| Message ID | 20180214130059.19052-1-linus.walleij@linaro.org |
|---|---|
| State | New |
| Headers | show |
| Series | drm/bridge: sii902x: Fall back to standard modes | expand |
Hm, hard to get review feedback on this one. It gives me proper video on an ARM Versatile Express utilizing the bridge driver with a plugged in DVI-to-VGA dongle with the new PL111 DRI driver. Liviu? Pawel? Some ACK is fine to know I am doing the right thing :) Yours, Linus Walleij On Wed, Feb 14, 2018 at 2:00 PM, Linus Walleij <linus.walleij@linaro.org> wrote: > The following happens when connection a DVI output driven > from the SiI9022 using a DVI-to-VGA adapter plug: > > i2c i2c-0: sendbytes: NAK bailout. > i2c i2c-0: sendbytes: NAK bailout. > > Then no picture. Apparently the I2C engine inside the SiI9022 > is not smart enough to try to fall back to DDC I2C. Or the > vendor have not integrated the electronics properly. I don't > know which one it is. > > By using standard modes as fallback, the bridge probes nicely > with a minor warning and we get picture. > > This code is inspired by similar code in the dumb VGA bridge. > > Signed-off-by: Linus Walleij <linus.walleij@linaro.org> > --- > drivers/gpu/drm/bridge/sii902x.c | 15 +++++++++++++-- > 1 file changed, 13 insertions(+), 2 deletions(-) > > diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c > index b1ab4ab09532..4483095c4013 100644 > --- a/drivers/gpu/drm/bridge/sii902x.c > +++ b/drivers/gpu/drm/bridge/sii902x.c > @@ -168,8 +168,19 @@ static int sii902x_get_modes(struct drm_connector *connector) > return ret; > > edid = drm_get_edid(connector, sii902x->i2c->adapter); > - drm_mode_connector_update_edid_property(connector, edid); > - if (edid) { > + if (!edid) { > + /* > + * This happens when using a simple DVI-to-VGA converter > + * dongle for example: the I2C lines are not bridged over > + * to VGA DDC. > + */ > + DRM_INFO("EDID readout failed, falling back to standard modes\n"); > + ret = drm_add_modes_noedid(connector, 1920, 1080); > + /* Set some standard resolution most monitors can handle */ > + drm_set_preferred_mode(connector, 1024, 768); > + } else { > + /* Data from EDID readout */ > + drm_mode_connector_update_edid_property(connector, edid); > num = drm_add_edid_modes(connector, edid); > kfree(edid); > } > -- > 2.14.3 >
On Thu, Mar 01, 2018 at 10:02:55PM +0100, Linus Walleij wrote: > Hm, hard to get review feedback on this one. > > It gives me proper video on an ARM Versatile Express utilizing the > bridge driver with a plugged in DVI-to-VGA dongle with the new > PL111 DRI driver. > > Liviu? Pawel? > > Some ACK is fine to know I am doing the right thing :) Why isn't the probe helper's noedid fallback working? > > Yours, > Linus Walleij > > On Wed, Feb 14, 2018 at 2:00 PM, Linus Walleij <linus.walleij@linaro.org> wrote: > > The following happens when connection a DVI output driven > > from the SiI9022 using a DVI-to-VGA adapter plug: > > > > i2c i2c-0: sendbytes: NAK bailout. > > i2c i2c-0: sendbytes: NAK bailout. > > > > Then no picture. Apparently the I2C engine inside the SiI9022 > > is not smart enough to try to fall back to DDC I2C. Or the > > vendor have not integrated the electronics properly. I don't > > know which one it is. > > > > By using standard modes as fallback, the bridge probes nicely > > with a minor warning and we get picture. > > > > This code is inspired by similar code in the dumb VGA bridge. > > > > Signed-off-by: Linus Walleij <linus.walleij@linaro.org> > > --- > > drivers/gpu/drm/bridge/sii902x.c | 15 +++++++++++++-- > > 1 file changed, 13 insertions(+), 2 deletions(-) > > > > diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c > > index b1ab4ab09532..4483095c4013 100644 > > --- a/drivers/gpu/drm/bridge/sii902x.c > > +++ b/drivers/gpu/drm/bridge/sii902x.c > > @@ -168,8 +168,19 @@ static int sii902x_get_modes(struct drm_connector *connector) > > return ret; > > > > edid = drm_get_edid(connector, sii902x->i2c->adapter); > > - drm_mode_connector_update_edid_property(connector, edid); > > - if (edid) { > > + if (!edid) { > > + /* > > + * This happens when using a simple DVI-to-VGA converter > > + * dongle for example: the I2C lines are not bridged over > > + * to VGA DDC. > > + */ > > + DRM_INFO("EDID readout failed, falling back to standard modes\n"); > > + ret = drm_add_modes_noedid(connector, 1920, 1080); > > + /* Set some standard resolution most monitors can handle */ > > + drm_set_preferred_mode(connector, 1024, 768); > > + } else { > > + /* Data from EDID readout */ > > + drm_mode_connector_update_edid_property(connector, edid); > > num = drm_add_edid_modes(connector, edid); > > kfree(edid); > > } > > -- > > 2.14.3 > > > _______________________________________________ > dri-devel mailing list > dri-devel@lists.freedesktop.org > https://lists.freedesktop.org/mailman/listinfo/dri-devel
