Re: [PATCH v4 2/4] clk: rockchip: Add internal support for 24-bit fractional dividers

Co-developed-by: Cunhao Lu <redacted>
Signed-off-by: Cunhao Lu <redacted>
---
Changes in v3:
- Reject compensated ratios that exceed the actual field widths before
   multiplication or register writes.
---
  drivers/clk/rockchip/Makefile                    |   1 +
  drivers/clk/rockchip/clk-fractional-divider-v2.c | 354 +++++++++++++++++++++++
  drivers/clk/rockchip/clk.c                       |  10 +
  drivers/clk/rockchip/clk.h                       |  25 ++
  4 files changed, 390 insertions(+)

diff --git a/drivers/clk/rockchip/Makefile b/drivers/clk/rockchip/Makefile
index 554b7eb83dc91..91d4ea4837e3e 100644
--- a/drivers/clk/rockchip/Makefile
+++ b/drivers/clk/rockchip/Makefile

@@ -10,6 +10,7 @@ clk-rockchip-y += clk-pll.o
  clk-rockchip-y += clk-cpu.o
  clk-rockchip-y += clk-gate-grf.o
  clk-rockchip-y += clk-half-divider.o
+clk-rockchip-y += clk-fractional-divider-v2.o
  clk-rockchip-y += clk-inverter.o
  clk-rockchip-y += clk-mmc-phase.o
  clk-rockchip-y += clk-muxgrf.o

diff --git a/drivers/clk/rockchip/clk-fractional-divider-v2.c b/drivers/clk/rockchip/clk-fractional-divider-v2.c
new file mode 100644
index 0000000000000..102e03f9d6e60
--- /dev/null
+++ b/drivers/clk/rockchip/clk-fractional-divider-v2.c

