#include <linux/errno.h>
#include <linux/delay.h>
#include <linux/clk.h>
-#include <asm/bitops.h>
-
-#include <asm/io.h>
+#include <linux/bitops.h>
+#include <linux/io.h>
#include <asm/arch/clock.h>
+#include <asm/arch/clockdomain.h>
#include <asm/arch/sram.h>
#include <asm/arch/cpu.h>
+#include <asm/arch/prcm.h>
#include <asm/div64.h>
#include "memory.h"
#define MAX_CLOCK_ENABLE_WAIT 100000
+/* DPLL rate rounding: minimum DPLL multiplier, divider values */
+#define DPLL_MIN_MULTIPLIER 1
+#define DPLL_MIN_DIVIDER 1
+
+/* Possible error results from _dpll_test_mult */
+#define DPLL_MULT_UNDERFLOW (1 << 0)
+
+/*
+ * Scale factor to mitigate roundoff errors in DPLL rate rounding.
+ * The higher the scale factor, the greater the risk of arithmetic overflow,
+ * but the closer the rounded rate to the target rate. DPLL_SCALE_FACTOR
+ * must be a power of DPLL_SCALE_BASE.
+ */
+#define DPLL_SCALE_FACTOR 64
+#define DPLL_SCALE_BASE 2
+#define DPLL_ROUNDING_VAL ((DPLL_SCALE_BASE / 2) * \
+ (DPLL_SCALE_FACTOR / DPLL_SCALE_BASE))
+
u8 cpu_mask;
/*-------------------------------------------------------------------------
- * Omap2 specific clock functions
+ * OMAP2/3 specific clock functions
*-------------------------------------------------------------------------*/
+/**
+ * omap2_init_clk_clkdm - look up a clockdomain name, store pointer in clk
+ * @clk: OMAP clock struct ptr to use
+ *
+ * Convert a clockdomain name stored in a struct clk 'clk' into a
+ * clockdomain pointer, and save it into the struct clk. Intended to be
+ * called during clk_register(). No return value.
+ */
+void omap2_init_clk_clkdm(struct clk *clk)
+{
+ struct clockdomain *clkdm;
+
+ if (!clk->clkdm_name)
+ return;
+
+ clkdm = clkdm_lookup(clk->clkdm_name);
+ if (clkdm) {
+ pr_debug("clock: associated clk %s to clkdm %s\n",
+ clk->name, clk->clkdm_name);
+ clk->clkdm = clkdm;
+ } else {
+ pr_debug("clock: could not associate clk %s to "
+ "clkdm %s\n", clk->name, clk->clkdm_name);
+ }
+}
+
/**
* omap2_init_clksel_parent - set a clksel clk's parent field from the hardware
* @clk: OMAP clock struct ptr to use
{
long long dpll_clk;
u32 dpll_mult, dpll_div, dpll;
- const struct dpll_data *dd;
+ struct dpll_data *dd;
dd = clk->dpll_data;
/* REVISIT: What do we return on error? */
* 24xx uses 0 to indicate not ready, and 1 to indicate ready.
* 34xx reverses this, just to keep us on our toes
*/
- if (cpu_mask & (RATE_IN_242X | RATE_IN_243X)) {
+ if (cpu_mask & (RATE_IN_242X | RATE_IN_243X))
ena = mask;
- } else if (cpu_mask & RATE_IN_343X) {
+ else if (cpu_mask & RATE_IN_343X)
ena = 0;
- }
/* Wait for lock */
while (((__raw_readl(reg) & mask) != ena) &&
* Note: We don't need special code here for INVERT_ENABLE
* for the time being since INVERT_ENABLE only applies to clocks enabled by
* CM_CLKEN_PLL
+ *
+ * REVISIT: This code is ugly and does not belong here.
*/
static void omap2_clk_wait_ready(struct clk *clk)
{
- void __iomem *reg, *other_reg, *st_reg;
- u32 bit;
-
- /*
- * REVISIT: This code is pretty ugly. It would be nice to generalize
- * it and pull it into struct clk itself somehow.
- */
- reg = clk->enable_reg;
- if ((((u32)reg & 0xff) >= CM_FCLKEN1) &&
- (((u32)reg & 0xff) <= OMAP24XX_CM_FCLKEN2))
- other_reg = (void __iomem *)(((u32)reg & ~0xf0) | 0x10); /* CM_ICLKEN* */
- else if ((((u32)reg & 0xff) >= CM_ICLKEN1) &&
- (((u32)reg & 0xff) <= OMAP24XX_CM_ICLKEN4))
- other_reg = (void __iomem *)(((u32)reg & ~0xf0) | 0x00); /* CM_FCLKEN* */
+ u32 bit, reg, other_reg, st_reg;
+
+ reg = (__force u32)clk->enable_reg;
+ if (((reg & 0xff) >= CM_FCLKEN1) &&
+ ((reg & 0xff) <= OMAP24XX_CM_FCLKEN2))
+ other_reg = ((reg & ~0xf0) | 0x10); /* CM_ICLKEN* */
+ else if (((reg & 0xff) >= CM_ICLKEN1) &&
+ ((reg & 0xff) <= OMAP24XX_CM_ICLKEN4))
+ other_reg = ((reg & ~0xf0) | 0x00); /* CM_FCLKEN* */
else
return;
/* REVISIT: What are the appropriate exclusions for 34XX? */
/* No check for DSS or cam clocks */
- if (cpu_is_omap24xx() && ((u32)reg & 0x0f) == 0) { /* CM_{F,I}CLKEN1 */
+ if (cpu_is_omap24xx() && (reg & 0x0f) == 0) { /* CM_{F,I}CLKEN1 */
if (clk->enable_bit == OMAP24XX_EN_DSS2_SHIFT ||
clk->enable_bit == OMAP24XX_EN_DSS1_SHIFT ||
clk->enable_bit == OMAP24XX_EN_CAM_SHIFT)
/* REVISIT: What are the appropriate exclusions for 34XX? */
/* OMAP3: ignore DSS-mod clocks */
if (cpu_is_omap34xx() &&
- (((u32)reg & ~0xff) == (u32)OMAP_CM_REGADDR(OMAP3430_DSS_MOD, 0)))
+ ((reg & ~0xff) == cm_read_mod_reg(OMAP3430_DSS_MOD, 0) ||
+ (((reg & ~0xff) == cm_read_mod_reg(CORE_MOD, 0)) &&
+ clk->enable_bit == OMAP3430_EN_SSI_SHIFT)))
return;
/* Check if both functional and interface clocks
* are running. */
bit = 1 << clk->enable_bit;
- if (!(__raw_readl(other_reg) & bit))
+ if (!(__raw_readl((__force void __iomem *)other_reg) & bit))
return;
- st_reg = (void __iomem *)(((u32)other_reg & ~0xf0) | 0x20); /* CM_IDLEST* */
+ st_reg = ((other_reg & ~0xf0) | 0x20); /* CM_IDLEST* */
- omap2_wait_clock_ready(st_reg, bit, clk->name);
+ omap2_wait_clock_ready((__force void __iomem *)st_reg, bit, clk->name);
}
/* Enables clock without considering parent dependencies or use count
* REVISIT: Maybe change this to use clk->enable like on omap1?
*/
-int _omap2_clk_enable(struct clk *clk)
+static int _omap2_clk_enable(struct clk *clk)
{
u32 regval32;
if (clk->enable)
return clk->enable(clk);
- if (unlikely(clk->enable_reg == 0)) {
+ if (!clk->enable_reg) {
printk(KERN_ERR "clock.c: Enable for %s without enable code\n",
clk->name);
return 0; /* REVISIT: -EINVAL */
}
/* Disables clock without considering parent dependencies or use count */
-void _omap2_clk_disable(struct clk *clk)
+static void _omap2_clk_disable(struct clk *clk)
{
u32 regval32;
return;
}
- if (clk->enable_reg == 0) {
+ if (!clk->enable_reg) {
/*
* 'Independent' here refers to a clock which is not
* controlled by its parent.
{
if (clk->usecount > 0 && !(--clk->usecount)) {
_omap2_clk_disable(clk);
- if (likely((u32)clk->parent))
+ if (clk->parent)
omap2_clk_disable(clk->parent);
+ if (clk->clkdm)
+ omap2_clkdm_clk_disable(clk->clkdm, clk);
+
}
}
int ret = 0;
if (clk->usecount++ == 0) {
- if (likely((u32)clk->parent))
+ if (clk->parent)
ret = omap2_clk_enable(clk->parent);
- if (unlikely(ret != 0)) {
+ if (ret != 0) {
clk->usecount--;
return ret;
}
+ if (clk->clkdm)
+ omap2_clkdm_clk_enable(clk->clkdm, clk);
+
ret = _omap2_clk_enable(clk);
- if (unlikely(ret != 0) && clk->parent) {
- omap2_clk_disable(clk->parent);
- clk->usecount--;
+ if (ret != 0) {
+ if (clk->clkdm)
+ omap2_clkdm_clk_disable(clk->clkdm, clk);
+
+ if (clk->parent) {
+ omap2_clk_disable(clk->parent);
+ clk->usecount--;
+ }
}
}
if (div == 0)
return;
- if (unlikely(clk->rate == clk->parent->rate / div))
+ if (clk->rate == (clk->parent->rate / div))
return;
clk->rate = clk->parent->rate / div;
pr_debug("clock: new clock rate is %ld (div %d)\n", clk->rate, div);
- if (unlikely(clk->flags & RATE_PROPAGATES))
+ if (clk->flags & RATE_PROPAGATES)
propagate_rate(clk);
}
* the element associated with the supplied parent clock address.
* Returns a pointer to the struct clksel on success or NULL on error.
*/
-const struct clksel *omap2_get_clksel_by_parent(struct clk *clk,
- struct clk *src_clk)
+static const struct clksel *omap2_get_clksel_by_parent(struct clk *clk,
+ struct clk *src_clk)
{
const struct clksel *clks;
*new_div = 1;
clks = omap2_get_clksel_by_parent(clk, clk->parent);
- if (clks == NULL)
+ if (!clks)
return ~0;
for (clkr = clks->rates; clkr->div; clkr++) {
/* Given a clock and a rate apply a clock specific rounding function */
long omap2_clk_round_rate(struct clk *clk, unsigned long rate)
{
- if (clk->round_rate != 0)
+ if (clk->round_rate)
return clk->round_rate(clk, rate);
if (clk->flags & RATE_FIXED)
const struct clksel_rate *clkr;
clks = omap2_get_clksel_by_parent(clk, clk->parent);
- if (clks == NULL)
+ if (!clks)
return 0;
for (clkr = clks->rates; clkr->div; clkr++) {
WARN_ON(div == 0);
clks = omap2_get_clksel_by_parent(clk, clk->parent);
- if (clks == NULL)
+ if (!clks)
return 0;
for (clkr = clks->rates; clkr->div; clkr++) {
*
* Returns the address of the clksel register upon success or NULL on error.
*/
-void __iomem *omap2_get_clksel(struct clk *clk, u32 *field_mask)
+static void __iomem *omap2_get_clksel(struct clk *clk, u32 *field_mask)
{
- if (unlikely((clk->clksel_reg == 0) || (clk->clksel_mask == 0)))
+ if (!clk->clksel_reg || (clk->clksel_mask == 0))
return NULL;
*field_mask = clk->clksel_mask;
void __iomem *div_addr;
div_addr = omap2_get_clksel(clk, &field_mask);
- if (div_addr == 0)
+ if (!div_addr)
return 0;
field_val = __raw_readl(div_addr) & field_mask;
int omap2_clksel_set_rate(struct clk *clk, unsigned long rate)
{
- u32 field_mask, field_val, reg_val, validrate, new_div = 0;
+ u32 field_mask, field_val, validrate, new_div = 0;
void __iomem *div_addr;
validrate = omap2_clksel_round_rate_div(clk, rate, &new_div);
return -EINVAL;
div_addr = omap2_get_clksel(clk, &field_mask);
- if (div_addr == 0)
+ if (!div_addr)
return -EINVAL;
field_val = omap2_divisor_to_clksel(clk, new_div);
if (field_val == ~0)
return -EINVAL;
- reg_val = __raw_readl(div_addr);
- reg_val &= ~field_mask;
- reg_val |= (field_val << __ffs(field_mask));
- __raw_writel(reg_val, div_addr);
+ cm_rmw_reg_bits(field_mask, field_val << __ffs(field_mask), div_addr);
+
wmb();
clk->rate = clk->parent->rate / new_div;
if (clk->flags & DELAYED_APP && cpu_is_omap24xx()) {
- __raw_writel(OMAP24XX_VALID_CONFIG, OMAP24XX_PRCM_CLKCFG_CTRL);
+ prm_write_mod_reg(OMAP24XX_VALID_CONFIG,
+ OMAP24XX_GR_MOD, OMAP24XX_PRCM_CLKCFG_CTRL_OFFSET);
wmb();
}
return -EINVAL;
/* dpll_ck, core_ck, virt_prcm_set; plus all clksel clocks */
- if (clk->set_rate != 0)
+ if (clk->set_rate)
ret = clk->set_rate(clk, rate);
- if (unlikely(ret == 0 && (clk->flags & RATE_PROPAGATES)))
+ if (ret == 0 && (clk->flags & RATE_PROPAGATES))
propagate_rate(clk);
return ret;
const struct clksel_rate *clkr;
*parent_div = 0;
- *src_addr = 0;
+ *src_addr = NULL;
clks = omap2_get_clksel_by_parent(clk, src_clk);
- if (clks == NULL)
+ if (!clks)
return 0;
