From: Chunming Zhou <david1.zhou@amd.com>
To: Christian.Koenig@amd.com, dri-devel@lists.freedesktop.org,
amd-gfx@lists.freedesktop.org
Cc: "Daniel Rakos" <Daniel.Rakos@amd.com>,
"Jason Ekstrand" <jason@jlekstrand.net>,
"Dave Airlie" <airlied@redhat.com>,
"Christian König" <christian.koenig@amd.com>
Subject: [PATCH 05/11] drm/syncobj: add support for timeline point wait v8
Date: Fri, 7 Dec 2018 17:55:55 +0800 [thread overview]
Message-ID: <20181207095601.2058-5-david1.zhou@amd.com> (raw)
In-Reply-To: <20181207095601.2058-1-david1.zhou@amd.com>
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: Daniel Rakos <Daniel.Rakos@amd.com>
Cc: Jason Ekstrand <jason@jlekstrand.net>
Cc: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
---
drivers/gpu/drm/drm_internal.h | 2 +
drivers/gpu/drm/drm_ioctl.c | 2 +
drivers/gpu/drm/drm_syncobj.c | 153 ++++++++++++++++++++++++++-------
include/uapi/drm/drm.h | 15 ++++
4 files changed, 143 insertions(+), 29 deletions(-)
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index c7a7d7ce5d1c..18b41e10195c 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -178,6 +178,8 @@ 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 51f798e2194f..348079bb0965 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);
}
@@ -148,10 +155,8 @@ 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 */
@@ -182,10 +187,8 @@ 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);
@@ -642,13 +645,27 @@ 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,
@@ -656,12 +673,27 @@ 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
@@ -669,9 +701,13 @@ 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 {
@@ -680,7 +716,13 @@ 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++;
@@ -713,7 +755,8 @@ 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,
@@ -758,6 +801,9 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
}
kfree(entries);
+err_free_points:
+ kfree(points);
+
return timeout;
}
@@ -796,19 +842,33 @@ 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;
}
@@ -894,13 +954,48 @@ 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_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 300f336633f2..0092111d002c 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -737,6 +737,7 @@ struct drm_syncobj_handle {
#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2)
struct drm_syncobj_wait {
__u64 handles;
/* absolute timeout */
@@ -747,6 +748,19 @@ 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;
@@ -909,6 +923,7 @@ 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.
--
2.17.1
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2018-12-07 9:55 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-07 9:55 [PATCH 01/11] dma-buf: make fence sequence numbers 64 bit v2 Chunming Zhou
2018-12-07 9:55 ` [PATCH 02/11] dma-buf: add new dma_fence_chain container v4 Chunming Zhou
2019-02-15 14:23 ` Lionel Landwerlin via dri-devel
[not found] ` <6c2adaf5-6871-20be-a26d-182f8ca8ab8a-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
2019-02-15 14:32 ` Koenig, Christian
[not found] ` <e170ceed-fdb7-8b4a-93d7-e565641390b3-5C7GfCeVMHo@public.gmane.org>
2019-02-15 15:52 ` Lionel Landwerlin via amd-gfx
[not found] ` <bbae2023-8dee-692e-9549-40779a202587-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
2019-02-15 16:39 ` Christian König via amd-gfx
2019-02-15 16:49 ` Jason Ekstrand
[not found] ` <CAOFGe96HUkzHPJKYT-07X3vMvCRD-=Hba1=Ke24qt_PY2vn0YQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2019-02-15 17:51 ` Christian König via amd-gfx
