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