for (clkr = clks->rates; clkr->div; clkr++) {
void __iomem *src_addr;
u32 field_val, field_mask, reg_val, parent_div;
- if (unlikely(clk->flags & CONFIG_PARTICIPANT))
+ if (clk->flags & CONFIG_PARTICIPANT)
return -EINVAL;
if (!clk->clksel)
field_val = omap2_clksel_get_src_field(&src_addr, new_parent,
&field_mask, clk, &parent_div);
- if (src_addr == 0)
+ if (!src_addr)
return -EINVAL;
if (clk->usecount > 0)
wmb();
if (clk->flags & DELAYED_APP && cpu_is_omap24xx()) {
- __raw_writel(OMAP24XX_VALID_CONFIG, OMAP24XX_PRCM_CLKCFG_CTRL);
+ prm_write_mod_reg(OMAP24XX_VALID_CONFIG,
+ OMAP24XX_GR_MOD, OMAP24XX_PRCM_CLKCFG_CTRL_OFFSET);
wmb();
}
pr_debug("clock: set parent of %s to %s (new rate %ld)\n",
clk->name, clk->parent->name, clk->rate);
- if (unlikely(clk->flags & RATE_PROPAGATES))
+ if (clk->flags & RATE_PROPAGATES)
propagate_rate(clk);
return 0;
}
+/* DPLL rate rounding code */
+
+/**
+ * omap2_dpll_set_rate_tolerance: set the error tolerance during rate rounding
+ * @clk: struct clk * of the DPLL
+ * @tolerance: maximum rate error tolerance
+ *
+ * Set the maximum DPLL rate error tolerance for the rate rounding
+ * algorithm. The rate tolerance is an attempt to balance DPLL power
+ * saving (the least divider value "n") vs. rate fidelity (the least
+ * difference between the desired DPLL target rate and the rounded
+ * rate out of the algorithm). So, increasing the tolerance is likely
+ * to decrease DPLL power consumption and increase DPLL rate error.
+ * Returns -EINVAL if provided a null clock ptr or a clk that is not a
+ * DPLL; or 0 upon success.
+ */
+int omap2_dpll_set_rate_tolerance(struct clk *clk, unsigned int tolerance)
+{
+ if (!clk || !clk->dpll_data)
+ return -EINVAL;
+
+ clk->dpll_data->rate_tolerance = tolerance;
+
+ return 0;
+}
+
+static unsigned long _dpll_compute_new_rate(unsigned long parent_rate,
+ unsigned int m, unsigned int n)
+{
+ unsigned long long num;
+
+ num = (unsigned long long)parent_rate * m;
+ do_div(num, n);
+ return num;
+}
+
+/*
+ * _dpll_test_mult - test a DPLL multiplier value
+ * @m: pointer to the DPLL m (multiplier) value under test
+ * @n: current DPLL n (divider) value under test
+ * @new_rate: pointer to storage for the resulting rounded rate
+ * @target_rate: the desired DPLL rate
+ * @parent_rate: the DPLL's parent clock rate
+ *
+ * This code tests a DPLL multiplier value, ensuring that the
+ * resulting rate will not be higher than the target_rate, and that
+ * the multiplier value itself is valid for the DPLL. Initially, the
+ * integer pointed to by the m argument should be prescaled by
+ * multiplying by DPLL_SCALE_FACTOR. The code will replace this with
+ * a non-scaled m upon return. This non-scaled m will result in a
+ * new_rate as close as possible to target_rate (but not greater than
+ * target_rate) given the current (parent_rate, n, prescaled m)
+ * triple. Returns DPLL_MULT_UNDERFLOW in the event that the
+ * non-scaled m attempted to underflow, which can allow the calling
+ * function to bail out early; or 0 upon success.
