diff options
Diffstat (limited to 'arch/arm')
-rw-r--r-- | arch/arm/include/asm/pgtable.h | 1 | ||||
-rw-r--r-- | arch/arm/include/asm/processor.h | 2 | ||||
-rw-r--r-- | arch/arm/include/asm/topology.h | 35 | ||||
-rw-r--r-- | arch/arm/kernel/topology.c | 485 | ||||
-rw-r--r-- | arch/arm/mach-exynos4/platsmp.c | 10 | ||||
-rw-r--r-- | arch/arm/mach-msm/platsmp.c | 6 | ||||
-rw-r--r-- | arch/arm/mach-omap2/omap-smp.c | 10 | ||||
-rw-r--r-- | arch/arm/mach-pxa/cm-x300.c | 8 | ||||
-rw-r--r-- | arch/arm/mach-realview/platsmp.c | 10 | ||||
-rw-r--r-- | arch/arm/mach-shmobile/platsmp.c | 6 | ||||
-rw-r--r-- | arch/arm/mach-tegra/platsmp.c | 8 | ||||
-rw-r--r-- | arch/arm/mach-ux500/cpu.c | 25 | ||||
-rw-r--r-- | arch/arm/mach-ux500/platsmp.c | 10 | ||||
-rw-r--r-- | arch/arm/mach-vexpress/ct-ca9x4.c | 6 | ||||
-rw-r--r-- | arch/arm/mm/mmap.c | 196 | ||||
-rw-r--r-- | arch/arm/plat-mxc/include/mach/iomux-v3.h | 10 |
16 files changed, 744 insertions, 84 deletions
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index aec18abf4e6..9d5255ae784 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -305,6 +305,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) * We provide our own arch_get_unmapped_area to cope with VIPT caches. */ #define HAVE_ARCH_UNMAPPED_AREA +#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN /* * remap a physical page `pfn' of size `size' with page protection `prot' diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index b2d9df5667a..ce280b8d613 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -123,6 +123,8 @@ static inline void prefetch(const void *ptr) #endif +#define HAVE_ARCH_PICK_MMAP_LAYOUT + #endif #endif /* __ASM_ARM_PROCESSOR_H */ diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index a7e457ed27c..f7f02e392ef 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -25,7 +25,7 @@ extern struct cputopo_arm cpu_topology[NR_CPUS]; void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); -const struct cpumask *cpu_coregroup_mask(unsigned int cpu); +const struct cpumask *cpu_coregroup_mask(int cpu); #else @@ -34,6 +34,39 @@ static inline void store_cpu_topology(unsigned int cpuid) { } #endif +/* Common values for CPUs */ +#ifndef SD_CPU_INIT +#define SD_CPU_INIT (struct sched_domain) { \ + .min_interval = 1, \ + .max_interval = 4, \ + .busy_factor = 64, \ + .imbalance_pct = 125, \ + .cache_nice_tries = 1, \ + .busy_idx = 2, \ + .idle_idx = 1, \ + .newidle_idx = 0, \ + .wake_idx = 0, \ + .forkexec_idx = 0, \ + \ + .flags = 1*SD_LOAD_BALANCE \ + | 1*SD_BALANCE_NEWIDLE \ + | 1*SD_BALANCE_EXEC \ + | 1*SD_BALANCE_FORK \ + | 0*SD_BALANCE_WAKE \ + | 1*SD_WAKE_AFFINE \ + | 0*SD_PREFER_LOCAL \ + | 0*SD_SHARE_CPUPOWER \ + | 0*SD_SHARE_PKG_RESOURCES \ + | 0*SD_SERIALIZE \ + | arch_sd_sibling_asym_packing() \ + | sd_balance_for_package_power() \ + | sd_power_saving_flags() \ + , \ + .last_balance = jiffies, \ + .balance_interval = 1, \ +} +#endif + #include <asm-generic/topology.h> #endif /* _ASM_ARM_TOPOLOGY_H */ diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 1040c00405d..053ce9cbc0b 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -18,6 +18,17 @@ #include <linux/node.h> #include <linux/nodemask.h> #include <linux/sched.h> +#include <linux/cpumask.h> +#include <linux/cpuset.h> + +#ifdef CONFIG_CPU_FREQ +#include <linux/cpufreq.h> +#endif + +#ifdef CONFIG_DEBUG_FS +#include <linux/debugfs.h> +#include <linux/uaccess.h> /* for copy_from_user */ +#endif #include <asm/cputype.h> #include <asm/topology.h> @@ -43,12 +54,327 @@ struct cputopo_arm cpu_topology[NR_CPUS]; -const struct cpumask *cpu_coregroup_mask(unsigned int cpu) +/* + * cpu power scale management + */ + +/* + * a per cpu data structure should be better because each cpu is mainly + * using its own cpu_power even it's not always true because of + * no_hz_idle_balance + */ + +static DEFINE_PER_CPU(unsigned int, cpu_scale); + +/* + * cpu topology mask management + */ + +unsigned int advanced_topology = 1; + +static void normal_cpu_topology_mask(void); +static void (*set_cpu_topology_mask)(void) = normal_cpu_topology_mask; + +#ifdef CONFIG_CPU_FREQ +/* + * This struct describes parameters to compute cpu_power + */ +struct cputopo_power { + int id; + int max; /* max idx in the table */ + unsigned int step; /* frequency step for the table */ + unsigned int *table; /* table of cpu_power */ +}; + +/* default table with one default cpu_power value */ +unsigned int table_default_power[1] = { + 1024 +}; + +static struct cputopo_power default_cpu_power = { + .max = 1, + .step = 1, + .table = table_default_power, +}; + +/* CA-9 table with cpufreq modifying cpu_power */ +#define CPU_MAX_FREQ 10 +/* we use a 200Mhz step for scaling cpu power */ +#define CPU_TOPO_FREQ_STEP 200000 +/* This table sets the cpu_power scale of a cpu according to 2 inputs which are + * the frequency and the sched_mc mode. The content of this table could be SoC + * specific so we should add a method to overwrite this default table. + * TODO: Study how to use DT for setting this table + */ +unsigned int table_ca9_power[CPU_MAX_FREQ] = { +/* freq< 200 400 600 800 1000 1200 1400 1600 1800 other*/ + 4096, 4096, 4096, 1024, 1024, 1024, 1024, 1024, 1024, 1024, /* Power save mode CA9 MP */ +}; + +static struct cputopo_power CA9_cpu_power = { + .max = CPU_MAX_FREQ, + .step = CPU_TOPO_FREQ_STEP, + .table = table_ca9_power, +}; + +#define ARM_CORTEX_A9_DEFAULT_SCALE 0 +#define ARM_CORTEX_A9_POWER_SCALE 1 +/* This table list all possible cpu power configuration */ +struct cputopo_power *table_config[2] = { + &default_cpu_power, + &CA9_cpu_power, +}; + +struct cputopo_scale { + int id; + int freq; + struct cputopo_power *power; +}; + +/* + * The table will be mostly used by one cpu which will update the + * configuration for all cpu on a cpufreq notification + * or a sched_mc level change + */ +static struct cputopo_scale cpu_power[NR_CPUS]; + +static void set_cpufreq_scale(unsigned int cpuid, unsigned int freq) +{ + unsigned int idx; + + cpu_power[cpuid].freq = freq; + + idx = freq / cpu_power[cpuid].power->step; + if (idx >= cpu_power[cpuid].power->max) + idx = cpu_power[cpuid].power->max - 1; + + per_cpu(cpu_scale, cpuid) = cpu_power[cpuid].power->table[idx]; + smp_wmb(); +} + +static void set_power_scale(unsigned int cpu, unsigned int idx) +{ + cpu_power[cpu].id = idx; + cpu_power[cpu].power = table_config[idx]; + + set_cpufreq_scale(cpu, cpu_power[cpu].freq); +} + +static int topo_cpufreq_transition(struct notifier_block *nb, + unsigned long state, void *data) +{ + struct cpufreq_freqs *freqs = data; + + if (state == CPUFREQ_POSTCHANGE || state == CPUFREQ_RESUMECHANGE) + set_cpufreq_scale(freqs->cpu, freqs->new); + + return NOTIFY_OK; +} + +static struct notifier_block topo_cpufreq_nb = { + .notifier_call = topo_cpufreq_transition, +}; + +static int topo_cpufreq_init(void) +{ + unsigned int cpu; + + /* TODO set initial value according to current freq */ + + /* init core mask */ + for_each_possible_cpu(cpu) { + cpu_power[cpu].freq = 