diff mbox

[v10,03/11] ARM: hisi: enable MCPM implementation

Message ID 1404957850-13340-4-git-send-email-haojian.zhuang@linaro.org
State Changes Requested
Headers show

Commit Message

Haojian Zhuang July 10, 2014, 2:04 a.m. UTC
Multiple CPU clusters are used in Hisilicon HiP04 SoC. Now use MCPM
framework to manage power on HiP04 SoC.

Signed-off-by: Haojian Zhuang <haojian.zhuang@linaro.org>
---
 arch/arm/mach-hisi/Makefile   |   1 +
 arch/arm/mach-hisi/platmcpm.c | 331 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 332 insertions(+)
 create mode 100644 arch/arm/mach-hisi/platmcpm.c

Comments

Nicolas Pitre July 12, 2014, 9:31 p.m. UTC | #1
On Thu, 10 Jul 2014, Haojian Zhuang wrote:

> Multiple CPU clusters are used in Hisilicon HiP04 SoC. Now use MCPM
> framework to manage power on HiP04 SoC.
> 
> Signed-off-by: Haojian Zhuang <haojian.zhuang@linaro.org>
> ---
>  arch/arm/mach-hisi/Makefile   |   1 +
>  arch/arm/mach-hisi/platmcpm.c | 331 ++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 332 insertions(+)
>  create mode 100644 arch/arm/mach-hisi/platmcpm.c
> 
> diff --git a/arch/arm/mach-hisi/Makefile b/arch/arm/mach-hisi/Makefile
> index ee2506b..d64831e 100644
> --- a/arch/arm/mach-hisi/Makefile
> +++ b/arch/arm/mach-hisi/Makefile
> @@ -3,4 +3,5 @@
>  #
>  
>  obj-y	+= hisilicon.o
> +obj-$(CONFIG_MCPM)		+= platmcpm.o
>  obj-$(CONFIG_SMP)		+= platsmp.o hotplug.o headsmp.o
> diff --git a/arch/arm/mach-hisi/platmcpm.c b/arch/arm/mach-hisi/platmcpm.c
> new file mode 100644
> index 0000000..3befcb3
> --- /dev/null
> +++ b/arch/arm/mach-hisi/platmcpm.c
> @@ -0,0 +1,331 @@
> +/*
> + * Copyright (c) 2013-2014 Linaro Ltd.
> + * Copyright (c) 2013-2014 Hisilicon Limited.
> + *
> + * This program is free software; you can redistribute it and/or modify it
> + * under the terms and conditions of the GNU General Public License,
> + * version 2, as published by the Free Software Foundation.
> + */
> +#include <linux/delay.h>
> +#include <linux/io.h>
> +#include <linux/of_address.h>
> +
> +#include <asm/cputype.h>
> +#include <asm/cp15.h>
> +#include <asm/mcpm.h>
> +
> +#include "core.h"
> +
> +/* bits definition in SC_CPU_RESET_REQ[x]/SC_CPU_RESET_DREQ[x]
> + * 1 -- unreset; 0 -- reset
> + */
> +#define CORE_RESET_BIT(x)		(1 << x)
> +#define NEON_RESET_BIT(x)		(1 << (x + 4))
> +#define CORE_DEBUG_RESET_BIT(x)		(1 << (x + 9))
> +#define CLUSTER_L2_RESET_BIT		(1 << 8)
> +#define CLUSTER_DEBUG_RESET_BIT		(1 << 13)
> +
> +/*
> + * bits definition in SC_CPU_RESET_STATUS[x]
> + * 1 -- reset status; 0 -- unreset status
> + */
> +#define CORE_RESET_STATUS(x)		(1 << x)
> +#define NEON_RESET_STATUS(x)		(1 << (x + 4))
> +#define CORE_DEBUG_RESET_STATUS(x)	(1 << (x + 9))
> +#define CLUSTER_L2_RESET_STATUS		(1 << 8)
> +#define CLUSTER_DEBUG_RESET_STATUS	(1 << 13)
> +#define CORE_WFI_STATUS(x)		(1 << (x + 16))
> +#define CORE_WFE_STATUS(x)		(1 << (x + 20))
> +#define CORE_DEBUG_ACK(x)		(1 << (x + 24))
> +
> +#define SC_CPU_RESET_REQ(x)		(0x520 + (x << 3))	/* reset */
> +#define SC_CPU_RESET_DREQ(x)		(0x524 + (x << 3))	/* unreset */
> +#define SC_CPU_RESET_STATUS(x)		(0x1520 + (x << 3))
> +
> +#define FAB_SF_MODE			0x0c
> +#define FAB_SF_INVLD			0x10
> +
> +/* bits definition in FB_SF_INVLD */
> +#define FB_SF_INVLD_START		(1 << 8)
> +
> +#define HIP04_MAX_CLUSTERS		4
> +#define HIP04_MAX_CPUS_PER_CLUSTER	4
> +
> +#define POLL_MSEC	10
> +#define TIMEOUT_MSEC	1000
> +
> +struct hip04_secondary_cpu_data {
> +	u32	bootwrapper_phys;
> +	u32	bootwrapper_size;
> +	u32	bootwrapper_magic;
> +	u32	relocation_entry;
> +	u32	relocation_size;
> +};
> +
> +static void __iomem *relocation, *sysctrl, *fabric;
> +static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER];
> +static DEFINE_SPINLOCK(boot_lock);
> +static struct hip04_secondary_cpu_data hip04_boot;
> +static u32 fabric_phys_addr;
> +
> +static bool hip04_cluster_down(unsigned int cluster)
> +{
> +	int i;
> +
> +	for (i = 0; i < HIP04_MAX_CPUS_PER_CLUSTER; i++)
> +		if (hip04_cpu_table[cluster][i])
> +			return false;
> +	return true;
> +}
> +
> +static int hip04_mcpm_power_up(unsigned int cpu, unsigned int cluster)
> +{
> +	unsigned long data, mask;
> +
> +	if (!relocation || !sysctrl)
> +		return -ENODEV;
> +	if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER)
> +		return -EINVAL;
> +
> +	spin_lock_irq(&boot_lock);
> +
> +	if (hip04_cpu_table[cluster][cpu]) {
> +		hip04_cpu_table[cluster][cpu]++;
> +		spin_unlock_irq(&boot_lock);
> +		return 0;
> +	}
> +
> +	writel_relaxed(hip04_boot.bootwrapper_phys, relocation);
> +	writel_relaxed(hip04_boot.bootwrapper_magic, relocation + 4);
> +	writel_relaxed(virt_to_phys(mcpm_entry_point), relocation + 8);
> +	writel_relaxed(0, relocation + 12);
> +
> +	if (hip04_cluster_down(cluster)) {
> +		data = CLUSTER_DEBUG_RESET_BIT;
> +		writel_relaxed(data, sysctrl + SC_CPU_RESET_DREQ(cluster));
> +		do {
> +			mask = CLUSTER_DEBUG_RESET_STATUS;
> +			data = readl_relaxed(sysctrl + \
> +					     SC_CPU_RESET_STATUS(cluster));
> +		} while (data & mask);
> +	}
> +
> +	hip04_cpu_table[cluster][cpu]++;
> +
> +	data = CORE_RESET_BIT(cpu) | NEON_RESET_BIT(cpu) | \
> +	       CORE_DEBUG_RESET_BIT(cpu);
> +	writel_relaxed(data, sysctrl + SC_CPU_RESET_DREQ(cluster));
> +	spin_unlock_irq(&boot_lock);
> +	msleep(POLL_MSEC);
> +
> +	return 0;
> +}
> +
> +static void hip04_mcpm_power_down(void)
> +{
> +	unsigned int mpidr, cpu, cluster, data = 0;
> +	bool skip_reset = false;
> +
> +	mpidr = read_cpuid_mpidr();
> +	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
> +	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
> +
> +	__mcpm_cpu_going_down(cpu, cluster);
> +
> +	spin_lock(&boot_lock);
> +	BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
> +	hip04_cpu_table[cluster][cpu]--;
> +	if (hip04_cpu_table[cluster][cpu] == 1) {
> +		/* A power_up request went ahead of us. */
> +		skip_reset = true;
> +	} else if (hip04_cpu_table[cluster][cpu] > 1) {
> +		pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu);
> +		BUG();
> +	}
> +	spin_unlock(&boot_lock);
> +
> +	v7_exit_coherency_flush(louis);
> +
> +	__mcpm_cpu_down(cpu, cluster);

