[PATCH v1 1/4] clk: sunxi-ng: add cycle-masking divider (maskdiv) clock type

Juan Manuel López Carrillo <[email protected]>
Newsgroups dev.linux.lists.linux-sunxi,org.infradead.lists.linux-arm-kernel,org.kernel.vger.linux-clk,org.kernel.vger.linux-devicetree,org.kernel.vger.linux-kernel
Message-ID <[email protected]>
Some mod clocks do not divide their parent with a linear M+1 divider:
the M factor masks (swallows) M pulses out of every 2^width parent
cycles, so the average output rate is

	rate = parent * (2^width - M) / 2^width

and the surviving pulses keep the parent period.  The A523/T527 GPU
clock (GPU_CLK_REG, 0x670) is such a divider: "FACTOR_M: mask M cycles
at 16 cycles", GPU_CLK = Clock Source * ((16-M)/16) (T527 user manual
v0.92, section 2.7.6.58).

Modelling these registers with the linear ccu_div type programs a
faster clock than requested for every M > 0 (e.g. M=1 on a 800 MHz
parent yields 750 MHz, not 400 MHz).

Add a small ccu type implementing the masking semantics.  Because the
masked output is not an even pulse train, determine_rate prefers, among
the parents that reach the requested rate, the one needing the least
masking.  set_rate_and_parent follows the same ordering rule as
clk_composite_set_rate_and_parent() so no intermediate configuration
overshoots both the old and the new rate.

Signed-off-by: Juan Manuel López Carrillo <[email protected]>
---
 drivers/clk/sunxi-ng/Makefile      |   1 +
 drivers/clk/sunxi-ng/ccu_maskdiv.c | 199 +++++++++++++++++++++++++++++
 drivers/clk/sunxi-ng/ccu_maskdiv.h |  71 ++++++++++
 3 files changed, 271 insertions(+)
 create mode 100644 drivers/clk/sunxi-ng/ccu_maskdiv.c
 create mode 100644 drivers/clk/sunxi-ng/ccu_maskdiv.h

