As commented in drm_atomic_helper_wait_for_vblanks(), userspace relies on cursor ioctls being unsynced. Converting the rockchip driver to atomic has significantly impacted cursor performance by making every cursor update wait for vblank.
By skipping the vblank sync when the framebuffer has not changed (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid this for the common case of moving the cursor and only need to delay the cursor ioctl when the cursor icon changes.
I originally inserted a check on legacy_cursor_update as well, but that caused a storm of iommu page faults. I didn't investigate the cause of those since this change gives enough of a performance improvement for my use case.
This is RFC because of that and because the framebuffer_changed() function is copied from drm_atomic_helper.c as a quick way to test the result.
Signed-off-by: John Keeping john@metanate.com --- drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f784488..8fd9821 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -177,8 +177,28 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); }
+static bool framebuffer_changed(struct drm_device *dev, + struct drm_atomic_state *old_state, + struct drm_crtc *crtc) +{ + struct drm_plane *plane; + struct drm_plane_state *old_plane_state; + int i; + + for_each_plane_in_state(old_state, plane, old_plane_state, i) { + if (plane->state->crtc != crtc && + old_plane_state->crtc != crtc) + continue; + + if (plane->state->fb != old_plane_state->fb) + return true; + } + + return false; +} + static void -rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) +rockchip_atomic_wait_for_complete(struct drm_device *dev, struct drm_atomic_state *old_state) { struct drm_crtc_state *old_crtc_state; struct drm_crtc *crtc; @@ -194,6 +214,9 @@ rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) if (!crtc->state->active) continue;
+ if (!framebuffer_changed(dev, old_state, crtc)) + continue; + ret = drm_crtc_vblank_get(crtc); if (ret != 0) continue; @@ -241,7 +264,7 @@ rockchip_atomic_commit_complete(struct rockchip_atomic_commit *commit)
drm_atomic_helper_commit_planes(dev, state, true);
- rockchip_atomic_wait_for_complete(state); + rockchip_atomic_wait_for_complete(dev, state);
drm_atomic_helper_cleanup_planes(dev, state);
On Wed, Jan 13, 2016 at 12:53:34PM +0000, John Keeping wrote:
As commented in drm_atomic_helper_wait_for_vblanks(), userspace relies on cursor ioctls being unsynced. Converting the rockchip driver to atomic has significantly impacted cursor performance by making every cursor update wait for vblank.
By skipping the vblank sync when the framebuffer has not changed (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid this for the common case of moving the cursor and only need to delay the cursor ioctl when the cursor icon changes.
I originally inserted a check on legacy_cursor_update as well, but that caused a storm of iommu page faults. I didn't investigate the cause of those since this change gives enough of a performance improvement for my use case.
This is RFC because of that and because the framebuffer_changed() function is copied from drm_atomic_helper.c as a quick way to test the result.
Signed-off-by: John Keeping john@metanate.com
drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f784488..8fd9821 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -177,8 +177,28 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); }
+static bool framebuffer_changed(struct drm_device *dev,
struct drm_atomic_state *old_state,struct drm_crtc *crtc)+{
- struct drm_plane *plane;
- struct drm_plane_state *old_plane_state;
- int i;
- for_each_plane_in_state(old_state, plane, old_plane_state, i) {
if (plane->state->crtc != crtc &&old_plane_state->crtc != crtc)continue;if (plane->state->fb != old_plane_state->fb)return true;- }
- return false;
+}
Please don't hand-roll logic that affects semantics like this. Instead please use drm_atomic_helper_wait_for_vblanks(), which should do this correctly for you.
If that's not the case then we need to improve the generic helper, or figure out what's different with rockhip.
Thanks, Daniel
static void -rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) +rockchip_atomic_wait_for_complete(struct drm_device *dev, struct drm_atomic_state *old_state) { struct drm_crtc_state *old_crtc_state; struct drm_crtc *crtc; @@ -194,6 +214,9 @@ rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) if (!crtc->state->active) continue;
if (!framebuffer_changed(dev, old_state, crtc))continue;- ret = drm_crtc_vblank_get(crtc); if (ret != 0) continue;
@@ -241,7 +264,7 @@ rockchip_atomic_commit_complete(struct rockchip_atomic_commit *commit)
drm_atomic_helper_commit_planes(dev, state, true);
- rockchip_atomic_wait_for_complete(state);
rockchip_atomic_wait_for_complete(dev, state);
drm_atomic_helper_cleanup_planes(dev, state);
-- 2.7.0.rc3.140.g520a093
dri-devel mailing list dri-devel@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/dri-devel
On Wed, 13 Jan 2016 15:23:20 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 12:53:34PM +0000, John Keeping wrote:
As commented in drm_atomic_helper_wait_for_vblanks(), userspace relies on cursor ioctls being unsynced. Converting the rockchip driver to atomic has significantly impacted cursor performance by making every cursor update wait for vblank.
By skipping the vblank sync when the framebuffer has not changed (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid this for the common case of moving the cursor and only need to delay the cursor ioctl when the cursor icon changes.
I originally inserted a check on legacy_cursor_update as well, but that caused a storm of iommu page faults. I didn't investigate the cause of those since this change gives enough of a performance improvement for my use case.
This is RFC because of that and because the framebuffer_changed() function is copied from drm_atomic_helper.c as a quick way to test the result.
Signed-off-by: John Keeping john@metanate.com
drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f784488..8fd9821 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -177,8 +177,28 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); }
+static bool framebuffer_changed(struct drm_device *dev,
struct drm_atomic_state *old_state,struct drm_crtc *crtc)+{
- struct drm_plane *plane;
- struct drm_plane_state *old_plane_state;
- int i;
- for_each_plane_in_state(old_state, plane, old_plane_state,
i) {
if (plane->state->crtc != crtc &&old_plane_state->crtc != crtc)continue;if (plane->state->fb != old_plane_state->fb)return true;- }
- return false;
+}
Please don't hand-roll logic that affects semantics like this. Instead please use drm_atomic_helper_wait_for_vblanks(), which should do this correctly for you.
If that's not the case then we need to improve the generic helper, or figure out what's different with rockhip.
According to commit 63ebb9f (drm/rockchip: Convert to support atomic API) it's because rockchip doesn't have a hardware vblank counter.
I'm not entirely clear on why this prevents the use of drm_atomic_helper_wait_for_vblanks().
static void -rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) +rockchip_atomic_wait_for_complete(struct drm_device *dev, struct drm_atomic_state *old_state) { struct drm_crtc_state *old_crtc_state; struct drm_crtc *crtc; @@ -194,6 +214,9 @@ rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) if (!crtc->state->active) continue;
if (!framebuffer_changed(dev, old_state, crtc))continue;- ret = drm_crtc_vblank_get(crtc); if (ret != 0) continue;
@@ -241,7 +264,7 @@ rockchip_atomic_commit_complete(struct rockchip_atomic_commit *commit) drm_atomic_helper_commit_planes(dev, state, true);
- rockchip_atomic_wait_for_complete(state);
rockchip_atomic_wait_for_complete(dev, state);
drm_atomic_helper_cleanup_planes(dev, state);
-- 2.7.0.rc3.140.g520a093
dri-devel mailing list dri-devel@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/dri-devel
On Wed, Jan 13, 2016 at 02:34:25PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 15:23:20 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 12:53:34PM +0000, John Keeping wrote:
As commented in drm_atomic_helper_wait_for_vblanks(), userspace relies on cursor ioctls being unsynced. Converting the rockchip driver to atomic has significantly impacted cursor performance by making every cursor update wait for vblank.
By skipping the vblank sync when the framebuffer has not changed (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid this for the common case of moving the cursor and only need to delay the cursor ioctl when the cursor icon changes.
I originally inserted a check on legacy_cursor_update as well, but that caused a storm of iommu page faults. I didn't investigate the cause of those since this change gives enough of a performance improvement for my use case.
This is RFC because of that and because the framebuffer_changed() function is copied from drm_atomic_helper.c as a quick way to test the result.
Signed-off-by: John Keeping john@metanate.com
drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f784488..8fd9821 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -177,8 +177,28 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); }
+static bool framebuffer_changed(struct drm_device *dev,
struct drm_atomic_state *old_state,struct drm_crtc *crtc)+{
- struct drm_plane *plane;
- struct drm_plane_state *old_plane_state;
- int i;
- for_each_plane_in_state(old_state, plane, old_plane_state,
i) {
if (plane->state->crtc != crtc &&old_plane_state->crtc != crtc)continue;if (plane->state->fb != old_plane_state->fb)return true;- }
- return false;
+}
Please don't hand-roll logic that affects semantics like this. Instead please use drm_atomic_helper_wait_for_vblanks(), which should do this correctly for you.
If that's not the case then we need to improve the generic helper, or figure out what's different with rockhip.
According to commit 63ebb9f (drm/rockchip: Convert to support atomic API) it's because rockchip doesn't have a hardware vblank counter.
I'm not entirely clear on why this prevents the use of drm_atomic_helper_wait_for_vblanks().
Hm, that commit isn't terribly helpful. If that's really needed then imo I think we should extract a "drm_atomic_helper_plane_needs_vblank_wait()" helper that's used by both. But since rockchip does vblank_get/put calls I'd hope vblanks actually work correctly. And then the helper should work too. -Daniel
On Wed, 13 Jan 2016 16:40:05 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 02:34:25PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 15:23:20 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 12:53:34PM +0000, John Keeping wrote:
As commented in drm_atomic_helper_wait_for_vblanks(), userspace relies on cursor ioctls being unsynced. Converting the rockchip driver to atomic has significantly impacted cursor performance by making every cursor update wait for vblank.