On Thu, Mar 1, 2018 at 10:18 PM, Ville Syrjälä <ville.syrjala@linux.intel.com> wrote: > On Thu, Mar 01, 2018 at 10:02:55PM +0100, Linus Walleij wrote: >> Hm, hard to get review feedback on this one. >> >> It gives me proper video on an ARM Versatile Express utilizing the >> bridge driver with a plugged in DVI-to-VGA dongle with the new >> PL111 DRI driver. >> >> Liviu? Pawel? >> >> Some ACK is fine to know I am doing the right thing :) > > Why isn't the probe helper's noedid fallback working? Where is that in the call chain? The problem I have is that the bridge is there, it gets properly initialized and used as connector and all. The only problem is that the DDI I2C portion of it is not working, so no modes are really added from the struct drm_connector_helper_funcs .get_modes() callback. Yours, Linus Walleij
On Thu, Mar 01, 2018 at 11:12:15PM +0100, Linus Walleij wrote: > On Thu, Mar 1, 2018 at 10:18 PM, Ville Syrjälä > <ville.syrjala@linux.intel.com> wrote: > > On Thu, Mar 01, 2018 at 10:02:55PM +0100, Linus Walleij wrote: > >> Hm, hard to get review feedback on this one. > >> > >> It gives me proper video on an ARM Versatile Express utilizing the > >> bridge driver with a plugged in DVI-to-VGA dongle with the new > >> PL111 DRI driver. > >> > >> Liviu? Pawel? > >> > >> Some ACK is fine to know I am doing the right thing :) > > > > Why isn't the probe helper's noedid fallback working? > > Where is that in the call chain? > > The problem I have is that the bridge is there, it gets properly > initialized and used as connector and all. The only problem is > that the DDI I2C portion of it is not working, so no modes are > really added from the struct drm_connector_helper_funcs > .get_modes() callback. The helper is what calls .get_modes(), and it has a noedid fallback for mode count==0.
On Fri, Mar 2, 2018 at 9:07 AM, Ville Syrjälä <ville.syrjala@linux.intel.com> wrote: > On Thu, Mar 01, 2018 at 11:12:15PM +0100, Linus Walleij wrote: >> On Thu, Mar 1, 2018 at 10:18 PM, Ville Syrjälä >> <ville.syrjala@linux.intel.com> wrote: >> > On Thu, Mar 01, 2018 at 10:02:55PM +0100, Linus Walleij wrote: >> >> Hm, hard to get review feedback on this one. >> >> >> >> It gives me proper video on an ARM Versatile Express utilizing the >> >> bridge driver with a plugged in DVI-to-VGA dongle with the new >> >> PL111 DRI driver. >> >> >> >> Liviu? Pawel? >> >> >> >> Some ACK is fine to know I am doing the right thing :) >> > >> > Why isn't the probe helper's noedid fallback working? >> >> Where is that in the call chain? >> >> The problem I have is that the bridge is there, it gets properly >> initialized and used as connector and all. The only problem is >> that the DDI I2C portion of it is not working, so no modes are >> really added from the struct drm_connector_helper_funcs >> .get_modes() callback. > > The helper is what calls .get_modes(), and it has a noedid > fallback for mode count==0. OK I'll debug from here and try to see what's wrong. Yours, Linus Walleij
diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c index b1ab4ab09532..4483095c4013 100644 --- a/drivers/gpu/drm/bridge/sii902x.c +++ b/drivers/gpu/drm/bridge/sii902x.c @@ -168,8 +168,19 @@ static int sii902x_get_modes(struct drm_connector *connector) return ret; edid = drm_get_edid(connector, sii902x->i2c->adapter); - drm_mode_connector_update_edid_property(connector, edid); - if (edid) { + if (!edid) { + /* + * This happens when using a simple DVI-to-VGA converter + * dongle for example: the I2C lines are not bridged over + * to VGA DDC. + */ + DRM_INFO("EDID readout failed, falling back to standard modes\n"); + ret = drm_add_modes_noedid(connector, 1920, 1080); + /* Set some standard resolution most monitors can handle */ + drm_set_preferred_mode(connector, 1024, 768); + } else { + /* Data from EDID readout */ + drm_mode_connector_update_edid_property(connector, edid); num = drm_add_edid_modes(connector, edid); kfree(edid); }
The following happens when connection a DVI output driven from the SiI9022 using a DVI-to-VGA adapter plug: i2c i2c-0: sendbytes: NAK bailout. i2c i2c-0: sendbytes: NAK bailout. Then no picture. Apparently the I2C engine inside the SiI9022 is not smart enough to try to fall back to DDC I2C. Or the vendor have not integrated the electronics properly. I don't know which one it is. By using standard modes as fallback, the bridge probes nicely with a minor warning and we get picture. This code is inspired by similar code in the dumb VGA bridge. Signed-off-by: Linus Walleij <linus.walleij@linaro.org> --- drivers/gpu/drm/bridge/sii902x.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-)