* [PATCH] nouveau build regression, undefined reference to `acpi_video_get_edid'
@ 2010-09-10 3:53 Phil Turmel
2010-09-14 13:21 ` Francisco Jerez
0 siblings, 1 reply; 5+ messages in thread
From: Phil Turmel @ 2010-09-10 3:53 UTC (permalink / raw)
To: linux-kernel
Cc: Ben Skeggs, Matthew Garrett, David Airlie,
Marcin Kościelnicki, Francisco Jerez, Dave Airlie, dri-devel
Hi all,
I've got a build breakage on my laptop:
drivers/built-in.o: In function `nouveau_acpi_edid':
(.text+0x13404e): undefined reference to `acpi_video_get_edid'
make: *** [.tmp_vmlinux1] Error 1
Introduced by:
a6ed76d7ffc62ffa474b41d31b011b6853c5de32 is the first bad commit
commit a6ed76d7ffc62ffa474b41d31b011b6853c5de32
Author: Ben Skeggs <bskeggs@redhat.com>
Date: Mon Jul 12 15:33:07 2010 +1000
drm/nouveau: support fetching LVDS EDID from ACPI
Based on a patch from Matthew Garrett.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Acked-by: Matthew Garrett <mjg@redhat.com>
:040000 040000 2fbe9b4d9778329908107e72c11b100c2f5a460b 97dcf06923bb576298746584c45d17d3be9edcf8 M drivers
It doesn't seem to revert cleanly, but I believe the problem lies in these
two config entries:
CONFIG_ACPI=y
CONFIG_ACPI_VIDEO=m
Having the nouveau ACPI features depend on CONFIG_ACPI_VIDEO instead of
bare CONFIG_ACPI builds, boots, and works for me.
Signed-off-by: Philip J. Turmel <philip@turmel.org>
---
Presumably, this could also be solved by adding
"select ACPI_VIDEO if ACPI" to the nouveau Kconfig.
I'd be happy to try that, if this approach is flawed.
diff --git a/drivers/gpu/drm/nouveau/Makefile b/drivers/gpu/drm/nouveau/Makefile
index e9b06e4..4e295b5 100644
--- a/drivers/gpu/drm/nouveau/Makefile
+++ b/drivers/gpu/drm/nouveau/Makefile
@@ -28,6 +28,6 @@ nouveau-y := nouveau_drv.o nouveau_state.o nouveau_channel.o nouveau_mem.o \
nouveau-$(CONFIG_DRM_NOUVEAU_DEBUG) += nouveau_debugfs.o
nouveau-$(CONFIG_COMPAT) += nouveau_ioc32.o
nouveau-$(CONFIG_DRM_NOUVEAU_BACKLIGHT) += nouveau_backlight.o
-nouveau-$(CONFIG_ACPI) += nouveau_acpi.o
+nouveau-$(CONFIG_ACPI_VIDEO) += nouveau_acpi.o
obj-$(CONFIG_DRM_NOUVEAU)+= nouveau.o
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index b1be617..bd995b4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -842,7 +842,7 @@ extern int nouveau_dma_wait(struct nouveau_channel *, int slots, int size);
/* nouveau_acpi.c */
#define ROM_BIOS_PAGE 4096
-#if defined(CONFIG_ACPI)
+#if defined(CONFIG_ACPI_VIDEO)
void nouveau_register_dsm_handler(void);
void nouveau_unregister_dsm_handler(void);
int nouveau_acpi_get_bios_chunk(uint8_t *bios, int offset, int len);
^ permalink raw reply related [flat|nested] 5+ messages in thread* Re: [PATCH] nouveau build regression, undefined reference to `acpi_video_get_edid'
2010-09-10 3:53 [PATCH] nouveau build regression, undefined reference to `acpi_video_get_edid' Phil Turmel
@ 2010-09-14 13:21 ` Francisco Jerez
2010-09-14 13:59 ` Phil Turmel
0 siblings, 1 reply; 5+ messages in thread
From: Francisco Jerez @ 2010-09-14 13:21 UTC (permalink / raw)
To: Phil Turmel
Cc: linux-kernel, Ben Skeggs, Matthew Garrett, David Airlie,
Marcin Kościelnicki, Dave Airlie, dri-devel
[-- Attachment #1.1: Type: text/plain, Size: 2724 bytes --]
Phil Turmel <philip@turmel.org> writes:
> Hi all,
>
> I've got a build breakage on my laptop:
>
> drivers/built-in.o: In function `nouveau_acpi_edid':
> (.text+0x13404e): undefined reference to `acpi_video_get_edid'
> make: *** [.tmp_vmlinux1] Error 1
>
> Introduced by:
>
> a6ed76d7ffc62ffa474b41d31b011b6853c5de32 is the first bad commit
> commit a6ed76d7ffc62ffa474b41d31b011b6853c5de32
> Author: Ben Skeggs <bskeggs@redhat.com>
> Date: Mon Jul 12 15:33:07 2010 +1000
>
> drm/nouveau: support fetching LVDS EDID from ACPI
>
> Based on a patch from Matthew Garrett.