By skipping the vblank sync when the framebuffer has not changed (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid this for the common case of moving the cursor and only need to delay the cursor ioctl when the cursor icon changes.
I originally inserted a check on legacy_cursor_update as well, but that caused a storm of iommu page faults. I didn't investigate the cause of those since this change gives enough of a performance improvement for my use case.
This is RFC because of that and because the framebuffer_changed() function is copied from drm_atomic_helper.c as a quick way to test the result.
Signed-off-by: John Keeping john@metanate.com
drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f784488..8fd9821 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -177,8 +177,28 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); }
+static bool framebuffer_changed(struct drm_device *dev,
struct drm_atomic_state *old_state,struct drm_crtc *crtc)+{
- struct drm_plane *plane;
- struct drm_plane_state *old_plane_state;
- int i;
- for_each_plane_in_state(old_state, plane, old_plane_state,
i) {
if (plane->state->crtc != crtc &&old_plane_state->crtc != crtc)continue;if (plane->state->fb != old_plane_state->fb)return true;- }
- return false;
+}
Please don't hand-roll logic that affects semantics like this. Instead please use drm_atomic_helper_wait_for_vblanks(), which should do this correctly for you.
If that's not the case then we need to improve the generic helper, or figure out what's different with rockhip.
According to commit 63ebb9f (drm/rockchip: Convert to support atomic API) it's because rockchip doesn't have a hardware vblank counter.
I'm not entirely clear on why this prevents the use of drm_atomic_helper_wait_for_vblanks().
Hm, that commit isn't terribly helpful. If that's really needed then imo I think we should extract a "drm_atomic_helper_plane_needs_vblank_wait()" helper that's used by both. But since rockchip does vblank_get/put calls I'd hope vblanks actually work correctly. And then the helper should work too.
I tried switching the call to rockchip_crtc_wait_for_update() to drm_atomic_helper_wait_for_vblanks() and it works fine until I switch the buffer associated with a cursor, at which point I get iommu page faults, presumably because the GEM buffer is unreferenced too early.
AFAICT the buffer will be released via drm_atomic_state_free() unconditionally, but I suspect I'm missing something since that would mean every driver would hit a similar problem.
On Wed, Jan 13, 2016 at 03:55:29PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 16:40:05 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 02:34:25PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 15:23:20 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 12:53:34PM +0000, John Keeping wrote:
As commented in drm_atomic_helper_wait_for_vblanks(), userspace relies on cursor ioctls being unsynced. Converting the rockchip driver to atomic has significantly impacted cursor performance by making every cursor update wait for vblank.
By skipping the vblank sync when the framebuffer has not changed (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid this for the common case of moving the cursor and only need to delay the cursor ioctl when the cursor icon changes.
I originally inserted a check on legacy_cursor_update as well, but that caused a storm of iommu page faults. I didn't investigate the cause of those since this change gives enough of a performance improvement for my use case.
This is RFC because of that and because the framebuffer_changed() function is copied from drm_atomic_helper.c as a quick way to test the result.
Signed-off-by: John Keeping john@metanate.com
drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f784488..8fd9821 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -177,8 +177,28 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); }
+static bool framebuffer_changed(struct drm_device *dev,
struct drm_atomic_state *old_state,struct drm_crtc *crtc)+{
- struct drm_plane *plane;
- struct drm_plane_state *old_plane_state;
- int i;
- for_each_plane_in_state(old_state, plane, old_plane_state,
i) {
if (plane->state->crtc != crtc &&old_plane_state->crtc != crtc)continue;if (plane->state->fb != old_plane_state->fb)return true;- }
- return false;
+}
Please don't hand-roll logic that affects semantics like this. Instead please use drm_atomic_helper_wait_for_vblanks(), which should do this correctly for you.
If that's not the case then we need to improve the generic helper, or figure out what's different with rockhip.
According to commit 63ebb9f (drm/rockchip: Convert to support atomic API) it's because rockchip doesn't have a hardware vblank counter.
I'm not entirely clear on why this prevents the use of drm_atomic_helper_wait_for_vblanks().
Hm, that commit isn't terribly helpful. If that's really needed then imo I think we should extract a "drm_atomic_helper_plane_needs_vblank_wait()" helper that's used by both. But since rockchip does vblank_get/put calls I'd hope vblanks actually work correctly. And then the helper should work too.
I tried switching the call to rockchip_crtc_wait_for_update() to drm_atomic_helper_wait_for_vblanks() and it works fine until I switch the buffer associated with a cursor, at which point I get iommu page faults, presumably because the GEM buffer is unreferenced too early.
AFAICT the buffer will be released via drm_atomic_state_free() unconditionally, but I suspect I'm missing something since that would mean every driver would hit a similar problem.
Yeah, with the helper we always skip, which means when the cursor bo changes you indeed unmap too early. So can't even share the overall condition, but we could definitely share the little framebuffer_changed helper. Plus rockchip_crtc_wait_for_update should have a big comment explaining why we have different rules than core helpers!
Cheers, Daniel
On Wed, 13 Jan 2016 17:21:56 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 03:55:29PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 16:40:05 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 02:34:25PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 15:23:20 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 12:53:34PM +0000, John Keeping wrote:
As commented in drm_atomic_helper_wait_for_vblanks(), userspace relies on cursor ioctls being unsynced. Converting the rockchip driver to atomic has significantly impacted cursor performance by making every cursor update wait for vblank.
By skipping the vblank sync when the framebuffer has not changed (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid this for the common case of moving the cursor and only need to delay the cursor ioctl when the cursor icon changes.
I originally inserted a check on legacy_cursor_update as well, but that caused a storm of iommu page faults. I didn't investigate the cause of those since this change gives enough of a performance improvement for my use case.
This is RFC because of that and because the framebuffer_changed() function is copied from drm_atomic_helper.c as a quick way to test the result.
Signed-off-by: John Keeping john@metanate.com
drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f784488..8fd9821 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -177,8 +177,28 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); }
+static bool framebuffer_changed(struct drm_device *dev,
struct drm_atomic_state *old_state,struct drm_crtc *crtc)+{
- struct drm_plane *plane;
- struct drm_plane_state *old_plane_state;
- int i;
- for_each_plane_in_state(old_state, plane, old_plane_state,
i) {
if (plane->state->crtc != crtc &&old_plane_state->crtc != crtc)continue;if (plane->state->fb != old_plane_state->fb)return true;- }
- return false;
+}
Please don't hand-roll logic that affects semantics like this. Instead please use drm_atomic_helper_wait_for_vblanks(), which should do this correctly for you.
If that's not the case then we need to improve the generic helper, or figure out what's different with rockhip.
According to commit 63ebb9f (drm/rockchip: Convert to support atomic API) it's because rockchip doesn't have a hardware vblank counter.
I'm not entirely clear on why this prevents the use of drm_atomic_helper_wait_for_vblanks().
Hm, that commit isn't terribly helpful. If that's really needed then imo I think we should extract a "drm_atomic_helper_plane_needs_vblank_wait()" helper that's used by both. But since rockchip does vblank_get/put calls I'd hope vblanks actually work correctly. And then the helper should work too.
I tried switching the call to rockchip_crtc_wait_for_update() to drm_atomic_helper_wait_for_vblanks() and it works fine until I switch the buffer associated with a cursor, at which point I get iommu page faults, presumably because the GEM buffer is unreferenced too early.
AFAICT the buffer will be released via drm_atomic_state_free() unconditionally, but I suspect I'm missing something since that would mean every driver would hit a similar problem.
Yeah, with the helper we always skip, which means when the cursor bo changes you indeed unmap too early. So can't even share the overall condition, but we could definitely share the little framebuffer_changed helper.
That leaves me with the question: why do other atomic drivers work?
If drm_atomic_helper_wait_for_vblanks() skipping vblanks results in the cursor bo being unmapped too early for rockchip, why is it not unmapped too early for all of the other drivers using that helper?
On Wed, Jan 13, 2016 at 04:40:38PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 17:21:56 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 03:55:29PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 16:40:05 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 02:34:25PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 15:23:20 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 12:53:34PM +0000, John Keeping wrote: > As commented in drm_atomic_helper_wait_for_vblanks(), userspace > relies on cursor ioctls being unsynced. Converting the rockchip > driver to atomic has significantly impacted cursor performance by > making every cursor update wait for vblank. > > By skipping the vblank sync when the framebuffer has not changed > (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid > this for the common case of moving the cursor and only need to > delay the cursor ioctl when the cursor icon changes. > > I originally inserted a check on legacy_cursor_update as well, but > that caused a storm of iommu page faults. I didn't investigate the > cause of those since this change gives enough of a performance > improvement for my use case. > > This is RFC because of that and because the framebuffer_changed() > function is copied from drm_atomic_helper.c as a quick way to test > the result. > > Signed-off-by: John Keeping john@metanate.com > --- > drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 27 > +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 > deletions(-) > > diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c > b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f784488..8fd9821 > 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c > +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c > @@ -177,8 +177,28 @@ static void > rockchip_crtc_wait_for_update(struct drm_crtc *crtc) > crtc_funcs->wait_for_update(crtc); } > > +static bool framebuffer_changed(struct drm_device *dev, > + struct drm_atomic_state *old_state, > + struct drm_crtc *crtc) > +{ > + struct drm_plane *plane; > + struct drm_plane_state *old_plane_state; > + int i; > + > + for_each_plane_in_state(old_state, plane, old_plane_state, > i) { > + if (plane->state->crtc != crtc && > + old_plane_state->crtc != crtc) > + continue; > + > + if (plane->state->fb != old_plane_state->fb) > + return true; > + } > + > + return false; > +}
Please don't hand-roll logic that affects semantics like this. Instead please use drm_atomic_helper_wait_for_vblanks(), which should do this correctly for you.
