Kernel启动流程源码解析 4 start_kernel 上
一 start_kernel
start_kernel函数是kernel启动过程执行的第一个c语言函数，其通过调用一系列初始化函数完成的内核的初始化工作，上篇分析
local_irq_enable之前的代码。
1.0 start_kernel
定义在init/main.c中
asmlinkage void __init start_kernel(void)
{
char * command_line;
extern const struct kernel_param __start___param[], __stop___param[];
/*
* Need to run as early as possible, to initialize the
* lockdep hash:
*/
lockdep_init(); // 初始化内核死锁检测机制的哈希表
smp_setup_processor_id(); // 返回cpu号，单核cpu返回0
debug_objects_early_init(); // 对调试对象进行早期的初始化
cgroup_init_early(); // 对Control Groups进行早期的初始化
local_irq_disable(); // 关闭当前cpu的中断
early_boot_irqs_disabled = true;
/*
* Interrupts are still disabled. Do necessary setups, then
* enable them
*/
boot_cpu_init(); // 设置当前cpu位激活状态
page_address_init(); // 初始化高端内存的，arm没有用到
pr_notice("%s", linux_banner);
setup_arch(&command_line); // 内核架构相关初始化函数
/*
* Set up the the initial canary ASAP:
*/
boot_init_stack_canary(); //
初始化栈canary值，canary值用于防止栈溢出攻击的堆栈的保护字
mm_init_owner(&init_mm, &init_task); // mm.owner =
&init_task
mm_init_cpumask(&init_mm);
setup_command_line(command_line); // 对cmdline进行备份
setup_nr_cpu_ids(); //
nr_cpu_ids
setup_per_cpu_areas(); //
每个cpu的per-cpu变量副本分配空间
smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
build_all_zonelists(NULL, NULL); //
建立系统内存页区(zone)链表
page_alloc_init(); // 内存页初始化
pr_notice("Kernel command line: %s\n", boot_command_line);
parse_early_param(); // 解析
需要'早期'处理的启动参数
用？
setup_arch已经调用了一次
parse_args("Booting kernel", static_command_line, __start___param,
__stop___param - __start___param,
-1, -1, &unknown_bootoption); // 解析cmdline中的启动参数
jump_label_init(); // 处理静态定义在跳转标号
/*
* These use large bootmem allocations and must precede
* kmem_cache_init()
*/
setup_log_buf(0); // 使用memblock_alloc分配一个启动时log缓冲区
pidhash_init(); // 初始化pid散列表
vfs_caches_init_early(); // 初始化
dentry和inode的hashtable
sort_main_extable(); // 对内核异常向量表进行排序
trap_init(); // 对内核陷阱异常进行初始化，arm没有用到
mm_init(); //
初始化内核内存分配器，过度到伙伴系统，启动slab机制，初始化非连续内存区
/*
* Set up the scheduler prior starting any interrupts (such as the
* timer interrupt). Full topology setup happens at smp_init()
* time - but meanwhile we still have a functioning scheduler.
*/
sched_init(); // 初始化进程调度器
/*
* Disable preemption - early bootup scheduling is extremely
* fragile until we cpu_idle() for the first time.
*/
preempt_disable(); // 进制内核抢占
if (WARN(!irqs_disabled(), "Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable(); // 关闭本地中断
idr_init_cache(); // 创建idr（整数id管理机制）高速缓存
perf_event_init(); // 初始化性能诊断工具
rcu_init(); // 初始化rcu机制（读-写-拷贝）
tick_nohz_init(); // 初始化动态时钟框架
radix_tree_init(); // 初始化内核基数树
/* init some links before init_ISA_irqs() */
early_irq_init(); // arm64没有用到
init_IRQ(); // 初始化中断
tick_init(); // 初始化时钟滴答控制器
init_timers(); // 初始化内核定时器
hrtimers_init(); // 初始化高精度时钟
softirq_init(); // 初始化软中断
timekeeping_init(); //
初始化了大量的时钟相关全局变量
time_init(); // 时钟初始化
profile_init(); //
对内核的一个性能测试工具profile进行初始化
call_function_init(); //
smp下跨cpu的函数传递初始化
WARN(!irqs_disabled(), "Interrupts were enabled early\n");
early_boot_irqs_disabled = false;
local_irq_enable(); // 使能当前cpu中断
kmem_cache_init_late();
/*
* HACK ALERT! This is early. We're enabling the console before
* we've done PCI setups etc, and console_init() must be aware of
* this. But we do want output early, in case something goes wrong.