+ */
+static int _dpll_test_mult(int *m, int n, unsigned long *new_rate,
+ unsigned long target_rate,
+ unsigned long parent_rate)
+{
+ int flags = 0, carry = 0;
+
+ /* Unscale m and round if necessary */
+ if (*m % DPLL_SCALE_FACTOR >= DPLL_ROUNDING_VAL)
+ carry = 1;
+ *m = (*m / DPLL_SCALE_FACTOR) + carry;
+
+ /*
+ * The new rate must be <= the target rate to avoid programming
+ * a rate that is impossible for the hardware to handle
+ */
+ *new_rate = _dpll_compute_new_rate(parent_rate, *m, n);
+ if (*new_rate > target_rate) {
+ (*m)--;
+ *new_rate = 0;
+ }
+
+ /* Guard against m underflow */
+ if (*m < DPLL_MIN_MULTIPLIER) {
+ *m = DPLL_MIN_MULTIPLIER;
+ *new_rate = 0;
+ flags = DPLL_MULT_UNDERFLOW;
+ }
+
+ if (*new_rate == 0)
+ *new_rate = _dpll_compute_new_rate(parent_rate, *m, n);
+
+ return flags;
+}
+
+/**
+ * omap2_dpll_round_rate - round a target rate for an OMAP DPLL
+ * @clk: struct clk * for a DPLL
+ * @target_rate: desired DPLL clock rate
+ *
+ * Given a DPLL, a desired target rate, and a rate tolerance, round
+ * the target rate to a possible, programmable rate for this DPLL.
+ * Rate tolerance is assumed to be set by the caller before this
+ * function is called. Attempts to select the minimum possible n
+ * within the tolerance to reduce power consumption. Stores the
+ * computed (m, n) in the DPLL's dpll_data structure so set_rate()
+ * will not need to call this (expensive) function again. Returns ~0
+ * if the target rate cannot be rounded, either because the rate is
+ * too low or because the rate tolerance is set too tightly; or the
+ * rounded rate upon success.
+ */
+long omap2_dpll_round_rate(struct clk *clk, unsigned long target_rate)
+{
+ int m, n, r, e, scaled_max_m;
+ unsigned long scaled_rt_rp, new_rate;
+ int min_e = -1, min_e_m = -1, min_e_n = -1;
+
+ if (!clk || !clk->dpll_data)
+ return ~0;
+
+ pr_debug("clock: starting DPLL round_rate for clock %s, target rate "
+ "%ld\n", clk->name, target_rate);
+
+ scaled_rt_rp = target_rate / (clk->parent->rate / DPLL_SCALE_FACTOR);
+ scaled_max_m = clk->dpll_data->max_multiplier * DPLL_SCALE_FACTOR;
+
+ clk->dpll_data->last_rounded_rate = 0;
+
+ for (n = clk->dpll_data->max_divider; n >= DPLL_MIN_DIVIDER; n--) {
+
+ /* Compute the scaled DPLL multiplier, based on the divider */
+ m = scaled_rt_rp * n;
+
+ /*
+ * Since we're counting n down, a m overflow means we can
+ * can immediately skip to the next n
+ */
+ if (m > scaled_max_m)
+ continue;
+
+ r = _dpll_test_mult(&m, n, &new_rate, target_rate,
+ clk->parent->rate);
+
+ e = target_rate - new_rate;
+ pr_debug("clock: n = %d: m = %d: rate error is %d "
+ "(new_rate = %ld)\n", n, m, e, new_rate);
+
+ if (min_e == -1 ||
+ min_e >= (int)(abs(e) - clk->dpll_data->rate_tolerance)) {
+ min_e = e;
+ min_e_m = m;
+ min_e_n = n;
+
+ pr_debug("clock: found new least error %d\n", min_e);
+ }
+
+ /*
+ * Since we're counting n down, a m underflow means we
+ * can bail out completely (since as n decreases in
+ * the next iteration, there's no way that m can
+ * increase beyond the current m)
+ */
+ if (r & DPLL_MULT_UNDERFLOW)
+ break;
+ }
+
+ if (min_e < 0) {
+ pr_debug("clock: error: target rate or tolerance too low\n");
+ return ~0;
+ }
+
+ clk->dpll_data->last_rounded_m = min_e_m;
+ clk->dpll_data->last_rounded_n = min_e_n;
+ clk->dpll_data->last_rounded_rate =
+ _dpll_compute_new_rate(clk->parent->rate, min_e_m, min_e_n);
+
+ pr_debug("clock: final least error: e = %d, m = %d, n = %d\n",
+ min_e, min_e_m, min_e_n);
+ pr_debug("clock: final rate: %ld (target rate: %ld)\n",
+ clk->dpll_data->last_rounded_rate, target_rate);
+
+ return clk->dpll_data->last_rounded_rate;
+}
+
/*-------------------------------------------------------------------------
* Omap2 clock reset and init functions
*-------------------------------------------------------------------------*/
projects / linux-2.6-omap-h63xx.git / blobdiff