If that's not the case then we need to improve the generic helper, or figure out what's different with rockhip.
According to commit 63ebb9f (drm/rockchip: Convert to support atomic API) it's because rockchip doesn't have a hardware vblank counter.
I'm not entirely clear on why this prevents the use of drm_atomic_helper_wait_for_vblanks().
Hm, that commit isn't terribly helpful. If that's really needed then imo I think we should extract a "drm_atomic_helper_plane_needs_vblank_wait()" helper that's used by both. But since rockchip does vblank_get/put calls I'd hope vblanks actually work correctly. And then the helper should work too.
I tried switching the call to rockchip_crtc_wait_for_update() to drm_atomic_helper_wait_for_vblanks() and it works fine until I switch the buffer associated with a cursor, at which point I get iommu page faults, presumably because the GEM buffer is unreferenced too early.
AFAICT the buffer will be released via drm_atomic_state_free() unconditionally, but I suspect I'm missing something since that would mean every driver would hit a similar problem.
Yeah, with the helper we always skip, which means when the cursor bo changes you indeed unmap too early. So can't even share the overall condition, but we could definitely share the little framebuffer_changed helper.
That leaves me with the question: why do other atomic drivers work?
If drm_atomic_helper_wait_for_vblanks() skipping vblanks results in the cursor bo being unmapped too early for rockchip, why is it not unmapped too early for all of the other drivers using that helper?
It's unmapped too early for everyone, it's just that normally that doesn't result in a fireworks show. What we maybe could/should do is do the unmapping asynchronously, but that runs into the overall "current atomic helpers don't do async yet" problem. Might be a good point to start fixing this up though. -Daniel
On Wed, 13 Jan 2016 18:19:17 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 04:40:38PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 17:21:56 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 03:55:29PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 16:40:05 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 02:34:25PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 15:23:20 +0100, Daniel Vetter wrote:
> On Wed, Jan 13, 2016 at 12:53:34PM +0000, John Keeping wrote: > > As commented in drm_atomic_helper_wait_for_vblanks(), userspace > > relies on cursor ioctls being unsynced. Converting the rockchip > > driver to atomic has significantly impacted cursor performance by > > making every cursor update wait for vblank. > > > > By skipping the vblank sync when the framebuffer has not changed > > (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid > > this for the common case of moving the cursor and only need to > > delay the cursor ioctl when the cursor icon changes. > > > > I originally inserted a check on legacy_cursor_update as well, but > > that caused a storm of iommu page faults. I didn't investigate the > > cause of those since this change gives enough of a performance > > improvement for my use case. > > > > This is RFC because of that and because the framebuffer_changed() > > function is copied from drm_atomic_helper.c as a quick way to test > > the result. > > > > Signed-off-by: John Keeping john@metanate.com > > --- > > drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 27 > > +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 > > deletions(-) > > > > diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c > > b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f784488..8fd9821 > > 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c > > +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c > > @@ -177,8 +177,28 @@ static void > > rockchip_crtc_wait_for_update(struct drm_crtc *crtc) > > crtc_funcs->wait_for_update(crtc); } > > > > +static bool framebuffer_changed(struct drm_device *dev, > > + struct drm_atomic_state *old_state, > > + struct drm_crtc *crtc) > > +{ > > + struct drm_plane *plane; > > + struct drm_plane_state *old_plane_state; > > + int i; > > + > > + for_each_plane_in_state(old_state, plane, old_plane_state, > > i) { > > + if (plane->state->crtc != crtc && > > + old_plane_state->crtc != crtc) > > + continue; > > + > > + if (plane->state->fb != old_plane_state->fb) > > + return true; > > + } > > + > > + return false; > > +} > > Please don't hand-roll logic that affects semantics like this. Instead > please use drm_atomic_helper_wait_for_vblanks(), which should do this > correctly for you. > > If that's not the case then we need to improve the generic helper, or > figure out what's different with rockhip.
According to commit 63ebb9f (drm/rockchip: Convert to support atomic API) it's because rockchip doesn't have a hardware vblank counter.
I'm not entirely clear on why this prevents the use of drm_atomic_helper_wait_for_vblanks().
Hm, that commit isn't terribly helpful. If that's really needed then imo I think we should extract a "drm_atomic_helper_plane_needs_vblank_wait()" helper that's used by both. But since rockchip does vblank_get/put calls I'd hope vblanks actually work correctly. And then the helper should work too.
I tried switching the call to rockchip_crtc_wait_for_update() to drm_atomic_helper_wait_for_vblanks() and it works fine until I switch the buffer associated with a cursor, at which point I get iommu page faults, presumably because the GEM buffer is unreferenced too early.
AFAICT the buffer will be released via drm_atomic_state_free() unconditionally, but I suspect I'm missing something since that would mean every driver would hit a similar problem.
Yeah, with the helper we always skip, which means when the cursor bo changes you indeed unmap too early. So can't even share the overall condition, but we could definitely share the little framebuffer_changed helper.
That leaves me with the question: why do other atomic drivers work?
If drm_atomic_helper_wait_for_vblanks() skipping vblanks results in the cursor bo being unmapped too early for rockchip, why is it not unmapped too early for all of the other drivers using that helper?
It's unmapped too early for everyone, it's just that normally that doesn't result in a fireworks show. What we maybe could/should do is do the unmapping asynchronously, but that runs into the overall "current atomic helpers don't do async yet" problem. Might be a good point to start fixing this up though.
OK, thanks, I think I'm beginning to understand how this all fits together.
It looks like there are two options for me to get reasonable cursor performance on rockchip in the short term:
1) Export the current framebuffer_changed() function as drm_atomic_helper_framebuffer_changed() and use it in rockchip_crtc_wait_for_update().
2) Add a mechanism to suppress the legacy_cursor_update check in drm_atomic_helper_wait_for_vblanks() and switch the rockchip driver over to it.
In both of these cases we're only restoring the unsynced cursor ioctls behaviour when the cursor is moved but it will still be expensive when the cursor bo changes. That gives sufficient performance in my testing.
On 2016年01月14日 01:39, John Keeping wrote:
On Wed, 13 Jan 2016 18:19:17 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 04:40:38PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 17:21:56 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 03:55:29PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 16:40:05 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 02:34:25PM +0000, John Keeping wrote: > On Wed, 13 Jan 2016 15:23:20 +0100, Daniel Vetter wrote: > >> On Wed, Jan 13, 2016 at 12:53:34PM +0000, John Keeping wrote: >>> As commented in drm_atomic_helper_wait_for_vblanks(), userspace >>> relies on cursor ioctls being unsynced. Converting the rockchip >>> driver to atomic has significantly impacted cursor performance by >>> making every cursor update wait for vblank. >>> >>> By skipping the vblank sync when the framebuffer has not changed >>> (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid >>> this for the common case of moving the cursor and only need to >>> delay the cursor ioctl when the cursor icon changes. >>> >>> I originally inserted a check on legacy_cursor_update as well, but >>> that caused a storm of iommu page faults. I didn't investigate the >>> cause of those since this change gives enough of a performance >>> improvement for my use case. >>> >>> This is RFC because of that and because the framebuffer_changed() >>> function is copied from drm_atomic_helper.c as a quick way to test >>> the result. >>> >>> Signed-off-by: John Keeping john@metanate.com >>> --- >>> drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 27 >>> +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 >>> deletions(-) >>> >>> diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c >>> b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f784488..8fd9821 >>> 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c >>> +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c >>> @@ -177,8 +177,28 @@ static void >>> rockchip_crtc_wait_for_update(struct drm_crtc *crtc) >>> crtc_funcs->wait_for_update(crtc); } >>> >>> +static bool framebuffer_changed(struct drm_device *dev, >>> + struct drm_atomic_state *old_state, >>> + struct drm_crtc *crtc) >>> +{ >>> + struct drm_plane *plane; >>> + struct drm_plane_state *old_plane_state; >>> + int i; >>> + >>> + for_each_plane_in_state(old_state, plane, old_plane_state, >>> i) { >>> + if (plane->state->crtc != crtc && >>> + old_plane_state->crtc != crtc) >>> + continue; >>> + >>> + if (plane->state->fb != old_plane_state->fb) >>> + return true; >>> + } >>> + >>> + return false; >>> +} >> Please don't hand-roll logic that affects semantics like this. Instead >> please use drm_atomic_helper_wait_for_vblanks(), which should do this >> correctly for you. >> >> If that's not the case then we need to improve the generic helper, or >> figure out what's different with rockhip. > According to commit 63ebb9f (drm/rockchip: Convert to support atomic > API) it's because rockchip doesn't have a hardware vblank counter. > > I'm not entirely clear on why this prevents the use of > drm_atomic_helper_wait_for_vblanks(). Hm, that commit isn't terribly helpful. If that's really needed then imo I think we should extract a "drm_atomic_helper_plane_needs_vblank_wait()" helper that's used by both. But since rockchip does vblank_get/put calls I'd hope vblanks actually work correctly. And then the helper should work too.