What if there is a hip04_mcpm_power_up() being called on another CPU 
right here?  There is a race that I illustrated in a previous email 
which is still unresolved.

> +
> +	if (!skip_reset) {
> +		data = CORE_RESET_BIT(cpu) | NEON_RESET_BIT(cpu) | \
> +		       CORE_DEBUG_RESET_BIT(cpu);
> +		writel_relaxed(data, sysctrl + SC_CPU_RESET_REQ(cluster));
> +	}
> +}
> +
> +static int hip04_mcpm_wait_for_powerdown(unsigned int cpu, unsigned int cluster)
> +{
> +	unsigned int data, tries;
> +
> +	BUG_ON(cluster >= HIP04_MAX_CLUSTERS ||
> +	       cpu >= HIP04_MAX_CPUS_PER_CLUSTER);
> +
> +	for (tries = 0; tries < TIMEOUT_MSEC / POLL_MSEC; tries++) {
> +		data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster));
> +		if (!(data & CORE_RESET_STATUS(cpu))) {
> +			msleep(POLL_MSEC);
> +			continue;
> +		}
> +		return 0;
> +	}
> +	return -ETIMEDOUT;
> +}
> +
> +static void hip04_mcpm_powered_up(void)
> +{
> +	if (!relocation)
> +		return;
> +	spin_lock(&boot_lock);
> +	writel_relaxed(0, relocation);
> +	writel_relaxed(0, relocation + 4);
> +	writel_relaxed(0, relocation + 8);
> +	writel_relaxed(0, relocation + 12);
> +	spin_unlock(&boot_lock);
> +}
> +
> +static void __naked hip04_mcpm_power_up_setup(unsigned int affinity_level)
> +{
> +	asm volatile ("			\n"
> +	/* calculate fabric phys address */
> +"	adr	r2, 2f			\n"
> +"	ldmia	r2, {r1, r3}		\n"
> +"	sub	r0, r2, r1		\n"
> +"	add	r2, r0, r3		\n"
> +"	ldr	r2, [r2]		\n"

You may replace the above 2 instructions with "ldr r2, [r0, r3]".

> +	/* get cluster id from MPIDR */
> +"	mrc	p15, 0, r0, c0, c0, 5	\n"
> +"	ubfx	r1, r0, #8, #8		\n"
> +"	and	r1, r1, #0xf		\n"

You don't need the "and" here.  It is implicit in ubfx.

