence, 1)); + if (!fence || dma_fence_chain_find_seqno(&fence, wait->point)) { + dma_fence_put(fence); list_add_tail(&wait->node, &syncobj->cb_list); + } else if (!fence) { + wait->fence = dma_fence_get_stub(); + } else { + wait->fence = fence; + } spin_unlock(&syncobj->lock); } @@ -150,10 +157,8 @@ void drm_syncobj_add_point(struct drm_syncobj *syncobj, dma_fence_chain_init(chain, prev, fence, point); rcu_assign_pointer(syncobj->fence, &chain->base); - list_for_each_entry_safe(cur, tmp, &syncobj->cb_list, node) { - list_del_init(&cur->node); + list_for_each_entry_safe(cur, tmp, &syncobj->cb_list, node) syncobj_wait_syncobj_func(syncobj, cur); - } spin_unlock(&syncobj->lock); /* Walk the chain once to trigger garbage collection */ @@ -185,10 +190,8 @@ void drm_syncobj_replace_fence(struct drm_syncobj *syncobj, rcu_assign_pointer(syncobj->fence, fence); if (fence != old_fence) { - list_for_each_entry_safe(cur, tmp, &syncobj->cb_list, node) { - list_del_init(&cur->node); + list_for_each_entry_safe(cur, tmp, &syncobj->cb_list, node) syncobj_wait_syncobj_func(syncobj, cur); - } } spin_unlock(&syncobj->lock); @@ -645,13 +648,27 @@ static void syncobj_wait_fence_func(struct dma_fence *fence, static void syncobj_wait_syncobj_func(struct drm_syncobj *syncobj, struct syncobj_wait_entry *wait) { + struct dma_fence *fence; + /* This happens inside the syncobj lock */ - wait->fence = dma_fence_get(rcu_dereference_protected(syncobj->fence, - lockdep_is_held(&syncobj->lock))); + fence = rcu_dereference_protected(syncobj->fence, + lockdep_is_held(&syncobj->lock)); + dma_fence_get(fence); + if (!fence || dma_fence_chain_find_seqno(&fence, wait->point)) { + dma_fence_put(fence); + return; + } else if (!fence) { + wait->fence = dma_fence_get_stub(); + } else { + wait->fence = fence; + } + wake_up_process(wait->task); + list_del_init(&wait->node); } static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, + void __user *user_points, uint32_t count, uint32_t flags, signed long timeout, @@ -659,12 +676,27 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, { struct syncobj_wait_entry *entries; struct dma_fence *fence; + uint64_t *points; uint32_t signaled_count, i; - entries = kcalloc(count, sizeof(*entries), GFP_KERNEL); - if (!entries) + points = kmalloc_array(count, sizeof(*points), GFP_KERNEL); + if (points == NULL) return -ENOMEM; + if (!user_points) { + memset(points, 0, count * sizeof(uint64_t)); + + } else if (copy_from_user(points, user_points, + sizeof(uint64_t) * count)) { + timeout = -EFAULT; + goto err_free_points; + } + + entries = kcalloc(count, sizeof(*entries), GFP_KERNEL); + if (!entries) { + timeout = -ENOMEM; + goto err_free_points; + } /* Walk the list of sync objects and initialize entries. We do * this up-front so that we can properly return -EINVAL if there is * a syncobj with a missing fence and then never have the chance of @@ -672,9 +704,13 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, */ signaled_count = 0; for (i = 0; i < count; ++i) { + struct dma_fence *fence; + entries[i].task = current; - entries[i].fence = drm_syncobj_fence_get(syncobjs[i]); - if (!entries[i].fence) { + entries[i].point = points[i]; + fence = drm_syncobj_fence_get(syncobjs[i]); + if (!fence || dma_fence_chain_find_seqno(&fence, points[i])) { + dma_fence_put(fence); if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { continue; } else { @@ -683,7 +719,13 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, } } - if (dma_fence_is_signaled(entries[i].fence)) { + if (fence) + entries[i].fence = fence; + else + entries[i].fence = dma_fence_get_stub(); + + if ((flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE) || + dma_fence_is_signaled(entries[i].fence)) { if (signaled_count == 0 && idx) *idx = i; signaled_count++; @@ -716,7 +758,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, if (!fence) continue; - if (dma_fence_is_signaled(fence) || + if ((flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE) || + dma_fence_is_signaled(fence) || (!entries[i].fence_cb.func && dma_fence_add_callback(fence, &entries[i].fence_cb, @@ -761,6 +804,9 @@ cleanup_entries: } kfree(entries); +err_free_points: + kfree(points); + return timeout; } @@ -800,19 +846,33 @@ EXPORT_SYMBOL(drm_timeout_abs_to_jiffies); static int drm_syncobj_array_wait(struct drm_device *dev, struct drm_file *file_private, struct drm_syncobj_wait *wait, - struct drm_syncobj **syncobjs) + struct drm_syncobj_timeline_wait *timeline_wait, + struct drm_syncobj **syncobjs, bool timeline) { - signed long timeout = drm_timeout_abs_to_jiffies(wait->timeout_nsec); + signed long timeout = 0; uint32_t first = ~0; - timeout = drm_syncobj_array_wait_timeout(syncobjs, - wait->count_handles, - wait->flags, - timeout, &first); - if (timeout < 0) - return timeout; - - wait->first_signaled = first; + if (!timeline) { + timeout = drm_timeout_abs_to_jiffies(wait->timeout_nsec); + timeout = drm_syncobj_array_wait_timeout(syncobjs, + NULL, + wait->count_handles, + wait->flags, + timeout, &first); + if (timeout < 0) + return timeout; + wait->first_signaled = first; + } else { + timeout = drm_timeout_abs_to_jiffies(timeline_wait->timeout_nsec); + timeout = drm_syncobj_array_wait_timeout(syncobjs, + u64_to_user_ptr(timeline_wait->points), + timeline_wait->count_handles, + timeline_wait->flags, + timeout, &first); + if (timeout < 0) + return timeout; + timeline_wait->first_signaled = first; + } return 0; } @@ -898,7 +958,7 @@ drm_syncobj_wait_ioctl(struct drm_device *dev, void *data, return ret; ret = drm_syncobj_array_wait(dev, file_private, - args, syncobjs); + args, NULL, syncobjs, false); drm_syncobj_array_free(syncobjs, args->count_handles); @@ -906,6 +966,41 @@ drm_syncobj_wait_ioctl(struct drm_device *dev, void *data, } int +drm_syncobj_timeline_wait_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private) +{ + struct drm_syncobj_timeline_wait *args = data; + struct drm_syncobj **syncobjs; + int ret = 0; + + if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ)) + return -ENODEV; + + if (args->flags & ~(DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL | + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) + return -EINVAL; + + if (args->count_handles == 0) + return -EINVAL; + + ret = drm_syncobj_array_find(file_private, + u64_to_user_ptr(args->handles), + args->count_handles, + &syncobjs); + if (ret < 0) + return ret; + + ret = drm_syncobj_array_wait(dev, file_private, + NULL, args, syncobjs, true); + + drm_syncobj_array_free(syncobjs, args->count_handles); + + return ret; +} + + +int drm_syncobj_reset_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) { |