[GIT,PULL,2/2] Samsung fixes-2 for v4.0
mbox

Message ID 54F4B33E.3070803@kernel.org
State New
Headers show

Pull-request

git://git.kernel.org/pub/scm/linux/kernel/git/kgene/linux-samsung.git

Message

'Kukjin Kim' March 2, 2015, 7 p.m. UTC
Hi,

Please pull Samsung tmu and hdmi regression fixes for v4.0 and I know
this is quite big for fixes but I couldn't handle this series for
previous merge window because of dependency with driver side...sorry for
that and please pull so that we could support them in v4.0 on exynos
platforms.

Thanks,
Kukjin

The following changes since commit c517d838eb7d07bbe9507871fab3931deccff539:

  Linux 4.0-rc1 (2015-02-22 18:21:14 -0800)

are available in the git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/kgene/linux-samsung.git
tags/samsung-fixes-dt

for you to fetch changes up to 2d2c9a8d0a4f90e298315d2f4a282d8bd5d45e5c:

  ARM: dts: add display power domain for exynos5250 (2015-02-27 05:29:32
+0900)

----------------------------------------------------------------
Samsung tmu and hdmi regression fixes for v4.0

- The thermal management unit and HDMI (drm mixer driver) related
reworks have been merged in v4.0 merge window. So if this DT changes
are missed for v4.0, we regressions in v4.0 release for exynos
platforms such as exynos5250, exynos5420, exynos4 SoCs.

- Note since there was a dependency with driver side, this cannot
be sent to upstream during preivous merge window and now it has been
resolved.

----------------------------------------------------------------
Andrzej Hajda (1):
      ARM: dts: add display power domain for exynos5250

Lukasz Majewski (9):
      ARM: dts: Enable TMU for exynos4210-trats
      ARM: dts: Add LDO10 for TMU for exynos4412-odroid-common
      ARM: dts: Enable TMU for exynos4412-odriod-common
      ARM: dts: Adding CPU cooling binding for Exynos SoCs
      ARM: dts: add TMU default definitions for exynos4412
      ARM: dts: default trip points definition for exynos5420
      ARM: dts: define default thermal-zones for exynos4
      ARM: dts: Trip points and sensor configuration data for exynos5440
      ARM: dts: Provide dt bindings identical for Exynos TMU

Marek Szyprowski (6):
      dt-bindings: document a note about power domain subdomains
      ARM: EXYNOS: add support for sub-power domains
      ARM: dts: add hdmi related nodes for exynos4 SoCs
      ARM: dts: add dependency between TV and LCD0 power domains for exynos4
      ARM: dts: enable hdmi support for exynos4412-odroid-common
      ARM: dts: add 'hdmi' clock to mixer nodes for exynos5250 and
exynos5420

Tomasz Stanislawski (1):
      ARM: dts: enable hdmi support for exynos4210-universal_c210

