kernel_optimize_test/drivers/clk/clk-fractional-divider.c

222 lines
5.0 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2014 Intel Corporation
*
* Adjustable fractional divider clock implementation.
* Output rate = (m / n) * parent_rate.
* Uses rational best approximation algorithm.
*/
#include <linux/clk-provider.h>
clk: Remove io.h from clk-provider.h Now that we've gotten rid of clk_readl() we can remove io.h from the clk-provider header and push out the io.h include to any code that isn't already including the io.h header but using things like readl/writel, etc. Found with this grep: git grep -l clk-provider.h | grep '.c$' | xargs git grep -L 'linux/io.h' | \ xargs git grep -l \ -e '\<__iowrite32_copy\>' --or \ -e '\<__ioread32_copy\>' --or \ -e '\<__iowrite64_copy\>' --or \ -e '\<ioremap_page_range\>' --or \ -e '\<ioremap_huge_init\>' --or \ -e '\<arch_ioremap_pud_supported\>' --or \ -e '\<arch_ioremap_pmd_supported\>' --or \ -e '\<devm_ioport_map\>' --or \ -e '\<devm_ioport_unmap\>' --or \ -e '\<IOMEM_ERR_PTR\>' --or \ -e '\<devm_ioremap\>' --or \ -e '\<devm_ioremap_nocache\>' --or \ -e '\<devm_ioremap_wc\>' --or \ -e '\<devm_iounmap\>' --or \ -e '\<devm_ioremap_release\>' --or \ -e '\<devm_memremap\>' --or \ -e '\<devm_memunmap\>' --or \ -e '\<__devm_memremap_pages\>' --or \ -e '\<pci_remap_cfgspace\>' --or \ -e '\<arch_has_dev_port\>' --or \ -e '\<arch_phys_wc_add\>' --or \ -e '\<arch_phys_wc_del\>' --or \ -e '\<memremap\>' --or \ -e '\<memunmap\>' --or \ -e '\<arch_io_reserve_memtype_wc\>' --or \ -e '\<arch_io_free_memtype_wc\>' --or \ -e '\<__io_aw\>' --or \ -e '\<__io_pbw\>' --or \ -e '\<__io_paw\>' --or \ -e '\<__io_pbr\>' --or \ -e '\<__io_par\>' --or \ -e '\<__raw_readb\>' --or \ -e '\<__raw_readw\>' --or \ -e '\<__raw_readl\>' --or \ -e '\<__raw_readq\>' --or \ -e '\<__raw_writeb\>' --or \ -e '\<__raw_writew\>' --or \ -e '\<__raw_writel\>' --or \ -e '\<__raw_writeq\>' --or \ -e '\<readb\>' --or \ -e '\<readw\>' --or \ -e '\<readl\>' --or \ -e '\<readq\>' --or \ -e '\<writeb\>' --or \ -e '\<writew\>' --or \ -e '\<writel\>' --or \ -e '\<writeq\>' --or \ -e '\<readb_relaxed\>' --or \ -e '\<readw_relaxed\>' --or \ -e '\<readl_relaxed\>' --or \ -e '\<readq_relaxed\>' --or \ -e '\<writeb_relaxed\>' --or \ -e '\<writew_relaxed\>' --or \ -e '\<writel_relaxed\>' --or \ -e '\<writeq_relaxed\>' --or \ -e '\<readsb\>' --or \ -e '\<readsw\>' --or \ -e '\<readsl\>' --or \ -e '\<readsq\>' --or \ -e '\<writesb\>' --or \ -e '\<writesw\>' --or \ -e '\<writesl\>' --or \ -e '\<writesq\>' --or \ -e '\<inb\>' --or \ -e '\<inw\>' --or \ -e '\<inl\>' --or \ -e '\<outb\>' --or \ -e '\<outw\>' --or \ -e '\<outl\>' --or \ -e '\<inb_p\>' --or \ -e '\<inw_p\>' --or \ -e '\<inl_p\>' --or \ -e '\<outb_p\>' --or \ -e '\<outw_p\>' --or \ -e '\<outl_p\>' --or \ -e '\<insb\>' --or \ -e '\<insw\>' --or \ -e '\<insl\>' --or \ -e '\<outsb\>' --or \ -e '\<outsw\>' --or \ -e '\<outsl\>' --or \ -e '\<insb_p\>' --or \ -e '\<insw_p\>' --or \ -e '\<insl_p\>' --or \ -e '\<outsb_p\>' --or \ -e '\<outsw_p\>' --or \ -e '\<outsl_p\>' --or \ -e '\<ioread8\>' --or \ -e '\<ioread16\>' --or \ -e '\<ioread32\>' --or \ -e '\<ioread64\>' --or \ -e '\<iowrite8\>' --or \ -e '\<iowrite16\>' --or \ -e '\<iowrite32\>' --or \ -e '\<iowrite64\>' --or \ -e '\<ioread16be\>' --or \ -e '\<ioread32be\>' --or \ -e '\<ioread64be\>' --or \ -e '\<iowrite16be\>' --or \ -e '\<iowrite32be\>' --or \ -e '\<iowrite64be\>' --or \ -e '\<ioread8_rep\>' --or \ -e '\<ioread16_rep\>' --or \ -e '\<ioread32_rep\>' --or \ -e '\<ioread64_rep\>' --or \ -e '\<iowrite8_rep\>' --or \ -e '\<iowrite16_rep\>' --or \ -e '\<iowrite32_rep\>' --or \ -e '\<iowrite64_rep\>' --or \ -e '\<__io_virt\>' --or \ -e '\<pci_iounmap\>' --or \ -e '\<virt_to_phys\>' --or \ -e '\<phys_to_virt\>' --or \ -e '\<ioremap_uc\>' --or \ -e '\<ioremap\>' --or \ -e '\<__ioremap\>' --or \ -e '\<iounmap\>' --or \ -e '\<ioremap\>' --or \ -e '\<ioremap_nocache\>' --or \ -e '\<ioremap_uc\>' --or \ -e '\<ioremap_wc\>' --or \ -e '\<ioremap_wc\>' --or \ -e '\<ioremap_wt\>' --or \ -e '\<ioport_map\>' --or \ -e '\<ioport_unmap\>' --or \ -e '\<ioport_map\>' --or \ -e '\<ioport_unmap\>' --or \ -e '\<xlate_dev_kmem_ptr\>' --or \ -e '\<xlate_dev_mem_ptr\>' --or \ -e '\<unxlate_dev_mem_ptr\>' --or \ -e '\<virt_to_bus\>' --or \ -e '\<bus_to_virt\>' --or \ -e '\<memset_io\>' --or \ -e '\<memcpy_fromio\>' --or \ -e '\<memcpy_toio\>' I also reordered a couple includes when they weren't alphabetical and removed clk.h from kona, replacing it with clk-provider.h because that driver doesn't use clk consumer APIs. Acked-by: Geert Uytterhoeven <geert+renesas@glider.be> Cc: Chen-Yu Tsai <wens@csie.org> Acked-by: Maxime Ripard <maxime.ripard@bootlin.com> Acked-by: Tero Kristo <t-kristo@ti.com> Acked-by: Sekhar Nori <nsekhar@ti.com> Cc: Krzysztof Kozlowski <krzk@kernel.org> Acked-by: Mark Brown <broonie@kernel.org> Cc: Chris Zankel <chris@zankel.net> Acked-by: Max Filippov <jcmvbkbc@gmail.com> Acked-by: John Crispin <john@phrozen.org> Acked-by: Heiko Stuebner <heiko@sntech.de> Signed-off-by: Stephen Boyd <sboyd@kernel.org>
2019-04-19 06:20:22 +08:00
#include <linux/io.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/slab.h>
#include <linux/rational.h>
static inline u32 clk_fd_readl(struct clk_fractional_divider *fd)
{
if (fd->flags & CLK_FRAC_DIVIDER_BIG_ENDIAN)
return ioread32be(fd->reg);
return readl(fd->reg);
}
static inline void clk_fd_writel(struct clk_fractional_divider *fd, u32 val)
{
if (fd->flags & CLK_FRAC_DIVIDER_BIG_ENDIAN)
iowrite32be(val, fd->reg);
else
writel(val, fd->reg);
}
static unsigned long clk_fd_recalc_rate(struct clk_hw *hw,
unsigned long parent_rate)
{
struct clk_fractional_divider *fd = to_clk_fd(hw);
unsigned long flags = 0;
unsigned long m, n;
u32 val;
u64 ret;
if (fd->lock)
spin_lock_irqsave(fd->lock, flags);
else
__acquire(fd->lock);
val = clk_fd_readl(fd);
if (fd->lock)
spin_unlock_irqrestore(fd->lock, flags);
else
__release(fd->lock);
m = (val & fd->mmask) >> fd->mshift;
n = (val & fd->nmask) >> fd->nshift;
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_fd_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.