I tried switching the call to rockchip_crtc_wait_for_update() to drm_atomic_helper_wait_for_vblanks() and it works fine until I switch the buffer associated with a cursor, at which point I get iommu page faults, presumably because the GEM buffer is unreferenced too early.
AFAICT the buffer will be released via drm_atomic_state_free() unconditionally, but I suspect I'm missing something since that would mean every driver would hit a similar problem.
Yeah, with the helper we always skip, which means when the cursor bo changes you indeed unmap too early. So can't even share the overall condition, but we could definitely share the little framebuffer_changed helper.
That leaves me with the question: why do other atomic drivers work?
If drm_atomic_helper_wait_for_vblanks() skipping vblanks results in the cursor bo being unmapped too early for rockchip, why is it not unmapped too early for all of the other drivers using that helper?
It's unmapped too early for everyone, it's just that normally that doesn't result in a fireworks show. What we maybe could/should do is do the unmapping asynchronously, but that runs into the overall "current atomic helpers don't do async yet" problem. Might be a good point to start fixing this up though.
OK, thanks, I think I'm beginning to understand how this all fits together.
It looks like there are two options for me to get reasonable cursor performance on rockchip in the short term:
Export the current framebuffer_changed() function as drm_atomic_helper_framebuffer_changed() and use it in rockchip_crtc_wait_for_update().
Add a mechanism to suppress the legacy_cursor_update check in drm_atomic_helper_wait_for_vblanks() and switch the rockchip driver over to it.
In both of these cases we're only restoring the unsynced cursor ioctls behaviour when the cursor is moved but it will still be expensive when the cursor bo changes. That gives sufficient performance in my testing.
Thanks for point that.
because rockchip not support hardware vblank counter, use drm_atomic_helper_wait_for_vblanks have under issues:
| <-- HW vsync irq and reg take effect plane_commit ---> | get_vblank and wait -> | | <-- handle_vblank, vblank->count + 1 cleanup_fb ---> | iommu crash ---> | | <-- HW vsync irq and reg take effect there is no hardware vblank counter on rockchip vop, we can't ensure the consistency of reg take effect and vblank->count, if plane commit hit into the period of reg take effect and vblank->count, cleanup_fb happen before old_fb swap out from vop, then iommu crash.
That is why I special the wait_for_vblanks, we need check the reg really take effect before clean up old fb. at vop_win_pending_is_complete function, check win enable and win address, to ensure that.
Not only rockchip drm do that thing:
exynos also check address before cleanup fb if (start == start_s) exynos_drm_crtc_finish_update(ctx->crtc, plane);
Thanks.
-- Ｍark Yao
On Thu, Jan 14, 2016 at 2:16 AM, Mark yao mark.yao@rock-chips.com wrote:
On 2016年01月14日 01:39, John Keeping wrote:
On Wed, 13 Jan 2016 18:19:17 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 04:40:38PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 17:21:56 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 03:55:29PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 16:40:05 +0100, Daniel Vetter wrote:
> > On Wed, Jan 13, 2016 at 02:34:25PM +0000, John Keeping wrote: >> >> On Wed, 13 Jan 2016 15:23:20 +0100, Daniel Vetter wrote: >> >>> >>> On Wed, Jan 13, 2016 at 12:53:34PM +0000, John Keeping wrote: >>>> >>>> As commented in drm_atomic_helper_wait_for_vblanks(), userspace >>>> relies on cursor ioctls being unsynced. Converting the rockchip >>>> driver to atomic has significantly impacted cursor performance by >>>> making every cursor update wait for vblank. >>>> >>>> By skipping the vblank sync when the framebuffer has not changed >>>> (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid >>>> this for the common case of moving the cursor and only need to >>>> delay the cursor ioctl when the cursor icon changes. >>>> >>>> I originally inserted a check on legacy_cursor_update as well, but >>>> that caused a storm of iommu page faults. I didn't investigate >>>> the >>>> cause of those since this change gives enough of a performance >>>> improvement for my use case. >>>> >>>> This is RFC because of that and because the framebuffer_changed() >>>> function is copied from drm_atomic_helper.c as a quick way to test >>>> the result. >>>> >>>> Signed-off-by: John Keeping john@metanate.com >>>> --- >>>> drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 27 >>>> +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 >>>> deletions(-) >>>> >>>> diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c >>>> b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index >>>> f784488..8fd9821 >>>> 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c >>>> +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c >>>> @@ -177,8 +177,28 @@ static void >>>> rockchip_crtc_wait_for_update(struct drm_crtc *crtc) >>>> crtc_funcs->wait_for_update(crtc); } >>>> +static bool framebuffer_changed(struct drm_device *dev, >>>> + struct drm_atomic_state >>>> *old_state, >>>> + struct drm_crtc *crtc) >>>> +{ >>>> + struct drm_plane *plane; >>>> + struct drm_plane_state *old_plane_state; >>>> + int i; >>>> + >>>> + for_each_plane_in_state(old_state, plane, old_plane_state, >>>> i) { >>>> + if (plane->state->crtc != crtc && >>>> + old_plane_state->crtc != crtc) >>>> + continue; >>>> + >>>> + if (plane->state->fb != old_plane_state->fb) >>>> + return true; >>>> + } >>>> + >>>> + return false; >>>> +} >>> >>> Please don't hand-roll logic that affects semantics like this. >>> Instead >>> please use drm_atomic_helper_wait_for_vblanks(), which should do >>> this >>> correctly for you. >>> >>> If that's not the case then we need to improve the generic helper, >>> or >>> figure out what's different with rockhip. >> >> According to commit 63ebb9f (drm/rockchip: Convert to support atomic >> API) it's because rockchip doesn't have a hardware vblank counter. >> >> I'm not entirely clear on why this prevents the use of >> drm_atomic_helper_wait_for_vblanks(). > > Hm, that commit isn't terribly helpful. If that's really needed then > imo I > think we should extract a > "drm_atomic_helper_plane_needs_vblank_wait()" > helper that's used by both. But since rockchip does vblank_get/put > calls > I'd hope vblanks actually work correctly. And then the helper should > work > too.
I tried switching the call to rockchip_crtc_wait_for_update() to drm_atomic_helper_wait_for_vblanks() and it works fine until I switch the buffer associated with a cursor, at which point I get iommu page faults, presumably because the GEM buffer is unreferenced too early.
AFAICT the buffer will be released via drm_atomic_state_free() unconditionally, but I suspect I'm missing something since that would mean every driver would hit a similar problem.
Yeah, with the helper we always skip, which means when the cursor bo changes you indeed unmap too early. So can't even share the overall condition, but we could definitely share the little framebuffer_changed helper.
That leaves me with the question: why do other atomic drivers work?
If drm_atomic_helper_wait_for_vblanks() skipping vblanks results in the cursor bo being unmapped too early for rockchip, why is it not unmapped too early for all of the other drivers using that helper?
It's unmapped too early for everyone, it's just that normally that doesn't result in a fireworks show. What we maybe could/should do is do the unmapping asynchronously, but that runs into the overall "current atomic helpers don't do async yet" problem. Might be a good point to start fixing this up though.
OK, thanks, I think I'm beginning to understand how this all fits together.
It looks like there are two options for me to get reasonable cursor performance on rockchip in the short term:
Export the current framebuffer_changed() function as drm_atomic_helper_framebuffer_changed() and use it in rockchip_crtc_wait_for_update().
Add a mechanism to suppress the legacy_cursor_update check in drm_atomic_helper_wait_for_vblanks() and switch the rockchip driver over to it.
In both of these cases we're only restoring the unsynced cursor ioctls behaviour when the cursor is moved but it will still be expensive when the cursor bo changes. That gives sufficient performance in my testing.
Thanks for point that.
because rockchip not support hardware vblank counter, use drm_atomic_helper_wait_for_vblanks have under issues:
| <-- HW vsync irq and reg takeeffect plane_commit ---> | get_vblank and wait -> | | <-- handle_vblank, vblank->count + 1 cleanup_fb ---> | iommu crash ---> | | <-- HW vsync irq and reg take effect there is no hardware vblank counter on rockchip vop, we can't ensure the consistency of reg take effect and vblank->count, if plane commit hit into the period of reg take effect and vblank->count, cleanup_fb happen before old_fb swap out from vop, then iommu crash.
That is why I special the wait_for_vblanks, we need check the reg really take effect before clean up old fb. at vop_win_pending_is_complete function, check win enable and win address, to ensure that.
Not only rockchip drm do that thing:
exynos also check address before cleanup fb if (start == start_s) exynos_drm_crtc_finish_update(ctx->crtc, plane);
Thanks.
Do you have a scanline counter or something similar at least? Any other indication about how far along the chip is with scanning out? We use that in i915 to avoid races with the interrupt handler and detect this w/a scenario.
I think if you have a scanline counter then it should magically work, since the vblank code will realize that you're already past the last vblank interrupt and /should/ have incremented already. Or something like that.
