ARM: OMAP4: Enhance support for DPLLs with 4X multiplier

On OMAP4 devices, the ABE DPLL has an internal 4X multiplier that can
be enabled or disabled in addition to the standard configurable
multiplier (M) for OMAP DPLLs. When configuring the ABE DPLL the 4X
multiplier is accounted for by checking to see whether it is enabled or
not. However, when calculating a new rate we only check to see if the
rate can be achieved with the current setting for the 4X multiplier.
Enhance the round_rate() function for such DPLLs to see if the rate
can be achieved with the 4X multiplier if it cannot be achieved without
the 4X multiplier.

This change is necessary, because when using the 32kHz clock as the
source clock for the ABE DPLL, the default DPLL frequency for the ABE
DPLL cannot be achieved without enabling the 4X multiplier.

When using the 32kHz clock as the source clock for the ABE DPLL and
attempting to lock the DPLL to 98.304MHz (default frequency), it was
found that the DPLL would fail to lock if the low-power mode for the DPLL
was not enabled. From reviewing boot-loader settings that configure the
ABE DPLL it was found that the low-power mode is enabled when using the
32kHz clock source, however, the documentation for OMAP does not state
that this is a requirement. Therefore, introduce a new function for
OMAP4 devices to see if low-power mode can be enabled when calculating a
new rate to ensure the DPLL will lock.

New variables for the last calculated 4X multiplier and low-power
setting have been added to the dpll data structure as well as variables
defining the bit mask for enabling these features via the DPLL's
control_reg. It is possible that we could eliminate these bit masks from
the dpll data structure as these bit masks are not unique to OMAP4, if
it is preferred.

The function omap3_noncore_program_dpll() has been updated to avoid
passing the calculated values for the multiplier (M) and divider (N) as
these are stored in the clk structure.

Signed-off-by: Jon Hunter <jon-hunter@ti.com>
Signed-off-by: Paul Walmsley <paul@pwsan.com>
diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c
index fafb28c..2bb1883 100644
--- a/arch/arm/mach-omap2/dpll3xxx.c
+++ b/arch/arm/mach-omap2/dpll3xxx.c
@@ -291,16 +291,13 @@
 
 /*
  * _omap3_noncore_dpll_program - set non-core DPLL M,N values directly
- * @clk: struct clk * of DPLL to set
- * @m: DPLL multiplier to set
- * @n: DPLL divider to set
- * @freqsel: FREQSEL value to set
+ * @clk:	struct clk * of DPLL to set
+ * @freqsel:	FREQSEL value to set
  *
- * Program the DPLL with the supplied M, N values, and wait for the DPLL to
- * lock..  Returns -EINVAL upon error, or 0 upon success.
+ * Program the DPLL with the last M, N values calculated, and wait for
+ * the DPLL to lock. Returns -EINVAL upon error, or 0 upon success.
  */
-static int omap3_noncore_dpll_program(struct clk_hw_omap *clk, u16 m, u8 n,
-				      u16 freqsel)
+static int omap3_noncore_dpll_program(struct clk_hw_omap *clk, u16 freqsel)
 {
 	struct dpll_data *dd = clk->dpll_data;
 	u8 dco, sd_div;
@@ -323,23 +320,45 @@
 	/* Set DPLL multiplier, divider */
 	v = __raw_readl(dd->mult_div1_reg);
 	v &= ~(dd->mult_mask | dd->div1_mask);
-	v |= m << __ffs(dd->mult_mask);
-	v |= (n - 1) << __ffs(dd->div1_mask);
+	v |= dd->last_rounded_m << __ffs(dd->mult_mask);
+	v |= (dd->last_rounded_n - 1) << __ffs(dd->div1_mask);
 
 	/* Configure dco and sd_div for dplls that have these fields */
 	if (dd->dco_mask) {
-		_lookup_dco(clk, &dco, m, n);
+		_lookup_dco(clk, &dco, dd->last_rounded_m, dd->last_rounded_n);
 		v &= ~(dd->dco_mask);
 		v |= dco << __ffs(dd->dco_mask);
 	}
 	if (dd->sddiv_mask) {
-		_lookup_sddiv(clk, &sd_div, m, n);
+		_lookup_sddiv(clk, &sd_div, dd->last_rounded_m,
+			      dd->last_rounded_n);
 		v &= ~(dd->sddiv_mask);
 		v |= sd_div << __ffs(dd->sddiv_mask);
 	}
 
 	__raw_writel(v, dd->mult_div1_reg);
 
+	/* Set 4X multiplier and low-power mode */
+	if (dd->m4xen_mask || dd->lpmode_mask) {
+		v = __raw_readl(dd->control_reg);
+
+		if (dd->m4xen_mask) {
+			if (dd->last_rounded_m4xen)
+				v |= dd->m4xen_mask;
+			else
+				v &= ~dd->m4xen_mask;
+		}
+
+		if (dd->lpmode_mask) {
+			if (dd->last_rounded_lpmode)
+				v |= dd->lpmode_mask;
+			else
+				v &= ~dd->lpmode_mask;
+		}
+
+		__raw_writel(v, dd->control_reg);
+	}
+
 	/* We let the clock framework set the other output dividers later */
 
 	/* REVISIT: Set ramp-up delay? */
@@ -492,8 +511,7 @@
 		pr_debug("%s: %s: set rate: locking rate to %lu.\n",
 			 __func__, __clk_get_name(hw->clk), rate);
 
-		ret = omap3_noncore_dpll_program(clk, dd->last_rounded_m,
-						dd->last_rounded_n, freqsel);
+		ret = omap3_noncore_dpll_program(clk, freqsel);
 		if (!ret)
 			new_parent = dd->clk_ref;
 	}