On Rockchip rk3288-based Chromebooks when you do a suspend/resume
cycle:
1. You lose the ability to detect an HDMI device being plugged in.
2. If you're using the i2c bus built in to dw_hdmi then it stops
working.
Let's call the core dw-hdmi's suspend/resume functions to restore
things.
NOTE: in downstream Chrome OS (based on kernel 3.14) we used the
"late/early" versions of suspend/resume because we found that the VOP
was sometimes resuming before dw_hdmi and then calling into us before
we were fully resumed. For now I have gone back to the normal
suspend/resume because I can't reproduce the problems.
Signed-off-by: Douglas Anderson <[email protected]>
---
Changes in v3:
- dw_hdmi_resume() is now a void function (Laurent)
Changes in v2:
- Add forgotten static (Laurent)
- No empty stub for suspend (Laurent)
drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
index 4cdc9f86c2e5..7bb0f922b303 100644
--- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
@@ -542,11 +542,25 @@ static int dw_hdmi_rockchip_remove(struct platform_device *pdev)
return 0;
}
+static int __maybe_unused dw_hdmi_rockchip_resume(struct device *dev)
+{
+ struct rockchip_hdmi *hdmi = dev_get_drvdata(dev);
+
+ dw_hdmi_resume(hdmi->hdmi);
+
+ return 0;
+}
+
+static const struct dev_pm_ops dw_hdmi_rockchip_pm = {
+ SET_SYSTEM_SLEEP_PM_OPS(NULL, dw_hdmi_rockchip_resume)
+};
+
struct platform_driver dw_hdmi_rockchip_pltfm_driver = {
.probe = dw_hdmi_rockchip_probe,
.remove = dw_hdmi_rockchip_remove,
.driver = {
.name = "dwhdmi-rockchip",
+ .pm = &dw_hdmi_rockchip_pm,
.of_match_table = dw_hdmi_rockchip_dt_ids,
},
};
--
2.22.0.rc1.311.g5d7573a151-goog
On Tue, Jun 04, 2019 at 01:42:07PM -0700, Douglas Anderson wrote:
> On Rockchip rk3288-based Chromebooks when you do a suspend/resume
> cycle:
>
> 1. You lose the ability to detect an HDMI device being plugged in.
>
> 2. If you're using the i2c bus built in to dw_hdmi then it stops
> working.
>
> Let's call the core dw-hdmi's suspend/resume functions to restore
> things.
>
> NOTE: in downstream Chrome OS (based on kernel 3.14) we used the
> "late/early" versions of suspend/resume because we found that the VOP
> was sometimes resuming before dw_hdmi and then calling into us before
> we were fully resumed. For now I have gone back to the normal
> suspend/resume because I can't reproduce the problems.
>
> Signed-off-by: Douglas Anderson <[email protected]>
> ---
>
> Changes in v3:
> - dw_hdmi_resume() is now a void function (Laurent)
>
> Changes in v2:
> - Add forgotten static (Laurent)
> - No empty stub for suspend (Laurent)
>
> drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c | 14 ++++++++++++++
> 1 file changed, 14 insertions(+)
>
> diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
> index 4cdc9f86c2e5..7bb0f922b303 100644
> --- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
> +++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
> @@ -542,11 +542,25 @@ static int dw_hdmi_rockchip_remove(struct platform_device *pdev)
> return 0;
> }
>
> +static int __maybe_unused dw_hdmi_rockchip_resume(struct device *dev)
> +{
> + struct rockchip_hdmi *hdmi = dev_get_drvdata(dev);
> +
> + dw_hdmi_resume(hdmi->hdmi);
The rockchip driver is already using the atomic suspend/resume helpers (via the
modeset helpers). Would you be able to accomplish the same thing by just moving
this call into the encoder enable callback?
.enable is called on resume via the atomic commit framework, so everything is
ordered properly. Of course, this would reset the dw_hdmi bridge on each enable,
but I don't think that would be a problem?