[not found] ` <a0b27d87-50f2-56ce-1db7-5a1dc005a798-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2019-02-15 18:16 ` Jason Ekstrand
[not found] ` <CAOFGe9611MqmsvdvZS4_vuJjrrUAmjK5-41Z6tpaxTHJsB8CwA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2019-02-15 18:33 ` Koenig, Christian
[not found] ` <f933f9ec-6e69-f9df-f12f-5f1844a2ad37-5C7GfCeVMHo@public.gmane.org>
2019-02-15 19:11 ` Jason Ekstrand
2018-12-07 9:55 ` [PATCH 03/11] drm/syncobj: remove drm_syncobj_cb and cleanup Chunming Zhou
2018-12-07 9:55 ` Chunming Zhou [this message]
2018-12-07 9:55 ` [PATCH 08/11] drm/amdgpu: add timeline support in amdgpu CS v2 Chunming Zhou
2018-12-07 9:56 ` [PATCH 10/11] drm/syncobj: add timeline signal ioctl for syncobj Chunming Zhou
[not found] ` <20181207095601.2058-10-david1.zhou-5C7GfCeVMHo@public.gmane.org>
2018-12-07 11:31 ` Christian König
2018-12-07 13:09 ` Chunming Zhou
[not found] ` <8c34aaf0-13b3-4070-f4ef-076fe1ab3197-5C7GfCeVMHo@public.gmane.org>
2018-12-07 13:14 ` Koenig, Christian
[not found] ` <20181207095601.2058-1-david1.zhou-5C7GfCeVMHo@public.gmane.org>
2018-12-07 9:55 ` [PATCH 04/11] drm/syncobj: add new drm_syncobj_add_point interface v2 Chunming Zhou
2018-12-07 9:55 ` [PATCH 06/11] drm/syncobj: add timeline payload query ioctl v4 Chunming Zhou
[not found] ` <20181207095601.2058-6-david1.zhou-5C7GfCeVMHo@public.gmane.org>
2019-02-15 19:31 ` Lionel Landwerlin via amd-gfx
[not found] ` <157f8231-57e2-0492-de5d-f9ba4761c4c9-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
2019-02-16 19:22 ` Christian König via amd-gfx
[not found] ` <a24728a8-5b80-e746-a1f2-6555cd817e99-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2019-02-18 3:10 ` zhoucm1
[not found] ` <eae060f6-6493-ef71-ed9d-52d7dd768b03-5C7GfCeVMHo@public.gmane.org>
2019-02-18 7:28 ` Koenig, Christian
[not found] ` <4becddef-3bb3-5a66-34d4-95cced896939-5C7GfCeVMHo@public.gmane.org>
2019-02-18 11:40 ` Lionel Landwerlin
2018-12-07 9:55 ` [PATCH 07/11] drm/syncobj: use the timeline point in drm_syncobj_find_fence v3 Chunming Zhou
2018-12-07 9:55 ` [PATCH 09/11] drm/syncobj: add transition iotcls between binary and timeline Chunming Zhou
2018-12-07 11:28 ` Koenig, Christian
[not found] ` <20181207095601.2058-9-david1.zhou-5C7GfCeVMHo@public.gmane.org>
2019-02-15 14:28 ` Lionel Landwerlin via amd-gfx
2019-02-18 10:35 ` zhoucm1
2019-02-18 11:01 ` Koenig, Christian
[not found] ` <27a38e11-0c77-4340-aac9-b02e816c6f58-2ueSQiBKiTY7tOexoI0I+QC/G2K4zDHf@public.gmane.org>
2019-02-18 12:07 ` Lionel Landwerlin
[not found] ` <83890a08-769a-b52a-f2f6-9fe425f2562c-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
2019-02-18 17:01 ` Koenig, Christian
[not found] ` <64c548d0-b062-f937-30a5-5a4d3f296f91-5C7GfCeVMHo@public.gmane.org>
2019-02-19 10:46 ` zhoucm1
[not found] ` <c2c12849-d26b-3212-40ca-682d6f8006fa-5C7GfCeVMHo@public.gmane.org>
2019-02-19 11:29 ` Lionel Landwerlin
2019-02-19 11:32 ` Koenig, Christian
2019-02-20 4:53 ` zhoucm1
2019-02-20 7:59 ` Koenig, Christian
[not found] ` <976d7032-1cde-0427-ce56-38c2ac8881ec-5C7GfCeVMHo@public.gmane.org>
2019-02-20 8:10 ` zhoucm1
[not found] ` <730eaa42-d852-e9d8-7756-43fb256a466f-5C7GfCeVMHo@public.gmane.org>
2019-02-20 8:24 ` Koenig, Christian
2018-12-07 9:56 ` [PATCH 11/11] drm/amdgpu: update version for timeline syncobj support in amdgpu Chunming Zhou
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20181207095601.2058-5-david1.zhou@amd.com \
--to=david1.zhou@amd.com \
--cc=Christian.Koenig@amd.com \
--cc=Daniel.Rakos@amd.com \
--cc=airlied@redhat.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=jason@jlekstrand.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox