[PATCH 1/5] drm: add support of syncobj timeline point wait v4
Christian König
ckoenig.leichtzumerken at gmail.com
Fri Nov 2 08:35:08 UTC 2018
Am 02.11.18 um 09:25 schrieb Chunming Zhou:
> 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
>
> Signed-off-by: Chunming Zhou <david1.zhou at amd.com>
> Cc: Daniel Rakos <Daniel.Rakos at amd.com>
> Cc: Jason Ekstrand <jason at jlekstrand.net>
> Cc: Bas Nieuwenhuizen <bas at basnieuwenhuizen.nl>
> Cc: Dave Airlie <airlied at redhat.com>
> Cc: Christian König <christian.koenig at amd.com>
> Cc: Chris Wilson <chris at chris-wilson.co.uk>
> ---
> drivers/gpu/drm/drm_internal.h | 2 +
> drivers/gpu/drm/drm_ioctl.c | 2 +
> drivers/gpu/drm/drm_syncobj.c | 115 ++++++++++++++++++++++++++++-----
> include/uapi/drm/drm.h | 18 ++++++
> 4 files changed, 121 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
> index 0c4eb4a9ab31..566d44e3c782 100644
> --- a/drivers/gpu/drm/drm_internal.h
> +++ b/drivers/gpu/drm/drm_internal.h
> @@ -183,6 +183,8 @@ int drm_syncobj_fd_to_handle_ioctl(struct drm_device *dev, void *data,
> struct drm_file *file_private);
> int drm_syncobj_wait_ioctl(struct drm_device *dev, void *data,
> struct drm_file *file_private);
> +int drm_syncobj_timeline_wait_ioctl(struct drm_device *dev, void *data,
> + struct drm_file *file_private);
> int drm_syncobj_reset_ioctl(struct drm_device *dev, void *data,
> struct drm_file *file_private);
> int drm_syncobj_signal_ioctl(struct drm_device *dev, void *data,
> diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
> index 94bd872d56c4..a9a17ed35cc4 100644
> --- a/drivers/gpu/drm/drm_ioctl.c
> +++ b/drivers/gpu/drm/drm_ioctl.c
> @@ -675,6 +675,8 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
> DRM_UNLOCKED|DRM_RENDER_ALLOW),
> DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_WAIT, drm_syncobj_wait_ioctl,
> DRM_UNLOCKED|DRM_RENDER_ALLOW),
> + DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT, drm_syncobj_timeline_wait_ioctl,
> + DRM_UNLOCKED|DRM_RENDER_ALLOW),
> DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_RESET, drm_syncobj_reset_ioctl,
> DRM_UNLOCKED|DRM_RENDER_ALLOW),
> DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_SIGNAL, drm_syncobj_signal_ioctl,
> diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
> index 4dca5f7e8c4b..9dc54a345480 100644
> --- a/drivers/gpu/drm/drm_syncobj.c
> +++ b/drivers/gpu/drm/drm_syncobj.c
> @@ -153,11 +153,12 @@ static void drm_syncobj_add_callback_locked(struct drm_syncobj *syncobj,
> }
>
> static void drm_syncobj_fence_get_or_add_callback(struct drm_syncobj *syncobj,
> + uint64_t point,
> struct dma_fence **fence,
> struct drm_syncobj_cb *cb,
> drm_syncobj_func_t func)
> {
> - u64 pt_value = 0;
> + u64 pt_value = point;
>
> WARN_ON(*fence);
>
> @@ -854,6 +855,7 @@ struct syncobj_wait_entry {
> struct dma_fence *fence;
> struct dma_fence_cb fence_cb;
> struct drm_syncobj_cb syncobj_cb;
> + u64 point;
> };
>
> static void syncobj_wait_fence_func(struct dma_fence *fence,
> @@ -871,12 +873,13 @@ static void syncobj_wait_syncobj_func(struct drm_syncobj *syncobj,
> struct syncobj_wait_entry *wait =
> container_of(cb, struct syncobj_wait_entry, syncobj_cb);
>
> - drm_syncobj_search_fence(syncobj, 0, 0, &wait->fence);
> + drm_syncobj_search_fence(syncobj, wait->point, 0, &wait->fence);
>
> wake_up_process(wait->task);
> }
>
> 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,
> @@ -884,12 +887,37 @@ 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;
> + }
> +
> +
Double empty line here.
> + if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE) {
> + struct dma_fence *fence;
> + for (i = 0; i < count; ++i) {
> + timeout = drm_syncobj_search_fence(syncobjs[i], points[i],
> + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT,
> + &fence);
> + if (timeout)
> + goto err_free_points;
> + }
> + goto err_free_points;
A comment would be nice here to note that we only wait for the fences to
become available.
Alternatively it might be a good idea to make this an separate IOCTL.
Apart from those nit picks looks quite good to me,
Christian.
> + }
> + 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
> @@ -898,7 +926,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
> signaled_count = 0;
> for (i = 0; i < count; ++i) {
> entries[i].task = current;
> - drm_syncobj_search_fence(syncobjs[i], 0, 0,
> + entries[i].point = points[i];
> + drm_syncobj_search_fence(syncobjs[i], points[i], 0,
> &entries[i].fence);
> if (!entries[i].fence) {
> if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) {
> @@ -934,6 +963,7 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
> continue;
>
> drm_syncobj_fence_get_or_add_callback(syncobjs[i],
> + entries[i].point,
> &entries[i].fence,
> &entries[i].syncobj_cb,
> syncobj_wait_syncobj_func);
> @@ -996,6 +1026,9 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
> }
> kfree(entries);
>
> +err_free_points:
> + kfree(points);
> +
> return timeout;
> }
>
> @@ -1034,19 +1067,33 @@ static signed long drm_timeout_abs_to_jiffies(int64_t timeout_nsec)
> 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;
> }
>
> @@ -1132,13 +1179,49 @@ 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);
>
> return ret;
> }
>
> +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_COMPLETED |
> + 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)
> diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
> index cebdb2541eb7..c8bc1414753d 100644
> --- a/include/uapi/drm/drm.h
> +++ b/include/uapi/drm/drm.h
> @@ -738,6 +738,10 @@ struct drm_syncobj_handle {
>
> #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
> #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
> +/* wait for time point to be completed */
> +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_COMPLETED (1 << 2)
> +/* wait for time point to become available */
> +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 3)
> struct drm_syncobj_wait {
> __u64 handles;
> /* absolute timeout */
> @@ -748,6 +752,19 @@ struct drm_syncobj_wait {
> __u32 pad;
> };
>
> +struct drm_syncobj_timeline_wait {
> + __u64 handles;
> + /* wait on specific timeline point for every handles*/
> + __u64 points;
> + /* absolute timeout */
> + __s64 timeout_nsec;
> + __u32 count_handles;
> + __u32 flags;
> + __u32 first_signaled; /* only valid when not waiting all */
> + __u32 pad;
> +};
> +
> +
> struct drm_syncobj_array {
> __u64 handles;
> __u32 count_handles;
> @@ -910,6 +927,7 @@ extern "C" {
> #define DRM_IOCTL_MODE_GET_LEASE DRM_IOWR(0xC8, struct drm_mode_get_lease)
> #define DRM_IOCTL_MODE_REVOKE_LEASE DRM_IOWR(0xC9, struct drm_mode_revoke_lease)
>
> +#define DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT DRM_IOWR(0xCA, struct drm_syncobj_timeline_wait)
> /**
> * Device specific ioctls should only be in their respective headers
> * The device specific ioctl range is from 0x40 to 0x9f.
More information about the dri-devel
mailing list