*/
console_init();
if (panic_later)
panic(panic_later, panic_param);
lockdep_info();
/*
* Need to run this when irqs are enabled, because it wants
* to self-test [hard/soft]-irqs on/off lock inversion bugs
* too:
*/
locking_selftest();
#ifdef CONFIG_BLK_DEV_INITRD
if (initrd_start && !initrd_below_start_ok &&
page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) {
pr_crit("initrd overwritten (0x%08lx < 0x%08lx) - disabling it.\n",
page_to_pfn(virt_to_page((void *)initrd_start)),
min_low_pfn);
initrd_start = 0;
}
#endif
page_cgroup_init();
debug_objects_mem_init();
kmemleak_init();
setup_per_cpu_pageset();
numa_policy_init();
if (late_time_init)
late_time_init();
sched_clock_init();
calibrate_delay();
pidmap_init();
anon_vma_init();
#ifdef CONFIG_X86
if (efi_enabled(EFI_RUNTIME_SERVICES))
efi_enter_virtual_mode();
#endif
thread_info_cache_init();
cred_init();
fork_init(totalram_pages);
proc_caches_init();
buffer_init();
key_init();
security_init();
dbg_late_init();
vfs_caches_init(totalram_pages);
signals_init();
/* rootfs populating might need page-writeback */
page_writeback_init();
#ifdef CONFIG_PROC_FS
proc_root_init();
#endif
cgroup_init();
cpuset_init();
taskstats_init_early();
delayacct_init();
check_bugs();
acpi_early_init(); /* before LAPIC and SMP init */
sfi_init_late();
if (efi_enabled(EFI_RUNTIME_SERVICES)) {
efi_late_init();
efi_free_boot_services();
}
ftrace_init();
/* Do the rest non-__init'ed, we're now alive */
rest_init();
}
1.1 lockdep_init
定义在kernel/lockdep.c中
void lockdep_init(void)
{
int i;
/*
* Some architectures have their own start_kernel()
* code which calls lockdep_init(), while we also
* call lockdep_init() from the start_kernel() itself,
* and we want to initialize the hashes only once:
*/
if (lockdep_initialized)
return;
for (i = 0; i < CLASSHASH_SIZE; i++)
INIT_LIST_HEAD(classhash_table + i);
for (i = 0; i < CHAINHASH_SIZE; i++)
INIT_LIST_HEAD(chainhash_table + i);
lockdep_initialized = 1;
}
1.2 debug_objects_early_init
定义在lib/debugobjects.c中
void __init debug_objects_early_init(void)
{
int i;
for (i = 0; i < ODEBUG_HASH_SIZE; i++)
raw_spin_lock_init(&obj_hash[i].lock);
for (i = 0; i < ODEBUG_POOL_SIZE; i++)
hlist_add_head(&obj_static_pool[i].node, &obj_pool);
}
1.3 cgroup_init_early
定义在kernel/cgroup.c
int __init cgroup_init_early(void)
{
int i;
atomic_set(&init_css_set.refcount, 1);
INIT_LIST_HEAD(&init_css_set.cg_links);
INIT_LIST_HEAD(&init_css_set.tasks);
INIT_HLIST_NODE(&init_css_set.hlist);
css_set_count = 1;
init_cgroup_root(&rootnode);
root_count = 1;
init_task.cgroups = &init_css_set;
init_css_set_link.cg = &init_css_set;
init_css_set_link.cgrp = dummytop;
list_add(&init_css_set_link.cgrp_link_list,
&rootnode.top_cgroup.css_sets);
list_add(&init_css_set_link.cg_link_list,
&init_css_set.cg_links);
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
struct cgroup_subsys *ss = subsys[i];
/* at bootup time, we don't worry about modular subsystems */
if (!ss || ss->module)
continue;
BUG_ON(!ss->name);
BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN);
BUG_ON(!ss->css_alloc);
BUG_ON(!ss->css_free);
if (ss->subsys_id != i) {
printk(KERN_ERR "cgroup: Subsys %s id == %d\n",
ss->name, ss->subsys_id);
BUG();
}
if (ss->early_init)
cgroup_init_subsys(ss);
}
return 0;
}
1.4 local_irq_disable
trace_hardirqs_off_caller定义在kernel/lockdep.c中
#define local_irq_disable() \
do { raw_local_irq_disable(); trace_hardirqs_off(); } while (0)
void trace_hardirqs_off(void)
{
trace_hardirqs_off_caller(CALLER_ADDR0);
}
void trace_hardirqs_off_caller(unsigned long ip)
{
struct task_struct *curr = current;
time_hardirqs_off(CALLER_ADDR0, ip);
if (unlikely(!debug_locks || current->lockdep_recursion))
return;
/*
* So we're supposed to get called after you mask local IRQs, but for
* some reason the hardware doesn't quite think you did a proper job.