> +	/* 1 << cluster id */
> +"	mov	r0, #1			\n"
> +"	mov	r3, r0, lsl r1		\n"
> +"	ldr	r0, [r2, #"__stringify(FAB_SF_MODE)"]	\n"
> +"	tst	r0, r3			\n"
> +"	bxne	lr			\n"

Instead of running all this code all the time, you could simply test r0 
at the very beginning and if it is not equal to 1 then return 
immediately. If it is 1 that means the CPU executing this code is the 
first one to run in the cluster, in which case you also don't have to 
test if the cluster snoop is already enabled here.

> +"	orr	r1, r0, r3		\n"
> +"	str	r1, [r2, #"__stringify(FAB_SF_MODE)"]	\n"
> +"1:	ldr	r0, [r2, #"__stringify(FAB_SF_MODE)"]	\n"
> +"	tst	r0, r3			\n"
> +"	beq	1b			\n"
> +"	bx	lr			\n"
> +
> +"	.align	2			\n"
> +"2:	.word	.			\n"
> +"	.word	fabric_phys_addr	\n"
> +	);
> +}

Of course you will also have to enable the snoops for the current 
cluster in hip04_cpu_table_init() as well.


> +
> +static const struct mcpm_platform_ops hip04_mcpm_ops = {
> +	.power_up		= hip04_mcpm_power_up,
> +	.power_down		= hip04_mcpm_power_down,
> +	.wait_for_powerdown	= hip04_mcpm_wait_for_powerdown,
> +	.powered_up		= hip04_mcpm_powered_up,
> +};
> +
> +static bool __init hip04_cpu_table_init(void)
> +{
> +	unsigned int mpidr, cpu, cluster;
> +
> +	mpidr = read_cpuid_mpidr();
> +	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
> +	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
> +
> +	if (cluster >= HIP04_MAX_CLUSTERS ||
> +	    cpu >= HIP04_MAX_CPUS_PER_CLUSTER) {
> +		pr_err("%s: boot CPU is out of bound!\n", __func__);
> +		return false;
> +	}
> +	hip04_cpu_table[cluster][cpu] = 1;
> +	return true;
> +}
> +
> +static int __init hip04_mcpm_init(void)
> +{
> +	struct device_node *np, *np_fab;
> +	struct resource fab_res;
> +	int ret = -ENODEV;
> +
> +	np = of_find_compatible_node(NULL, NULL, "hisilicon,sysctrl");
> +	if (!np)
> +		goto err;
> +	np_fab = of_find_compatible_node(NULL, NULL, "hisilicon,hip04-fabric");
> +	if (!np_fab)
> +		goto err;
> +
> +	if (of_property_read_u32(np, "bootwrapper-phys",
> +				 &hip04_boot.bootwrapper_phys)) {
> +		pr_err("failed to get bootwrapper-phys\n");
> +		ret = -EINVAL;
> +		goto err;
> +	}
> +	if (of_property_read_u32(np, "bootwrapper-size",
> +				 &hip04_boot.bootwrapper_size)) {
> +		pr_err("failed to get bootwrapper-size\n");
> +		ret = -EINVAL;
> +		goto err;
> +	}
> +	if (of_property_read_u32(np, "bootwrapper-magic",
> +				 &hip04_boot.bootwrapper_magic)) {
> +		pr_err("failed to get bootwrapper-magic\n");
> +		ret = -EINVAL;
> +		goto err;
> +	}
> +	if (of_property_read_u32(np, "relocation-entry",
> +				 &hip04_boot.relocation_entry)) {
> +		pr_err("failed to get relocation-entry\n");
> +		ret = -EINVAL;
> +		goto err;
> +	}
> +	if (of_property_read_u32(np, "relocation-size",
> +				 &hip04_boot.relocation_size)) {
> +		pr_err("failed to get relocation-size\n");
> +		ret = -EINVAL;
> +		goto err;
> +	}
> +
> +	relocation = ioremap(hip04_boot.relocation_entry,
> +			     hip04_boot.relocation_size);
> +	if (!relocation) {
> +		pr_err("failed to map relocation space\n");
> +		ret = -ENOMEM;
> +		goto err;
> +	}
> +	sysctrl = of_iomap(np, 0);
> +	if (!sysctrl) {
> +		pr_err("failed to get sysctrl base\n");
> +		ret = -ENOMEM;
> +		goto err_sysctrl;
> +	}
> +	ret = of_address_to_resource(np_fab, 0, &fab_res);
> +	if (ret) {
> +		pr_err("failed to get fabric base phys\n");
> +		goto err_fabric;
> +	}
> +	fabric_phys_addr = fab_res.start;
> +	sync_cache_w(&fabric_phys_addr);
> +	fabric = of_iomap(np_fab, 0);
> +	if (!fabric) {
> +		pr_err("failed to get fabric base\n");
> +		ret = -ENOMEM;
> +		goto err_fabric;
> +	}
> +
> +	if (!hip04_cpu_table_init())
> +		return -EINVAL;
> +	ret = mcpm_platform_register(&hip04_mcpm_ops);
> +	if (!ret) {
> +		mcpm_sync_init(hip04_mcpm_power_up_setup);
> +		pr_info("HiP04 MCPM initialized\n");
> +	}
> +	mcpm_smp_set_ops();
> +	return ret;
> +err_fabric:
> +	iounmap(sysctrl);
> +err_sysctrl:
> +	iounmap(relocation);
> +err:
> +	return ret;
> +}
> +early_initcall(hip04_mcpm_init);
> -- 
> 1.9.1
> 
>
Haojian Zhuang July 14, 2014, 2:37 a.m. UTC | #2
On 13 July 2014 05:31, Nicolas Pitre <nicolas.pitre@linaro.org> wrote:
> On Thu, 10 Jul 2014, Haojian Zhuang wrote:
>
>> Multiple CPU clusters are used in Hisilicon HiP04 SoC. Now use MCPM
>> framework to manage power on HiP04 SoC.
>>
>> Signed-off-by: Haojian Zhuang <haojian.zhuang@linaro.org>
>> ---
>>  arch/arm/mach-hisi/Makefile   |   1 +
>>  arch/arm/mach-hisi/platmcpm.c | 331 ++++++++++++++++++++++++++++++++++++++++++
>>  2 files changed, 332 insertions(+)
>>  create mode 100644 arch/arm/mach-hisi/platmcpm.c
>>
>> diff --git a/arch/arm/mach-hisi/Makefile b/arch/arm/mach-hisi/Makefile
>> index ee2506b..d64831e 100644
>> +
>> +static void hip04_mcpm_power_down(void)
>> +{
>> +     unsigned int mpidr, cpu, cluster, data = 0;
>> +     bool skip_reset = false;
>> +
>> +     mpidr = read_cpuid_mpidr();
>> +     cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
>> +     cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
>> +
>> +     __mcpm_cpu_going_down(cpu, cluster);
>> +
>> +     spin_lock(&boot_lock);
>> +     BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
>> +     hip04_cpu_table[cluster][cpu]--;
>> +     if (hip04_cpu_table[cluster][cpu] == 1) {
>> +             /* A power_up request went ahead of us. */
>> +             skip_reset = true;
>> +     } else if (hip04_cpu_table[cluster][cpu] > 1) {
>> +             pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu);
>> +             BUG();
>> +     }
>> +     spin_unlock(&boot_lock);
>> +
>> +     v7_exit_coherency_flush(louis);
>> +
>> +     __mcpm_cpu_down(cpu, cluster);
>
> What if there is a hip04_mcpm_power_up() being called on another CPU
> right here?  There is a race that I illustrated in a previous email
> which is still unresolved.
>