0; + cpu_power[cpu].power = &default_cpu_power; + } + + return cpufreq_register_notifier(&topo_cpufreq_nb, + CPUFREQ_TRANSITION_NOTIFIER); +} +#else +#define ARM_CORTEX_A9_DEFAULT_SCALE 0 +#define ARM_CORTEX_A9_POWER_SCALE 0 +/* This table list all possible cpu power configuration */ +unsigned int table_config[1] = { + 1024, +}; + +static void set_power_scale(unsigned int cpu, unsigned int idx) +{ + per_cpu(cpu_scale, cpu) = table_config[idx]; +} + +static inline int topo_cpufreq_init(void) {return 0; } +#endif + +static int init_cpu_power_scale(void) +{ + /* register cpufreq notifer */ + topo_cpufreq_init(); + + /* Do we need to change default config */ + advanced_topology = 1; + + /* Force a cpu topology update */ + rebuild_sched_domains(); + + return 0; +} + +core_initcall(init_cpu_power_scale); + +/* + * Update the cpu power + */ + +unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu) +{ + return per_cpu(cpu_scale, cpu); +} + +/* + * sched_domain flag configuration + */ +/* TODO add a config flag for this function */ +int arch_sd_sibling_asym_packing(void) +{ + if (sched_smt_power_savings || sched_mc_power_savings) + return SD_ASYM_PACKING; + return 0; +} + +/* + * default topology function + */ + +const struct cpumask *cpu_coregroup_mask(int cpu) { return &cpu_topology[cpu].core_sibling; } /* + * clear cpu topology masks + */ +static void clear_cpu_topology_mask(void) +{ + unsigned int cpuid; + for_each_possible_cpu(cpuid) { + struct cputopo_arm *cpuid_topo = &(cpu_topology[cpuid]); + cpumask_clear(&cpuid_topo->core_sibling); + cpumask_clear(&cpuid_topo->thread_sibling); + } + smp_wmb(); +} + +/* + * default_cpu_topology_mask set the core and thread mask as described in the + * ARM ARM + */ +static inline void default_cpu_topology_mask(unsigned int cpuid) +{ + struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid]; + unsigned int cpu; + + for_each_possible_cpu(cpu) { + struct cputopo_arm *cpu_topo = &cpu_topology[cpu]; + + if (cpuid_topo->socket_id == cpu_topo->socket_id) { + cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, + &cpuid_topo->core_sibling); + + if (cpuid_topo->core_id == cpu_topo->core_id) { + cpumask_set_cpu(cpuid, + &cpu_topo->thread_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, + &cpuid_topo->thread_sibling); + } + } + } + smp_wmb(); +} + +static void normal_cpu_topology_mask(void) +{ + unsigned int cpuid; + + for_each_possible_cpu(cpuid) { + default_cpu_topology_mask(cpuid); + set_power_scale(cpuid, ARM_CORTEX_A9_DEFAULT_SCALE); + } + smp_wmb(); +} + +/* + * For Cortex-A9 MPcore, we emulate a multi-package topology in power mode. + * The goal is to gathers tasks on 1 virtual package + */ +static void power_cpu_topology_mask_CA9(void) +{ + unsigned int cpuid, cpu; + + for_each_possible_cpu(cpuid) { + struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid]; + + for_each_possible_cpu(cpu) { + struct cputopo_arm *cpu_topo = &cpu_topology[cpu]; + + if ((cpuid_topo->socket_id == cpu_topo->socket_id) + && ((cpuid & 0x1) == (cpu & 0x1))) { + cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, + &cpuid_topo->core_sibling); + + if (cpuid_topo->core_id == cpu_topo->core_id) { + cpumask_set_cpu(cpuid, + &cpu_topo->thread_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, + &cpuid_topo->thread_sibling); + } + } + } + set_power_scale(cpuid, ARM_CORTEX_A9_POWER_SCALE); + } + smp_wmb(); +} + +#define ARM_FAMILY_MASK 0xFF0FFFF0 +#define ARM_CORTEX_A9_FAMILY 0x410FC090 + +/* update_cpu_topology_policy select