*/
if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
return;
if (curr->hardirqs_enabled) {
/*
* We have done an ON -> OFF transition:
*/
curr->hardirqs_enabled = 0;
curr->hardirq_disable_ip = ip;
curr->hardirq_disable_event = ++curr->irq_events;
debug_atomic_inc(hardirqs_off_events);
} else
debug_atomic_inc(redundant_hardirqs_off);
}
1.5 boot_cpu_init
定义在init/main.c中
static void __init boot_cpu_init(void)
{
int cpu = smp_processor_id();
/* Mark the boot cpu "present", "online" etc for SMP and UP case */
set_cpu_online(cpu, true);
set_cpu_active(cpu, true);
set_cpu_present(cpu, true);
set_cpu_possible(cpu, true);
}
1.6 setup_per_cpu_areas
定义在mm/percpu.c中
void __init setup_per_cpu_areas(void)
{
unsigned long delta;
unsigned int cpu;
int rc;
/*
* Always reserve area for module percpu variables. That's
* what the legacy allocator did.
*/
rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL,
pcpu_dfl_fc_alloc, pcpu_dfl_fc_free);
if (rc < 0)
panic("Failed to initialize percpu areas.");
delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
for_each_possible_cpu(cpu)
__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
}
1.7 build_all_zonelists
定义在mm/page_alloc.c中
void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
{
set_zonelist_order();
if (system_state == SYSTEM_BOOTING) {
__build_all_zonelists(NULL);
mminit_verify_zonelist();
cpuset_init_current_mems_allowed();
} else {
/* we have to stop all cpus to guarantee there is no user
of zonelist */
#ifdef CONFIG_MEMORY_HOTPLUG
if (zone)
setup_zone_pageset(zone);
#endif
stop_machine(__build_all_zonelists, pgdat, NULL);
/* cpuset refresh routine should be here */
}
vm_total_pages = nr_free_pagecache_pages();
/*
* Disable grouping by mobility if the number of pages in the
* system is too low to allow the mechanism to work. It would be
* more accurate, but expensive to check per-zone. This check is
* made on memory-hotadd so a system can start with mobility
* disabled and enable it later
*/
if (vm_total_pages < (pageblock_nr_pages * MIGRATE_TYPES))
page_group_by_mobility_disabled = 1;
else
page_group_by_mobility_disabled = 0;
printk("Built %i zonelists in %s order, mobility grouping %s. "
"Total pages: %ld\n",
nr_online_nodes,
zonelist_order_name[current_zonelist_order],
page_group_by_mobility_disabled ? "off" : "on",
vm_total_pages);
#ifdef CONFIG_NUMA
printk("Policy zone: %s\n", zone_names[policy_zone]);
#endif
}
1.8 page_alloc_init
定义在mm/page_alloc.c中
void __init page_alloc_init(void)
{
hotcpu_notifier(page_alloc_cpu_notify, 0);
}
static int page_alloc_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
{
int cpu = (unsigned long)hcpu;
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
lru_add_drain_cpu(cpu);
drain_pages(cpu);
/*
* Spill the event counters of the dead processor
* into the current processors event counters.
