diff options
| author | Paul Walmsley <paul@pwsan.com> | 2010-02-22 22:09:22 -0700 |
|---|---|---|
| committer | Paul Walmsley <paul@pwsan.com> | 2010-02-24 12:29:42 -0700 |
| commit | 81b34fbecbfbf24ed95c2d80d5cb14149652408f (patch) | |
| tree | b29a0d117a7dda644e6d37931a7999095aeeaf69 /arch/arm/mach-omap2/Makefile | |
| parent | 657ebfadc19c5a14f709dee1645082828330d5d4 (diff) | |
| download | kernel_samsung_smdk4412-81b34fbecbfbf24ed95c2d80d5cb14149652408f.zip kernel_samsung_smdk4412-81b34fbecbfbf24ed95c2d80d5cb14149652408f.tar.gz kernel_samsung_smdk4412-81b34fbecbfbf24ed95c2d80d5cb14149652408f.tar.bz2 | |
OMAP2 clock: split OMAP2420, OMAP2430 clock data into their own files
In preparation for multi-OMAP2 kernels, split
mach-omap2/clock2xxx_data.c into mach-omap2/clock2420_data.c and
mach-omap2/clock2430_data.c. 2430 uses a different device space
physical memory layout than past or future OMAPs, and we use a
different virtual memory layout as well, which causes trouble for
architecture-level code/data that tries to support both. We tried
using offsets from the virtual base last year, but those patches never
made it upstream; so after some discussion with Tony about the best
all-around approach, we'll just grit our teeth and duplicate the
structures. The maintenance advantages of a single kernel config that
can compile and boot on OMAP2, 3, and 4 platforms are simply too
compelling.
This approach does have some nice benefits beyond multi-OMAP 2 kernel
support. The runtime size of OMAP2420-specific and OMAP2430-specific
kernels is smaller, since unused clocks for the other OMAP2 chip will
no longer be compiled in. (At some point we will mark the clock data
__initdata and allocate it during registration, which will eliminate
the runtime memory advantage.) It also makes the clock trees slightly
easier to read, since 2420-specific and 2430-specific clocks are no
longer mixed together.
This patch also splits 2430-specific clock code into its own file,
mach-omap2/clock2430.c, which is only compiled in for 2430 builds -
mostly for organizational clarity.
While here, fix a bug in the OMAP2430 clock tree: "emul_ck" was
incorrectly marked as being 2420-only, when actually it is present on
both OMAP2420 and OMAP2430.
Thanks to Tony for some good discussions about how to approach this
problem.
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Richard Woodruff <r-woodruff2@ti.com>
Diffstat (limited to 'arch/arm/mach-omap2/Makefile')
| -rw-r--r-- | arch/arm/mach-omap2/Makefile | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile index 5f10d32..5da5ca1 100644 --- a/arch/arm/mach-omap2/Makefile +++ b/arch/arm/mach-omap2/Makefile @@ -57,10 +57,12 @@ obj-$(CONFIG_ARCH_OMAP4) += cm4xxx.o # Clock framework obj-$(CONFIG_ARCH_OMAP2) += $(clock-common) clock2xxx.o \ - clock2xxx_data.o clkt2xxx_sys.o \ + clkt2xxx_sys.o \ clkt2xxx_dpllcore.o \ clkt2xxx_virt_prcm_set.o \ clkt2xxx_apll.o clkt2xxx_osc.o +obj-$(CONFIG_ARCH_OMAP2420) += clock2420_data.o +obj-$(CONFIG_ARCH_OMAP2430) += clock2430.o clock2430_data.o obj-$(CONFIG_ARCH_OMAP3) += $(clock-common) clock3xxx.o \ clock34xx.o clkt34xx_dpll3m2.o \ clock3517.o clock36xx.o \ |