a cpu topology policy according to the + * available cores. + * TODO: The current version assumes that all cores are exactly the same which + * might not be true. We need to update it to take into account various + * configuration among which system with different kind of core. + */ +static int update_cpu_topology_policy(void) +{ + unsigned long cpuid; + + if (sched_mc_power_savings == POWERSAVINGS_BALANCE_NONE) { + set_cpu_topology_mask = normal_cpu_topology_mask; + return 0; + } + + cpuid = read_cpuid_id(); + cpuid &= ARM_FAMILY_MASK; + + switch (cpuid) { + case ARM_CORTEX_A9_FAMILY: + set_cpu_topology_mask = power_cpu_topology_mask_CA9; + break; + default: + set_cpu_topology_mask = normal_cpu_topology_mask; + break; + } + + return 0; +} + +/* * store_cpu_topology is called at boot when only one cpu is running * and with the mutex cpu_hotplug.lock locked, when several cpus have booted, * which prevents simultaneous write access to cpu_topology array @@ -57,7 +383,6 @@ void store_cpu_topology(unsigned int cpuid) { struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid]; unsigned int mpidr; - unsigned int cpu; /* If the cpu topology has been already set, just return */ if (cpuid_topo->core_id != -1) @@ -99,26 +424,11 @@ void store_cpu_topology(unsigned int cpuid) cpuid_topo->socket_id = -1; } - /* update core and thread sibling masks */ - for_each_possible_cpu(cpu) { - struct cputopo_arm *cpu_topo = &cpu_topology[cpu]; - - if (cpuid_topo->socket_id == cpu_topo->socket_id) { - cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); - if (cpu != cpuid) - cpumask_set_cpu(cpu, - &cpuid_topo->core_sibling); - - if (cpuid_topo->core_id == cpu_topo->core_id) { - cpumask_set_cpu(cpuid, - &cpu_topo->thread_sibling); - if (cpu != cpuid) - cpumask_set_cpu(cpu, - &cpuid_topo->thread_sibling); - } - } - } - smp_wmb(); + /* + * The core and thread sibling masks can also be updated during the + * call of arch_update_cpu_topology + */ + default_cpu_topology_mask(cpuid); printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", cpuid, cpu_topology[cpuid].thread_id, @@ -127,6 +437,27 @@ void store_cpu_topology(unsigned int cpuid) } /* + * arch_update_cpu_topology is called by the scheduler before building + * a new sched_domain hierarchy. + */ +int arch_update_cpu_topology(void) +{ + if (!advanced_topology) + return 0; + + /* clear core threads mask */ + clear_cpu_topology_mask(); + + /* set topology policy */ + update_cpu_topology_policy(); + + /* set topology mask and power */ + (*set_cpu_topology_mask)(); + + return 1; +} + +/* * init_cpu_topology is called at boot when only one cpu is running * which prevent simultaneous write access to cpu_topology array */ @@ -143,6 +474,116 @@ void init_cpu_topology(void) cpu_topo->socket_id = -1; cpumask_clear(&cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); + + per_cpu(cpu_scale, cpu) = SCHED_POWER_SCALE; } smp_wmb(); } + +/* + * debugfs interface for scaling cpu power + */ + +#ifdef CONFIG_DEBUG_FS +static struct dentry *topo_debugfs_root; + +static ssize_t dbg_write(struct file *file, const char __user *buf, + size_t size, loff_t *off) +{ + unsigned int *value = file->f_dentry->d_inode->i_private; + char cdata[128]; + unsigned long tmp; + unsigned int cpu; + + if (size < (sizeof(cdata)-1)) { + if (copy_from_user(cdata, buf, size)) + return -EFAULT; + cdata[size] = 0; + if (!strict_strtoul(cdata, 10, &tmp)) { + *value = tmp; + +#ifdef CONFIG_CPU_FREQ + for_each_online_cpu(cpu) + set_power_scale(cpu, cpu_power[cpu].id); +#endif + } + return size; + } + return -EINVAL; +} + +static ssize_t dbg_read(struct file *file, char __user *buf, + size_t size, loff_t *off) +{ + unsigned int *value = file->f_dentry->d_inode->i_private; + char cdata[128]; + unsigned int len; + + len = sprintf(cdata, "%u\n", *value); + return simple_read_from_buffer(buf, size, off, cdata, len); +} + +static const struct file_operations debugfs_fops = { + .read = dbg_read, + .write = dbg_write, +}; + +static struct dentry *topo_debugfs_register(unsigned int cpu, + struct dentry *parent) +{ + struct dentry *cpu_d, *d; + char cpu_name[16]; + + sprintf(cpu_name, "cpu%u", cpu); + + cpu_d = debugfs_create_dir(cpu_name, parent); + if (!cpu_d) + return NULL; + + d = debugfs_create_file("cpu_power", S_IRUGO | S_IWUGO, + cpu_d, &per_cpu(cpu_scale, cpu), &debugfs_fops); + if (!d) + goto err_out; + +#ifdef CONFIG_CPU_FREQ + d = debugfs_create_file("scale", S_IRUGO | S_IWUGO, + cpu_d, &cpu_power[cpu].id, &debugfs_fops); + if (!d) + goto err_out; + + d = debugfs_create_file("freq", S_IRUGO, + cpu_d, &cpu_power[cpu].freq, &debugfs_fops); + if (!d) + goto err_out; +#endif + return cpu_d; + +err_out: + debugfs_remove_recursive(cpu_d); + return NULL; +} + +static int __init topo_debugfs_init(void) +{ + struct dentry *d; + unsigned int cpu; + + d = debugfs_create_dir("cpu_topo", NULL); + if (!d) + return -ENOMEM; + topo_debugfs_root = d; + + for_each_possible_cpu(cpu) { + d = topo_debugfs_register(cpu, topo_debugfs_root); + if (d == NULL) + goto err_out; + } + return 0; + +err_out: + debugfs_remove_recursive(topo_debugfs_root); + return -ENOMEM; +} + +late_initcall(topo_debugfs_init); +#endif diff --git a/arch/arm/mach-exynos4/platsmp.c b/arch/arm/mach-exynos4/platsmp.c index ca01370840d..c345b783cde 100644 --- a/arch/arm/mach-exynos4/platsmp.c +++ b/arch/arm/mach-exynos4/platsmp.c @@ -195,12 +195,10 @@ void __init smp_init_cpus(void) ncores = scu_base ? scu_get_core_count(scu_base) : 1; /* sanity check */ - if (ncores > NR_CPUS) { - printk(KERN_WARNING - "EXYNOS4: no. of cores (%d) greater than configured " - "maximum of %d - clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-msm/platsmp.c b/arch/arm/mach-msm/platsmp.c index 1a1af9e5625..72765952091 100644 --- a/arch/arm/mach-msm/platsmp.c +++ b/arch/arm/mach-msm/platsmp.c @@ -156,6 +156,12 @@ void __init smp_init_cpus(void) { unsigned int i, ncores = get_core_count(); + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; + } + for (i = 0; i < ncores; i++) set_cpu_possible(i, true); diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index ce65e9329c7..889464dc7b2 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -109,12 +109,10 @@ void __init smp_init_cpus(void) ncores = scu_get_core_count(scu_base); /* sanity check */ - if (ncores > NR_CPUS) { - printk(KERN_WARNING - "OMAP4: no. of cores (%d) greater than configured " - "maximum of %d - clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c index 9ac0225cd51..e40dc47cf2f 100644 --- a/arch/arm/mach-pxa/cm-x300.c +++ b/arch/arm/mach-pxa/cm-x300.c @@ -775,7 +775,6 @@ static struct gpio cm_x300_wi2wi_gpios[] __initdata = { static void __init cm_x300_init_wi2wi(void) { - int bt_reset, wlan_en; int err; if (system_rev < 130) { @@ -791,12 +790,11 @@ static void __init cm_x300_init_wi2wi(void) } udelay(10); - gpio_set_value(bt_reset, 0); + gpio_set_value(cm_x300_wi2wi_gpios[1].gpio, 0); udelay(10); - gpio_set_value(bt_reset, 1); + gpio_set_value(cm_x300_wi2wi_gpios[1].gpio, 