Merge branch 'clk-frac-divider' into clk-next

- Add power of two flag to fractional divider clk type

* clk-frac-divider:
  clk: fractional-divider: Document the arithmetics used behind the code
  clk: fractional-divider: Introduce POWER_OF_TWO_PS flag
  clk: fractional-divider: Hide clk_fractional_divider_ops from wide audience
  clk: fractional-divider: Export approximation algorithm to the CCF users

drivers/acpi/acpi_lpss.c

@@ -436,8 +436,8 @@ static int register_device_clock(struct acpi_device *adev,
 		if (!clk_name)
 			return -ENOMEM;
 		clk = clk_register_fractional_divider(NULL, clk_name, parent,
-						      0, prv_base,
-						      1, 15, 16, 15, 0, NULL);
+						      CLK_FRAC_DIVIDER_POWER_OF_TWO_PS,
+						      prv_base, 1, 15, 16, 15, 0, NULL);
 		parent = clk_name;
 
 		clk_name = kasprintf(GFP_KERNEL, "%s-update", devname);

drivers/clk/clk-fractional-divider.c

@@ -3,8 +3,39 @@
  * Copyright (C) 2014 Intel Corporation
  *
  * Adjustable fractional divider clock implementation.
- * Output rate = (m / n) * parent_rate.
  * Uses rational best approximation algorithm.
+ *
+ * Output is calculated as
+ *
+ *	rate = (m / n) * parent_rate				(1)
+ *
+ * This is useful when we have a prescaler block which asks for
+ * m (numerator) and n (denominator) values to be provided to satisfy
+ * the (1) as much as possible.
+ *
+ * Since m and n have the limitation by a range, e.g.
+ *
+ *	n >= 1, n < N_width, where N_width = 2^nwidth		(2)
+ *
+ * for some cases the output may be saturated. Hence, from (1) and (2),
+ * assuming the worst case when m = 1, the inequality
+ *
+ *	floor(log2(parent_rate / rate)) <= nwidth		(3)
+ *
+ * may be derived. Thus, in cases when
+ *
+ *	(parent_rate / rate) >> N_width				(4)
+ *
+ * we might scale up the rate by 2^scale (see the description of
+ * CLK_FRAC_DIVIDER_POWER_OF_TWO_PS for additional information), where
+ *
+ *	scale = floor(log2(parent_rate / rate)) - nwidth	(5)
+ *
+ * and assume that the IP, that needs m and n, has also its own
+ * prescaler, which is capable to divide by 2^scale. In this way
+ * we get the denominator to satisfy the desired range (2) and
+ * at the same time much much better result of m and n than simple
+ * saturated values.
  */
 
 #include <linux/clk-provider.h>
@@ -14,6 +45,8 @@
 #include <linux/slab.h>
 #include <linux/rational.h>
 
+#include "clk-fractional-divider.h"
+
 static inline u32 clk_fd_readl(struct clk_fractional_divider *fd)
 {
 	if (fd->flags & CLK_FRAC_DIVIDER_BIG_ENDIAN)
@@ -68,21 +101,26 @@ static unsigned long clk_fd_recalc_rate(struct clk_hw *hw,
 	return ret;
 }
 
-static void clk_fd_general_approximation(struct clk_hw *hw, unsigned long rate,
-					 unsigned long *parent_rate,
-					 unsigned long *m, unsigned long *n)
+void clk_fractional_divider_general_approximation(struct clk_hw *hw,
+						  unsigned long rate,
+						  unsigned long *parent_rate,
+						  unsigned long *m, unsigned long *n)
 {
 	struct clk_fractional_divider *fd = to_clk_fd(hw);
-	unsigned long scale;
 
 	/*
 	 * Get rate closer to *parent_rate to guarantee there is no overflow
 	 * for m and n. In the result it will be the nearest rate left shifted
 	 * by (scale - fd->nwidth) bits.
+	 *
+	 * For the detailed explanation see the top comment in this file.
 	 */
-	scale = fls_long(*parent_rate / rate - 1);
-	if (scale > fd->nwidth)
-		rate <<= scale - fd->nwidth;
+	if (fd->flags & CLK_FRAC_DIVIDER_POWER_OF_TWO_PS) {
+		unsigned long scale = fls_long(*parent_rate / rate - 1);
+
+		if (scale > fd->nwidth)
+			rate <<= scale - fd->nwidth;
+	}
 
 	rational_best_approximation(rate, *parent_rate,
 			GENMASK(fd->mwidth - 1, 0), GENMASK(fd->nwidth - 1, 0),
@@ -102,7 +140,7 @@ static long clk_fd_round_rate(struct clk_hw *hw, unsigned long rate,
 	if (fd->approximation)
 		fd->approximation(hw, rate, parent_rate, &m, &n);
 	else
-		clk_fd_general_approximation(hw, rate, parent_rate, &m, &n);
+		clk_fractional_divider_general_approximation(hw, rate, parent_rate, &m, &n);
 
 	ret = (u64)*parent_rate * m;
 	do_div(ret, n);

drivers/clk/clk-fractional-divider.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _CLK_FRACTIONAL_DIV_H
+#define _CLK_FRACTIONAL_DIV_H
+
+struct clk_hw;
+
+extern const struct clk_ops clk_fractional_divider_ops;
+
+void clk_fractional_divider_general_approximation(struct clk_hw *hw,
+						  unsigned long rate,
+						  unsigned long *parent_rate,
+						  unsigned long *m,
+						  unsigned long *n);
+
+#endif

drivers/clk/imx/clk-composite-7ulp.c

@@ -10,6 +10,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 
+#include "../clk-fractional-divider.h"
 #include "clk.h"
 