Thanks for your reminder again. I'll move it into the protection.

>> +
>> +     if (!skip_reset) {
>> +             data = CORE_RESET_BIT(cpu) | NEON_RESET_BIT(cpu) | \
>> +                    CORE_DEBUG_RESET_BIT(cpu);
>> +             writel_relaxed(data, sysctrl + SC_CPU_RESET_REQ(cluster));
>> +     }
>> +}
>> +
>> +static int hip04_mcpm_wait_for_powerdown(unsigned int cpu, unsigned int cluster)
>> +{
>> +     unsigned int data, tries;
>> +
>> +     BUG_ON(cluster >= HIP04_MAX_CLUSTERS ||
>> +            cpu >= HIP04_MAX_CPUS_PER_CLUSTER);
>> +
>> +     for (tries = 0; tries < TIMEOUT_MSEC / POLL_MSEC; tries++) {
>> +             data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster));
>> +             if (!(data & CORE_RESET_STATUS(cpu))) {
>> +                     msleep(POLL_MSEC);
>> +                     continue;
>> +             }
>> +             return 0;
>> +     }
>> +     return -ETIMEDOUT;
>> +}
>> +
>> +static void hip04_mcpm_powered_up(void)
>> +{
>> +     if (!relocation)
>> +             return;
>> +     spin_lock(&boot_lock);
>> +     writel_relaxed(0, relocation);
>> +     writel_relaxed(0, relocation + 4);
>> +     writel_relaxed(0, relocation + 8);
>> +     writel_relaxed(0, relocation + 12);
>> +     spin_unlock(&boot_lock);
>> +}
>> +
>> +static void __naked hip04_mcpm_power_up_setup(unsigned int affinity_level)
>> +{
>> +     asm volatile ("                 \n"
>> +     /* calculate fabric phys address */
>> +"    adr     r2, 2f                  \n"
>> +"    ldmia   r2, {r1, r3}            \n"
>> +"    sub     r0, r2, r1              \n"
>> +"    add     r2, r0, r3              \n"
>> +"    ldr     r2, [r2]                \n"
>
> You may replace the above 2 instructions with "ldr r2, [r0, r3]".
>
OK.

>> +     /* get cluster id from MPIDR */
>> +"    mrc     p15, 0, r0, c0, c0, 5   \n"
>> +"    ubfx    r1, r0, #8, #8          \n"
>> +"    and     r1, r1, #0xf            \n"
>
> You don't need the "and" here.  It is implicit in ubfx.
>
OK.

>> +     /* 1 << cluster id */
>> +"    mov     r0, #1                  \n"
>> +"    mov     r3, r0, lsl r1          \n"
>> +"    ldr     r0, [r2, #"__stringify(FAB_SF_MODE)"]   \n"
>> +"    tst     r0, r3                  \n"
>> +"    bxne    lr                      \n"
>
> Instead of running all this code all the time, you could simply test r0
> at the very beginning and if it is not equal to 1 then return
> immediately. If it is 1 that means the CPU executing this code is the
> first one to run in the cluster, in which case you also don't have to
> test if the cluster snoop is already enabled here.
>

Since I need to enable the cluster snoop for cluster 0. At this time,
it's not enabled although core0 is running.