* This artificially elevates the count of the current
* processor.
*/
vm_events_fold_cpu(cpu);
/*
* Zero the differential counters of the dead processor
* so that the vm statistics are consistent.
*
* This is only okay since the processor is dead and cannot
* race with what we are doing.
*/
refresh_cpu_vm_stats(cpu);
}
return NOTIFY_OK;
}
1.9 parse_args
定义在kernel/params.c中
/* Args looks like "foo=bar,bar2 baz=fuz wiz". */
int parse_args(const char *doing,
char *args,
const struct kernel_param *params,
unsigned num,
s16 min_level,
s16 max_level,
int (*unknown)(char *param, char *val, const char *doing))
{
char *param, *val;
/* Chew leading spaces */
args = skip_spaces(args);
if (*args)
pr_debug("doing %s, parsing ARGS: '%s'\n", doing, args);
while (*args) {
int ret;
int irq_was_disabled;
args = next_arg(args, ¶m, &val);
irq_was_disabled = irqs_disabled();
ret = parse_one(param, val, doing, params, num,
min_level, max_level, unknown);
if (irq_was_disabled && !irqs_disabled())
pr_warn("%s: option '%s' enabled irq's!\n",
doing, param);
switch (ret) {
case -ENOENT:
pr_err("%s: Unknown parameter `%s'\n", doing, param);
return ret;
case -ENOSPC:
pr_err("%s: `%s' too large for parameter `%s'\n",
doing, val ?: "", param);
return ret;
case 0:
break;
default:
pr_err("%s: `%s' invalid for parameter `%s'\n",
doing, val ?: "", param);
return ret;
}
}
/* All parsed OK. */
return 0;
}
1.10 jump_label_init
定义在kernel/jump_label.c中
void __init jump_label_init(void)
{
struct jump_entry *iter_start = __start___jump_table;
struct jump_entry *iter_stop = __stop___jump_table;
struct static_key *key = NULL;
struct jump_entry *iter;
jump_label_lock();
jump_label_sort_entries(iter_start, iter_stop);
for (iter = iter_start; iter < iter_stop; iter++) {
struct static_key *iterk;
iterk = (struct static_key *)(unsigned long)iter->key;
arch_jump_label_transform_static(iter, jump_label_type(iterk));
if (iterk == key)
continue;
key = iterk;
/*
* Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH.
*/
*((unsigned long *)&key->entries) += (unsigned long)iter;
#ifdef CONFIG_MODULES
key->next = NULL;
#endif
}
jump_label_unlock();
}
1.11 setup_log_buf
定义在kernel/printk.c中
void __init setup_log_buf(int early)
{
unsigned long flags;
char *new_log_buf;
int free;
if (!new_log_buf_len)
return;
if (early) {
unsigned long mem;
mem = memblock_alloc(new_log_buf_len, PAGE_SIZE);
if (!mem)
return;
new_log_buf = __va(mem);
} else {
new_log_buf = alloc_bootmem_nopanic(new_log_buf_len);
}
if (unlikely(!new_log_buf)) {
pr_err("log_buf_len: %ld bytes not available\n",
new_log_buf_len);
return;
}
raw_spin_lock_irqsave(&logbuf_lock, flags);
log_buf_len = new_log_buf_len;
log_buf = new_log_buf;
new_log_buf_len = 0;
free = __LOG_BUF_LEN - log_next_idx;
memcpy(log_buf, __log_buf, __LOG_BUF_LEN);
raw_spin_unlock_irqrestore(&logbuf_lock, flags);
pr_info("log_buf_len: %d\n", log_buf_len);
pr_info("early log buf free: %d(%d%%)\n",
free, (free * 100) / __LOG_BUF_LEN);
}
1.12 vfs_caches_init_early
定义在fs/dcache.c中
void __init vfs_caches_init_early(void)
{
dcache_init_early();
inode_init_early();
}
static void __init dcache_init_early(void)
{
unsigned int loop;
/* If hashes are distributed across NUMA nodes, defer
* hash allocation until vmalloc space is available.