 .../bindings/arm/exynos/power_domain.txt           |  2 +
 .../devicetree/bindings/power/power_domain.txt     | 29 ++++++++++
 arch/arm/boot/dts/exynos3250.dtsi                  |  2 +
 arch/arm/boot/dts/exynos4-cpu-thermal.dtsi         | 52 ++++++++++++++++++
 arch/arm/boot/dts/exynos4.dtsi                     | 45 +++++++++++++++
 arch/arm/boot/dts/exynos4210-trats.dts             | 19 +++++++
 arch/arm/boot/dts/exynos4210-universal_c210.dts    | 57 +++++++++++++++++++
 arch/arm/boot/dts/exynos4210.dtsi                  | 38 ++++++++++++-
 arch/arm/boot/dts/exynos4212.dtsi                  |  5 +-
 arch/arm/boot/dts/exynos4412-odroid-common.dtsi    | 64
++++++++++++++++++++++
 arch/arm/boot/dts/exynos4412-tmu-sensor-conf.dtsi  | 24 ++++++++
 arch/arm/boot/dts/exynos4412-trats2.dts            | 15 +++++
 arch/arm/boot/dts/exynos4412.dtsi                  |  5 +-
 arch/arm/boot/dts/exynos4x12.dtsi                  | 12 ++++
 arch/arm/boot/dts/exynos5250.dtsi                  | 44 +++++++++++++--
 arch/arm/boot/dts/exynos5420-trip-points.dtsi      | 35 ++++++++++++
 arch/arm/boot/dts/exynos5420.dtsi                  | 33 ++++++++++-
 arch/arm/boot/dts/exynos5440-tmu-sensor-conf.dtsi  | 24 ++++++++
 arch/arm/boot/dts/exynos5440-trip-points.dtsi      | 25 +++++++++
 arch/arm/boot/dts/exynos5440.dtsi                  | 18 ++++++
 arch/arm/mach-exynos/pm_domains.c                  | 28 ++++++++++
 21 files changed, 565 insertions(+), 11 deletions(-)
 create mode 100644 arch/arm/boot/dts/exynos4-cpu-thermal.dtsi
 create mode 100644 arch/arm/boot/dts/exynos4412-tmu-sensor-conf.dtsi
 create mode 100644 arch/arm/boot/dts/exynos5420-trip-points.dtsi
 create mode 100644 arch/arm/boot/dts/exynos5440-tmu-sensor-conf.dtsi
 create mode 100644 arch/arm/boot/dts/exynos5440-trip-points.dtsi

Comments

Arnd Bergmann March 4, 2015, 8:04 p.m. UTC | #1
On Tuesday 03 March 2015 04:00:14 Kukjin Kim wrote:
> Please pull Samsung tmu and hdmi regression fixes for v4.0 and I know
> this is quite big for fixes but I couldn't handle this series for
> previous merge window because of dependency with driver side...sorry for
> that and please pull so that we could support them in v4.0 on exynos
> platforms.

What kind of dependency do you have there? It really should not be
necessary to wait for driver changes, unless you do an incompatible
DT binding change, which you should avoid.

I've pulled it into fixes, but won't forward it until I hear a
good explanation.

	Arnd
Arnd Bergmann March 4, 2015, 11:04 p.m. UTC | #2
On Wednesday 04 March 2015 21:04:40 Arnd Bergmann wrote:
> On Tuesday 03 March 2015 04:00:14 Kukjin Kim wrote:
> > Please pull Samsung tmu and hdmi regression fixes for v4.0 and I know
> > this is quite big for fixes but I couldn't handle this series for
> > previous merge window because of dependency with driver side...sorry for
> > that and please pull so that we could support them in v4.0 on exynos
> > platforms.
> 
> What kind of dependency do you have there? It really should not be
> necessary to wait for driver changes, unless you do an incompatible
> DT binding change, which you should avoid.
> 
> I've pulled it into fixes, but won't forward it until I hear a
> good explanation.

Even with both fixes-1 and fixes-2 applied, we still get boot failures
on Exynos:

http://arm-soc.lixom.net/bootlogs/arm-soc/v4.0-rc2-104-g2ee4716/

Any idea what is going on?

	Arnd
Javier Martinez Canillas March 5, 2015, 12:38 a.m. UTC | #3
Hello Arnd,

On Thu, Mar 5, 2015 at 12:04 AM, Arnd Bergmann <arnd@arndb.de> wrote:
> On Wednesday 04 March 2015 21:04:40 Arnd Bergmann wrote:
>> On Tuesday 03 March 2015 04:00:14 Kukjin Kim wrote:
>> > Please pull Samsung tmu and hdmi regression fixes for v4.0 and I know
>> > this is quite big for fixes but I couldn't handle this series for
>> > previous merge window because of dependency with driver side...sorry for
>> > that and please pull so that we could support them in v4.0 on exynos
>> > platforms.
>>
>> What kind of dependency do you have there? It really should not be
>> necessary to wait for driver changes, unless you do an incompatible
>> DT binding change, which you should avoid.
>>
>> I've pulled it into fixes, but won't forward it until I hear a
>> good explanation.
>
> Even with both fixes-1 and fixes-2 applied, we still get boot failures
> on Exynos:
>
> http://arm-soc.lixom.net/bootlogs/arm-soc/v4.0-rc2-104-g2ee4716/
>
> Any idea what is going on?
>

Yes, the problem is the Exynos DRM driver which has a lot of issues.
It's broken if CONFIG_DRM_EXYNOS_IOMMU is enabled which defaults to
yes after commit 8dcc14f82f06 ("drm/exynos: IOMMU support should not
be selectable by user").

