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/io.c | |
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/io.c')
-rw-r--r-- | arch/arm/mach-omap2/io.c | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index 2c51854..f168557 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -340,8 +340,10 @@ void __init omap2_init_common_hw(struct omap_sdrc_params *sdrc_cs0, omap_pm_if_early_init(mpu_opps, dsp_opps, l3_opps); #endif - if (cpu_is_omap24xx()) - omap2xxx_clk_init(); + if (cpu_is_omap2420()) + omap2420_clk_init(); + else if (cpu_is_omap2430()) + omap2430_clk_init(); else if (cpu_is_omap34xx()) omap3xxx_clk_init(); else if (cpu_is_omap44xx()) |