*/
if (hashdist)
return;
dentry_hashtable =
alloc_large_system_hash("Dentry cache",
sizeof(struct hlist_bl_head),
dhash_entries,
13,
HASH_EARLY,
&d_hash_shift,
&d_hash_mask,
0,
0);
for (loop = 0; loop < (1U << d_hash_shift); loop++)
INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
}
void __init inode_init_early(void)
{
unsigned int loop;
/* If hashes are distributed across NUMA nodes, defer
* hash allocation until vmalloc space is available.
*/
if (hashdist)
return;
inode_hashtable =
alloc_large_system_hash("Inode-cache",
sizeof(struct hlist_head),
ihash_entries,
14,
HASH_EARLY,
&i_hash_shift,
&i_hash_mask,
0,
0);
for (loop = 0; loop < (1U << i_hash_shift); loop++)
INIT_HLIST_HEAD(&inode_hashtable[loop]);
}
1.13 perf_event_init
定义在kernel/events/core.c中
void __init perf_event_init(void)
{
int ret;
idr_init(&pmu_idr);
perf_event_init_all_cpus();
init_srcu_struct(&pmus_srcu);
perf_pmu_register(&perf_swevent, "software", PERF_TYPE_SOFTWARE);
perf_pmu_register(&perf_cpu_clock, NULL, -1);
perf_pmu_register(&perf_task_clock, NULL, -1);
perf_tp_register();
perf_cpu_notifier(perf_cpu_notify);
register_reboot_notifier(&perf_reboot_notifier);
ret = init_hw_breakpoint();
WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
/* do not patch jump label more than once per second */
jump_label_rate_limit(&perf_sched_events, HZ);
/*
* Build time assertion that we keep the data_head at the intended
* location. IOW, validation we got the __reserved[] size right.
*/
BUILD_BUG_ON((offsetof(struct perf_event_mmap_page, data_head))
!= 1024);
}
1.14 rcu_init
定义在kernel/rcutree.c中
void __init rcu_init(void)
{
int cpu;
rcu_bootup_announce();
rcu_init_geometry();
rcu_init_one(&rcu_sched_state, &rcu_sched_data);
rcu_init_one(&rcu_bh_state, &rcu_bh_data);
__rcu_init_preempt();
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
/*
* We don't need protection against CPU-hotplug here because
* this is called early in boot, before either interrupts
* or the scheduler are operational.
*/
cpu_notifier(rcu_cpu_notify, 0);
for_each_online_cpu(cpu)
rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
}
1.15 tick_nohz_init
定义在kernel/time/tick-sched.c中
void __init tick_nohz_init(void)
{
int cpu;
if (!have_nohz_full_mask) {
if (tick_nohz_init_all() < 0)
return;
}
cpu_notifier(tick_nohz_cpu_down_callback, 0);
/* Make sure full dynticks CPU are also RCU nocbs */
for_each_cpu(cpu, nohz_full_mask) {
if (!rcu_is_nocb_cpu(cpu)) {
pr_warning("NO_HZ: CPU %d is not RCU nocb: "
"cleared from nohz_full range", cpu);
cpumask_clear_cpu(cpu, nohz_full_mask);
}
}
cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), nohz_full_mask);
pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf);
}
1.16 radix_tree_init
定义在lib/radix-tree.c中
void __init radix_tree_init(void)
{
radix_tree_node_cachep = kmem_cache_create("radix_tree_node",
sizeof(struct radix_tree_node), 0,
SLAB_PANIC | SLAB_RECLAIM_ACCOUNT,
radix_tree_node_ctor);
radix_tree_init_maxindex();
hotcpu_notifier(radix_tree_callback, 0);
}
1.17 init_timers
定义在kernel/timer.c中
void __init init_timers(void)
{
int err;
/* ensure there are enough low bits for flags in timer->base pointer */
BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK);
err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
(void *)(long)smp_processor_id());
init_timer_stats();
BUG_ON(err != NOTIFY_OK);
register_cpu_notifier(&timers_nb);
open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
}
1.18 hrtimers_init
定义在kernel/hrtimer.c中
void __init hrtimers_init(void)