Otherwise if this is common we might want to figure out how to solve this in a generic way. It's one of these problems that will make generic async support almost impossible. -Daniel
On 2016年01月14日 16:32, Daniel Vetter wrote:
On Thu, Jan 14, 2016 at 2:16 AM, Mark yao mark.yao@rock-chips.com wrote:
On 2016年01月14日 01:39, John Keeping wrote:
On Wed, 13 Jan 2016 18:19:17 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 04:40:38PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 17:21:56 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 03:55:29PM +0000, John Keeping wrote: > On Wed, 13 Jan 2016 16:40:05 +0100, Daniel Vetter wrote: > >> On Wed, Jan 13, 2016 at 02:34:25PM +0000, John Keeping wrote: >>> On Wed, 13 Jan 2016 15:23:20 +0100, Daniel Vetter wrote: >>> >>>> On Wed, Jan 13, 2016 at 12:53:34PM +0000, John Keeping wrote: >>>>> As commented in drm_atomic_helper_wait_for_vblanks(), userspace >>>>> relies on cursor ioctls being unsynced. Converting the rockchip >>>>> driver to atomic has significantly impacted cursor performance by >>>>> making every cursor update wait for vblank. >>>>> >>>>> By skipping the vblank sync when the framebuffer has not changed >>>>> (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid >>>>> this for the common case of moving the cursor and only need to >>>>> delay the cursor ioctl when the cursor icon changes. >>>>> >>>>> I originally inserted a check on legacy_cursor_update as well, but >>>>> that caused a storm of iommu page faults. I didn't investigate >>>>> the >>>>> cause of those since this change gives enough of a performance >>>>> improvement for my use case. >>>>> >>>>> This is RFC because of that and because the framebuffer_changed() >>>>> function is copied from drm_atomic_helper.c as a quick way to test >>>>> the result. >>>>> >>>>> Signed-off-by: John Keeping john@metanate.com >>>>> --- >>>>> drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 27 >>>>> +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 >>>>> deletions(-) >>>>> >>>>> diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c >>>>> b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index >>>>> f784488..8fd9821 >>>>> 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c >>>>> +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c >>>>> @@ -177,8 +177,28 @@ static void >>>>> rockchip_crtc_wait_for_update(struct drm_crtc *crtc) >>>>> crtc_funcs->wait_for_update(crtc); } >>>>> +static bool framebuffer_changed(struct drm_device *dev, >>>>> + struct drm_atomic_state >>>>> *old_state, >>>>> + struct drm_crtc *crtc) >>>>> +{ >>>>> + struct drm_plane *plane; >>>>> + struct drm_plane_state *old_plane_state; >>>>> + int i; >>>>> + >>>>> + for_each_plane_in_state(old_state, plane, old_plane_state, >>>>> i) { >>>>> + if (plane->state->crtc != crtc && >>>>> + old_plane_state->crtc != crtc) >>>>> + continue; >>>>> + >>>>> + if (plane->state->fb != old_plane_state->fb) >>>>> + return true; >>>>> + } >>>>> + >>>>> + return false; >>>>> +} >>>> Please don't hand-roll logic that affects semantics like this. >>>> Instead >>>> please use drm_atomic_helper_wait_for_vblanks(), which should do >>>> this >>>> correctly for you. >>>> >>>> If that's not the case then we need to improve the generic helper, >>>> or >>>> figure out what's different with rockhip. >>> According to commit 63ebb9f (drm/rockchip: Convert to support atomic >>> API) it's because rockchip doesn't have a hardware vblank counter. >>> >>> I'm not entirely clear on why this prevents the use of >>> drm_atomic_helper_wait_for_vblanks(). >> Hm, that commit isn't terribly helpful. If that's really needed then >> imo I >> think we should extract a >> "drm_atomic_helper_plane_needs_vblank_wait()" >> helper that's used by both. But since rockchip does vblank_get/put >> calls >> I'd hope vblanks actually work correctly. And then the helper should >> work >> too. > I tried switching the call to rockchip_crtc_wait_for_update() to > drm_atomic_helper_wait_for_vblanks() and it works fine until I switch > the buffer associated with a cursor, at which point I get iommu page > faults, presumably because the GEM buffer is unreferenced too early. > > AFAICT the buffer will be released via drm_atomic_state_free() > unconditionally, but I suspect I'm missing something since that would > mean every driver would hit a similar problem. Yeah, with the helper we always skip, which means when the cursor bo changes you indeed unmap too early. So can't even share the overall condition, but we could definitely share the little framebuffer_changed helper.
That leaves me with the question: why do other atomic drivers work?
If drm_atomic_helper_wait_for_vblanks() skipping vblanks results in the cursor bo being unmapped too early for rockchip, why is it not unmapped too early for all of the other drivers using that helper?
It's unmapped too early for everyone, it's just that normally that doesn't result in a fireworks show. What we maybe could/should do is do the unmapping asynchronously, but that runs into the overall "current atomic helpers don't do async yet" problem. Might be a good point to start fixing this up though.
OK, thanks, I think I'm beginning to understand how this all fits together.
It looks like there are two options for me to get reasonable cursor performance on rockchip in the short term:
Export the current framebuffer_changed() function as drm_atomic_helper_framebuffer_changed() and use it in rockchip_crtc_wait_for_update().
Add a mechanism to suppress the legacy_cursor_update check in drm_atomic_helper_wait_for_vblanks() and switch the rockchip driver over to it.
In both of these cases we're only restoring the unsynced cursor ioctls behaviour when the cursor is moved but it will still be expensive when the cursor bo changes. That gives sufficient performance in my testing.
Thanks for point that.
because rockchip not support hardware vblank counter, use drm_atomic_helper_wait_for_vblanks have under issues:
| <-- HW vsync irq and reg takeeffect plane_commit ---> | get_vblank and wait -> | | <-- handle_vblank, vblank->count + 1 cleanup_fb ---> | iommu crash ---> | | <-- HW vsync irq and reg take effect there is no hardware vblank counter on rockchip vop, we can't ensure the consistency of reg take effect and vblank->count, if plane commit hit into the period of reg take effect and vblank->count, cleanup_fb happen before old_fb swap out from vop, then iommu crash.
That is why I special the wait_for_vblanks, we need check the reg really take effect before clean up old fb. at vop_win_pending_is_complete function, check win enable and win address, to ensure that.
Not only rockchip drm do that thing:
exynos also check address before cleanup fb if (start == start_s) exynos_drm_crtc_finish_update(ctx->crtc, plane);
Thanks.
Do you have a scanline counter or something similar at least? Any other indication about how far along the chip is with scanning out? We use that in i915 to avoid races with the interrupt handler and detect this w/a scenario.
I think if you have a scanline counter then it should magically work, since the vblank code will realize that you're already past the last vblank interrupt and /should/ have incremented already. Or something like that.
Otherwise if this is common we might want to figure out how to solve this in a generic way. It's one of these problems that will make generic async support almost impossible. -Daniel
No, both rk3288 or rk3036 not support hardware vblank counter and scanline counter.
At android side, we use same way, check address and enable bit to ensure register take effect.
On future chips, scanline counter and hardware counter would be support, but not now.
On Thu, Jan 14, 2016 at 04:46:37PM +0800, Mark yao wrote:
On 2016年01月14日 16:32, Daniel Vetter wrote:
On Thu, Jan 14, 2016 at 2:16 AM, Mark yao mark.yao@rock-chips.com wrote:
On 2016年01月14日 01:39, John Keeping wrote:
On Wed, 13 Jan 2016 18:19:17 +0100, Daniel Vetter wrote:
On Wed, Jan 13, 2016 at 04:40:38PM +0000, John Keeping wrote:
On Wed, 13 Jan 2016 17:21:56 +0100, Daniel Vetter wrote:
>On Wed, Jan 13, 2016 at 03:55:29PM +0000, John Keeping wrote: >>On Wed, 13 Jan 2016 16:40:05 +0100, Daniel Vetter wrote: >> >>>On Wed, Jan 13, 2016 at 02:34:25PM +0000, John Keeping wrote: >>>>On Wed, 13 Jan 2016 15:23:20 +0100, Daniel Vetter wrote: >>>> >>>>>On Wed, Jan 13, 2016 at 12:53:34PM +0000, John Keeping wrote: >>>>>>As commented in drm_atomic_helper_wait_for_vblanks(), userspace >>>>>>relies on cursor ioctls being unsynced. Converting the rockchip >>>>>>driver to atomic has significantly impacted cursor performance by >>>>>>making every cursor update wait for vblank. >>>>>> >>>>>>By skipping the vblank sync when the framebuffer has not changed >>>>>>(as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid >>>>>>this for the common case of moving the cursor and only need to >>>>>>delay the cursor ioctl when the cursor icon changes. >>>>>> >>>>>>I originally inserted a check on legacy_cursor_update as well, but >>>>>>that caused a storm of iommu page faults. I didn't investigate >>>>>>the >>>>>>cause of those since this change gives enough of a performance >>>>>>improvement for my use case. >>>>>> >>>>>>This is RFC because of that and because the framebuffer_changed() >>>>>>function is copied from drm_atomic_helper.c as a quick way to test >>>>>>the result. >>>>>> >>>>>>Signed-off-by: John Keeping john@metanate.com >>>>>>--- >>>>>> drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 27 >>>>>>+++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 >>>>>>deletions(-) >>>>>> >>>>>>diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c >>>>>>b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index >>>>>>f784488..8fd9821 >>>>>>100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c >>>>>>+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c >>>>>>@@ -177,8 +177,28 @@ static void >>>>>>rockchip_crtc_wait_for_update(struct drm_crtc *crtc) >>>>>>crtc_funcs->wait_for_update(crtc); } >>>>>> +static bool framebuffer_changed(struct drm_device *dev, >>>>>>+ struct drm_atomic_state >>>>>>*old_state, >>>>>>+ struct drm_crtc *crtc) >>>>>>+{ >>>>>>+ struct drm_plane *plane; >>>>>>+ struct drm_plane_state *old_plane_state; >>>>>>+ int i; >>>>>>+ >>>>>>+ for_each_plane_in_state(old_state, plane, old_plane_state, >>>>>>i) { >>>>>>+ if (plane->state->crtc != crtc && >>>>>>+ old_plane_state->crtc != crtc) >>>>>>+ continue; >>>>>>+ >>>>>>+ if (plane->state->fb != old_plane_state->fb) >>>>>>+ return true; >>>>>>+ } >>>>>>+ >>>>>>+ return false; >>>>>>+} >>>>>Please don't hand-roll logic that affects semantics like this. >>>>>Instead >>>>>please use drm_atomic_helper_wait_for_vblanks(), which should do >>>>>this >>>>>correctly for you. >>>>> >>>>>If that's not the case then we need to improve the generic helper, >>>>>or >>>>>figure out what's different with rockhip. >>>>According to commit 63ebb9f (drm/rockchip: Convert to support atomic >>>>API) it's because rockchip doesn't have a hardware vblank counter. >>>> >>>>I'm not entirely clear on why this prevents the use of >>>>drm_atomic_helper_wait_for_vblanks(). >>>Hm, that commit isn't terribly helpful. If that's really needed then >>>imo I >>>think we should extract a >>>"drm_atomic_helper_plane_needs_vblank_wait()" >>>helper that's used by both. But since rockchip does vblank_get/put >>>calls >>>I'd hope vblanks actually work correctly. And then the helper should >>>work >>>too. >>I tried switching the call to rockchip_crtc_wait_for_update() to >>drm_atomic_helper_wait_for_vblanks() and it works fine until I switch >>the buffer associated with a cursor, at which point I get iommu page >>faults, presumably because the GEM buffer is unreferenced too early. >> >>AFAICT the buffer will be released via drm_atomic_state_free() >>unconditionally, but I suspect I'm missing something since that would >>mean every driver would hit a similar problem. >Yeah, with the helper we always skip, which means when the cursor bo >changes you indeed unmap too early. So can't even share the overall >condition, but we could definitely share the little framebuffer_changed >helper. That leaves me with the question: why do other atomic drivers work?
If drm_atomic_helper_wait_for_vblanks() skipping vblanks results in the cursor bo being unmapped too early for rockchip, why is it not unmapped too early for all of the other drivers using that helper?
It's unmapped too early for everyone, it's just that normally that doesn't result in a fireworks show. What we maybe could/should do is do the unmapping asynchronously, but that runs into the overall "current atomic helpers don't do async yet" problem. Might be a good point to start fixing this up though.
OK, thanks, I think I'm beginning to understand how this all fits together.
It looks like there are two options for me to get reasonable cursor performance on rockchip in the short term:
Export the current framebuffer_changed() function as drm_atomic_helper_framebuffer_changed() and use it in rockchip_crtc_wait_for_update().
Add a mechanism to suppress the legacy_cursor_update check in drm_atomic_helper_wait_for_vblanks() and switch the rockchip driver over to it.
In both of these cases we're only restoring the unsynced cursor ioctls behaviour when the cursor is moved but it will still be expensive when the cursor bo changes. That gives sufficient performance in my testing.
Thanks for point that.
because rockchip not support hardware vblank counter, use drm_atomic_helper_wait_for_vblanks have under issues:
| <-- HW vsync irq and reg takeeffect plane_commit ---> | get_vblank and wait -> | | <-- handle_vblank, vblank->count + 1 cleanup_fb ---> | iommu crash ---> | | <-- HW vsync irq and reg take effect there is no hardware vblank counter on rockchip vop, we can't ensure the consistency of reg take effect and vblank->count, if plane commit hit into the period of reg take effect and vblank->count, cleanup_fb happen before old_fb swap out from vop, then iommu crash.
That is why I special the wait_for_vblanks, we need check the reg really take effect before clean up old fb. at vop_win_pending_is_complete function, check win enable and win address, to ensure that.
Not only rockchip drm do that thing:
exynos also check address before cleanup fb if (start == start_s) exynos_drm_crtc_finish_update(ctx->crtc, plane);
Thanks.
Do you have a scanline counter or something similar at least? Any other indication about how far along the chip is with scanning out? We use that in i915 to avoid races with the interrupt handler and detect this w/a scenario.
I think if you have a scanline counter then it should magically work, since the vblank code will realize that you're already past the last vblank interrupt and /should/ have incremented already. Or something like that.
Otherwise if this is common we might want to figure out how to solve this in a generic way. It's one of these problems that will make generic async support almost impossible. -Daniel
No, both rk3288 or rk3036 not support hardware vblank counter and scanline counter.
At android side, we use same way, check address and enable bit to ensure register take effect.
On future chips, scanline counter and hardware counter would be support, but not now.
Ugh. Oh well, there's not really anything we can do in core nore helpers to make this easier for drivers. This really only can be fixed sensibly at the hardware level.
So yeah I think exposing framebuffer_changed as a helper is the way to go here.
Thanks, Daniel
On Thu, 14 Jan 2016 15:20:47 +0100, Daniel Vetter wrote:
Ugh. Oh well, there's not really anything we can do in core nore helpers to make this easier for drivers. This really only can be fixed sensibly at the hardware level.
So yeah I think exposing framebuffer_changed as a helper is the way to go here.
OK, here's a series to do that. I also added a comment to rockchip_atomic_wait_for_complete() explaining why we can't use drm_atomic_helper_wait_for_vblanks().
John Keeping (3): drm/atomic-helper: Export framebuffer_changed() drm/rockchip: don't wait for vblank if fb hasn't changed drm/rockchip: explain why we can't wait_for_vblanks
drivers/gpu/drm/drm_atomic_helper.c | 24 ++++++++++++++++++++---- drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 14 ++++++++++++-- include/drm/drm_atomic_helper.h | 4 ++++ 3 files changed, 36 insertions(+), 6 deletions(-)
The Rockchip driver cannot use drm_atomic_helper_wait_for_vblanks() because it has hardware counters for neither vblanks nor scanlines.
In order to simplify re-implementing the functionality for this driver, export the framebuffer_changed() helper so it can be reused.
Signed-off-by: John Keeping john@metanate.com --- drivers/gpu/drm/drm_atomic_helper.c | 24 ++++++++++++++++++++---- include/drm/drm_atomic_helper.h | 4 ++++ 2 files changed, 24 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 268d37f..7449293 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -948,9 +948,23 @@ static void wait_for_fences(struct drm_device *dev, } }
-static bool framebuffer_changed(struct drm_device *dev, - struct drm_atomic_state *old_state, - struct drm_crtc *crtc) +/** + * drm_atomic_helper_framebuffer_changed - check if framebuffer has changed + * @dev: DRM device + * @old_state: atomic state object with old state structures + * @crtc: DRM crtc + * + * Checks whether the framebuffer used for this CRTC changes as a result of + * the atomic update. This is useful for drivers which cannot use + * drm_atomic_helper_wait_for_vblanks() and need to reimplement its + * functionality. + * + * Returns: + * true if the framebuffer changed. + */ +bool drm_atomic_helper_framebuffer_changed(struct drm_device *dev, + struct drm_atomic_state *old_state, + struct drm_crtc *crtc) { struct drm_plane *plane; struct drm_plane_state *old_plane_state; @@ -967,6 +981,7 @@ static bool framebuffer_changed(struct drm_device *dev,
return false; } +EXPORT_SYMBOL(drm_atomic_helper_framebuffer_changed);
/** * drm_atomic_helper_wait_for_vblanks - wait for vblank on crtcs @@ -1001,7 +1016,8 @@ drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, if (old_state->legacy_cursor_update) continue;
- if (!framebuffer_changed(dev, old_state, crtc)) + if (!drm_atomic_helper_framebuffer_changed(dev, + old_state, crtc)) continue;
ret = drm_crtc_vblank_get(crtc); diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h index a286cce..74fce78 100644 --- a/include/drm/drm_atomic_helper.h +++ b/include/drm/drm_atomic_helper.h @@ -42,6 +42,10 @@ int drm_atomic_helper_commit(struct drm_device *dev, struct drm_atomic_state *state, bool async);
+bool drm_atomic_helper_framebuffer_changed(struct drm_device *dev, + struct drm_atomic_state *old_state, + struct drm_crtc *crtc); + void drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, struct drm_atomic_state *old_state);
On Thu, Jan 14, 2016 at 02:39:40PM +0000, John Keeping wrote:
The Rockchip driver cannot use drm_atomic_helper_wait_for_vblanks() because it has hardware counters for neither vblanks nor scanlines.
In order to simplify re-implementing the functionality for this driver, export the framebuffer_changed() helper so it can be reused.
Signed-off-by: John Keeping john@metanate.com
Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch And since I don't expect anyone else to need this anytime soon probably best you just pull this in through rockchip trees.