Sean
> +
> + return 0;
> +}
> +
> +static const struct dev_pm_ops dw_hdmi_rockchip_pm = {
> + SET_SYSTEM_SLEEP_PM_OPS(NULL, dw_hdmi_rockchip_resume)
> +};
> +
> struct platform_driver dw_hdmi_rockchip_pltfm_driver = {
> .probe = dw_hdmi_rockchip_probe,
> .remove = dw_hdmi_rockchip_remove,
> .driver = {
> .name = "dwhdmi-rockchip",
> + .pm = &dw_hdmi_rockchip_pm,
> .of_match_table = dw_hdmi_rockchip_dt_ids,
> },
> };
> --
> 2.22.0.rc1.311.g5d7573a151-goog
>
--
Sean Paul, Software Engineer, Google / Chromium OS
Hi,
On Thu, Jun 6, 2019 at 9:42 AM Sean Paul <[email protected]> wrote:
>
> On Tue, Jun 04, 2019 at 01:42:07PM -0700, Douglas Anderson wrote:
> > On Rockchip rk3288-based Chromebooks when you do a suspend/resume
> > cycle:
> >
> > 1. You lose the ability to detect an HDMI device being plugged in.
> >
> > 2. If you're using the i2c bus built in to dw_hdmi then it stops
> > working.
> >
> > Let's call the core dw-hdmi's suspend/resume functions to restore
> > things.
> >
> > NOTE: in downstream Chrome OS (based on kernel 3.14) we used the
> > "late/early" versions of suspend/resume because we found that the VOP
> > was sometimes resuming before dw_hdmi and then calling into us before
> > we were fully resumed. For now I have gone back to the normal
> > suspend/resume because I can't reproduce the problems.
> >
> > Signed-off-by: Douglas Anderson <[email protected]>
> > ---
> >
> > Changes in v3:
> > - dw_hdmi_resume() is now a void function (Laurent)
> >
> > Changes in v2:
> > - Add forgotten static (Laurent)
> > - No empty stub for suspend (Laurent)
> >
> > drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c | 14 ++++++++++++++
> > 1 file changed, 14 insertions(+)
> >
> > diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
> > index 4cdc9f86c2e5..7bb0f922b303 100644
> > --- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
> > +++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
> > @@ -542,11 +542,25 @@ static int dw_hdmi_rockchip_remove(struct platform_device *pdev)
> > return 0;
> > }
> >
> > +static int __maybe_unused dw_hdmi_rockchip_resume(struct device *dev)
> > +{
> > + struct rockchip_hdmi *hdmi = dev_get_drvdata(dev);
> > +
> > + dw_hdmi_resume(hdmi->hdmi);
>
> The rockchip driver is already using the atomic suspend/resume helpers (via the
> modeset helpers). Would you be able to accomplish the same thing by just moving
> this call into the encoder enable callback?
>
> .enable is called on resume via the atomic commit framework, so everything is
> ordered properly. Of course, this would reset the dw_hdmi bridge on each enable,
> but I don't think that would be a problem?
I tried and it sorta kinda half worked, but...
1. One of the problems solved by this patch is making "hot plug
detect" work after suspend / resume. AKA: if you have nothing plugged
in to the HDMI port and then suspend/resume you need to be able to
detect when something is plugged in. When nothing is plugged in then
the ".enable" isn't called at resume time.