*/
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 long clk_fd_round_rate(struct clk_hw *hw, unsigned long rate,
unsigned long *parent_rate)
{
struct clk_fractional_divider *fd = to_clk_fd(hw);
unsigned long m, n;
u64 ret;
clk: fractional-divider: check parent rate only if flag is set Custom approximation of fractional-divider may not need parent clock rate checking. For example Rockchip SoCs work fine using grand parent clock rate even if target rate is greater than parent. This patch checks parent clock rate only if CLK_SET_RATE_PARENT flag is set. For detailed example, clock tree of Rockchip I2S audio hardware. - Clock rate of CPLL is 1.2GHz, GPLL is 491.52MHz. - i2s1_div is integer divider can divide N (N is 1~128). Input clock is CPLL or GPLL. Initial divider value is N = 1. Ex) PLL = CPLL, N = 10, i2s1_div output rate is CPLL / 10 = 1.2GHz / 10 = 120MHz - i2s1_frac is fractional divider can divide input to x/y, x and y are 16bit integer. CPLL --> | selector | ---> i2s1_div -+--> | selector | --> I2S1 MCLK GPLL --> | | ,--------------' | | `--> i2s1_frac ---> | | Clock mux system try to choose suitable one from i2s1_div and i2s1_frac for master clock (MCLK) of I2S1. Bad scenario as follows: - Try to set MCLK to 8.192MHz (32kHz audio replay) Candidate setting is - i2s1_div: GPLL / 60 = 8.192MHz i2s1_div candidate is exactly same as target clock rate, so mux choose this clock source. i2s1_div output rate is changed 491.52MHz -> 8.192MHz - After that try to set to 11.2896MHz (44.1kHz audio replay) Candidate settings are - i2s1_div : CPLL / 107 = 11.214945MHz - i2s1_frac: i2s1_div = 8.192MHz This is because clk_fd_round_rate() thinks target rate (11.2896MHz) is higher than parent rate (i2s1_div = 8.192MHz) and returns parent clock rate. Above is current upstreamed behavior. Clock mux system choose i2s1_div, but this clock rate is not acceptable for I2S driver, so users cannot replay audio. Expected behavior is: - Try to set master clock to 11.2896MHz (44.1kHz audio replay) Candidate settings are - i2s1_div : CPLL / 107 = 11.214945MHz - i2s1_frac: i2s1_div * 147/6400 = 11.2896MHz Change i2s1_div to GPLL / 1 = 491.52MHz at same time. If apply this commit, clk_fd_round_rate() calls custom approximate function of Rockchip even if target rate is higher than parent. Custom function changes both grand parent (i2s1_div) and parent (i2s_frac) settings at same time. Clock mux system can choose i2s1_frac and audio works fine. Signed-off-by: Katsuhiro Suzuki <katsuhiro@katsuster.net> Reviewed-by: Heiko Stuebner <heiko@sntech.de> [sboyd@kernel.org: Make function into a macro instead] Signed-off-by: Stephen Boyd <sboyd@kernel.org>
2019-02-10 23:38:06 +08:00
if (!rate || (!clk_hw_can_set_rate_parent(hw) && rate >= *parent_rate))
return *parent_rate;
if (fd->approximation)
fd->approximation(hw, rate, parent_rate, &m, &n);
else
clk_fd_general_approximation(hw, rate, parent_rate, &m, &n);
ret = (u64)*parent_rate * m;
do_div(ret, n);
return ret;
}
static int clk_fd_set_rate(struct clk_hw *hw, unsigned long rate,
unsigned long parent_rate)
{
struct clk_fractional_divider *fd = to_clk_fd(hw);
unsigned long flags = 0;
unsigned long m, n;
u32 val;
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--;
}
if (fd->lock)
spin_lock_irqsave(fd->lock, flags);
else
__acquire(fd->lock);
val = clk_fd_readl(fd);
val &= ~(fd->mmask | fd->nmask);
val |= (m << fd->mshift) | (n << fd->nshift);
clk_fd_writel(fd, val);
if (fd->lock)
spin_unlock_irqrestore(fd->lock, flags);
else
__release(fd->lock);
return 0;
}
const struct clk_ops clk_fractional_divider_ops = {
.recalc_rate = clk_fd_recalc_rate,
.round_rate = clk_fd_round_rate,
.set_rate = clk_fd_set_rate,
};
EXPORT_SYMBOL_GPL(clk_fractional_divider_ops);
struct clk_hw *clk_hw_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,
u8 clk_divider_flags, spinlock_t *lock)
{
struct clk_fractional_divider *fd;
struct clk_init_data init;
struct clk_hw *hw;
int ret;
fd = kzalloc(sizeof(*fd), GFP_KERNEL);
if (!fd)
return ERR_PTR(-ENOMEM);
init.name = name;
init.ops = &clk_fractional_divider_ops;
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;
fd->mmask = GENMASK(mwidth - 1, 0) << mshift;
fd->nshift = nshift;
fd->nwidth = nwidth;
fd->nmask = GENMASK(nwidth - 1, 0) << 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;
}
EXPORT_SYMBOL_GPL(clk_hw_register_fractional_divider);
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,
u8 clk_divider_flags, spinlock_t *lock)
{
struct clk_hw *hw;
hw = clk_hw_register_fractional_divider(dev, name, parent_name, flags,
reg, mshift, mwidth, nshift, nwidth, clk_divider_flags,
lock);
if (IS_ERR(hw))
return ERR_CAST(hw);
return hw->clk;
}
EXPORT_SYMBOL_GPL(clk_register_fractional_divider);
void clk_hw_unregister_fractional_divider(struct clk_hw *hw)
{
struct clk_fractional_divider *fd;
fd = to_clk_fd(hw);
clk_hw_unregister(hw);
kfree(fd);
}