>> +"    orr     r1, r0, r3              \n"
>> +"    str     r1, [r2, #"__stringify(FAB_SF_MODE)"]   \n"
>> +"1:  ldr     r0, [r2, #"__stringify(FAB_SF_MODE)"]   \n"
>> +"    tst     r0, r3                  \n"
>> +"    beq     1b                      \n"
>> +"    bx      lr                      \n"
>> +
>> +"    .align  2                       \n"
>> +"2:  .word   .                       \n"
>> +"    .word   fabric_phys_addr        \n"
>> +     );
>> +}
>
> Of course you will also have to enable the snoops for the current
> cluster in hip04_cpu_table_init() as well.

It means that I need to reserve the copy to enable the snoop in c code
for cluster 0. Is it right?

>
>
>> +
>> +static const struct mcpm_platform_ops hip04_mcpm_ops = {
>> +     .power_up               = hip04_mcpm_power_up,
>> +     .power_down             = hip04_mcpm_power_down,
>> +     .wait_for_powerdown     = hip04_mcpm_wait_for_powerdown,
>> +     .powered_up             = hip04_mcpm_powered_up,
>> +};
>> +
>> +static bool __init hip04_cpu_table_init(void)
>> +{
>> +     unsigned int mpidr, cpu, cluster;
>> +
>> +     mpidr = read_cpuid_mpidr();
>> +     cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
>> +     cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
>> +
>> +     if (cluster >= HIP04_MAX_CLUSTERS ||
>> +         cpu >= HIP04_MAX_CPUS_PER_CLUSTER) {
>> +             pr_err("%s: boot CPU is out of bound!\n", __func__);
>> +             return false;
>> +     }
>> +     hip04_cpu_table[cluster][cpu] = 1;
>> +     return true;
>> +}
>> +
>> +static int __init hip04_mcpm_init(void)
>> +{
>> +     struct device_node *np, *np_fab;
>> +     struct resource fab_res;
>> +     int ret = -ENODEV;
>> +
>> +     np = of_find_compatible_node(NULL, NULL, "hisilicon,sysctrl");
>> +     if (!np)
>> +             goto err;
>> +     np_fab = of_find_compatible_node(NULL, NULL, "hisilicon,hip04-fabric");
>> +     if (!np_fab)
>> +             goto err;
>> +
>> +     if (of_property_read_u32(np, "bootwrapper-phys",
>> +                              &hip04_boot.bootwrapper_phys)) {
>> +             pr_err("failed to get bootwrapper-phys\n");
>> +             ret = -EINVAL;
>> +             goto err;
>> +     }
>> +     if (of_property_read_u32(np, "bootwrapper-size",
>> +                              &hip04_boot.bootwrapper_size)) {
>> +             pr_err("failed to get bootwrapper-size\n");
>> +             ret = -EINVAL;
>> +             goto err;
>> +     }
>> +     if (of_property_read_u32(np, "bootwrapper-magic",
>> +                              &hip04_boot.bootwrapper_magic)) {
>> +             pr_err("failed to get bootwrapper-magic\n");
>> +             ret = -EINVAL;
>> +             goto err;
>> +     }
>> +     if (of_property_read_u32(np, "relocation-entry",
>> +                              &hip04_boot.relocation_entry)) {
>> +             pr_err("failed to get relocation-entry\n");
>> +             ret = -EINVAL;
>> +             goto err;
>> +     }
>> +     if (of_property_read_u32(np, "relocation-size",
>> +                              &hip04_boot.relocation_size)) {
>> +             pr_err("failed to get relocation-size\n");
>> +             ret = -EINVAL;
>> +             goto err;
>> +     }
>> +
>> +     relocation = ioremap(hip04_boot.relocation_entry,
>> +                          hip04_boot.relocation_size);
>> +     if (!relocation) {
>> +             pr_err("failed to map relocation space\n");
>> +             ret = -ENOMEM;
>> +             goto err;
>> +     }
>> +     sysctrl = of_iomap(np, 0);
>> +     if (!sysctrl) {
>> +             pr_err("failed to get sysctrl base\n");
>> +             ret = -ENOMEM;
>> +             goto err_sysctrl;
>> +     }
>> +     ret = of_address_to_resource(np_fab, 0, &fab_res);
>> +     if (ret) {
>> +             pr_err("failed to get fabric base phys\n");
>> +             goto err_fabric;
>> +     }
>> +     fabric_phys_addr = fab_res.start;
>> +     sync_cache_w(&fabric_phys_addr);
>> +     fabric = of_iomap(np_fab, 0);
>> +     if (!fabric) {
>> +             pr_err("failed to get fabric base\n");
>> +             ret = -ENOMEM;
>> +             goto err_fabric;
>> +     }
>> +
>> +     if (!hip04_cpu_table_init())
>> +             return -EINVAL;
>> +     ret = mcpm_platform_register(&hip04_mcpm_ops);
>> +     if (!ret) {
>> +             mcpm_sync_init(hip04_mcpm_power_up_setup);
>> +             pr_info("HiP04 MCPM initialized\n");
>> +     }
>> +     mcpm_smp_set_ops();
>> +     return ret;
>> +err_fabric:
>> +     iounmap(sysctrl);
>> +err_sysctrl:
>> +     iounmap(relocation);
>> +err:
>> +     return ret;
>> +}
>> +early_initcall(hip04_mcpm_init);
>> --
>> 1.9.1
>>
>>
Nicolas Pitre July 14, 2014, 9:41 a.m. UTC | #3
On Mon, 14 Jul 2014, Haojian Zhuang wrote:

> On 13 July 2014 05:31, Nicolas Pitre <nicolas.pitre@linaro.org> wrote:
> > On Thu, 10 Jul 2014, Haojian Zhuang wrote:
> >
> >> +static void __naked hip04_mcpm_power_up_setup(unsigned int affinity_level)
> >> +{
> >> +     asm volatile ("                 \n"
> >> +     /* calculate fabric phys address */
> >> +"    adr     r2, 2f                  \n"
> >> +"    ldmia   r2, {r1, r3}            \n"
> >> +"    sub     r0, r2, r1              \n"
> >> +"    add     r2, r0, r3              \n"
> >> +"    ldr     r2, [r2]                \n"
> >
> > You may replace the above 2 instructions with "ldr r2, [r0, r3]".
> >
> OK.
> 
> >> +     /* get cluster id from MPIDR */
> >> +"    mrc     p15, 0, r0, c0, c0, 5   \n"
> >> +"    ubfx    r1, r0, #8, #8          \n"
> >> +"    and     r1, r1, #0xf            \n"
> >
> > You don't need the "and" here.  It is implicit in ubfx.
> >
> OK.
> 
> >> +     /* 1 << cluster id */
> >> +"    mov     r0, #1                  \n"
> >> +"    mov     r3, r0, lsl r1          \n"
> >> +"    ldr     r0, [r2, #"__stringify(FAB_SF_MODE)"]   \n"
> >> +"    tst     r0, r3                  \n"
> >> +"    bxne    lr                      \n"
> >
> > Instead of running all this code all the time, you could simply test r0
> > at the very beginning and if it is not equal to 1 then return
> > immediately. If it is 1 that means the CPU executing this code is the
> > first one to run in the cluster, in which case you also don't have to
> > test if the cluster snoop is already enabled here.
> >
> 
> Since I need to enable the cluster snoop for cluster 0. At this time,
> it's not enabled although core0 is running.

Yes, hence my next comment.

> >> +"    orr     r1, r0, r3              \n"
> >> +"    str     r1, [r2, #"__stringify(FAB_SF_MODE)"]   \n"
> >> +"1:  ldr     r0, [r2, #"__stringify(FAB_SF_MODE)"]   \n"
> >> +"    tst     r0, r3                  \n"
> >> +"    beq     1b                      \n"
> >> +"    bx      lr                      \n"
> >> +
> >> +"    .align  2                       \n"
> >> +"2:  .word   .                       \n"
> >> +"    .word   fabric_phys_addr        \n"
> >> +     );
> >> +}
> >
> > Of course you will also have to enable the snoops for the current
> > cluster in hip04_cpu_table_init() as well.
> 
> It means that I need to reserve the copy to enable the snoop in c code
> for cluster 0. Is it right?

Yes. And it can be __init just like hip04_cpu_table_init().


Nicolas
diff mbox

Patch

diff --git a/arch/arm/mach-hisi/Makefile b/arch/arm/mach-hisi/Makefile
index ee2506b..d64831e 100644
--- a/arch/arm/mach-hisi/Makefile
+++ b/arch/arm/mach-hisi/Makefile
@@ -3,4 +3,5 @@ 
 #
 