@@ -0,0 +1,354 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2024 Rockchip Electronics Co., Ltd.
+ *
+ * Adjustable fractional divider clock implementation.
+ * 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 a much better result of m and n than simple
+ * saturated values.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/rational.h>
+#include "clk.h"
+
+struct clk_fractional_divider_v2 {
+	struct clk_hw	hw;
+	void __iomem	*reg;
+	void __iomem	*high_reg;
+	u8		mshift;
+	u8		mwidth;
+	u32		mmask;
+	u8		nshift;
+	u8		nwidth;
+	u32		nmask;
+	u8		high_mshift;
+	u8		high_mwidth;
+	u32		high_mmask;
+	u8		high_nshift;
+	u8		high_nwidth;
+	u32		high_nmask;
+	u8		flags;
+	void		(*approximation)(struct clk_hw *hw,
+					 unsigned long rate,
+					 unsigned long *parent_rate,
+					 unsigned long *m, unsigned long *n);
+	spinlock_t	*lock; /* Protects the low and high register pair. */
+};
+
+#define to_clk_fd_v2(_hw) container_of(_hw, struct clk_fractional_divider_v2, hw)
+
+static inline u32 clk_fd_v2_readl(struct clk_fractional_divider_v2 *fd,
+				  void __iomem *reg)
+{
+	return readl(reg);
+}
+
+static inline void clk_fd_v2_writel(struct clk_fractional_divider_v2 *fd,
+				    void __iomem *reg, u32 val)
+{
+	writel(val, reg);
+}
+
+static unsigned long clk_fd_v2_recalc_rate(struct clk_hw *hw,
+					   unsigned long parent_rate)
+{
+	struct clk_fractional_divider_v2 *fd = to_clk_fd_v2(hw);
+	unsigned long flags = 0;
+	unsigned long m_low, n_low, m_high, n_high, m, n;
+	u32 val_low, val_high;
+	u64 ret;
+
+	if (fd->lock)
+		spin_lock_irqsave(fd->lock, flags);
+	else
+		__acquire(fd->lock);
+
+	val_low = clk_fd_v2_readl(fd, fd->reg);
+	val_high = clk_fd_v2_readl(fd, fd->high_reg);
+
+	if (fd->lock)
+		spin_unlock_irqrestore(fd->lock, flags);
+	else
+		__release(fd->lock);
+
+	m_low = (val_low & fd->mmask) >> fd->mshift;
+	n_low = (val_low & fd->nmask) >> fd->nshift;
+	m_high = (val_high & fd->high_mmask) >> fd->high_mshift;
+	n_high = (val_high & fd->high_nmask) >> fd->high_nshift;
+	m = (m_high << 16) | m_low;
+	n = (n_high << 16) | n_low;
+
+	if (fd->flags & CLK_FRAC_DIVIDER_ZERO_BASED) {
+		m++;
+		n++;
+	}
+
+	if (!n || !m)
+		return parent_rate;
+
+	ret = (u64)parent_rate * m;
+	do_div(ret, n);
+
+	return ret;
+}
+
+static void clk_fractional_divider_general_approximation_v2(struct clk_hw *hw,
+							    unsigned long rate,
+							    unsigned long *parent_rate,
+							    unsigned long *m, unsigned long *n)
+{
+	struct clk_fractional_divider_v2 *fd = to_clk_fd_v2(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;
+
+	rational_best_approximation(rate, *parent_rate,
+				    GENMASK(fd->mwidth - 1, 0),
+				    GENMASK(fd->nwidth - 1, 0),
+				    m, n);
+}
+
+static int clk_fd_v2_get_divider(struct clk_hw *hw, unsigned long rate,
+				 unsigned long parent_rate,
+				 unsigned long *m, unsigned long *n)
+{
+	struct clk_fractional_divider_v2 *fd = to_clk_fd_v2(hw);
+	u32 factor;
+
+	rational_best_approximation(rate, parent_rate,
+				    GENMASK(fd->mwidth - 1, 0),
+				    GENMASK(fd->nwidth - 1, 0),
+				    m, n);
+
+	if (fd->flags & CLK_FRAC_DIVIDER_ZERO_BASED) {
+		(*m)--;
+		(*n)--;
+	}
+	/*
+	 * When compensation the fractional divider,
+	 * the [1:0] bits of the numerator register are omitted,
+	 * which will lead to a large deviation in the result.
+	 * Therefore, it is required that the numerator must
+	 * be at least 4.
+	 *
+	 * Note that there are some exceptions here:
+	 * If there is an even frac div, we need to keep the original
+	 * numerator(<4) and denominator. Otherwise, it may cause the
+	 * issue that the duty ratio is not 50%.
+	 */
+	if (*m < 4 && *m != 0) {
+		if (*n % 2 == 0)
+			factor = 1;
+		else
+			factor = DIV_ROUND_UP(4, *m);
+
+		if (*m > GENMASK(fd->mwidth - 1, 0) / factor ||
+		    *n > GENMASK(fd->nwidth - 1, 0) / factor)
+			return -EINVAL;
+
+		*n *= factor;
+		*m *= factor;
+	}
+
+	return 0;
+}
+
+static int clk_fd_v2_determine_rate(struct clk_hw *hw,
+				    struct clk_rate_request *req)
+{
+	struct clk_fractional_divider_v2 *fd = to_clk_fd_v2(hw);
+	unsigned long m, n;
+	u64 ret;
+
+	if (!req->rate || req->rate >= req->best_parent_rate) {