2. I'm not so convinced about the whole ordering being correct.
Unfortunately on my system (Chrome OS running the chromeos-4.19
kernel) we end up getting an i2c transfer before the ".enable" is
called. I put a dump_stack() in the i2c transfer:
[ 42.212516] CPU: 0 PID: 1479 Comm: DrmThread Tainted: G C
4.19.47 #60
[ 42.221182] Hardware name: Rockchip (Device Tree)
[ 42.226449] [<c0211a64>] (unwind_backtrace) from [<c020cf0c>]
(show_stack+0x20/0x24)
[ 42.235114] [<c020cf0c>] (show_stack) from [<c0a1b8d4>]
(dump_stack+0x84/0xa4)
[ 42.243195] [<c0a1b8d4>] (dump_stack) from [<c067d7c4>]
(dw_hdmi_i2c_wait+0x6c/0xa8)
[ 42.251858] [<c067d7c4>] (dw_hdmi_i2c_wait) from [<c067d9a8>]
(dw_hdmi_i2c_xfer+0x1a8/0x30c)
[ 42.261298] [<c067d9a8>] (dw_hdmi_i2c_xfer) from [<c0798704>]
(__i2c_transfer+0x3a8/0x5d8)
[ 42.270543] [<c0798704>] (__i2c_transfer) from [<c07989c8>]
(i2c_transfer+0x94/0xc4)
[ 42.279204] [<c07989c8>] (i2c_transfer) from [<c064e6b0>]
(drm_do_probe_ddc_edid+0xbc/0x11c)
[ 42.288642] [<c064e6b0>] (drm_do_probe_ddc_edid) from [<c064e744>]
(drm_probe_ddc+0x34/0x5c)
[ 42.298081] [<c064e744>] (drm_probe_ddc) from [<c0651b98>]
(drm_get_edid+0x60/0x2e0)
[ 42.306743] [<c0651b98>] (drm_get_edid) from [<c067d710>]
(dw_hdmi_connector_get_modes+0x30/0x78)
[ 42.316669] [<c067d710>] (dw_hdmi_connector_get_modes) from
[<c0634f38>] (drm_helper_probe_single_connector_modes+0x218/0x5c0)
[ 42.329413] [<c0634f38>] (drm_helper_probe_single_connector_modes)
from [<c065b38c>] (drm_mode_getconnector+0x144/0x418)
[ 42.341573] [<c065b38c>] (drm_mode_getconnector) from [<c0646844>]
(drm_ioctl_kernel+0xa0/0xf0)
[ 42.351303] [<c0646844>] (drm_ioctl_kernel) from [<c0646d34>]
(drm_ioctl+0x32c/0x3c0)
[ 42.360063] [<c0646d34>] (drm_ioctl) from [<c03ed0cc>] (vfs_ioctl+0x28/0x44)
[ 42.367946] [<c03ed0cc>] (vfs_ioctl) from [<c03edee8>]
(do_vfs_ioctl+0x718/0x8b0)
[ 42.376315] [<c03edee8>] (do_vfs_ioctl) from [<c03ee0dc>]
(ksys_ioctl+0x5c/0x84)
[ 42.384587] [<c03ee0dc>] (ksys_ioctl) from [<c03ee11c>] (sys_ioctl+0x18/0x1c)
[ 42.392570] [<c03ee11c>] (sys_ioctl) from [<c02011d4>]
(__sys_trace_return+0x0/0x10)
...I see several transfers fail and then finally a few seconds later
finally see the .enable call:
[ 44.021501] DOUG: dw_hdmi_rockchip_encoder_enable start
[ 44.027792] DOUG: dw_hdmi_rockchip_encoder_enable end
I can gather more info if it's useful.
===
...any chance we can keep the patch as-is, or do you have ideas of how
to solve the above problems?
Thanks!
-Doug
On Thu, Jun 06, 2019 at 03:58:21PM -0700, Doug Anderson wrote:
> Hi,
>
> On Thu, Jun 6, 2019 at 9:42 AM Sean Paul <[email protected]> wrote:
> >
> > On Tue, Jun 04, 2019 at 01:42:07PM -0700, Douglas Anderson wrote:
> > > On Rockchip rk3288-based Chromebooks when you do a suspend/resume
> > > cycle:
> > >
> > > 1. You lose the ability to detect an HDMI device being plugged in.
> > >
> > > 2. If you're using the i2c bus built in to dw_hdmi then it stops
> > > working.
> > >
> > > Let's call the core dw-hdmi's suspend/resume functions to restore
> > > things.
> > >
> > > NOTE: in downstream Chrome OS (based on kernel 3.14) we used the
> > > "late/early" versions of suspend/resume because we found that the VOP
> > > was sometimes resuming before dw_hdmi and then calling into us before
> > > we were fully resumed. For now I have gone back to the normal
> > > suspend/resume because I can't reproduce the problems.
> > >
> > > Signed-off-by: Douglas Anderson <[email protected]>
> > > ---
> > >
> > > Changes in v3:
> > > - dw_hdmi_resume() is now a void function (Laurent)
> > >
> > > Changes in v2:
> > > - Add forgotten static (Laurent)
> > > - No empty stub for suspend (Laurent)
> > >
> > > drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c | 14 ++++++++++++++
> > > 1 file changed, 14 insertions(+)
> > >
> > > diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
> > > index 4cdc9f86c2e5..7bb0f922b303 100644
> > > --- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
> > > +++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
> > > @@ -542,11 +542,25 @@ static int dw_hdmi_rockchip_remove(struct platform_device *pdev)
> > > return 0;
> > > }
> > >
> > > +static int __maybe_unused dw_hdmi_rockchip_resume(struct device *dev)
> > > +{
> > > + struct rockchip_hdmi *hdmi = dev_get_drvdata(dev);
> > > +
> > > + dw_hdmi_resume(hdmi->hdmi);
> >
> > The rockchip driver is already using the atomic suspend/resume helpers (via the
> > modeset helpers). Would you be able to accomplish the same thing by just moving
> > this call into the encoder enable callback?
> >
> > .enable is called on resume via the atomic commit framework, so everything is
> > ordered properly. Of course, this would reset the dw_hdmi bridge on each enable,
> > but I don't think that would be a problem?
>
> I tried and it sorta kinda half worked, but...
>
> 1. One of the problems solved by this patch is making "hot plug
> detect" work after suspend / resume. AKA: if you have nothing plugged
> in to the HDMI port and then suspend/resume you need to be able to
> detect when something is plugged in. When nothing is plugged in then
> the ".enable" isn't called at resume time.
>
Ahh, ok. So we've hit this with other bridges/dongles as well, and yeah the
solution is to keep the bridge powered up enough to detect hotplug, so you would
need to do some work in .resume
Usually there's a second stage of enable where you power things on more fully
and that is done in .enable
> 2. I'm not so convinced about the whole ordering being correct.
> Unfortunately on my system (Chrome OS running the chromeos-4.19
> kernel) we end up getting an i2c transfer before the ".enable" is
> called. I put a dump_stack() in the i2c transfer:
>
> [ 42.212516] CPU: 0 PID: 1479 Comm: DrmThread Tainted: G C
> 4.19.47 #60
> [ 42.221182] Hardware name: Rockchip (Device Tree)
> [ 42.226449] [<c0211a64>] (unwind_backtrace) from [<c020cf0c>]
> (show_stack+0x20/0x24)
> [ 42.235114] [<c020cf0c>] (show_stack) from [<c0a1b8d4>]
> (dump_stack+0x84/0xa4)
> [ 42.243195] [<c0a1b8d4>] (dump_stack) from [<c067d7c4>]
> (dw_hdmi_i2c_wait+0x6c/0xa8)
> [ 42.251858] [<c067d7c4>] (dw_hdmi_i2c_wait) from [<c067d9a8>]
> (dw_hdmi_i2c_xfer+0x1a8/0x30c)
> [ 42.261298] [<c067d9a8>] (dw_hdmi_i2c_xfer) from [<c0798704>]
> (__i2c_transfer+0x3a8/0x5d8)
> [ 42.270543] [<c0798704>] (__i2c_transfer) from [<c07989c8>]
> (i2c_transfer+0x94/0xc4)
> [ 42.279204] [<c07989c8>] (i2c_transfer) from [<c064e6b0>]
> (drm_do_probe_ddc_edid+0xbc/0x11c)
> [ 42.288642] [<c064e6b0>] (drm_do_probe_ddc_edid) from [<c064e744>]
> (drm_probe_ddc+0x34/0x5c)
> [ 42.298081] [<c064e744>] (drm_probe_ddc) from [<c0651b98>]
> (drm_get_edid+0x60/0x2e0)
> [ 42.306743] [<c0651b98>] (drm_get_edid) from [<c067d710>]
> (dw_hdmi_connector_get_modes+0x30/0x78)
> [ 42.316669] [<c067d710>] (dw_hdmi_connector_get_modes) from
> [<c0634f38>] (drm_helper_probe_single_connector_modes+0x218/0x5c0)
> [ 42.329413] [<c0634f38>] (drm_helper_probe_single_connector_modes)
> from [<c065b38c>] (drm_mode_getconnector+0x144/0x418)
> [ 42.341573] [<c065b38c>] (drm_mode_getconnector) from [<c0646844>]
> (drm_ioctl_kernel+0xa0/0xf0)
> [ 42.351303] [<c0646844>] (drm_ioctl_kernel) from [<c0646d34>]
> (drm_ioctl+0x32c/0x3c0)
> [ 42.360063] [<c0646d34>] (drm_ioctl) from [<c03ed0cc>] (vfs_ioctl+0x28/0x44)
> [ 42.367946] [<c03ed0cc>] (vfs_ioctl) from [<c03edee8>]
> (do_vfs_ioctl+0x718/0x8b0)
> [ 42.376315] [<c03edee8>] (do_vfs_ioctl) from [<c03ee0dc>]
> (ksys_ioctl+0x5c/0x84)
> [ 42.384587] [<c03ee0dc>] (ksys_ioctl) from [<c03ee11c>] (sys_ioctl+0x18/0x1c)
> [ 42.392570] [<c03ee11c>] (sys_ioctl) from [<c02011d4>]
> (__sys_trace_return+0x0/0x10)
>
> ...I see several transfers fail and then finally a few seconds later
> finally see the .enable call:
This is usually solved by wrapping the code in detect() with an enable/disable
pair to turn on enough circuitry to do the i2c writes for edid read.
>
> [ 44.021501] DOUG: dw_hdmi_rockchip_encoder_enable start
> [ 44.027792] DOUG: dw_hdmi_rockchip_encoder_enable end
>
> I can gather more info if it's useful.
>
> ===
>
> ...any chance we can keep the patch as-is, or do you have ideas of how
> to solve the above problems?
Yeah, given the context I think this is Ok to apply as-is. Maybe we could
shave out some of the work done in resume and move it to a helper called in
enable/detect, but I don't think it's necessary to hold up getting things
working.
Thanks for the detailed explanation (as always :)
Reviewed-by: Sean Paul <[email protected]>
>
>
> Thanks!
>
> -Doug
--
Sean Paul, Software Engineer, Google / Chromium OS
> [ 42.351303] [<c0646844>] (drm_ioctl_kernel) from [<c0646d34>]
> (drm_ioctl+0x32c/0x3c0)
> [ 42.360063] [<c0646d34>] (drm_ioctl) from [<c03ed0cc>] (vfs_ioctl+0x28/0x44)
> [ 42.367946] [<c03ed0cc>] (vfs_ioctl) from [<c03edee8>]
> (do_vfs_ioctl+0x718/0x8b0)
> [ 42.376315] [<c03edee8>] (do_vfs_ioctl) from [<c03ee0dc>]
> (ksys_ioctl+0x5c/0x84)
> [ 42.384587] [<c03ee0dc>] (ksys_ioctl) from [<c03ee11c>] (sys_ioctl+0x18/0x1c)
> [ 42.392570] [<c03ee11c>] (sys_ioctl) from [<c02011d4>]
> (__sys_trace_return+0x0/0x10)
>
> ...I see several transfers fail and then finally a few seconds later
> finally see the .enable call:
>
> [ 44.021501] DOUG: dw_hdmi_rockchip_encoder_enable start
> [ 44.027792] DOUG: dw_hdmi_rockchip_encoder_enable end
>
> I can gather more info if it's useful.
>
> ===
>
> ...any chance we can keep the patch as-is, or do you have ideas of how
> to solve the above problems?
>
>
> Thanks!
>
> -Doug
--
Sean Paul, Software Engineer, Google / Chromium OS
On Fri, Jun 07, 2019 at 02:06:03PM -0400, Sean Paul wrote:
> On Thu, Jun 06, 2019 at 03:58:21PM -0700, Doug Anderson wrote:
> > Hi,
> >
> > On Thu, Jun 6, 2019 at 9:42 AM Sean Paul <[email protected]> wrote:
> > >
> > > On Tue, Jun 04, 2019 at 01:42:07PM -0700, Douglas Anderson wrote:
> > > > On Rockchip rk3288-based Chromebooks when you do a suspend/resume
> > > > cycle:
> > > >
> > > > 1. You lose the ability to detect an HDMI device being plugged in.
> > > >
> > > > 2. If you're using the i2c bus built in to dw_hdmi then it stops
> > > > working.
> > > >
> > > > Let's call the core dw-hdmi's suspend/resume functions to restore
> > > > things.
> > > >
> > > > NOTE: in downstream Chrome OS (based on kernel 3.14) we used the
> > > > "late/early" versions of suspend/resume because we found that the VOP
> > > > was sometimes resuming before dw_hdmi and then calling into us before
> > > > we were fully resumed. For now I have gone back to the normal
> > > > suspend/resume because I can't reproduce the problems.