 obj-y	+= hisilicon.o
+obj-$(CONFIG_MCPM)		+= platmcpm.o
 obj-$(CONFIG_SMP)		+= platsmp.o hotplug.o headsmp.o
diff --git a/arch/arm/mach-hisi/platmcpm.c b/arch/arm/mach-hisi/platmcpm.c
new file mode 100644
index 0000000..3befcb3
--- /dev/null
+++ b/arch/arm/mach-hisi/platmcpm.c
@@ -0,0 +1,331 @@ 
+/*
+ * Copyright (c) 2013-2014 Linaro Ltd.
+ * Copyright (c) 2013-2014 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ */
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/of_address.h>
+
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+#include <asm/mcpm.h>
+
+#include "core.h"
+
+/* bits definition in SC_CPU_RESET_REQ[x]/SC_CPU_RESET_DREQ[x]
+ * 1 -- unreset; 0 -- reset
+ */
+#define CORE_RESET_BIT(x)		(1 << x)
+#define NEON_RESET_BIT(x)		(1 << (x + 4))
+#define CORE_DEBUG_RESET_BIT(x)		(1 << (x + 9))
+#define CLUSTER_L2_RESET_BIT		(1 << 8)
+#define CLUSTER_DEBUG_RESET_BIT		(1 << 13)
+
+/*
+ * bits definition in SC_CPU_RESET_STATUS[x]
+ * 1 -- reset status; 0 -- unreset status
+ */
+#define CORE_RESET_STATUS(x)		(1 << x)
+#define NEON_RESET_STATUS(x)		(1 << (x + 4))
+#define CORE_DEBUG_RESET_STATUS(x)	(1 << (x + 9))
+#define CLUSTER_L2_RESET_STATUS		(1 << 8)
+#define CLUSTER_DEBUG_RESET_STATUS	(1 << 13)
+#define CORE_WFI_STATUS(x)		(1 << (x + 16))
+#define CORE_WFE_STATUS(x)		(1 << (x + 20))
+#define CORE_DEBUG_ACK(x)		(1 << (x + 24))
+
+#define SC_CPU_RESET_REQ(x)		(0x520 + (x << 3))	/* reset */
+#define SC_CPU_RESET_DREQ(x)		(0x524 + (x << 3))	/* unreset */
+#define SC_CPU_RESET_STATUS(x)		(0x1520 + (x << 3))
+
+#define FAB_SF_MODE			0x0c
+#define FAB_SF_INVLD			0x10
+
+/* bits definition in FB_SF_INVLD */
+#define FB_SF_INVLD_START		(1 << 8)
+
+#define HIP04_MAX_CLUSTERS		4
+#define HIP04_MAX_CPUS_PER_CLUSTER	4
+
+#define POLL_MSEC	10
+#define TIMEOUT_MSEC	1000
+
+struct hip04_secondary_cpu_data {
+	u32	bootwrapper_phys;
+	u32	bootwrapper_size;
+	u32	bootwrapper_magic;
+	u32	relocation_entry;
+	u32	relocation_size;
+};
+
+static void __iomem *relocation, *sysctrl, *fabric;
+static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER];
+static DEFINE_SPINLOCK(boot_lock);
+static struct hip04_secondary_cpu_data hip04_boot;
+static u32 fabric_phys_addr;
+
+static bool hip04_cluster_down(unsigned int cluster)
+{
+	int i;
+
+	for (i = 0; i < HIP04_MAX_CPUS_PER_CLUSTER; i++)
+		if (hip04_cpu_table[cluster][i])
+			return false;
+	return true;
+}
+
+static int hip04_mcpm_power_up(unsigned int cpu, unsigned int cluster)
+{
+	unsigned long data, mask;
+
+	if (!relocation || !sysctrl)
+		return -ENODEV;
+	if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER)
+		return -EINVAL;
+
+	spin_lock_irq(&boot_lock);
+
+	if (hip04_cpu_table[cluster][cpu]) {
+		hip04_cpu_table[cluster][cpu]++;
+		spin_unlock_irq(&boot_lock);
+		return 0;
+	}
+
+	writel_relaxed(hip04_boot.bootwrapper_phys, relocation);
+	writel_relaxed(hip04_boot.bootwrapper_magic, relocation + 4);
+	writel_relaxed(virt_to_phys(mcpm_entry_point), relocation + 8);
+	writel_relaxed(0, relocation + 12);
+
+	if (hip04_cluster_down(cluster)) {
+		data = CLUSTER_DEBUG_RESET_BIT;
+		writel_relaxed(data, sysctrl + SC_CPU_RESET_DREQ(cluster));
+		do {
+			mask = CLUSTER_DEBUG_RESET_STATUS;
+			data = readl_relaxed(sysctrl + \
+					     SC_CPU_RESET_STATUS(cluster));
+		} while (data & mask);
+	}
+
+	hip04_cpu_table[cluster][cpu]++;
+
+	data = CORE_RESET_BIT(cpu) | NEON_RESET_BIT(cpu) | \
+	       CORE_DEBUG_RESET_BIT(cpu);
+	writel_relaxed(data, sysctrl + SC_CPU_RESET_DREQ(cluster));
+	spin_unlock_irq(&boot_lock);
+	msleep(POLL_MSEC);
+
+	return 0;
+}
+
+static void hip04_mcpm_power_down(void)
+{
+	unsigned int mpidr, cpu, cluster, data = 0;
+	bool skip_reset = false;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	__mcpm_cpu_going_down(cpu, cluster);
+
+	spin_lock(&boot_lock);
+	BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
+	hip04_cpu_table[cluster][cpu]--;
+	if (hip04_cpu_table[cluster][cpu] == 1) {
+		/* A power_up request went ahead of us. */
+		skip_reset = true;
+	} else if (hip04_cpu_table[cluster][cpu] > 1) {
+		pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu);
+		BUG();
+	}
+	spin_unlock(&boot_lock);
+
+	v7_exit_coherency_flush(louis);
+
+	__mcpm_cpu_down(cpu, cluster);
+
+	if (!skip_reset) {
+		data = CORE_RESET_BIT(cpu) | NEON_RESET_BIT(cpu) | \
+		       CORE_DEBUG_RESET_BIT(cpu);