1); - gpio_free(wlan_en); - gpio_free(bt_reset); + gpio_free_array(ARRAY_AND_SIZE(cm_x300_wi2wi_gpios)); } /* MFP */ diff --git a/arch/arm/mach-realview/platsmp.c b/arch/arm/mach-realview/platsmp.c index 4ae943bafa9..e83c654a58d 100644 --- a/arch/arm/mach-realview/platsmp.c +++ b/arch/arm/mach-realview/platsmp.c @@ -52,12 +52,10 @@ void __init smp_init_cpus(void) ncores = scu_base ? scu_get_core_count(scu_base) : 1; /* sanity check */ - if (ncores > NR_CPUS) { - printk(KERN_WARNING - "Realview: no. of cores (%d) greater than configured " - "maximum of %d - clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c index 66f980625a3..e4e485fa253 100644 --- a/arch/arm/mach-shmobile/platsmp.c +++ b/arch/arm/mach-shmobile/platsmp.c @@ -56,6 +56,12 @@ void __init smp_init_cpus(void) unsigned int ncores = shmobile_smp_get_core_count(); unsigned int i; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; + } + for (i = 0; i < ncores; i++) set_cpu_possible(i, true); diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c index 0886cbccdde..7d2b5d03c1d 100644 --- a/arch/arm/mach-tegra/platsmp.c +++ b/arch/arm/mach-tegra/platsmp.c @@ -114,10 +114,10 @@ void __init smp_init_cpus(void) { unsigned int i, ncores = scu_get_core_count(scu_base); - if (ncores > NR_CPUS) { - printk(KERN_ERR "Tegra: no. of cores (%u) greater than configured (%u), clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-ux500/cpu.c b/arch/arm/mach-ux500/cpu.c index 1da23bb87c1..8aa104a4711 100644 --- a/arch/arm/mach-ux500/cpu.c +++ b/arch/arm/mach-ux500/cpu.c @@ -99,7 +99,27 @@ static void ux500_l2x0_inv_all(void) ux500_cache_sync(); } -static int ux500_l2x0_init(void) +static int __init ux500_l2x0_unlock(void) +{ + int i; + + /* + * Unlock Data and Instruction Lock if locked. Ux500 U-Boot versions + * apparently locks both caches before jumping to the kernel. The + * l2x0 core will not touch the unlock registers if the l2x0 is + * already enabled, so we do it right here instead. The PL310 has + * 8 sets of registers, one per possible CPU. + */ + for (i = 0; i < 8; i++) { + writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE + + i * L2X0_LOCKDOWN_STRIDE); + writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_I_BASE + + i * L2X0_LOCKDOWN_STRIDE); + } + return 0; +} + +static int __init ux500_l2x0_init(void) { if (cpu_is_u5500()) l2x0_base = __io_address(U5500_L2CC_BASE); @@ -108,6 +128,9 @@ static int ux500_l2x0_init(void) else ux500_unknown_soc(); + /* Unlock before init */ + ux500_l2x0_unlock(); + /* 64KB way size, 8 way associativity, force WA */ l2x0_init(l2x0_base, 0x3e060000, 0xc0000fff); diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c index a33df5f4c27..eb5199102cf 100644 --- a/arch/arm/mach-ux500/platsmp.c +++ b/arch/arm/mach-ux500/platsmp.c @@ -156,12 +156,10 @@ void __init smp_init_cpus(void) ncores = scu_base ? scu_get_core_count(scu_base) : 1; /* sanity check */ - if (ncores > NR_CPUS) { - printk(KERN_WARNING - "U8500: no. of cores (%d) greater than configured " - "maximum of %d - clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c index bfd32f52c2d..2b1e836a76e 100644 --- a/arch/arm/mach-vexpress/ct-ca9x4.c +++ b/arch/arm/mach-vexpress/ct-ca9x4.c @@ -221,6 +221,12 @@ static void ct_ca9x4_init_cpu_map(void) { int i, ncores = scu_get_core_count(MMIO_P2V(A9_MPCORE_SCU)); + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; + } + for (i = 0; i < ncores; ++i) set_cpu_possible(i, true); diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 74be05f3e03..c2809d7990b 