+		req->rate = req->best_parent_rate;
+		return 0;
+	}
+
+	if (fd->approximation)
+		fd->approximation(hw, req->rate, &req->best_parent_rate, &m, &n);
+	else
+		clk_fractional_divider_general_approximation_v2(hw, req->rate,
+								&req->best_parent_rate,
+								&m, &n);
+
+	ret = (u64)req->best_parent_rate * m;
+	do_div(ret, n);
+	req->rate = ret;
+
+	/* Validate the rounded rate that set_rate() will receive. */
+	return clk_fd_v2_get_divider(hw, req->rate, req->best_parent_rate, &m, &n);
+}
+
+static int clk_fd_v2_set_rate(struct clk_hw *hw, unsigned long rate,
+			      unsigned long parent_rate)
+{
+	struct clk_fractional_divider_v2 *fd = to_clk_fd_v2(hw);
+	unsigned long flags = 0;
+	unsigned long m, n, m_low, n_low, m_high, n_high;
+	u32 val, val_high;
+	int ret;
+
+	ret = clk_fd_v2_get_divider(hw, rate, parent_rate, &m, &n);
+	if (ret)
+		return ret;
+
+	if (fd->lock)
+		spin_lock_irqsave(fd->lock, flags);
+	else
+		__acquire(fd->lock);
+
+	m_low = m & fd->nmask;
+	n_low = n & fd->nmask;
+	m_high = (m & GENMASK(fd->mwidth - 1, (fd->mwidth - fd->high_mwidth))) >>
+		 (fd->mwidth - fd->high_mwidth);
+	n_high = (n & GENMASK(fd->nwidth - 1, (fd->nwidth - fd->high_nwidth))) >>
+		 (fd->nwidth - fd->high_nwidth);
+
+	val_high = clk_fd_v2_readl(fd, fd->high_reg);
+	val_high &= ~(fd->high_mmask | fd->high_nmask);
+	val_high |= (m_high << fd->high_mshift) | (n_high << fd->high_nshift);
+
+	clk_fd_v2_writel(fd, fd->high_reg, val_high);
+
+	val = clk_fd_v2_readl(fd, fd->reg);
+	val &= ~(fd->mmask | fd->nmask);
+	val |= (m_low << fd->mshift) | (n_low << fd->nshift);
+	clk_fd_v2_writel(fd, fd->reg, val);
+
+	if (fd->lock)
+		spin_unlock_irqrestore(fd->lock, flags);
+	else
+		__release(fd->lock);
+
+	return 0;
+}
+
+static const struct clk_ops clk_fractional_divider_ops_v2 = {
+	.recalc_rate = clk_fd_v2_recalc_rate,
+	.determine_rate = clk_fd_v2_determine_rate,
+	.set_rate = clk_fd_v2_set_rate,
+};
+
+static struct clk_hw *clk_hw_register_fractional_divider_v2(struct device *dev,
+							    const char *name,
+							    const char *parent_name,
+							    unsigned long flags,
+							    void __iomem *reg,
+							    u8 mshift, u8 mwidth,
+							    u8 nshift, u8 nwidth,
+							    void __iomem *high_reg,
+							    u8 high_mshift, u8 high_mwidth,
+							    u8 high_nshift, u8 high_nwidth,
+							    u8 clk_divider_flags,
+							    spinlock_t *lock)
+{
+	struct clk_fractional_divider_v2 *fd;
+	struct clk_init_data init;
+	struct clk_hw *hw;
+	int ret;
+
+	fd = kzalloc_obj(*fd);
+	if (!fd)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.ops = &clk_fractional_divider_ops_v2;
+	init.flags = flags;
+	init.parent_names = parent_name ? &parent_name : NULL;
+	init.num_parents = parent_name ? 1 : 0;
+
+	fd->reg = reg;
+	fd->mshift = mshift;
+	fd->mwidth = mwidth + high_mwidth;
+	fd->mmask = GENMASK(mwidth - 1, 0) << mshift;
+	fd->nshift = nshift;
+	fd->nwidth = nwidth + high_nwidth;
+	fd->nmask = GENMASK(nwidth - 1, 0) << nshift;
+	fd->high_reg = high_reg;
+	fd->high_mshift = high_mshift;
+	fd->high_mwidth = high_mwidth;
+	fd->high_mmask = GENMASK(high_mwidth - 1, 0) << high_mshift;
+	fd->high_nshift = high_nshift;
+	fd->high_nwidth = high_nwidth;
+	fd->high_nmask = GENMASK(high_nwidth - 1, 0) << high_nshift;
+	fd->flags = clk_divider_flags;
+	fd->lock = lock;
+	fd->hw.init = &init;
+
+	hw = &fd->hw;
+	ret = clk_hw_register(dev, hw);
+	if (ret) {
+		kfree(fd);
+		hw = ERR_PTR(ret);
+	}
+
+	return hw;
+}
+
+struct clk *rockchip_clk_register_frac_v2(struct device *dev,
+					  const char *name,
+					  const char *parent_name,
+					  unsigned long flags,
+					  void __iomem *reg,
+					  u8 mshift, u8 width,
+					  void __iomem *high_reg,
+					  u8 high_mshift, u8 high_width,
+					  u8 clk_divider_flags,
+					  spinlock_t *lock)
+{
+	struct clk_hw *hw;
+
+	hw = clk_hw_register_fractional_divider_v2(dev, name, parent_name, flags,
+						   reg, mshift, width, 0, width,
+						   high_reg, high_mshift, high_width,
+						   0, high_width,
+						   clk_divider_flags,
+						   lock);
+	if (IS_ERR(hw))
+		return ERR_CAST(hw);
+	return hw->clk;
+}

diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c
index ee8c79b938d3c..0646a2e6af0a8 100644
--- a/drivers/clk/rockchip/clk.c
+++ b/drivers/clk/rockchip/clk.c

@@ -589,6 +589,16 @@ void rockchip_clk_register_branches(struct rockchip_clk_provider *ctx,
  				list->gate_flags, flags, list->child,
  				&ctx->lock);
  			break;
+		case branch_fraction_divider_v2:
+			clk = rockchip_clk_register_frac_v2(NULL, list->name,
+							    list->parent_names[0], flags,
+							    ctx->reg_base + list->muxdiv_offset,
+							    list->mux_shift, list->mux_width,
+							    ctx->reg_base + list->div_offset,
+							    list->div_shift, list->div_width,
+							    list->div_flags,
+							    &ctx->lock);
+			break;
  		case branch_half_divider:
  			clk = rockchip_clk_register_halfdiv(list->name,
  				list->parent_names, list->num_parents,

diff --git a/drivers/clk/rockchip/clk.h b/drivers/clk/rockchip/clk.h
index 72b36bba31523..dce4db3f67b04 100644
--- a/drivers/clk/rockchip/clk.h
+++ b/drivers/clk/rockchip/clk.h

@@ -781,6 +781,13 @@ struct clk *rockchip_clk_register_ddrclk(const char *name, int flags,
  					 int ddr_flags, void __iomem *reg_base,
  					 spinlock_t *lock);
  
+struct clk *rockchip_clk_register_frac_v2(struct device *dev,
+					  const char *name, const char *parent_name,
+					  unsigned long flags, void __iomem *reg,
+					  u8 mshift, u8 width,
+					  void __iomem *high_reg, u8 high_mshift, u8 high_width,
+					  u8 clk_divider_flags, spinlock_t *lock);
+
  #define ROCKCHIP_INVERTER_HIWORD_MASK	BIT(0)
  
  struct clk *rockchip_clk_register_inverter(const char *name,

@@ -806,6 +813,7 @@ enum rockchip_clk_branch_type {
  	branch_grf_mux,
  	branch_divider,
  	branch_fraction_divider,
+	branch_fraction_divider_v2,
  	branch_gate,
  	branch_grf_gate,
  	branch_linked_gate,

@@ -1014,6 +1022,23 @@ struct rockchip_clk_branch {
  		.child		= ch,				\
  	}
  
+#define COMPOSITE_FRAC_V2(_id, cname, pname, f, mo, ms, mw, do, ds, dw, df)\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_fraction_divider_v2,	\
+		.name		= cname,			\
+		.parent_names	= (const char *[]){ pname },	\
+		.num_parents	= 1,				\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.mux_shift	= ms,				\
+		.mux_width	= mw,				\
+		.div_offset	= do,				\
+		.div_shift	= ds,				\
+		.div_width	= dw,				\
+		.div_flags	= df,				\
+	}
+
  #define COMPOSITE_FRACMUX_NOGATE(_id, cname, pname, f, mo, df, ch) \
  	{							\
  		.id		= _id,				\