| Message ID | 20190925193154.20732-1-khilman@kernel.org |
|---|---|
| State | New |
| Headers | show |
| Series | drm/meson: enable runtime PM | expand |
Hi Kevin, On 25/09/2019 21:31, Kevin Hilman wrote: > From: Kevin Hilman <khilman@baylibre.com> > > On some SoCs, the VPU is in a power-domain and needs runtime PM > enabled and used in order to keep the power domain on. > > Signed-off-by: Kevin Hilman <khilman@baylibre.com> > --- > drivers/gpu/drm/meson/meson_drv.c | 4 ++++ > 1 file changed, 4 insertions(+) > > diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c > index 2310c96fff46..256b6a0e9c6b 100644 > --- a/drivers/gpu/drm/meson/meson_drv.c > +++ b/drivers/gpu/drm/meson/meson_drv.c > @@ -14,6 +14,7 @@ > #include <linux/platform_device.h> > #include <linux/component.h> > #include <linux/of_graph.h> > +#include <linux/pm_runtime.h> > > #include <drm/drmP.h> > #include <drm/drm_atomic.h> > @@ -274,6 +275,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) > > /* Hardware Initialization */ > > + pm_runtime_get_sync(dev); > meson_vpu_init(priv); > meson_venc_init(priv); > meson_vpp_init(priv); > @@ -416,6 +418,7 @@ static int meson_drv_probe(struct platform_device *pdev) > struct device_node *ep, *remote; > int count = 0; > > + pm_runtime_enable(&pdev->dev); > for_each_endpoint_of_node(np, ep) { > remote = of_graph_get_remote_port_parent(ep); > if (!remote || !of_device_is_available(remote)) { > @@ -440,6 +443,7 @@ static int meson_drv_probe(struct platform_device *pdev) > } > > /* If no output endpoints were available, simply bail out */ > + pm_runtime_disable(&pdev->dev); > return 0; > }; > > I'll rather implement true runtime PM instead, Neil
Neil Armstrong <narmstrong@baylibre.com> writes: > Hi Kevin, > > On 25/09/2019 21:31, Kevin Hilman wrote: >> From: Kevin Hilman <khilman@baylibre.com> >> >> On some SoCs, the VPU is in a power-domain and needs runtime PM >> enabled and used in order to keep the power domain on. >> >> Signed-off-by: Kevin Hilman <khilman@baylibre.com> >> --- >> drivers/gpu/drm/meson/meson_drv.c | 4 ++++ >> 1 file changed, 4 insertions(+) >> >> diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c >> index 2310c96fff46..256b6a0e9c6b 100644 >> --- a/drivers/gpu/drm/meson/meson_drv.c >> +++ b/drivers/gpu/drm/meson/meson_drv.c >> @@ -14,6 +14,7 @@ >> #include <linux/platform_device.h> >> #include <linux/component.h> >> #include <linux/of_graph.h> >> +#include <linux/pm_runtime.h> >> >> #include <drm/drmP.h> >> #include <drm/drm_atomic.h> >> @@ -274,6 +275,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) >> >> /* Hardware Initialization */ >> >> + pm_runtime_get_sync(dev); >> meson_vpu_init(priv); >> meson_venc_init(priv); >> meson_vpp_init(priv); >> @@ -416,6 +418,7 @@ static int meson_drv_probe(struct platform_device *pdev) >> struct device_node *ep, *remote; >> int count = 0; >> >> + pm_runtime_enable(&pdev->dev); >> for_each_endpoint_of_node(np, ep) { >> remote = of_graph_get_remote_port_parent(ep); >> if (!remote || !of_device_is_available(remote)) { >> @@ -440,6 +443,7 @@ static int meson_drv_probe(struct platform_device *pdev) >> } >> >> /* If no output endpoints were available, simply bail out */ >> + pm_runtime_disable(&pdev->dev); >> return 0; >> }; >> >> > > I'll rather implement true runtime PM instead, While this is a minimum implementation, can you explain what you mean by "true" runtime PM? Kevin
On 30/09/2019 17:34, Kevin Hilman wrote: > Neil Armstrong <narmstrong@baylibre.com> writes: > >> Hi Kevin, >> >> On 25/09/2019 21:31, Kevin Hilman wrote: >>> From: Kevin Hilman <khilman@baylibre.com> >>> >>> On some SoCs, the VPU is in a power-domain and needs runtime PM >>> enabled and used in order to keep the power domain on. >>> >>> Signed-off-by: Kevin Hilman <khilman@baylibre.com> >>> --- >>> drivers/gpu/drm/meson/meson_drv.c | 4 ++++ >>> 1 file changed, 4 insertions(+) >>> >>> diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c >>> index 2310c96fff46..256b6a0e9c6b 100644 >>> --- a/drivers/gpu/drm/meson/meson_drv.c >>> +++ b/drivers/gpu/drm/meson/meson_drv.c >>> @@ -14,6 +14,7 @@ >>> #include <linux/platform_device.h> >>> #include <linux/component.h> >>> #include <linux/of_graph.h> >>> +#include <linux/pm_runtime.h> >>> >>> #include <drm/drmP.h> >>> #include <drm/drm_atomic.h> >>> @@ -274,6 +275,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) >>> >>> /* Hardware Initialization */ >>> >>> + pm_runtime_get_sync(dev); >>> meson_vpu_init(priv); >>> meson_venc_init(priv); >>> meson_vpp_init(priv); >>> @@ -416,6 +418,7 @@ static int meson_drv_probe(struct platform_device *pdev) >>> struct device_node *ep, *remote; >>> int count = 0; >>> >>> + pm_runtime_enable(&pdev->dev); >>> for_each_endpoint_of_node(np, ep) { >>> remote = of_graph_get_remote_port_parent(ep); >>> if (!remote || !of_device_is_available(remote)) { >>> @@ -440,6 +443,7 @@ static int meson_drv_probe(struct platform_device *pdev) >>> } >>> >>> /* If no output endpoints were available, simply bail out */ >>> + pm_runtime_disable(&pdev->dev); >>> return 0; >>> }; >>> >>> >> >> I'll rather implement true runtime PM instead, > > While this is a minimum implementation, can you explain what you mean by > "true" runtime PM? Implementing runtime_sync()/_put when the display is used/unused. ARM did a good job in their malidp driver. Neil > > Kevin >
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 2310c96fff46..256b6a0e9c6b 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -14,6 +14,7 @@ #include <linux/platform_device.h> #include <linux/component.h> #include <linux/of_graph.h> +#include <linux/pm_runtime.h> #include <drm/drmP.h> #include <drm/drm_atomic.h> @@ -274,6 +275,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) /* Hardware Initialization */ + pm_runtime_get_sync(dev); meson_vpu_init(priv); meson_venc_init(priv); meson_vpp_init(priv); @@ -416,6 +418,7 @@ static int meson_drv_probe(struct platform_device *pdev) struct device_node *ep, *remote; int count = 0; + pm_runtime_enable(&pdev->dev); for_each_endpoint_of_node(np, ep) { remote = of_graph_get_remote_port_parent(ep); if (!remote || !of_device_is_available(remote)) { @@ -440,6 +443,7 @@ static int meson_drv_probe(struct platform_device *pdev) } /* If no output endpoints were available, simply bail out */ + pm_runtime_disable(&pdev->dev); return 0; };