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -9,13 +9,51 @@ #include <linux/io.h> #include <linux/personality.h> #include <linux/random.h> -#include <asm/cputype.h> -#include <asm/system.h> +#include <asm/cachetype.h> + +static inline unsigned long COLOUR_ALIGN_DOWN(unsigned long addr, + unsigned long pgoff) +{ + unsigned long base = addr & ~(SHMLBA-1); + unsigned long off = (pgoff << PAGE_SHIFT) & (SHMLBA-1); + + if (base + off <= addr) + return base + off; + + return base - off; +} #define COLOUR_ALIGN(addr,pgoff) \ ((((addr)+SHMLBA-1)&~(SHMLBA-1)) + \ (((pgoff)<<PAGE_SHIFT) & (SHMLBA-1))) +/* gap between mmap and stack */ +#define MIN_GAP (128*1024*1024UL) +#define MAX_GAP ((TASK_SIZE)/6*5) + +static int mmap_is_legacy(void) +{ + if (current->personality & ADDR_COMPAT_LAYOUT) + return 1; + + if (rlimit(RLIMIT_STACK) == RLIM_INFINITY) + return 1; + + return sysctl_legacy_va_layout; +} + +static unsigned long mmap_base(unsigned long rnd) +{ + unsigned long gap = rlimit(RLIMIT_STACK); + + if (gap < MIN_GAP) + gap = MIN_GAP; + else if (gap > MAX_GAP) + gap = MAX_GAP; + + return PAGE_ALIGN(TASK_SIZE - gap - rnd); +} + /* * We need to ensure that shared mappings are correctly aligned to * avoid aliasing issues with VIPT caches. We need to ensure that @@ -32,25 +70,15 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long start_addr; -#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) - unsigned int cache_type; - int do_align = 0, aliasing = 0; + int do_align = 0; + int aliasing = cache_is_vipt_aliasing() || icache_is_vipt_aliasing(); /* * We only need to do colour alignment if either the I or D - * caches alias. This is indicated by bits 9 and 21 of the - * cache type register. + * caches alias. */ - cache_type = read_cpuid_cachetype(); - if (cache_type != read_cpuid_id()) { - aliasing = (cache_type | cache_type >> 12) & (1 << 11); - if (aliasing) - do_align = filp || flags & MAP_SHARED; - } -#else -#define do_align 0 -#define aliasing 0 -#endif + if (aliasing) + do_align = filp || (flags & MAP_SHARED); /* * We enforce the MAP_FIXED case. @@ -79,13 +107,9 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, if (len > mm->cached_hole_size) { start_addr = addr = mm->free_area_cache; } else { - start_addr = addr = TASK_UNMAPPED_BASE; + start_addr = addr = mm->mmap_base; mm->cached_hole_size = 0; } - /* 8 bits of randomness in 20 address space bits */ - if ((current->flags & PF_RANDOMIZE) && - !(current->personality & ADDR_NO_RANDOMIZE)) - addr += (get_random_int() % (1 << 8)) << PAGE_SHIFT; full_search: if (do_align) @@ -122,6 +146,134 @@ full_search: } } +unsigned long +arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, + const unsigned long len, const unsigned long pgoff, + const unsigned long flags) +{ + struct vm_area_struct *vma; + struct mm_struct *mm = current->mm; + unsigned long addr = addr0; + int do_align = 0; + int aliasing = cache_is_vipt_aliasing() || icache_is_vipt_aliasing(); + + /* + * We only need to do colour alignment if either the I or D + * caches alias. + */ + if (aliasing) + do_align = filp || (flags & MAP_SHARED); + + /* requested length too big for entire address space */ + if (len > TASK_SIZE) + return -ENOMEM; + + if (flags & MAP_FIXED) { + if (aliasing && flags & MAP_SHARED && + (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1)) + return -EINVAL; + return addr; + } + + /* requesting a specific address */ + if (addr) { + if (do_align) + addr = COLOUR_ALIGN(addr, pgoff); + else + addr = PAGE_ALIGN(addr); + vma = find_vma(mm, addr); + if (TASK_SIZE - len >= addr && + (!vma || addr + len <= vma->vm_start)) + return addr; + } + + /* check if free_area_cache is useful for us */ + if (len <= mm->cached_hole_size) { + mm->cached_hole_size = 0; + mm->free_area_cache = mm->mmap_base; + } + + /* either no address requested or can't fit in requested address hole */ + addr = mm->free_area_cache; + if (do_align) { + unsigned long base = COLOUR_ALIGN_DOWN(addr - len, pgoff); + addr = base + len; + } + + /* make sure it can fit in the remaining address space */ + if (addr > len) { + vma = find_vma(mm, addr-len); + if (!vma || addr <= vma->vm_start) + /* remember the address as a hint for next time */ + return (mm->free_area_cache = addr-len); + } + + if (mm->mmap_base < len) + goto bottomup; + + addr = mm->mmap_base - len; + if (do_align) + addr = COLOUR_ALIGN_DOWN(addr, pgoff); + + do { + /* + * Lookup failure means no vma is above this address, + * else if new region fits below vma->vm_start, + * return with success: + */ + vma = find_vma(mm, addr); + if (!vma || addr+len <= vma->vm_start) + /* remember the address as a hint for next time */ + return (mm->free_area_cache = addr); + + /* remember the largest hole we saw so far */ + if (addr + mm->cached_hole_size < vma->vm_start) + mm->cached_hole_size = vma->vm_start - addr; + + /* try just below the current vma->vm_start */ + addr = vma->vm_start - len; + if (do_align) + addr = COLOUR_ALIGN_DOWN(addr, pgoff); + } while (len < vma->vm_start); + +bottomup: + /* + * A failed mmap() very likely causes application failure, + * so fall back to the bottom-up function here. This scenario + * can happen with large stack limits and large mmap() + * allocations. + */ + mm->cached_hole_size = ~0UL; + mm->free_area_cache = TASK_UNMAPPED_BASE; + addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags); + /* + * Restore the topdown base: + */ + mm->free_area_cache = mm->mmap_base; + mm->cached_hole_size = ~0UL; + + return addr; +} + +void arch_pick_mmap_layout(struct mm_struct *mm) +{ + unsigned long random_factor = 0UL; + + /* 8 bits of randomness in 20 address space bits */ + if ((current->flags & PF_RANDOMIZE) && + !(current->personality & ADDR_NO_RANDOMIZE)) + random_factor = (get_random_int() % (1 << 8)) << PAGE_SHIFT; + + if (mmap_is_legacy()) { + mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; + mm->get_unmapped_area = arch_get_unmapped_area; + mm->unmap_area = arch_unmap_area; + } else { + mm->mmap_base = mmap_base(random_factor); + mm->get_unmapped_area = arch_get_unmapped_area_topdown; + mm->unmap_area = arch_unmap_area_topdown; + } +} /* * You really shouldn't be using read() or write() on /dev/mem. This diff --git a/arch/arm/plat-mxc/include/mach/iomux-v3.h b/arch/arm/plat-mxc/include/mach/iomux-v3.h index ebbce33097a..45099566fec 100644 --- a/arch/arm/plat-mxc/include/mach/iomux-v3.h +++ b/arch/arm/plat-mxc/include/mach/iomux-v3.h @@ -89,11 +89,11 @@ typedef u64 iomux_v3_cfg_t; #define PAD_CTL_HYS (1 << 8) #define PAD_CTL_PKE (1 << 7) -#define PAD_CTL_PUE (1 << 6) -#define PAD_CTL_PUS_100K_DOWN (0 << 4) -#define PAD_CTL_PUS_47K_UP (1 << 4) -#define PAD_CTL_PUS_100K_UP (2 << 4) -#define PAD_CTL_PUS_22K_UP (3 << 4) +#define PAD_CTL_PUE (1 << 6 | PAD_CTL_PKE) +#define PAD_CTL_PUS_100K_DOWN (0 << 4 | PAD_CTL_PUE) +#define PAD_CTL_PUS_47K_UP (1 << 4 | PAD_CTL_PUE) +#define PAD_CTL_PUS_100K_UP (2 << 4 | PAD_CTL_PUE) +#define PAD_CTL_PUS_22K_UP (3 << 4 | PAD_CTL_PUE) #define PAD_CTL_ODE (1 << 3) |