Cheers, Daniel
drivers/gpu/drm/drm_atomic_helper.c | 24 ++++++++++++++++++++---- include/drm/drm_atomic_helper.h | 4 ++++ 2 files changed, 24 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 268d37f..7449293 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -948,9 +948,23 @@ static void wait_for_fences(struct drm_device *dev, } }
-static bool framebuffer_changed(struct drm_device *dev,
struct drm_atomic_state *old_state,struct drm_crtc *crtc)+/**
- drm_atomic_helper_framebuffer_changed - check if framebuffer has changed
- @dev: DRM device
- @old_state: atomic state object with old state structures
- @crtc: DRM crtc
- Checks whether the framebuffer used for this CRTC changes as a result of
- the atomic update. This is useful for drivers which cannot use
- drm_atomic_helper_wait_for_vblanks() and need to reimplement its
- functionality.
- Returns:
- true if the framebuffer changed.
- */
+bool drm_atomic_helper_framebuffer_changed(struct drm_device *dev,
struct drm_atomic_state *old_state,struct drm_crtc *crtc){ struct drm_plane *plane; struct drm_plane_state *old_plane_state; @@ -967,6 +981,7 @@ static bool framebuffer_changed(struct drm_device *dev,
return false; } +EXPORT_SYMBOL(drm_atomic_helper_framebuffer_changed);
/**
- drm_atomic_helper_wait_for_vblanks - wait for vblank on crtcs
@@ -1001,7 +1016,8 @@ drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, if (old_state->legacy_cursor_update) continue;
if (!framebuffer_changed(dev, old_state, crtc))
if (!drm_atomic_helper_framebuffer_changed(dev,old_state, crtc)) continue;ret = drm_crtc_vblank_get(crtc);
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h index a286cce..74fce78 100644 --- a/include/drm/drm_atomic_helper.h +++ b/include/drm/drm_atomic_helper.h @@ -42,6 +42,10 @@ int drm_atomic_helper_commit(struct drm_device *dev, struct drm_atomic_state *state, bool async);
+bool drm_atomic_helper_framebuffer_changed(struct drm_device *dev,
struct drm_atomic_state *old_state,struct drm_crtc *crtc);void drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, struct drm_atomic_state *old_state);
-- 2.7.0.226.gfe986fe
As commented in drm_atomic_helper_wait_for_vblanks(), userspace relies on cursor ioctls being unsynced. Converting the rockchip driver to atomic has significantly impacted cursor performance by making every cursor update wait for vblank.
By skipping the vblank sync when the framebuffer has not changed (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid this for the common case of moving the cursor and only need to delay the cursor ioctl when the cursor icon changes.
We cannot add the check on legacy_cursor_update since that results in the cursor bo being unreferenced while the hardware may still be reading it. Fully supporting unsynced cursor updates is left for the future when the atomic helper framework supports async updates.
Signed-off-by: John Keeping john@metanate.com --- drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f784488..679d23a 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -178,7 +178,7 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) }
static void -rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) +rockchip_atomic_wait_for_complete(struct drm_device *dev, struct drm_atomic_state *old_state) { struct drm_crtc_state *old_crtc_state; struct drm_crtc *crtc; @@ -194,6 +194,10 @@ rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) if (!crtc->state->active) continue;
+ if (!drm_atomic_helper_framebuffer_changed(dev, + old_state, crtc)) + continue; + ret = drm_crtc_vblank_get(crtc); if (ret != 0) continue; @@ -241,7 +245,7 @@ rockchip_atomic_commit_complete(struct rockchip_atomic_commit *commit)
drm_atomic_helper_commit_planes(dev, state, true);
- rockchip_atomic_wait_for_complete(state); + rockchip_atomic_wait_for_complete(dev, state);
drm_atomic_helper_cleanup_planes(dev, state);
Signed-off-by: John Keeping john@metanate.com --- drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 6 ++++++ 1 file changed, 6 insertions(+)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index 679d23a..b267ce4 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -177,6 +177,12 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); }
+/* + * We can't use drm_atomic_helper_wait_for_vblanks() because rk3288 and rk3066 + * have hardware counters for neither vblanks nor scanlines. This function is + * equivalent but uses rockchip_crtc_wait_for_update() instead of waiting for + * vblank_count to change. + */ static void rockchip_atomic_wait_for_complete(struct drm_device *dev, struct drm_atomic_state *old_state) {
On Thu, Jan 14, 2016 at 02:39:42PM +0000, John Keeping wrote:
Signed-off-by: John Keeping john@metanate.com
drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 6 ++++++ 1 file changed, 6 insertions(+)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index 679d23a..b267ce4 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -177,6 +177,12 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); }
+/*
- We can't use drm_atomic_helper_wait_for_vblanks() because rk3288 and rk3066
- have hardware counters for neither vblanks nor scanlines. This function is
- equivalent but uses rockchip_crtc_wait_for_update() instead of waiting for
- vblank_count to change.
- */
This is kind of misleading. From reading earlier parts of the thread the reason why drm_atomic_helper_wait_for_vblanks() won't work is because it has a potential race condition that can't be detected unless you also have a vblank counter. However, the above comment makes it work like drm_atomic_helper_wait_for_vblanks() doesn't work in the absence of a vblank counter, which isn't quite true.
Perhaps also the drm_atomic_helper_wait_for_vblanks() kerneldoc needs to be updated with these restrictions on its use?
Thierry
On Thu, 14 Jan 2016 15:57:05 +0100, Thierry Reding wrote:
On Thu, Jan 14, 2016 at 02:39:42PM +0000, John Keeping wrote:
Signed-off-by: John Keeping john@metanate.com
drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 6 ++++++ 1 file changed, 6 insertions(+)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index 679d23a..b267ce4 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -177,6 +177,12 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); }
+/*
- We can't use drm_atomic_helper_wait_for_vblanks() because rk3288 and rk3066
- have hardware counters for neither vblanks nor scanlines. This function is
- equivalent but uses rockchip_crtc_wait_for_update() instead of waiting for
- vblank_count to change.
- */
This is kind of misleading. From reading earlier parts of the thread the reason why drm_atomic_helper_wait_for_vblanks() won't work is because it has a potential race condition that can't be detected unless you also have a vblank counter. However, the above comment makes it work like drm_atomic_helper_wait_for_vblanks() doesn't work in the absence of a vblank counter, which isn't quite true.
How about something like this (using the sequence from Mark's message):
/* * We can't use drm_atomic_helper_wait_for_vblanks() because rk3288 and rk3066 * have hardware counters for neither vblanks nor scanlines, which results in * a race where: * | <-- HW vsync irq and reg take effect * plane_commit --> | * get_vblank and wait --> | * | <-- handle_vblank, vblank->count + 1 * cleanup_fb --> | * iommu crash --> | * | <-- HW vsync irq and reg take effect * * This function is equivalent but uses rockchip_crtc_wait_for_update() instead * of waiting for vblank_count to change. */
On 2016年01月15日 00:26, John Keeping wrote:
On Thu, 14 Jan 2016 15:57:05 +0100, Thierry Reding wrote:
On Thu, Jan 14, 2016 at 02:39:42PM +0000, John Keeping wrote:
Signed-off-by: John Keeping john@metanate.com
drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 6 ++++++ 1 file changed, 6 insertions(+)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index 679d23a..b267ce4 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -177,6 +177,12 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); }
+/*
- We can't use drm_atomic_helper_wait_for_vblanks() because rk3288 and rk3066
- have hardware counters for neither vblanks nor scanlines. This function is
- equivalent but uses rockchip_crtc_wait_for_update() instead of waiting for
- vblank_count to change.
- */
This is kind of misleading. From reading earlier parts of the thread the reason why drm_atomic_helper_wait_for_vblanks() won't work is because it has a potential race condition that can't be detected unless you also have a vblank counter. However, the above comment makes it work like drm_atomic_helper_wait_for_vblanks() doesn't work in the absence of a vblank counter, which isn't quite true.
How about something like this (using the sequence from Mark's message):
/*
- We can't use drm_atomic_helper_wait_for_vblanks() because rk3288 and rk3066
- have hardware counters for neither vblanks nor scanlines, which results in
- a race where:
| <-- HW vsync irq and reg take effectplane_commit --> |- get_vblank and wait --> |
| <-- handle_vblank, vblank->count + 1cleanup_fb --> |iommu crash --> || <-- HW vsync irq and reg take effect- This function is equivalent but uses rockchip_crtc_wait_for_update() instead
- of waiting for vblank_count to change.
*/
Looks good for me, but maybe Thierry has some more advices. :-)
The first two patches are unchanged since v1 but the comment in the third has been expanded following Thierry's comments.
John Keeping (3): drm/atomic-helper: Export framebuffer_changed() drm/rockchip: don't wait for vblank if fb hasn't changed drm/rockchip: explain why we can't wait_for_vblanks
drivers/gpu/drm/drm_atomic_helper.c | 24 ++++++++++++++++++++---- drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 23 +++++++++++++++++++++-- include/drm/drm_atomic_helper.h | 4 ++++ 3 files changed, 45 insertions(+), 6 deletions(-)
The Rockchip driver cannot use drm_atomic_helper_wait_for_vblanks() because it has hardware counters for neither vblanks nor scanlines.
In order to simplify re-implementing the functionality for this driver, export the framebuffer_changed() helper so it can be reused.