>
> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
> Acked-by: Matthew Garrett <mjg@redhat.com>
>
> :040000 040000 2fbe9b4d9778329908107e72c11b100c2f5a460b 97dcf06923bb576298746584c45d17d3be9edcf8 M drivers
>
> It doesn't seem to revert cleanly, but I believe the problem lies in these
> two config entries:
>
> CONFIG_ACPI=y
> CONFIG_ACPI_VIDEO=m
>
> Having the nouveau ACPI features depend on CONFIG_ACPI_VIDEO instead of
> bare CONFIG_ACPI builds, boots, and works for me.
>
nouveau_acpi_edid() is the only function that depends on ACPI_VIDEO,
ifdef'ing out the rest of the ACPI stuff in that case doesn't make much
sense to me.
> Signed-off-by: Philip J. Turmel <philip@turmel.org>
> ---
>
> Presumably, this could also be solved by adding
> "select ACPI_VIDEO if ACPI" to the nouveau Kconfig.
> I'd be happy to try that, if this approach is flawed.
>
> diff --git a/drivers/gpu/drm/nouveau/Makefile b/drivers/gpu/drm/nouveau/Makefile
> index e9b06e4..4e295b5 100644
> --- a/drivers/gpu/drm/nouveau/Makefile
> +++ b/drivers/gpu/drm/nouveau/Makefile
> @@ -28,6 +28,6 @@ nouveau-y := nouveau_drv.o nouveau_state.o nouveau_channel.o nouveau_mem.o \
> nouveau-$(CONFIG_DRM_NOUVEAU_DEBUG) += nouveau_debugfs.o
> nouveau-$(CONFIG_COMPAT) += nouveau_ioc32.o
> nouveau-$(CONFIG_DRM_NOUVEAU_BACKLIGHT) += nouveau_backlight.o
> -nouveau-$(CONFIG_ACPI) += nouveau_acpi.o
> +nouveau-$(CONFIG_ACPI_VIDEO) += nouveau_acpi.o
>
> obj-$(CONFIG_DRM_NOUVEAU)+= nouveau.o
> diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
> index b1be617..bd995b4 100644
> --- a/drivers/gpu/drm/nouveau/nouveau_drv.h
> +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
> @@ -842,7 +842,7 @@ extern int nouveau_dma_wait(struct nouveau_channel *, int slots, int size);
>
> /* nouveau_acpi.c */
> #define ROM_BIOS_PAGE 4096
> -#if defined(CONFIG_ACPI)
> +#if defined(CONFIG_ACPI_VIDEO)
> void nouveau_register_dsm_handler(void);
> void nouveau_unregister_dsm_handler(void);
> int nouveau_acpi_get_bios_chunk(uint8_t *bios, int offset, int len);
[-- Attachment #2: Type: application/pgp-signature, Size: 229 bytes --]
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] nouveau build regression, undefined reference to `acpi_video_get_edid'
2010-09-14 13:21 ` Francisco Jerez
@ 2010-09-14 13:59 ` Phil Turmel
2010-09-15 0:14 ` [PATCH v2] " Phil Turmel
0 siblings, 1 reply; 5+ messages in thread
From: Phil Turmel @ 2010-09-14 13:59 UTC (permalink / raw)
To: Francisco Jerez
Cc: linux-kernel, Ben Skeggs, Matthew Garrett, David Airlie,
Marcin Kos'cielnicki, Dave Airlie, dri-devel
Francisco Jerez wrote:
> Phil Turmel <philip@turmel.org> writes:
[snip /]
>> Having the nouveau ACPI features depend on CONFIG_ACPI_VIDEO instead of
>> bare CONFIG_ACPI builds, boots, and works for me.
> nouveau_acpi_edid() is the only function that depends on ACPI_VIDEO,
> ifdef'ing out the rest of the ACPI stuff in that case doesn't make much
> sense to me.
Understood. I noticed that DRM_I915 does a "select ACPI_VIDEO if ACPI",
which is why I mentioned that alternative below. I don't recall how I got
the y+m combination above (I tend to build stuff in), but a randconfig
could certainly hit this. I intend to leave it y+y when I'm done.
>> Presumably, this could also be solved by adding
>> "select ACPI_VIDEO if ACPI" to the nouveau Kconfig.
>> I'd be happy to try that, if this approach is flawed.
I'll test the Kconfig approach later today.