> > > >
> > > > Signed-off-by: Douglas Anderson <[email protected]>
> > > > ---
> > > >
> > > > Changes in v3:
> > > > - dw_hdmi_resume() is now a void function (Laurent)
> > > >
> > > > Changes in v2:
> > > > - Add forgotten static (Laurent)
> > > > - No empty stub for suspend (Laurent)
> > > >
> > > > drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c | 14 ++++++++++++++
> > > > 1 file changed, 14 insertions(+)
> > > >
> > > > diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
> > > > index 4cdc9f86c2e5..7bb0f922b303 100644
> > > > --- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
> > > > +++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
> > > > @@ -542,11 +542,25 @@ static int dw_hdmi_rockchip_remove(struct platform_device *pdev)
> > > > return 0;
> > > > }
> > > >
> > > > +static int __maybe_unused dw_hdmi_rockchip_resume(struct device *dev)
> > > > +{
> > > > + struct rockchip_hdmi *hdmi = dev_get_drvdata(dev);
> > > > +
> > > > + dw_hdmi_resume(hdmi->hdmi);
> > >
> > > The rockchip driver is already using the atomic suspend/resume helpers (via the
> > > modeset helpers). Would you be able to accomplish the same thing by just moving
> > > this call into the encoder enable callback?
> > >
> > > .enable is called on resume via the atomic commit framework, so everything is
> > > ordered properly. Of course, this would reset the dw_hdmi bridge on each enable,
> > > but I don't think that would be a problem?
> >
> > I tried and it sorta kinda half worked, but...
> >
> > 1. One of the problems solved by this patch is making "hot plug
> > detect" work after suspend / resume. AKA: if you have nothing plugged
> > in to the HDMI port and then suspend/resume you need to be able to
> > detect when something is plugged in. When nothing is plugged in then
> > the ".enable" isn't called at resume time.
> >
>
> Ahh, ok. So we've hit this with other bridges/dongles as well, and yeah the
> solution is to keep the bridge powered up enough to detect hotplug, so you would
> need to do some work in .resume
>
> Usually there's a second stage of enable where you power things on more fully
> and that is done in .enable
>
> > 2. I'm not so convinced about the whole ordering being correct.
> > Unfortunately on my system (Chrome OS running the chromeos-4.19
> > kernel) we end up getting an i2c transfer before the ".enable" is
> > called. I put a dump_stack() in the i2c transfer:
> >
> > [ 42.212516] CPU: 0 PID: 1479 Comm: DrmThread Tainted: G C
> > 4.19.47 #60
> > [ 42.221182] Hardware name: Rockchip (Device Tree)
> > [ 42.226449] [<c0211a64>] (unwind_backtrace) from [<c020cf0c>]
> > (show_stack+0x20/0x24)
> > [ 42.235114] [<c020cf0c>] (show_stack) from [<c0a1b8d4>]
> > (dump_stack+0x84/0xa4)
> > [ 42.243195] [<c0a1b8d4>] (dump_stack) from [<c067d7c4>]
> > (dw_hdmi_i2c_wait+0x6c/0xa8)
> > [ 42.251858] [<c067d7c4>] (dw_hdmi_i2c_wait) from [<c067d9a8>]
> > (dw_hdmi_i2c_xfer+0x1a8/0x30c)
> > [ 42.261298] [<c067d9a8>] (dw_hdmi_i2c_xfer) from [<c0798704>]
> > (__i2c_transfer+0x3a8/0x5d8)
> > [ 42.270543] [<c0798704>] (__i2c_transfer) from [<c07989c8>]
> > (i2c_transfer+0x94/0xc4)
> > [ 42.279204] [<c07989c8>] (i2c_transfer) from [<c064e6b0>]
> > (drm_do_probe_ddc_edid+0xbc/0x11c)
> > [ 42.288642] [<c064e6b0>] (drm_do_probe_ddc_edid) from [<c064e744>]
> > (drm_probe_ddc+0x34/0x5c)
> > [ 42.298081] [<c064e744>] (drm_probe_ddc) from [<c0651b98>]
> > (drm_get_edid+0x60/0x2e0)
> > [ 42.306743] [<c0651b98>] (drm_get_edid) from [<c067d710>]
> > (dw_hdmi_connector_get_modes+0x30/0x78)
> > [ 42.316669] [<c067d710>] (dw_hdmi_connector_get_modes) from
> > [<c0634f38>] (drm_helper_probe_single_connector_modes+0x218/0x5c0)
> > [ 42.329413] [<c0634f38>] (drm_helper_probe_single_connector_modes)
> > from [<c065b38c>] (drm_mode_getconnector+0x144/0x418)
> > [ 42.341573] [<c065b38c>] (drm_mode_getconnector) from [<c0646844>]
> > (drm_ioctl_kernel+0xa0/0xf0)
> > [ 42.351303] [<c0646844>] (drm_ioctl_kernel) from [<c0646d34>]
> > (drm_ioctl+0x32c/0x3c0)
> > [ 42.360063] [<c0646d34>] (drm_ioctl) from [<c03ed0cc>] (vfs_ioctl+0x28/0x44)
> > [ 42.367946] [<c03ed0cc>] (vfs_ioctl) from [<c03edee8>]
> > (do_vfs_ioctl+0x718/0x8b0)
> > [ 42.376315] [<c03edee8>] (do_vfs_ioctl) from [<c03ee0dc>]
> > (ksys_ioctl+0x5c/0x84)
> > [ 42.384587] [<c03ee0dc>] (ksys_ioctl) from [<c03ee11c>] (sys_ioctl+0x18/0x1c)
> > [ 42.392570] [<c03ee11c>] (sys_ioctl) from [<c02011d4>]
> > (__sys_trace_return+0x0/0x10)
> >
> > ...I see several transfers fail and then finally a few seconds later
> > finally see the .enable call:
>
> This is usually solved by wrapping the code in detect() with an enable/disable
> pair to turn on enough circuitry to do the i2c writes for edid read.
>
> >
> > [ 44.021501] DOUG: dw_hdmi_rockchip_encoder_enable start
> > [ 44.027792] DOUG: dw_hdmi_rockchip_encoder_enable end
> >
> > I can gather more info if it's useful.
> >
> > ===
> >
> > ...any chance we can keep the patch as-is, or do you have ideas of how
> > to solve the above problems?
>
> Yeah, given the context I think this is Ok to apply as-is. Maybe we could
> shave out some of the work done in resume and move it to a helper called in
> enable/detect, but I don't think it's necessary to hold up getting things
> working.
>
> Thanks for the detailed explanation (as always :)
>
> Reviewed-by: Sean Paul <[email protected]>
Applied both patches to drm-misc-next, thank you!
Sean
>
>
> >
> >
> > Thanks!
> >
> > -Doug
>
> --
> Sean Paul, Software Engineer, Google / Chromium OS
> > [ 42.351303] [<c0646844>] (drm_ioctl_kernel) from [<c0646d34>]
> > (drm_ioctl+0x32c/0x3c0)
> > [ 42.360063] [<c0646d34>] (drm_ioctl) from [<c03ed0cc>] (vfs_ioctl+0x28/0x44)
> > [ 42.367946] [<c03ed0cc>] (vfs_ioctl) from [<c03edee8>]
> > (do_vfs_ioctl+0x718/0x8b0)
> > [ 42.376315] [<c03edee8>] (do_vfs_ioctl) from [<c03ee0dc>]
> > (ksys_ioctl+0x5c/0x84)
> > [ 42.384587] [<c03ee0dc>] (ksys_ioctl) from [<c03ee11c>] (sys_ioctl+0x18/0x1c)
> > [ 42.392570] [<c03ee11c>] (sys_ioctl) from [<c02011d4>]
> > (__sys_trace_return+0x0/0x10)
> >
> > ...I see several transfers fail and then finally a few seconds later
> > finally see the .enable call:
> >
> > [ 44.021501] DOUG: dw_hdmi_rockchip_encoder_enable start
> > [ 44.027792] DOUG: dw_hdmi_rockchip_encoder_enable end
> >
> > I can gather more info if it's useful.
> >
> > ===
> >
> > ...any chance we can keep the patch as-is, or do you have ideas of how
> > to solve the above problems?
> >
> >
> > Thanks!
> >
> > -Doug
>
> --
> Sean Paul, Software Engineer, Google / Chromium OS
--
Sean Paul, Software Engineer, Google / Chromium OS