+		writel_relaxed(data, sysctrl + SC_CPU_RESET_REQ(cluster));
+	}
+}
+
+static int hip04_mcpm_wait_for_powerdown(unsigned int cpu, unsigned int cluster)
+{
+	unsigned int data, tries;
+
+	BUG_ON(cluster >= HIP04_MAX_CLUSTERS ||
+	       cpu >= HIP04_MAX_CPUS_PER_CLUSTER);
+
+	for (tries = 0; tries < TIMEOUT_MSEC / POLL_MSEC; tries++) {
+		data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster));
+		if (!(data & CORE_RESET_STATUS(cpu))) {
+			msleep(POLL_MSEC);
+			continue;
+		}
+		return 0;
+	}
+	return -ETIMEDOUT;
+}
+
+static void hip04_mcpm_powered_up(void)
+{
+	if (!relocation)
+		return;
+	spin_lock(&boot_lock);
+	writel_relaxed(0, relocation);
+	writel_relaxed(0, relocation + 4);
+	writel_relaxed(0, relocation + 8);
+	writel_relaxed(0, relocation + 12);
+	spin_unlock(&boot_lock);
+}
+
+static void __naked hip04_mcpm_power_up_setup(unsigned int affinity_level)
+{
+	asm volatile ("			\n"
+	/* calculate fabric phys address */
+"	adr	r2, 2f			\n"
+"	ldmia	r2, {r1, r3}		\n"
+"	sub	r0, r2, r1		\n"
+"	add	r2, r0, r3		\n"
+"	ldr	r2, [r2]		\n"
+	/* get cluster id from MPIDR */
+"	mrc	p15, 0, r0, c0, c0, 5	\n"
+"	ubfx	r1, r0, #8, #8		\n"
+"	and	r1, r1, #0xf		\n"
+	/* 1 << cluster id */
+"	mov	r0, #1			\n"
+"	mov	r3, r0, lsl r1		\n"
+"	ldr	r0, [r2, #"__stringify(FAB_SF_MODE)"]	\n"
+"	tst	r0, r3			\n"
+"	bxne	lr			\n"
+"	orr	r1, r0, r3		\n"
+"	str	r1, [r2, #"__stringify(FAB_SF_MODE)"]	\n"
+"1:	ldr	r0, [r2, #"__stringify(FAB_SF_MODE)"]	\n"
+"	tst	r0, r3			\n"
+"	beq	1b			\n"
+"	bx	lr			\n"
+
+"	.align	2			\n"
+"2:	.word	.			\n"
+"	.word	fabric_phys_addr	\n"
+	);
+}
+
+static const struct mcpm_platform_ops hip04_mcpm_ops = {
+	.power_up		= hip04_mcpm_power_up,
+	.power_down		= hip04_mcpm_power_down,
+	.wait_for_powerdown	= hip04_mcpm_wait_for_powerdown,
+	.powered_up		= hip04_mcpm_powered_up,
+};
+
+static bool __init hip04_cpu_table_init(void)
+{
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	if (cluster >= HIP04_MAX_CLUSTERS ||
+	    cpu >= HIP04_MAX_CPUS_PER_CLUSTER) {
+		pr_err("%s: boot CPU is out of bound!\n", __func__);
+		return false;
+	}
+	hip04_cpu_table[cluster][cpu] = 1;
+	return true;
+}
+
+static int __init hip04_mcpm_init(void)
+{
+	struct device_node *np, *np_fab;
+	struct resource fab_res;
+	int ret = -ENODEV;
+
+	np = of_find_compatible_node(NULL, NULL, "hisilicon,sysctrl");
+	if (!np)
+		goto err;
+	np_fab = of_find_compatible_node(NULL, NULL, "hisilicon,hip04-fabric");
+	if (!np_fab)
+		goto err;
+
+	if (of_property_read_u32(np, "bootwrapper-phys",
+				 &hip04_boot.bootwrapper_phys)) {
+		pr_err("failed to get bootwrapper-phys\n");
+		ret = -EINVAL;
+		goto err;
+	}
+	if (of_property_read_u32(np, "bootwrapper-size",
+				 &hip04_boot.bootwrapper_size)) {
+		pr_err("failed to get bootwrapper-size\n");
+		ret = -EINVAL;
+		goto err;
+	}
+	if (of_property_read_u32(np, "bootwrapper-magic",
+				 &hip04_boot.bootwrapper_magic)) {
+		pr_err("failed to get bootwrapper-magic\n");
+		ret = -EINVAL;
+		goto err;
+	}
+	if (of_property_read_u32(np, "relocation-entry",
+				 &hip04_boot.relocation_entry)) {
+		pr_err("failed to get relocation-entry\n");
+		ret = -EINVAL;
+		goto err;
+	}
+	if (of_property_read_u32(np, "relocation-size",
+				 &hip04_boot.relocation_size)) {
+		pr_err("failed to get relocation-size\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	relocation = ioremap(hip04_boot.relocation_entry,
+			     hip04_boot.relocation_size);
+	if (!relocation) {
+		pr_err("failed to map relocation space\n");
+		ret = -ENOMEM;
+		goto err;
+	}
+	sysctrl = of_iomap(np, 0);
+	if (!sysctrl) {
+		pr_err("failed to get sysctrl base\n");
+		ret = -ENOMEM;
+		goto err_sysctrl;
+	}
+	ret = of_address_to_resource(np_fab, 0, &fab_res);
+	if (ret) {
+		pr_err("failed to get fabric base phys\n");
+		goto err_fabric;
+	}
+	fabric_phys_addr = fab_res.start;
+	sync_cache_w(&fabric_phys_addr);
+	fabric = of_iomap(np_fab, 0);
+	if (!fabric) {
+		pr_err("failed to get fabric base\n");
+		ret = -ENOMEM;
+		goto err_fabric;
+	}
+
+	if (!hip04_cpu_table_init())
+		return -EINVAL;
+	ret = mcpm_platform_register(&hip04_mcpm_ops);
+	if (!ret) {
+		mcpm_sync_init(hip04_mcpm_power_up_setup);
+		pr_info("HiP04 MCPM initialized\n");
+	}
+	mcpm_smp_set_ops();
+	return ret;
+err_fabric:
+	iounmap(sysctrl);
+err_sysctrl:
+	iounmap(relocation);
+err:
+	return ret;
+}
+early_initcall(hip04_mcpm_init);