Regards,
Phil Turmel
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH v2] nouveau build regression, undefined reference to `acpi_video_get_edid'
2010-09-14 13:59 ` Phil Turmel
@ 2010-09-15 0:14 ` Phil Turmel
2010-09-17 3:39 ` Francisco Jerez
0 siblings, 1 reply; 5+ messages in thread
From: Phil Turmel @ 2010-09-15 0:14 UTC (permalink / raw)
To: Francisco Jerez
Cc: linux-kernel, Ben Skeggs, Matthew Garrett, David Airlie,
Marcin Kos'cielnicki, Dave Airlie, dri-devel
Build breakage:
drivers/built-in.o: In function `nouveau_acpi_edid':
(.text+0x13404e): undefined reference to `acpi_video_get_edid'
make: *** [.tmp_vmlinux1] Error 1
Introduced by:
a6ed76d7ffc62ffa474b41d31b011b6853c5de32 is the first bad commit
commit a6ed76d7ffc62ffa474b41d31b011b6853c5de32
Author: Ben Skeggs <bskeggs@redhat.com>
Date: Mon Jul 12 15:33:07 2010 +1000
drm/nouveau: support fetching LVDS EDID from ACPI
Based on a patch from Matthew Garrett.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Acked-by: Matthew Garrett <mjg@redhat.com>
:040000 040000 2fbe9b4d9778329908107e72c11b100c2f5a460b 97dcf06923bb576298746584c45d17d3be9edcf8 M drivers
It doesn't seem to revert cleanly, but the problem lies in these
two config entries:
CONFIG_ACPI=y
CONFIG_ACPI_VIDEO=m
Adding a select for ACPI_VIDEO appears to be the best solution, and
is comparable to what is done in DRM_I915. Builds, boots, and appears to
work correctly.
Signed-off-by: Philip J. Turmel <philip@turmel.org>
---
The first version disabled all ACPI functions in the nouveau driver if
ACPI_VIDEO wasn't set. Francisco Jerez <currojerez@riseup.net> pointed out
that this didn't make much sense.
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index d2d2804..72730e9 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -10,6 +10,7 @@ config DRM_NOUVEAU
select FB
select FRAMEBUFFER_CONSOLE if !EMBEDDED
select FB_BACKLIGHT if DRM_NOUVEAU_BACKLIGHT
+ select ACPI_VIDEO if ACPI
help
Choose this option for open-source nVidia support.
^ permalink raw reply related [flat|nested] 5+ messages in thread* Re: [PATCH v2] nouveau build regression, undefined reference to `acpi_video_get_edid'
2010-09-15 0:14 ` [PATCH v2] " Phil Turmel
@ 2010-09-17 3:39 ` Francisco Jerez
0 siblings, 0 replies; 5+ messages in thread
From: Francisco Jerez @ 2010-09-17 3:39 UTC (permalink / raw)
To: Phil Turmel
Cc: linux-kernel, Ben Skeggs, Matthew Garrett, David Airlie,
Marcin Kos'cielnicki, Dave Airlie, dri-devel
[-- Attachment #1.1: Type: text/plain, Size: 1785 bytes --]
Phil Turmel <philip@turmel.org> writes:
> Build breakage:
>
> drivers/built-in.o: In function `nouveau_acpi_edid':
> (.text+0x13404e): undefined reference to `acpi_video_get_edid'
> make: *** [.tmp_vmlinux1] Error 1
>
> Introduced by:
>
> a6ed76d7ffc62ffa474b41d31b011b6853c5de32 is the first bad commit
> commit a6ed76d7ffc62ffa474b41d31b011b6853c5de32
> Author: Ben Skeggs <bskeggs@redhat.com>
> Date: Mon Jul 12 15:33:07 2010 +1000
>
> drm/nouveau: support fetching LVDS EDID from ACPI
>
> Based on a patch from Matthew Garrett.
>
> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
> Acked-by: Matthew Garrett <mjg@redhat.com>
>
> :040000 040000 2fbe9b4d9778329908107e72c11b100c2f5a460b 97dcf06923bb576298746584c45d17d3be9edcf8 M drivers
>
> It doesn't seem to revert cleanly, but the problem lies in these
> two config entries:
>
> CONFIG_ACPI=y
> CONFIG_ACPI_VIDEO=m
>
> Adding a select for ACPI_VIDEO appears to be the best solution, and
> is comparable to what is done in DRM_I915. Builds, boots, and appears to
> work correctly.
>
> Signed-off-by: Philip J. Turmel <philip@turmel.org>
> ---
>
> The first version disabled all ACPI functions in the nouveau driver if
> ACPI_VIDEO wasn't set. Francisco Jerez <currojerez@riseup.net> pointed out
> that this didn't make much sense.
>
> diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
> index d2d2804..72730e9 100644
> --- a/drivers/gpu/drm/nouveau/Kconfig
> +++ b/drivers/gpu/drm/nouveau/Kconfig
> @@ -10,6 +10,7 @@ config DRM_NOUVEAU
> select FB
> select FRAMEBUFFER_CONSOLE if !EMBEDDED
> select FB_BACKLIGHT if DRM_NOUVEAU_BACKLIGHT
> + select ACPI_VIDEO if ACPI
> help
> Choose this option for open-source nVidia support.
Thanks, pushed to the nouveau tree.
[-- Attachment #2: Type: application/pgp-signature, Size: 229 bytes --]
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2010-09-17 3:40 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2010-09-10 3:53 [PATCH] nouveau build regression, undefined reference to `acpi_video_get_edid' Phil Turmel
2010-09-14 13:21 ` Francisco Jerez
2010-09-14 13:59 ` Phil Turmel
2010-09-15 0:14 ` [PATCH v2] " Phil Turmel
2010-09-17 3:39 ` Francisco Jerez
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox