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>
2010-02-23 05:09:22 +00:00
|
|
|
/*
|
|
|
|
* clock2430.c - OMAP2430-specific clock integration code
|
|
|
|
*
|
|
|
|
* Copyright (C) 2005-2008 Texas Instruments, Inc.
|
|
|
|
* Copyright (C) 2004-2010 Nokia Corporation
|
|
|
|
*
|
|
|
|
* Contacts:
|
|
|
|
* Richard Woodruff <r-woodruff2@ti.com>
|
|
|
|
* Paul Walmsley
|
|
|
|
*
|
|
|
|
* Based on earlier work by Tuukka Tikkanen, Tony Lindgren,
|
|
|
|
* Gordon McNutt and RidgeRun, Inc.
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
|
|
* published by the Free Software Foundation.
|
|
|
|
*/
|
|
|
|
#undef DEBUG
|
|
|
|
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/clk.h>
|
|
|
|
#include <linux/io.h>
|
|
|
|
|
2012-08-31 17:59:07 +00:00
|
|
|
#include "soc.h"
|
2012-02-24 18:34:35 +00:00
|
|
|
#include "iomap.h"
|
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>
2010-02-23 05:09:22 +00:00
|
|
|
#include "clock.h"
|
|
|
|
#include "clock2xxx.h"
|
2012-10-21 07:01:11 +00:00
|
|
|
#include "cm2xxx.h"
|
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>
2010-02-23 05:09:22 +00:00
|
|
|
#include "cm-regbits-24xx.h"
|
|
|
|
|
|
|
|
/**
|
|
|
|
* omap2430_clk_i2chs_find_idlest - return CM_IDLEST info for 2430 I2CHS
|
|
|
|
* @clk: struct clk * being enabled
|
|
|
|
* @idlest_reg: void __iomem ** to store CM_IDLEST reg address into
|
|
|
|
* @idlest_bit: pointer to a u8 to store the CM_IDLEST bit shift into
|
|
|
|
* @idlest_val: pointer to a u8 to store the CM_IDLEST indicator
|
|
|
|
*
|
|
|
|
* OMAP2430 I2CHS CM_IDLEST bits are in CM_IDLEST1_CORE, but the
|
|
|
|
* CM_*CLKEN bits are in CM_{I,F}CLKEN2_CORE. This custom function
|
|
|
|
* passes back the correct CM_IDLEST register address for I2CHS
|
|
|
|
* modules. No return value.
|
|
|
|
*/
|
|
|
|
static void omap2430_clk_i2chs_find_idlest(struct clk *clk,
|
|
|
|
void __iomem **idlest_reg,
|
|
|
|
u8 *idlest_bit,
|
|
|
|
u8 *idlest_val)
|
|
|
|
{
|
|
|
|
*idlest_reg = OMAP2430_CM_REGADDR(CORE_MOD, CM_IDLEST);
|
|
|
|
*idlest_bit = clk->enable_bit;
|
|
|
|
*idlest_val = OMAP24XX_CM_IDLEST_VAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* 2430 I2CHS has non-standard IDLEST register */
|
|
|
|
const struct clkops clkops_omap2430_i2chs_wait = {
|
|
|
|
.enable = omap2_dflt_clk_enable,
|
|
|
|
.disable = omap2_dflt_clk_disable,
|
|
|
|
.find_idlest = omap2430_clk_i2chs_find_idlest,
|
|
|
|
.find_companion = omap2_clk_dflt_find_companion,
|
|
|
|
};
|