linux_dsm_epyc7002/arch/arm/mach-prima2/pm.c
Russell King f81309067f ARM: move heavy barrier support out of line
The existing memory barrier macro causes a significant amount of code
to be inserted inline at every call site.  For example, in
gpio_set_irq_type(), we have this for mb():

c0344c08:       f57ff04e        dsb     st
c0344c0c:       e59f8190        ldr     r8, [pc, #400]  ; c0344da4 <gpio_set_irq_type+0x230>
c0344c10:       e3590004        cmp     r9, #4
c0344c14:       e5983014        ldr     r3, [r8, #20]
c0344c18:       0a000054        beq     c0344d70 <gpio_set_irq_type+0x1fc>
c0344c1c:       e3530000        cmp     r3, #0
c0344c20:       0a000004        beq     c0344c38 <gpio_set_irq_type+0xc4>
c0344c24:       e50b2030        str     r2, [fp, #-48]  ; 0xffffffd0
c0344c28:       e50bc034        str     ip, [fp, #-52]  ; 0xffffffcc
c0344c2c:       e12fff33        blx     r3
c0344c30:       e51bc034        ldr     ip, [fp, #-52]  ; 0xffffffcc
c0344c34:       e51b2030        ldr     r2, [fp, #-48]  ; 0xffffffd0
c0344c38:       e5963004        ldr     r3, [r6, #4]

Moving the outer_cache_sync() call out of line reduces the impact of
the barrier:

c0344968:       f57ff04e        dsb     st
c034496c:       e35a0004        cmp     sl, #4
c0344970:       e50b2030        str     r2, [fp, #-48]  ; 0xffffffd0
c0344974:       0a000044        beq     c0344a8c <gpio_set_irq_type+0x1b8>
c0344978:       ebf363dd        bl      c001d8f4 <arm_heavy_mb>
c034497c:       e5953004        ldr     r3, [r5, #4]

This should reduce the cache footprint of this code.  Overall, this
results in a reduction of around 20K in the kernel size:

    text    data      bss      dec     hex filename
10773970  667392 10369656 21811018 14ccf4a ../build/imx6/vmlinux-old
10754219  667392 10369656 21791267 14c8223 ../build/imx6/vmlinux-new

Another advantage to this approach is that we can finally resolve the
issue of SoCs which have their own memory barrier requirements within
multiplatform kernels (such as OMAP.)  Here, the bus interconnects
need additional handling to ensure that writes become visible in the
correct order (eg, between dma_map() operations, writes to DMA
coherent memory, and MMIO accesses.)

Acked-by: Tony Lindgren <tony@atomide.com>
Acked-by: Richard Woodruff <r-woodruff2@ti.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2015-07-25 15:28:05 +01:00

155 lines
3.4 KiB
C

/*
* power management entry for CSR SiRFprimaII
*
* Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company.
*
* Licensed under GPLv2 or later.
*/
#include <linux/kernel.h>
#include <linux/suspend.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_device.h>
#include <linux/of_platform.h>
#include <linux/io.h>
#include <linux/rtc/sirfsoc_rtciobrg.h>
#include <asm/outercache.h>
#include <asm/suspend.h>
#include <asm/hardware/cache-l2x0.h>
#include "pm.h"
/*
* suspend asm codes will access these to make DRAM become self-refresh and
* system sleep
*/
u32 sirfsoc_pwrc_base;
void __iomem *sirfsoc_memc_base;
static void sirfsoc_set_wakeup_source(void)
{
u32 pwr_trigger_en_reg;
pwr_trigger_en_reg = sirfsoc_rtc_iobrg_readl(sirfsoc_pwrc_base +
SIRFSOC_PWRC_TRIGGER_EN);
#define X_ON_KEY_B (1 << 0)
#define RTC_ALARM0_B (1 << 2)
#define RTC_ALARM1_B (1 << 3)
sirfsoc_rtc_iobrg_writel(pwr_trigger_en_reg | X_ON_KEY_B |
RTC_ALARM0_B | RTC_ALARM1_B,
sirfsoc_pwrc_base + SIRFSOC_PWRC_TRIGGER_EN);
}
static void sirfsoc_set_sleep_mode(u32 mode)
{
u32 sleep_mode = sirfsoc_rtc_iobrg_readl(sirfsoc_pwrc_base +
SIRFSOC_PWRC_PDN_CTRL);
sleep_mode &= ~(SIRFSOC_SLEEP_MODE_MASK << 1);
sleep_mode |= mode << 1;
sirfsoc_rtc_iobrg_writel(sleep_mode, sirfsoc_pwrc_base +
SIRFSOC_PWRC_PDN_CTRL);
}
static int sirfsoc_pre_suspend_power_off(void)
{
u32 wakeup_entry = virt_to_phys(cpu_resume);
sirfsoc_rtc_iobrg_writel(wakeup_entry, sirfsoc_pwrc_base +
SIRFSOC_PWRC_SCRATCH_PAD1);
sirfsoc_set_wakeup_source();
sirfsoc_set_sleep_mode(SIRFSOC_DEEP_SLEEP_MODE);
return 0;
}
static int sirfsoc_pm_enter(suspend_state_t state)
{
switch (state) {
case PM_SUSPEND_MEM:
sirfsoc_pre_suspend_power_off();
outer_disable();
/* go zzz */
cpu_suspend(0, sirfsoc_finish_suspend);
outer_resume();
break;
default:
return -EINVAL;
}
return 0;
}
static const struct platform_suspend_ops sirfsoc_pm_ops = {
.enter = sirfsoc_pm_enter,
.valid = suspend_valid_only_mem,
};
static const struct of_device_id pwrc_ids[] = {
{ .compatible = "sirf,prima2-pwrc" },
{}
};
static int __init sirfsoc_of_pwrc_init(void)
{
struct device_node *np;
np = of_find_matching_node(NULL, pwrc_ids);
if (!np) {
pr_err("unable to find compatible sirf pwrc node in dtb\n");
return -ENOENT;
}
/*
* pwrc behind rtciobrg is not located in memory space
* though the property is named reg. reg only means base
* offset for pwrc. then of_iomap is not suitable here.
*/
if (of_property_read_u32(np, "reg", &sirfsoc_pwrc_base))
panic("unable to find base address of pwrc node in dtb\n");
of_node_put(np);
return 0;
}
static const struct of_device_id memc_ids[] = {
{ .compatible = "sirf,prima2-memc" },
{}
};
static int sirfsoc_memc_probe(struct platform_device *op)
{
struct device_node *np = op->dev.of_node;
sirfsoc_memc_base = of_iomap(np, 0);
if (!sirfsoc_memc_base)
panic("unable to map memc registers\n");
return 0;
}
static struct platform_driver sirfsoc_memc_driver = {
.probe = sirfsoc_memc_probe,
.driver = {
.name = "sirfsoc-memc",
.of_match_table = memc_ids,
},
};
static int __init sirfsoc_memc_init(void)
{
return platform_driver_register(&sirfsoc_memc_driver);
}
int __init sirfsoc_pm_init(void)
{
sirfsoc_of_pwrc_init();
sirfsoc_memc_init();
suspend_set_ops(&sirfsoc_pm_ops);
return 0;
}