diff --git a/drivers/clk/sunxi-ng/Makefile b/drivers/clk/sunxi-ng/Makefile
index a1c4087d7..26313083c 100644
--- a/drivers/clk/sunxi-ng/Makefile
+++ b/drivers/clk/sunxi-ng/Makefile
@@ -10,6 +10,7 @@ sunxi-ccu-y			+= ccu_reset.o
 # Base clock types
 sunxi-ccu-y			+= ccu_div.o
 sunxi-ccu-y			+= ccu_frac.o
+sunxi-ccu-y			+= ccu_maskdiv.o
 sunxi-ccu-y			+= ccu_gate.o
 sunxi-ccu-y			+= ccu_mux.o
 sunxi-ccu-y			+= ccu_mult.o
diff --git a/drivers/clk/sunxi-ng/ccu_maskdiv.c b/drivers/clk/sunxi-ng/ccu_maskdiv.c
new file mode 100644
index 000000000..2d3cccf08
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_maskdiv.c
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2026 Juan Manuel López Carrillo
+ *
+ * Cycle-masking divider: the M factor masks M pulses out of every
+ * 2^width parent cycles instead of dividing the parent rate, so
+ *
+ *	rate = parent * (2^width - M) / 2^width
+ *
+ * The masked output is not an even pulse train: the surviving pulses
+ * keep the parent period. Rate selection therefore prefers, among the
+ * parents that reach the requested rate, the one needing the least
+ * masking.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/math64.h>
+
+#include "ccu_gate.h"
+#include "ccu_maskdiv.h"
+
+static unsigned long ccu_maskdiv_calc_rate(unsigned long parent_rate,
+					   unsigned int m, unsigned int width)
+{
+	unsigned int n = 1 << width;
+
+	return div_u64((u64)parent_rate * (n - m), n);
+}
+
+/*
+ * Smallest M (least masking) whose output does not exceed the requested
+ * rate; masking everything (M == 2^width) is never returned.
+ */
+static unsigned int ccu_maskdiv_find_m(unsigned long parent_rate,
+				       unsigned long rate, unsigned int width)
+{
+	unsigned int n = 1 << width;
+	u64 kept;
+
+	if (!parent_rate || rate >= parent_rate)
+		return 0;
+
+	kept = div64_ul((u64)rate * n, parent_rate);
+	if (!kept)
+		kept = 1;
+
+	return n - (unsigned int)kept;
+}
+
+static void ccu_maskdiv_disable(struct clk_hw *hw)
+{
+	struct ccu_maskdiv *cmd = hw_to_ccu_maskdiv(hw);
+
+	return ccu_gate_helper_disable(&cmd->common, cmd->enable);
+}
+
+static int ccu_maskdiv_enable(struct clk_hw *hw)
+{
+	struct ccu_maskdiv *cmd = hw_to_ccu_maskdiv(hw);
+
+	return ccu_gate_helper_enable(&cmd->common, cmd->enable);
+}
+
+static int ccu_maskdiv_is_enabled(struct clk_hw *hw)
+{
+	struct ccu_maskdiv *cmd = hw_to_ccu_maskdiv(hw);
+
+	return ccu_gate_helper_is_enabled(&cmd->common, cmd->enable);
+}
+
+static unsigned long ccu_maskdiv_recalc_rate(struct clk_hw *hw,
+					     unsigned long parent_rate)
+{
+	struct ccu_maskdiv *cmd = hw_to_ccu_maskdiv(hw);
+	unsigned int m;
+	u32 reg;
+
+	reg = readl(cmd->common.base + cmd->common.reg);
+	m = (reg >> cmd->shift) & ((1 << cmd->width) - 1);
+
+	return ccu_maskdiv_calc_rate(parent_rate, m, cmd->width);
+}
+
+static int ccu_maskdiv_determine_rate(struct clk_hw *hw,
+				      struct clk_rate_request *req)
+{
+	struct ccu_maskdiv *cmd = hw_to_ccu_maskdiv(hw);
+	unsigned long best_rate = 0, best_parent_rate = 0;
+	struct clk_hw *best_parent = NULL;
+	unsigned int best_m = UINT_MAX;
+	unsigned int i;
+
+	for (i = 0; i < clk_hw_get_num_parents(hw); i++) {
+		struct clk_hw *parent = clk_hw_get_parent_by_index(hw, i);
+		unsigned long parent_rate, new_rate;
+		unsigned int m;
+
+		if (!parent)
+			continue;
+
+		parent_rate = clk_hw_get_rate(parent);
+		m = ccu_maskdiv_find_m(parent_rate, req->rate, cmd->width);
+		new_rate = ccu_maskdiv_calc_rate(parent_rate, m, cmd->width);
+
+		if (new_rate > req->rate)
+			continue;
+
+		/* Closest rate first; on ties, the least masking */
+		if (new_rate > best_rate ||
+		    (new_rate == best_rate && m < best_m)) {
+			best_rate = new_rate;
+			best_parent_rate = parent_rate;
+			best_parent = parent;
+			best_m = m;
+		}
+	}
+
+	if (!best_parent)
+		return -EINVAL;
+
+	req->best_parent_hw = best_parent;
+	req->best_parent_rate = best_parent_rate;
+	req->rate = best_rate;
+
+	return 0;
+}
+
+static int ccu_maskdiv_set_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long parent_rate)
+{
+	struct ccu_maskdiv *cmd = hw_to_ccu_maskdiv(hw);