 #define PCG_PCS_SHIFT	24

drivers/clk/rockchip/clk.c

@@ -22,6 +22,8 @@
 #include <linux/regmap.h>
 #include <linux/reboot.h>
 #include <linux/rational.h>
+
+#include "../clk-fractional-divider.h"
 #include "clk.h"
 
 /*
@@ -178,10 +180,8 @@ static void rockchip_fractional_approximation(struct clk_hw *hw,
 		unsigned long rate, unsigned long *parent_rate,
 		unsigned long *m, unsigned long *n)
 {
-	struct clk_fractional_divider *fd = to_clk_fd(hw);
 	unsigned long p_rate, p_parent_rate;
 	struct clk_hw *p_parent;
-	unsigned long scale;
 
 	p_rate = clk_hw_get_rate(clk_hw_get_parent(hw));
 	if ((rate * 20 > p_rate) && (p_rate % rate != 0)) {
@@ -190,18 +190,7 @@ static void rockchip_fractional_approximation(struct clk_hw *hw,
 		*parent_rate = p_parent_rate;
 	}
 
-	/*
-	 * Get rate closer to *parent_rate to guarantee there is no overflow
-	 * for m and n. In the result it will be the nearest rate left shifted
-	 * by (scale - fd->nwidth) bits.
-	 */
-	scale = fls_long(*parent_rate / rate - 1);
-	if (scale > fd->nwidth)
-		rate <<= scale - fd->nwidth;
-
-	rational_best_approximation(rate, *parent_rate,
-			GENMASK(fd->mwidth - 1, 0), GENMASK(fd->nwidth - 1, 0),
-			m, n);
+	clk_fractional_divider_general_approximation(hw, rate, parent_rate, m, n);
 }
 
 static struct clk *rockchip_clk_register_frac_branch(

drivers/mfd/intel-lpss.c

@@ -301,7 +301,8 @@ static int intel_lpss_register_clock_divider(struct intel_lpss *lpss,
 
 	snprintf(name, sizeof(name), "%s-div", devname);
 	tmp = clk_register_fractional_divider(NULL, name, __clk_get_name(tmp),
-					      0, lpss->priv, 1, 15, 16, 15, 0,
+					      CLK_FRAC_DIVIDER_POWER_OF_TWO_PS,
+					      lpss->priv, 1, 15, 16, 15, 0,
 					      NULL);
 	if (IS_ERR(tmp))
 		return PTR_ERR(tmp);

include/linux/clk-provider.h

@@ -1001,6 +1001,12 @@ struct clk_hw *devm_clk_hw_register_fixed_factor(struct device *dev,
  * CLK_FRAC_DIVIDER_BIG_ENDIAN - By default little endian register accesses are
  *	used for the divider register.  Setting this flag makes the register
  *	accesses big endian.
+ * CLK_FRAC_DIVIDER_POWER_OF_TWO_PS - By default the resulting fraction might
+ *	be saturated and the caller will get quite far from the good enough
+ *	approximation. Instead the caller may require, by setting this flag,
+ *	to shift left by a few bits in case, when the asked one is quite small
+ *	to satisfy the desired range of denominator. It assumes that on the
+ *	caller's side the power-of-two capable prescaler exists.
  */
 struct clk_fractional_divider {
 	struct clk_hw	hw;
@@ -1020,10 +1026,10 @@ struct clk_fractional_divider {
 
 #define to_clk_fd(_hw) container_of(_hw, struct clk_fractional_divider, hw)
 
-#define CLK_FRAC_DIVIDER_ZERO_BASED	BIT(0)
-#define CLK_FRAC_DIVIDER_BIG_ENDIAN	BIT(1)
+#define CLK_FRAC_DIVIDER_ZERO_BASED		BIT(0)
+#define CLK_FRAC_DIVIDER_BIG_ENDIAN		BIT(1)
+#define CLK_FRAC_DIVIDER_POWER_OF_TWO_PS	BIT(2)
 
-extern const struct clk_ops clk_fractional_divider_ops;
 struct clk *clk_register_fractional_divider(struct device *dev,
 		const char *name, const char *parent_name, unsigned long flags,
 		void __iomem *reg, u8 mshift, u8 mwidth, u8 nshift, u8 nwidth,