I posted a patch to disable IOMMU support on Exynos to avoid these
boot failures and also mentioned to Kukjin that it should be a fix for
4.0 [0]. But even with IOMMU disabled, the Exynos DRM is broken in
some boards [1] so we may have to disable that driver until everything
gets sorted out and is stable again.

>         Arnd
> --

Best regards,
Javier

[0]: https://lkml.org/lkml/2015/3/3/60
[1]: https://lkml.org/lkml/2015/3/4/1070
Eduardo Valentin March 5, 2015, 12:34 p.m. UTC | #4
On Fri, Mar 06, 2015 at 07:16:53PM +0900, Kukjin Kim wrote:
> Arnd Bergmann wrote:
> > 
> + Eduardo
> 
> Hi Arnd,
> 
> > On Tuesday 03 March 2015 04:00:14 Kukjin Kim wrote:
> > > Please pull Samsung tmu and hdmi regression fixes for v4.0 and I know
> > > this is quite big for fixes but I couldn't handle this series for
> > > previous merge window because of dependency with driver side...sorry for
> > > that and please pull so that we could support them in v4.0 on exynos
> > > platforms.
> > 
> > What kind of dependency do you have there? It really should not be
> > necessary to wait for driver changes, unless you do an incompatible
> > DT binding change, which you should avoid.
> > 
> For TMU patches, I've asked Eduardo to provide topic branch for
> 'include/dt-bindings/thermal/thermal_exynos.h' has been added via thermal tree
> because if I can't apply the patch in Samsung tree for arm-soc, kernel build
> breakage will be happened. But I couldn't get Eduardo's topic branch.


Specifically, the developer, while migrating the driver to support DT
and OF thermal, decided to create a header with constants. The header is
used by DT files and the driver code. The header was the dependency.


BR,

Eduardo Valentin

> 
> http://www.spinics.net/lists/linux-samsung-soc/msg41877.html
> 
> 
> For HDMI patches, I thought the DT changes have a dependency with "drm/exynos:
> add support for 'hdmi' clock" so waited for its applying then in drm tree. But
> I couldn't send it to arm-soc after that...
> 
> http://www.spinics.net/lists/linux-samsung-soc/msg42173.html
> 
> 
> I asked about the situation (late DT changes?) when I sent a pull-request, then
> I couldn't get a access my kernel.org because of biz. trip to China :(
> 
> http://www.spinics.net/lists/linux-samsung-soc/msg42235.html
> 
> 
> > I've pulled it into fixes, but won't forward it until I hear a
> > good explanation.
> > 
> As you know, basically I tried to make a clear branch for pull-request but in
> that case, I couldn't find a solution. Sorry for the inconvenience.
> 
> I hope v4.0 can support them properly.
> 
> Thanks,
> Kukjin
>
'Kukjin Kim' March 6, 2015, 9:43 a.m. UTC | #5
Javier Martinez Canillas wrote:
> 
> Hello Arnd,
> 
Hi,

> On Thu, Mar 5, 2015 at 12:04 AM, Arnd Bergmann <arnd@arndb.de> wrote:
> > On Wednesday 04 March 2015 21:04:40 Arnd Bergmann wrote:
> >> On Tuesday 03 March 2015 04:00:14 Kukjin Kim wrote:
> >> > Please pull Samsung tmu and hdmi regression fixes for v4.0 and I know
> >> > this is quite big for fixes but I couldn't handle this series for
> >> > previous merge window because of dependency with driver side...sorry for
> >> > that and please pull so that we could support them in v4.0 on exynos
> >> > platforms.
> >>
> >> What kind of dependency do you have there? It really should not be
> >> necessary to wait for driver changes, unless you do an incompatible
> >> DT binding change, which you should avoid.
> >>
> >> I've pulled it into fixes, but won't forward it until I hear a
> >> good explanation.
> >
> > Even with both fixes-1 and fixes-2 applied, we still get boot failures
> > on Exynos:
> >
> > http://arm-soc.lixom.net/bootlogs/arm-soc/v4.0-rc2-104-g2ee4716/
> >
> > Any idea what is going on?
> >
> 
> Yes, the problem is the Exynos DRM driver which has a lot of issues.
> It's broken if CONFIG_DRM_EXYNOS_IOMMU is enabled which defaults to
> yes after commit 8dcc14f82f06 ("drm/exynos: IOMMU support should not
> be selectable by user").
> 
> I posted a patch to disable IOMMU support on Exynos to avoid these
> boot failures and also mentioned to Kukjin that it should be a fix for
> 4.0 [0]. But even with IOMMU disabled, the Exynos DRM is broken in
> some boards [1] so we may have to disable that driver until everything
> gets sorted out and is stable again.
> 
Yes, the fix is in my tree and it will be sent to upstream via arm-soc soon.

Thanks,
Kukjin
Javier Martinez Canillas March 6, 2015, 10:07 a.m. UTC | #6
Hello Kukjin,

On Fri, Mar 6, 2015 at 10:43 AM, Kukjin Kim <kgene@kernel.org> wrote:
> Javier Martinez Canillas wrote:
>>
>> Hello Arnd,
>>
> Hi,
>
>> On Thu, Mar 5, 2015 at 12:04 AM, Arnd Bergmann <arnd@arndb.de> wrote:
>> > On Wednesday 04 March 2015 21:04:40 Arnd Bergmann wrote:
>> >> On Tuesday 03 March 2015 04:00:14 Kukjin Kim wrote:
>> >> > Please pull Samsung tmu and hdmi regression fixes for v4.0 and I know
>> >> > this is quite big for fixes but I couldn't handle this series for
>> >> > previous merge window because of dependency with driver side...sorry for
>> >> > that and please pull so that we could support them in v4.0 on exynos
>> >> > platforms.
>> >>
>> >> What kind of dependency do you have there? It really should not be
>> >> necessary to wait for driver changes, unless you do an incompatible
>> >> DT binding change, which you should avoid.
>> >>
>> >> I've pulled it into fixes, but won't forward it until I hear a
>> >> good explanation.
>> >
>> > Even with both fixes-1 and fixes-2 applied, we still get boot failures
>> > on Exynos:
>> >
>> > http://arm-soc.lixom.net/bootlogs/arm-soc/v4.0-rc2-104-g2ee4716/
>> >
>> > Any idea what is going on?
>> >
>>
>> Yes, the problem is the Exynos DRM driver which has a lot of issues.
>> It's broken if CONFIG_DRM_EXYNOS_IOMMU is enabled which defaults to
>> yes after commit 8dcc14f82f06 ("drm/exynos: IOMMU support should not
>> be selectable by user").
>>
>> I posted a patch to disable IOMMU support on Exynos to avoid these
>> boot failures and also mentioned to Kukjin that it should be a fix for
>> 4.0 [0]. But even with IOMMU disabled, the Exynos DRM is broken in
>> some boards [1] so we may have to disable that driver until everything
>> gets sorted out and is stable again.
>>
> Yes, the fix is in my tree and it will be sent to upstream via arm-soc soon.
>

Thanks a lot for your help. You meant the patch to disable IOMMU
support right? While being there could you please also disable the DRM
driver as discussed since is unlikely that the Exynos DRM maintainers
would be able to sort out all the issues in time for 4.0.

> Thanks,
> Kukjin
>

Best regards,
Javier
'Kukjin Kim' March 6, 2015, 10:16 a.m. UTC | #7
Arnd Bergmann wrote:
> 
+ Eduardo

Hi Arnd,

> On Tuesday 03 March 2015 04:00:14 Kukjin Kim wrote:
> > Please pull Samsung tmu and hdmi regression fixes for v4.0 and I know
> > this is quite big for fixes but I couldn't handle this series for
> > previous merge window because of dependency with driver side...sorry for
> > that and please pull so that we could support them in v4.0 on exynos
> > platforms.
> 
> What kind of dependency do you have there? It really should not be
> necessary to wait for driver changes, unless you do an incompatible
> DT binding change, which you should avoid.
> 
For TMU patches, I've asked Eduardo to provide topic branch for
'include/dt-bindings/thermal/thermal_exynos.h' has been added via thermal tree
because if I can't apply the patch in Samsung tree for arm-soc, kernel build
breakage will be happened. But I couldn't get Eduardo's topic branch.

http://www.spinics.net/lists/linux-samsung-soc/msg41877.html


For HDMI patches, I thought the DT changes have a dependency with "drm/exynos:
add support for 'hdmi' clock" so waited for its applying then in drm tree. But
I couldn't send it to arm-soc after that...

http://www.spinics.net/lists/linux-samsung-soc/msg42173.html


I asked about the situation (late DT changes?) when I sent a pull-request, then
I couldn't get a access my kernel.org because of biz. trip to China :(

http://www.spinics.net/lists/linux-samsung-soc/msg42235.html


> I've pulled it into fixes, but won't forward it until I hear a
> good explanation.
> 
As you know, basically I tried to make a clear branch for pull-request but in
that case, I couldn't find a solution. Sorry for the inconvenience.

I hope v4.0 can support them properly.

Thanks,
Kukjin
Łukasz Majewski March 9, 2015, 7:44 a.m. UTC | #8
Hi Eduardo,

> On Fri, Mar 06, 2015 at 07:16:53PM +0900, Kukjin Kim wrote:
> > Arnd Bergmann wrote:
> > > 
> > + Eduardo
> > 
> > Hi Arnd,
> > 
> > > On Tuesday 03 March 2015 04:00:14 Kukjin Kim wrote:
> > > > Please pull Samsung tmu and hdmi regression fixes for v4.0 and
> > > > I know this is quite big for fixes but I couldn't handle this
> > > > series for previous merge window because of dependency with
> > > > driver side...sorry for that and please pull so that we could
> > > > support them in v4.0 on exynos platforms.
> > > 
> > > What kind of dependency do you have there? It really should not be
> > > necessary to wait for driver changes, unless you do an
> > > incompatible DT binding change, which you should avoid.
> > > 
> > For TMU patches, I've asked Eduardo to provide topic branch for
> > 'include/dt-bindings/thermal/thermal_exynos.h' has been added via
> > thermal tree because if I can't apply the patch in Samsung tree for
> > arm-soc, kernel build breakage will be happened. But I couldn't get
> > Eduardo's topic branch.
> 
> 
> Specifically, the developer, while migrating the driver to support DT
> and OF thermal, decided to create a header with constants. The header
> is used by DT files and the driver code. The header was the
> dependency.

Just my 2 cents :-).

The above situation is the justification for adding the whole patch set
to one repository when all ACKs are collected for it.