{
hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
(void *)(long)smp_processor_id());
register_cpu_notifier(&hrtimers_nb);
#ifdef CONFIG_HIGH_RES_TIMERS
open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
#endif
}
1.19 softirq_init
定义在kernel/softirq.c中
void __init softirq_init(void)
{
int cpu;
for_each_possible_cpu(cpu) {
int i;
per_cpu(tasklet_vec, cpu).tail =
&per_cpu(tasklet_vec, cpu).head;
per_cpu(tasklet_hi_vec, cpu).tail =
&per_cpu(tasklet_hi_vec, cpu).head;
for (i = 0; i < NR_SOFTIRQS; i++)
INIT_LIST_HEAD(&per_cpu(softirq_work_list[i], cpu));
}
register_hotcpu_notifier(&remote_softirq_cpu_notifier);
open_softirq(TASKLET_SOFTIRQ, tasklet_action);
open_softirq(HI_SOFTIRQ, tasklet_hi_action);
}
1.20 timekeeping_init
定义在kernel/time/timekeeping.c中
void __init timekeeping_init(void)
{
struct timekeeper *tk = &timekeeper;
struct clocksource *clock;
unsigned long flags;
struct timespec now, boot, tmp;
read_persistent_clock(&now);
if (!timespec_valid_strict(&now)) {
pr_warn("WARNING: Persistent clock returned invalid value!\n"
" Check your CMOS/BIOS settings.\n");
now.tv_sec = 0;
now.tv_nsec = 0;
} else if (now.tv_sec || now.tv_nsec)
persistent_clock_exist = true;
read_boot_clock(&boot);
if (!timespec_valid_strict(&boot)) {
pr_warn("WARNING: Boot clock returned invalid value!\n"
" Check your CMOS/BIOS settings.\n");
boot.tv_sec = 0;
boot.tv_nsec = 0;
}
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&timekeeper_seq);
ntp_init();
clock = clocksource_default_clock();
if (clock->enable)
clock->enable(clock);
tk_setup_internals(tk, clock);
tk_set_xtime(tk, &now);
tk->raw_time.tv_sec = 0;
tk->raw_time.tv_nsec = 0;
if (boot.tv_sec == 0 && boot.tv_nsec == 0)
boot = tk_xtime(tk);
set_normalized_timespec(&tmp, -boot.tv_sec, -boot.tv_nsec);
tk_set_wall_to_mono(tk, tmp);
tmp.tv_sec = 0;
tmp.tv_nsec = 0;
tk_set_sleep_time(tk, tmp);
memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper));
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
}
1.21 time_init
定义在arch/arm64/kernel/time.c中
void __init time_init(void)
{
u32 arch_timer_rate;
clocksource_of_init();
arch_timer_rate = arch_timer_get_rate();
if (!arch_timer_rate)
panic("Unable to initialise architected timer.\n");
/* Cache the sched_clock multiplier to save a divide in the hot path. */
sched_clock_mult = NSEC_PER_SEC / arch_timer_rate;
/* Calibrate the delay loop directly */
lpj_fine = arch_timer_rate / HZ;
}
1.22 profile_init
定义在kernel/profile.c中
int __ref profile_init(void)
{
int buffer_bytes;
if (!prof_on)
return 0;
/* only text is profiled */
prof_len = (_etext - _stext) >> prof_shift;
buffer_bytes = prof_len*sizeof(atomic_t);
if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
return -ENOMEM;
cpumask_copy(prof_cpu_mask, cpu_possible_mask);
prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL|__GFP_NOWARN);
if (prof_buffer)
return 0;
prof_buffer = alloc_pages_exact(buffer_bytes,
GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN);
if (prof_buffer)
return 0;
prof_buffer = vzalloc(buffer_bytes);
if (prof_buffer)
return 0;
free_cpumask_var(prof_cpu_mask);
return -ENOMEM;
}
1.23 call_function_init
定义在kernel/smp.c中
void __init call_function_init(void)
{
void *cpu = (void *)(long)smp_processor_id();
int i;
for_each_possible_cpu(i) {
struct call_single_queue *q = &per_cpu(call_single_queue, i);
raw_spin_lock_init(&q->lock);
INIT_LIST_HEAD(&q->list);
}
hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu);
register_cpu_notifier(&hotplug_cfd_notifier);
}