Signed-off-by: John Keeping john@metanate.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch --- Unchanged since v1.
drivers/gpu/drm/drm_atomic_helper.c | 24 ++++++++++++++++++++---- include/drm/drm_atomic_helper.h | 4 ++++ 2 files changed, 24 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 268d37f..7449293 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -948,9 +948,23 @@ static void wait_for_fences(struct drm_device *dev, } }
-static bool framebuffer_changed(struct drm_device *dev, - struct drm_atomic_state *old_state, - struct drm_crtc *crtc) +/** + * drm_atomic_helper_framebuffer_changed - check if framebuffer has changed + * @dev: DRM device + * @old_state: atomic state object with old state structures + * @crtc: DRM crtc + * + * Checks whether the framebuffer used for this CRTC changes as a result of + * the atomic update. This is useful for drivers which cannot use + * drm_atomic_helper_wait_for_vblanks() and need to reimplement its + * functionality. + * + * Returns: + * true if the framebuffer changed. + */ +bool drm_atomic_helper_framebuffer_changed(struct drm_device *dev, + struct drm_atomic_state *old_state, + struct drm_crtc *crtc) { struct drm_plane *plane; struct drm_plane_state *old_plane_state; @@ -967,6 +981,7 @@ static bool framebuffer_changed(struct drm_device *dev,
return false; } +EXPORT_SYMBOL(drm_atomic_helper_framebuffer_changed);
/** * drm_atomic_helper_wait_for_vblanks - wait for vblank on crtcs @@ -1001,7 +1016,8 @@ drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, if (old_state->legacy_cursor_update) continue;
- if (!framebuffer_changed(dev, old_state, crtc)) + if (!drm_atomic_helper_framebuffer_changed(dev, + old_state, crtc)) continue;
ret = drm_crtc_vblank_get(crtc); diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h index a286cce..74fce78 100644 --- a/include/drm/drm_atomic_helper.h +++ b/include/drm/drm_atomic_helper.h @@ -42,6 +42,10 @@ int drm_atomic_helper_commit(struct drm_device *dev, struct drm_atomic_state *state, bool async);
+bool drm_atomic_helper_framebuffer_changed(struct drm_device *dev, + struct drm_atomic_state *old_state, + struct drm_crtc *crtc); + void drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, struct drm_atomic_state *old_state);
On Tue, Jan 19, 2016 at 10:46:58AM +0000, John Keeping wrote:
The Rockchip driver cannot use drm_atomic_helper_wait_for_vblanks() because it has hardware counters for neither vblanks nor scanlines.
In order to simplify re-implementing the functionality for this driver, export the framebuffer_changed() helper so it can be reused.
Signed-off-by: John Keeping john@metanate.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch
Also ack for merging through rockchip git trees. I discussed this with Dave Airlie, he's ok with that. -Daniel
Unchanged since v1.
drivers/gpu/drm/drm_atomic_helper.c | 24 ++++++++++++++++++++---- include/drm/drm_atomic_helper.h | 4 ++++ 2 files changed, 24 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 268d37f..7449293 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -948,9 +948,23 @@ static void wait_for_fences(struct drm_device *dev, } }
-static bool framebuffer_changed(struct drm_device *dev,
struct drm_atomic_state *old_state,struct drm_crtc *crtc)+/**
- drm_atomic_helper_framebuffer_changed - check if framebuffer has changed
- @dev: DRM device
- @old_state: atomic state object with old state structures
- @crtc: DRM crtc
- Checks whether the framebuffer used for this CRTC changes as a result of
- the atomic update. This is useful for drivers which cannot use
- drm_atomic_helper_wait_for_vblanks() and need to reimplement its
- functionality.
- Returns:
- true if the framebuffer changed.
- */
+bool drm_atomic_helper_framebuffer_changed(struct drm_device *dev,
struct drm_atomic_state *old_state,struct drm_crtc *crtc){ struct drm_plane *plane; struct drm_plane_state *old_plane_state; @@ -967,6 +981,7 @@ static bool framebuffer_changed(struct drm_device *dev,
return false; } +EXPORT_SYMBOL(drm_atomic_helper_framebuffer_changed);
/**
- drm_atomic_helper_wait_for_vblanks - wait for vblank on crtcs
@@ -1001,7 +1016,8 @@ drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, if (old_state->legacy_cursor_update) continue;
if (!framebuffer_changed(dev, old_state, crtc))
if (!drm_atomic_helper_framebuffer_changed(dev,old_state, crtc)) continue;ret = drm_crtc_vblank_get(crtc);
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h index a286cce..74fce78 100644 --- a/include/drm/drm_atomic_helper.h +++ b/include/drm/drm_atomic_helper.h @@ -42,6 +42,10 @@ int drm_atomic_helper_commit(struct drm_device *dev, struct drm_atomic_state *state, bool async);
+bool drm_atomic_helper_framebuffer_changed(struct drm_device *dev,
struct drm_atomic_state *old_state,struct drm_crtc *crtc);void drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, struct drm_atomic_state *old_state);
-- 2.7.0.226.gfe986fe
As commented in drm_atomic_helper_wait_for_vblanks(), userspace relies on cursor ioctls being unsynced. Converting the rockchip driver to atomic has significantly impacted cursor performance by making every cursor update wait for vblank.
By skipping the vblank sync when the framebuffer has not changed (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid this for the common case of moving the cursor and only need to delay the cursor ioctl when the cursor icon changes.
We cannot add the check on legacy_cursor_update since that results in the cursor bo being unreferenced while the hardware may still be reading it. Fully supporting unsynced cursor updates is left for the future when the atomic helper framework supports async updates.
Signed-off-by: John Keeping john@metanate.com Tested-by: Heiko Stuebner heiko@sntech.de --- Unchanged since v1.
drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f784488..679d23a 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -178,7 +178,7 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) }
static void -rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) +rockchip_atomic_wait_for_complete(struct drm_device *dev, struct drm_atomic_state *old_state) { struct drm_crtc_state *old_crtc_state; struct drm_crtc *crtc; @@ -194,6 +194,10 @@ rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) if (!crtc->state->active) continue;
+ if (!drm_atomic_helper_framebuffer_changed(dev, + old_state, crtc)) + continue; + ret = drm_crtc_vblank_get(crtc); if (ret != 0) continue; @@ -241,7 +245,7 @@ rockchip_atomic_commit_complete(struct rockchip_atomic_commit *commit)
drm_atomic_helper_commit_planes(dev, state, true);
- rockchip_atomic_wait_for_complete(state); + rockchip_atomic_wait_for_complete(dev, state);
drm_atomic_helper_cleanup_planes(dev, state);
Signed-off-by: John Keeping john@metanate.com --- v2: - Add more detail of the particular race that could happen if we used drm_atomic_helper_wait_for_vblanks().
drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index 679d23a..cf0b7bd 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -177,6 +177,21 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); }
+/* + * We can't use drm_atomic_helper_wait_for_vblanks() because rk3288 and rk3066 + * have hardware counters for neither vblanks nor scanlines, which results in + * a race where: + * | <-- HW vsync irq and reg take effect + * plane_commit --> | + * get_vblank and wait --> | + * | <-- handle_vblank, vblank->count + 1 + * cleanup_fb --> | + * iommu crash --> | + * | <-- HW vsync irq and reg take effect + * + * This function is equivalent but uses rockchip_crtc_wait_for_update() instead + * of waiting for vblank_count to change. + */ static void rockchip_atomic_wait_for_complete(struct drm_device *dev, struct drm_atomic_state *old_state) {
On 2016年01月19日 18:46, John Keeping wrote:
The first two patches are unchanged since v1 but the comment in the third has been expanded following Thierry's comments.
John Keeping (3): drm/atomic-helper: Export framebuffer_changed() drm/rockchip: don't wait for vblank if fb hasn't changed drm/rockchip: explain why we can't wait_for_vblanks
drivers/gpu/drm/drm_atomic_helper.c | 24 ++++++++++++++++++++---- drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 23 +++++++++++++++++++++-- include/drm/drm_atomic_helper.h | 4 ++++ 3 files changed, 45 insertions(+), 6 deletions(-)
Hi John
Thanks for your fix, applied these three patches into my drm-next, :-)
Am Mittwoch, 13. Januar 2016, 12:53:34 schrieb John Keeping:
As commented in drm_atomic_helper_wait_for_vblanks(), userspace relies on cursor ioctls being unsynced. Converting the rockchip driver to atomic has significantly impacted cursor performance by making every cursor update wait for vblank.
By skipping the vblank sync when the framebuffer has not changed (as is done in drm_atomic_helper_wait_for_vblanks()) we can avoid this for the common case of moving the cursor and only need to delay the cursor ioctl when the cursor icon changes.
I originally inserted a check on legacy_cursor_update as well, but that caused a storm of iommu page faults. I didn't investigate the cause of those since this change gives enough of a performance improvement for my use case.
This is RFC because of that and because the framebuffer_changed() function is copied from drm_atomic_helper.c as a quick way to test the result.
Signed-off-by: John Keeping john@metanate.com
I've seen the effects now as well after making the atomic parts work on in my devtree - i.e. sluggish cursor movements.
This patch fixes that issue, so at least: Tested-by: Heiko Stuebner heiko@sntech.de
Right now I still see flickering on animated cursors though (like ones used by KDE), that wasn't present before.
Heiko
dri-devel@lists.freedesktop.org
-
Daniel Vetter -
Heiko Stuebner -
John Keeping -
Mark yao -
Thierry Reding