> 
> 
> BR,
> 
> Eduardo Valentin
> 
> > 
> > http://www.spinics.net/lists/linux-samsung-soc/msg41877.html
> > 
> > 
> > For HDMI patches, I thought the DT changes have a dependency with
> > "drm/exynos: add support for 'hdmi' clock" so waited for its
> > applying then in drm tree. But I couldn't send it to arm-soc after
> > that...
> > 
> > http://www.spinics.net/lists/linux-samsung-soc/msg42173.html
> > 
> > 
> > I asked about the situation (late DT changes?) when I sent a
> > pull-request, then I couldn't get a access my kernel.org because of
> > biz. trip to China :(
> > 
> > http://www.spinics.net/lists/linux-samsung-soc/msg42235.html
> > 
> > 
> > > I've pulled it into fixes, but won't forward it until I hear a
> > > good explanation.
> > > 
> > As you know, basically I tried to make a clear branch for
> > pull-request but in that case, I couldn't find a solution. Sorry
> > for the inconvenience.
> > 
> > I hope v4.0 can support them properly.
> > 
> > Thanks,
> > Kukjin
> >
'Kukjin Kim' March 9, 2015, 8:19 a.m. UTC | #9
Lukasz Majewski wrote:
> 
> Hi Eduardo,
> 
> > On Fri, Mar 06, 2015 at 07:16:53PM +0900, Kukjin Kim wrote:
> > > Arnd Bergmann wrote:
> > > >
> > > + Eduardo
> > >
> > > Hi Arnd,
> > >
> > > > On Tuesday 03 March 2015 04:00:14 Kukjin Kim wrote:
> > > > > Please pull Samsung tmu and hdmi regression fixes for v4.0 and
> > > > > I know this is quite big for fixes but I couldn't handle this
> > > > > series for previous merge window because of dependency with
> > > > > driver side...sorry for that and please pull so that we could
> > > > > support them in v4.0 on exynos platforms.
> > > >
> > > > What kind of dependency do you have there? It really should not be
> > > > necessary to wait for driver changes, unless you do an
> > > > incompatible DT binding change, which you should avoid.
> > > >
> > > For TMU patches, I've asked Eduardo to provide topic branch for
> > > 'include/dt-bindings/thermal/thermal_exynos.h' has been added via
> > > thermal tree because if I can't apply the patch in Samsung tree for
> > > arm-soc, kernel build breakage will be happened. But I couldn't get
> > > Eduardo's topic branch.
> >
> >
> > Specifically, the developer, while migrating the driver to support DT
> > and OF thermal, decided to create a header with constants. The header
> > is used by DT files and the driver code. The header was the
> > dependency.
> 
> Just my 2 cents :-).
> 
> The above situation is the justification for adding the whole patch set
> to one repository when all ACKs are collected for it.
> 
I don't think so, even your series can be upstreamed though, other useless
merge conflicts would be happened so we decided all of DT should be handled
in arch side not driver side. So please don't argue about that.

- Kukjin
Łukasz Majewski March 9, 2015, 8:28 a.m. UTC | #10
Hi Kukjin,

> Lukasz Majewski wrote:
> > 
> > Hi Eduardo,
> > 
> > > On Fri, Mar 06, 2015 at 07:16:53PM +0900, Kukjin Kim wrote:
> > > > Arnd Bergmann wrote:
> > > > >
> > > > + Eduardo
> > > >
> > > > Hi Arnd,
> > > >
> > > > > On Tuesday 03 March 2015 04:00:14 Kukjin Kim wrote:
> > > > > > Please pull Samsung tmu and hdmi regression fixes for v4.0
> > > > > > and I know this is quite big for fixes but I couldn't
> > > > > > handle this series for previous merge window because of
> > > > > > dependency with driver side...sorry for that and please
> > > > > > pull so that we could support them in v4.0 on exynos
> > > > > > platforms.
> > > > >
> > > > > What kind of dependency do you have there? It really should
> > > > > not be necessary to wait for driver changes, unless you do an
> > > > > incompatible DT binding change, which you should avoid.
> > > > >
> > > > For TMU patches, I've asked Eduardo to provide topic branch for
> > > > 'include/dt-bindings/thermal/thermal_exynos.h' has been added
> > > > via thermal tree because if I can't apply the patch in Samsung
> > > > tree for arm-soc, kernel build breakage will be happened. But I
> > > > couldn't get Eduardo's topic branch.
> > >
> > >
> > > Specifically, the developer, while migrating the driver to
> > > support DT and OF thermal, decided to create a header with
> > > constants. The header is used by DT files and the driver code.
> > > The header was the dependency.
> > 
> > Just my 2 cents :-).
> > 
> > The above situation is the justification for adding the whole patch
> > set to one repository when all ACKs are collected for it.
> > 
> I don't think so, even your series can be upstreamed though, other
> useless merge conflicts would be happened so we decided all of DT
> should be handled in arch side not driver side. So please don't argue
> about that.