+	unsigned int m;
+	unsigned long flags;
+	u32 reg;
+
+	m = ccu_maskdiv_find_m(parent_rate, rate, cmd->width);
+
+	spin_lock_irqsave(cmd->common.lock, flags);
+
+	reg = readl(cmd->common.base + cmd->common.reg);
+	reg &= ~GENMASK(cmd->shift + cmd->width - 1, cmd->shift);
+	writel(reg | (m << cmd->shift), cmd->common.base + cmd->common.reg);
+
+	spin_unlock_irqrestore(cmd->common.lock, flags);
+
+	return 0;
+}
+
+static u8 ccu_maskdiv_get_parent(struct clk_hw *hw)
+{
+	struct ccu_maskdiv *cmd = hw_to_ccu_maskdiv(hw);
+
+	return ccu_mux_helper_get_parent(&cmd->common, &cmd->mux);
+}
+
+static int ccu_maskdiv_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct ccu_maskdiv *cmd = hw_to_ccu_maskdiv(hw);
+
+	return ccu_mux_helper_set_parent(&cmd->common, &cmd->mux, index);
+}
+
+static int ccu_maskdiv_set_rate_and_parent(struct clk_hw *hw,
+					   unsigned long rate,
+					   unsigned long parent_rate, u8 index)
+{
+	/*
+	 * Same ordering rule as clk_composite_set_rate_and_parent(): if
+	 * switching the mux with the current M would overshoot the
+	 * requested rate, program the divider first, so the
+	 * intermediate rate never exceeds both the old and the new
+	 * rate.
+	 */
+	if (ccu_maskdiv_recalc_rate(hw, parent_rate) > rate) {
+		ccu_maskdiv_set_rate(hw, rate, parent_rate);
+		ccu_maskdiv_set_parent(hw, index);
+	} else {
+		ccu_maskdiv_set_parent(hw, index);
+		ccu_maskdiv_set_rate(hw, rate, parent_rate);
+	}
+
+	return 0;
+}
+
+const struct clk_ops ccu_maskdiv_ops = {
+	.disable	= ccu_maskdiv_disable,
+	.enable		= ccu_maskdiv_enable,
+	.is_enabled	= ccu_maskdiv_is_enabled,
+
+	.get_parent	= ccu_maskdiv_get_parent,
+	.set_parent	= ccu_maskdiv_set_parent,
+
+	.determine_rate	= ccu_maskdiv_determine_rate,
+	.recalc_rate	= ccu_maskdiv_recalc_rate,
+	.set_rate	= ccu_maskdiv_set_rate,
+	.set_rate_and_parent = ccu_maskdiv_set_rate_and_parent,
+};
+EXPORT_SYMBOL_NS_GPL(ccu_maskdiv_ops, "SUNXI_CCU");
diff --git a/drivers/clk/sunxi-ng/ccu_maskdiv.h b/drivers/clk/sunxi-ng/ccu_maskdiv.h
new file mode 100644
index 000000000..3cbfce064
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_maskdiv.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2026 Juan Manuel López Carrillo
+ */
+
+#ifndef _CCU_MASKDIV_H_
+#define _CCU_MASKDIV_H_
+
+#include <linux/clk-provider.h>
+
+#include "ccu_common.h"
+#include "ccu_mux.h"
+
+/*
+ * struct ccu_maskdiv - cycle-masking ("fractional") divider
+ *
+ * This divider does not divide the parent clock: it masks (swallows) M
+ * pulses out of every 2^width parent cycles, so the average output rate
+ * is
+ *
+ *	rate = parent * (2^width - M) / 2^width
+ *
+ * with the remaining pulses keeping the parent period. The A523/T527
+ * GPU clock (GPU_CLK_REG, 0x670) is such a divider: "FACTOR_M: mask M
+ * cycles at 16 cycles", GPU_CLK = Clock Source * ((16-M)/16) (T527 user
+ * manual v0.92, section 2.7.6.58).
+ *
+ * @shift:	shift of the M field in the register
+ * @width:	width of the M field; the mask window is 2^width cycles
+ */
+struct ccu_maskdiv {
+	u32			enable;
+
+	u8			shift;
+	u8			width;
+
+	struct ccu_mux_internal	mux;
+	struct ccu_common	common;
+};
+
+#define SUNXI_CCU_MASKDIV_HW_WITH_MUX_TABLE_GATE(_struct, _name,	\
+						 _parents, _table,	\
+						 _reg,			\
+						 _mshift, _mwidth,	\
+						 _muxshift, _muxwidth,	\
+						 _gate, _flags)		\
+	struct ccu_maskdiv _struct = {					\
+		.enable	= _gate,					\
+		.shift	= _mshift,					\
+		.width	= _mwidth,					\
+		.mux	= _SUNXI_CCU_MUX_TABLE(_muxshift, _muxwidth,	\
+					       _table),			\
+		.common	= {						\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT_PARENTS_HW(_name,	\
+								 _parents, \
+								 &ccu_maskdiv_ops, \
+								 _flags), \
+		},							\
+	}
+
+static inline struct ccu_maskdiv *hw_to_ccu_maskdiv(struct clk_hw *hw)
+{
+	struct ccu_common *common = hw_to_ccu_common(hw);
+
+	return container_of(common, struct ccu_maskdiv, common);
+}
+
+extern const struct clk_ops ccu_maskdiv_ops;
+
+#endif /* _CCU_MASKDIV_H_ */
-- 
2.47.3
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.