summaryrefslogtreecommitdiffstats
path: root/arch/arm/mach-omap2/clkt2xxx_apll.c
diff options
context:
space:
mode:
authorPaul Walmsley2010-02-23 06:09:22 +0100
committerPaul Walmsley2010-02-24 20:29:42 +0100
commit81b34fbecbfbf24ed95c2d80d5cb14149652408f (patch)
treeb29a0d117a7dda644e6d37931a7999095aeeaf69 /arch/arm/mach-omap2/clkt2xxx_apll.c
parentOMAP3/4 clock: split into per-chip family files (diff)
downloadkernel-qcow2-linux-81b34fbecbfbf24ed95c2d80d5cb14149652408f.tar.gz
kernel-qcow2-linux-81b34fbecbfbf24ed95c2d80d5cb14149652408f.tar.xz
kernel-qcow2-linux-81b34fbecbfbf24ed95c2d80d5cb14149652408f.zip
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/clkt2xxx_apll.c')
-rw-r--r--arch/arm/mach-omap2/clkt2xxx_apll.c4
1 files changed, 3 insertions, 1 deletions
diff --git a/arch/arm/mach-omap2/clkt2xxx_apll.c b/arch/arm/mach-omap2/clkt2xxx_apll.c
index d5b8b2bb0e9d..43d7246ce335 100644
--- a/arch/arm/mach-omap2/clkt2xxx_apll.c
+++ b/arch/arm/mach-omap2/clkt2xxx_apll.c
@@ -38,6 +38,8 @@
#define APLLS_CLKIN_13MHZ 2
#define APLLS_CLKIN_12MHZ 3
+void __iomem *cm_idlest_pll;
+
/* Private functions */
/* Enable an APLL if off */
@@ -56,7 +58,7 @@ static int omap2_clk_apll_enable(struct clk *clk, u32 status_mask)
cval |= apll_mask;
cm_write_mod_reg(cval, PLL_MOD, CM_CLKEN);
- omap2_cm_wait_idlest(OMAP_CM_REGADDR(PLL_MOD, CM_IDLEST), status_mask,
+ omap2_cm_wait_idlest(cm_idlest_pll, status_mask,
OMAP24XX_CM_IDLEST_VAL, clk->name);
/*