Ok, I will not :-)

> 
> - Kukjin
>
'Kukjin Kim' March 12, 2015, 11:15 a.m. UTC | #11
Eduardo Valentin wrote:
> 
Hi Eduardo,

> On Fri, Mar 06, 2015 at 07:16:53PM +0900, Kukjin Kim wrote:
> > Arnd Bergmann wrote:
> > >
> > + Eduardo
> >
> > Hi Arnd,
> >
> > > On Tuesday 03 March 2015 04:00:14 Kukjin Kim wrote:
> > > > Please pull Samsung tmu and hdmi regression fixes for v4.0 and I know
> > > > this is quite big for fixes but I couldn't handle this series for
> > > > previous merge window because of dependency with driver side...sorry for
> > > > that and please pull so that we could support them in v4.0 on exynos
> > > > platforms.
> > >
> > > What kind of dependency do you have there? It really should not be
> > > necessary to wait for driver changes, unless you do an incompatible
> > > DT binding change, which you should avoid.
> > >
> > For TMU patches, I've asked Eduardo to provide topic branch for
> > 'include/dt-bindings/thermal/thermal_exynos.h' has been added via thermal tree
> > because if I can't apply the patch in Samsung tree for arm-soc, kernel build
> > breakage will be happened. But I couldn't get Eduardo's topic branch.
> 
> 
> Specifically, the developer, while migrating the driver to support DT
> and OF thermal, decided to create a header with constants. The header is
> used by DT files and the driver code. The header was the dependency.
> 
Yes, sometimes we can't avoid the situation so it can be a kind of dependency...


Arnd,
Do you have any updates on this?

Thanks,
Kukjin

> 
> BR,
> 
> Eduardo Valentin
> 
> >
> > http://www.spinics.net/lists/linux-samsung-soc/msg41877.html
> >
> >
> > For HDMI patches, I thought the DT changes have a dependency with "drm/exynos:
> > add support for 'hdmi' clock" so waited for its applying then in drm tree. But
> > I couldn't send it to arm-soc after that...
> >
> > http://www.spinics.net/lists/linux-samsung-soc/msg42173.html
> >
> >
> > I asked about the situation (late DT changes?) when I sent a pull-request, then
> > I couldn't get a access my kernel.org because of biz. trip to China :(
> >
> > http://www.spinics.net/lists/linux-samsung-soc/msg42235.html
> >
> >
> > > I've pulled it into fixes, but won't forward it until I hear a
> > > good explanation.
> > >
> > As you know, basically I tried to make a clear branch for pull-request but in
> > that case, I couldn't find a solution. Sorry for the inconvenience.
> >
> > I hope v4.0 can support them properly.
> >
> > Thanks,
> > Kukjin
Javier Martinez Canillas March 14, 2015, 1:17 p.m. UTC | #12
Hello Kukjin,

On Fri, Mar 6, 2015 at 10:43 AM, Kukjin Kim <kgene@kernel.org> wrote:
>>
>> Yes, the problem is the Exynos DRM driver which has a lot of issues.
>> It's broken if CONFIG_DRM_EXYNOS_IOMMU is enabled which defaults to
>> yes after commit 8dcc14f82f06 ("drm/exynos: IOMMU support should not
>> be selectable by user").
>>
>> I posted a patch to disable IOMMU support on Exynos to avoid these
>> boot failures and also mentioned to Kukjin that it should be a fix for
>> 4.0 [0]. But even with IOMMU disabled, the Exynos DRM is broken in
>> some boards [1] so we may have to disable that driver until everything
>> gets sorted out and is stable again.
>>
> Yes, the fix is in my tree and it will be sent to upstream via arm-soc soon.
>

Sorry for pestering you but I see that the patch to disable
EXYNOS_IOMMU is still not in Linus' master and we are almost in
4.0-rc4 now.

A patch to the Exynos DRM driver to check for IOMMU and fail
gracefully has landed in 4.0-rc so now at least the machines boot but
with IOMMU enabled display is broken in the Exynos5 boards.

> Thanks,
> Kukjin

Best regards,
Javier