X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=init%2Fmain.c;h=495a5bc2f2adc54c17d5ee6b2f65f6c6f912f7a2;hb=43bc926fffd92024b46cafaf7350d669ba9ca884;hp=77e962511616e62cb6b3e748de5ee2d4a495c58d;hpb=5273a3df6485dc2ad6aa7ddd441b9a21970f003b;p=linux-2.6.git diff --git a/init/main.c b/init/main.c index 77e962511..495a5bc2f 100644 --- a/init/main.c +++ b/init/main.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -40,42 +41,39 @@ #include #include #include +#include #include #include +#include +#include +#include #include #include - -/* - * This is one of the first .c files built. Error out early - * if we have compiler trouble.. - */ -#if __GNUC__ == 2 && __GNUC_MINOR__ == 96 -#ifdef CONFIG_FRAME_POINTER -#error This compiler cannot compile correctly with frame pointers enabled -#endif -#endif +#include +#include +#include #ifdef CONFIG_X86_LOCAL_APIC #include #endif /* - * Versions of gcc older than that listed below may actually compile - * and link okay, but the end product can have subtle run time bugs. - * To avoid associated bogus bug reports, we flatly refuse to compile - * with a gcc that is known to be too old from the very beginning. + * This is one of the first .c files built. Error out early if we have compiler + * trouble. + * + * Versions of gcc older than that listed below may actually compile and link + * okay, but the end product can have subtle run time bugs. To avoid associated + * bogus bug reports, we flatly refuse to compile with a gcc that is known to be + * too old from the very beginning. */ -#if __GNUC__ < 2 || (__GNUC__ == 2 && __GNUC_MINOR__ < 95) +#if (__GNUC__ < 3) || (__GNUC__ == 3 && __GNUC_MINOR__ < 2) #error Sorry, your GCC is too old. It builds incorrect kernels. #endif -extern char *linux_banner; - static int init(void *); extern void init_IRQ(void); -extern void sock_init(void); extern void fork_init(unsigned long); extern void mca_init(void); extern void sbus_init(void); @@ -84,31 +82,44 @@ extern void signals_init(void); extern void buffer_init(void); extern void pidhash_init(void); extern void pidmap_init(void); -extern void pte_chain_init(void); +extern void prio_tree_init(void); extern void radix_tree_init(void); extern void free_initmem(void); extern void populate_rootfs(void); extern void driver_init(void); extern void prepare_namespace(void); +#ifdef CONFIG_ACPI +extern void acpi_early_init(void); +#else +static inline void acpi_early_init(void) { } +#endif +#ifndef CONFIG_DEBUG_RODATA +static inline void mark_rodata_ro(void) { } +#endif #ifdef CONFIG_TC extern void tc_init(void); #endif -int system_state; /* SYSTEM_BOOTING/RUNNING/SHUTDOWN */ +enum system_states system_state; +EXPORT_SYMBOL(system_state); /* * Boot command-line arguments */ -#define MAX_INIT_ARGS 8 -#define MAX_INIT_ENVS 8 +#define MAX_INIT_ARGS CONFIG_INIT_ENV_ARG_LIMIT +#define MAX_INIT_ENVS CONFIG_INIT_ENV_ARG_LIMIT extern void time_init(void); /* Default late time init is NULL. archs can override this later. */ void (*late_time_init)(void); extern void softirq_init(void); +/* Untouched command line (eg. for /proc) saved by arch-specific code. */ +char saved_command_line[COMMAND_LINE_SIZE]; + static char *execute_command; +static char *ramdisk_execute_command; /* Setup configured maximum number of CPUs to activate */ static unsigned int max_cpus = NR_CPUS; @@ -143,81 +154,40 @@ static char * argv_init[MAX_INIT_ARGS+2] = { "init", NULL, }; char * envp_init[MAX_INIT_ENVS+2] = { "HOME=/", "TERM=linux", NULL, }; static const char *panic_later, *panic_param; -__setup("profile=", profile_setup); +extern struct obs_kernel_param __setup_start[], __setup_end[]; static int __init obsolete_checksetup(char *line) { struct obs_kernel_param *p; - extern struct obs_kernel_param __setup_start, __setup_end; - p = &__setup_start; + p = __setup_start; do { int n = strlen(p->str); if (!strncmp(line, p->str, n)) { - if (!p->setup_func) { - printk(KERN_WARNING "Parameter %s is obsolete, ignored\n", p->str); + if (p->early) { + /* Already done in parse_early_param? (Needs + * exact match on param part) */ + if (line[n] == '\0' || line[n] == '=') + return 1; + } else if (!p->setup_func) { + printk(KERN_WARNING "Parameter %s is obsolete," + " ignored\n", p->str); return 1; } else if (p->setup_func(line + n)) return 1; } p++; - } while (p < &__setup_end); + } while (p < __setup_end); return 0; } -/* this should be approx 2 Bo*oMips to start (note initial shift), and will - still work even if initially too large, it will just take slightly longer */ +/* + * This should be approx 2 Bo*oMips to start (note initial shift), and will + * still work even if initially too large, it will just take slightly longer + */ unsigned long loops_per_jiffy = (1<<12); -#ifndef __ia64__ EXPORT_SYMBOL(loops_per_jiffy); -#endif - -/* This is the number of bits of precision for the loops_per_jiffy. Each - bit takes on average 1.5/HZ seconds. This (like the original) is a little - better than 1% */ -#define LPS_PREC 8 - -void __init calibrate_delay(void) -{ - unsigned long ticks, loopbit; - int lps_precision = LPS_PREC; - - loops_per_jiffy = (1<<12); - - printk("Calibrating delay loop... "); - while (loops_per_jiffy <<= 1) { - /* wait for "start of" clock tick */ - ticks = jiffies; - while (ticks == jiffies) - /* nothing */; - /* Go .. */ - ticks = jiffies; - __delay(loops_per_jiffy); - ticks = jiffies - ticks; - if (ticks) - break; - } - -/* Do a binary approximation to get loops_per_jiffy set to equal one clock - (up to lps_precision bits) */ - loops_per_jiffy >>= 1; - loopbit = loops_per_jiffy; - while ( lps_precision-- && (loopbit >>= 1) ) { - loops_per_jiffy |= loopbit; - ticks = jiffies; - while (ticks == jiffies); - ticks = jiffies; - __delay(loops_per_jiffy); - if (jiffies != ticks) /* longer than 1 tick */ - loops_per_jiffy &= ~loopbit; - } - -/* Round the value and print it */ - printk("%lu.%02lu BogoMIPS\n", - loops_per_jiffy/(500000/HZ), - (loops_per_jiffy/(5000/HZ)) % 100); -} static int __init debug_kernel(char *str) { @@ -238,20 +208,41 @@ static int __init quiet_kernel(char *str) __setup("debug", debug_kernel); __setup("quiet", quiet_kernel); -/* Unknown boot options get handed to init, unless they look like - failed parameters */ +static int __init loglevel(char *str) +{ + get_option(&str, &console_loglevel); + return 1; +} + +__setup("loglevel=", loglevel); + +/* + * Unknown boot options get handed to init, unless they look like + * failed parameters + */ static int __init unknown_bootoption(char *param, char *val) { /* Change NUL term back to "=", to make "param" the whole string. */ - if (val) - val[-1] = '='; + if (val) { + /* param=val or param="val"? */ + if (val == param+strlen(param)+1) + val[-1] = '='; + else if (val == param+strlen(param)+2) { + val[-2] = '='; + memmove(val-1, val, strlen(val)+1); + val--; + } else + BUG(); + } /* Handle obsolete-style parameters */ if (obsolete_checksetup(param)) return 0; - /* Preemptive maintenance for "why didn't my mispelled command - line work?" */ + /* + * Preemptive maintenance for "why didn't my mispelled command + * line work?" + */ if (strchr(param, '.') && (!val || strchr(param, '.') < val)) { printk(KERN_ERR "Unknown boot option `%s': ignoring\n", param); return 0; @@ -268,6 +259,8 @@ static int __init unknown_bootoption(char *param, char *val) panic_later = "Too many boot env vars at `%s'"; panic_param = param; } + if (!strncmp(param, envp_init[i], val - param)) + break; } envp_init[i] = param; } else { @@ -289,7 +282,8 @@ static int __init init_setup(char *str) unsigned int i; execute_command = str; - /* In case LILO is going to boot us with default command line, + /* + * In case LILO is going to boot us with default command line, * it prepends "auto" before the whole cmdline which makes * the shell think it should execute a script with such name. * So we ignore all arguments entered _before_ init=... [MJ] @@ -300,8 +294,17 @@ static int __init init_setup(char *str) } __setup("init=", init_setup); -extern void setup_arch(char **); -extern void cpu_idle(void); +static int __init rdinit_setup(char *str) +{ + unsigned int i; + + ramdisk_execute_command = str; + /* See "auto" comment in init_setup */ + for (i = 1; i < MAX_INIT_ARGS; i++) + argv_init[i] = NULL; + return 1; +} +__setup("rdinit=", rdinit_setup); #ifndef CONFIG_SMP @@ -320,7 +323,7 @@ static inline void smp_prepare_cpus(unsigned int maxcpus) { } #else #ifdef __GENERIC_PER_CPU -unsigned long __per_cpu_offset[NR_CPUS]; +unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); @@ -328,8 +331,7 @@ static void __init setup_per_cpu_areas(void) { unsigned long size, i; char *ptr; - /* Created by linker magic */ - extern char __per_cpu_start[], __per_cpu_end[]; + unsigned long nr_possible_cpus = num_possible_cpus(); /* Copy section for each CPU (we discard the original) */ size = ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES); @@ -337,12 +339,12 @@ static void __init setup_per_cpu_areas(void) if (size < PERCPU_ENOUGH_ROOM) size = PERCPU_ENOUGH_ROOM; #endif + ptr = alloc_bootmem(size * nr_possible_cpus); - ptr = alloc_bootmem(size * NR_CPUS); - - for (i = 0; i < NR_CPUS; i++, ptr += size) { + for_each_possible_cpu(i) { __per_cpu_offset[i] = ptr - __per_cpu_start; memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start); + ptr += size; } } #endif /* !__GENERIC_PER_CPU */ @@ -351,25 +353,21 @@ static void __init setup_per_cpu_areas(void) static void __init smp_init(void) { unsigned int i; - unsigned j = 1; /* FIXME: This should be done in userspace --RR */ - for (i = 0; i < NR_CPUS; i++) { + for_each_present_cpu(i) { if (num_online_cpus() >= max_cpus) break; - if (cpu_possible(i) && !cpu_online(i)) { + if (!cpu_online(i)) cpu_up(i); - j++; - } } /* Any cleanup work */ - printk("Brought up %u CPUs\n", j); + printk(KERN_INFO "Brought up %ld CPUs\n", (long)num_online_cpus()); smp_cpus_done(max_cpus); #if 0 /* Get other processors into their bootup holding patterns. */ - smp_threads_ready=1; smp_commence(); #endif } @@ -386,40 +384,100 @@ static void __init smp_init(void) */ static void noinline rest_init(void) + __releases(kernel_lock) { kernel_thread(init, NULL, CLONE_FS | CLONE_SIGHAND); + numa_default_policy(); unlock_kernel(); - cpu_idle(); + + /* + * The boot idle thread must execute schedule() + * at least one to get things moving: + */ + preempt_enable_no_resched(); + schedule(); + preempt_disable(); + + /* Call into cpu_idle with preempt disabled */ + cpu_idle(); } +/* Check for early params. */ +static int __init do_early_param(char *param, char *val) +{ + struct obs_kernel_param *p; + + for (p = __setup_start; p < __setup_end; p++) { + if (p->early && strcmp(param, p->str) == 0) { + if (p->setup_func(val) != 0) + printk(KERN_WARNING + "Malformed early option '%s'\n", param); + } + } + /* We accept everything at this stage. */ + return 0; +} + +/* Arch code calls this early on, or if not, just before other parsing. */ +void __init parse_early_param(void) +{ + static __initdata int done = 0; + static __initdata char tmp_cmdline[COMMAND_LINE_SIZE]; + + if (done) + return; + + /* All fall through to do_early_param. */ + strlcpy(tmp_cmdline, saved_command_line, COMMAND_LINE_SIZE); + parse_args("early options", tmp_cmdline, NULL, 0, do_early_param); + done = 1; +} + /* * Activate the first processor. */ +static void __init boot_cpu_init(void) +{ + int cpu = smp_processor_id(); + /* Mark the boot cpu "present", "online" etc for SMP and UP case */ + cpu_set(cpu, cpu_online_map); + cpu_set(cpu, cpu_present_map); + cpu_set(cpu, cpu_possible_map); +} + asmlinkage void __init start_kernel(void) { char * command_line; - extern char saved_command_line[]; extern struct kernel_param __start___param[], __stop___param[]; /* * Interrupts are still disabled. Do necessary setups, then * enable them */ lock_kernel(); + boot_cpu_init(); page_address_init(); + printk(KERN_NOTICE); printk(linux_banner); setup_arch(&command_line); setup_per_cpu_areas(); + smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ /* - * Mark the boot cpu "online" so that it can call console drivers in - * printk() and can access its per-cpu storage. + * 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. */ - smp_prepare_boot_cpu(); - + sched_init(); + /* + * Disable preemption - early bootup scheduling is extremely + * fragile until we cpu_idle() for the first time. + */ + preempt_disable(); build_all_zonelists(); page_alloc_init(); - printk("Kernel command line: %s\n", saved_command_line); + printk(KERN_NOTICE "Kernel command line: %s\n", saved_command_line); + parse_early_param(); parse_args("Booting kernel", command_line, __start___param, __stop___param - __start___param, &unknown_bootoption); @@ -428,7 +486,8 @@ asmlinkage void __init start_kernel(void) rcu_init(); init_IRQ(); pidhash_init(); - sched_init(); + init_timers(); + hrtimers_init(); softirq_init(); time_init(); @@ -450,14 +509,19 @@ asmlinkage void __init start_kernel(void) initrd_start = 0; } #endif + vfs_caches_init_early(); + cpuset_init_early(); mem_init(); kmem_cache_init(); + setup_per_cpu_pageset(); + numa_policy_init(); if (late_time_init) late_time_init(); calibrate_delay(); pidmap_init(); pgtable_cache_init(); - pte_chain_init(); + prio_tree_init(); + anon_vma_init(); #ifdef CONFIG_X86 if (efi_enabled) efi_enter_virtual_mode(); @@ -466,7 +530,8 @@ asmlinkage void __init start_kernel(void) proc_caches_init(); buffer_init(); unnamed_dev_init(); - security_scaffolding_startup(); + key_init(); + security_init(); vfs_caches_init(num_physpages); radix_tree_init(); signals_init(); @@ -475,15 +540,11 @@ asmlinkage void __init start_kernel(void) #ifdef CONFIG_PROC_FS proc_root_init(); #endif + cpuset_init(); + check_bugs(); - printk("POSIX conformance testing by UNIFIX\n"); - /* - * We count on the initial thread going ok - * Like idlers init is an unlocked kernel thread, which will - * make syscalls (and thus be locked). - */ - init_idle(current, smp_processor_id()); + acpi_early_init(); /* before LAPIC and SMP init */ /* Do the rest non-__init'ed, we're now alive */ rest_init(); @@ -498,27 +559,58 @@ static int __init initcall_debug_setup(char *str) } __setup("initcall_debug", initcall_debug_setup); +#ifdef CONFIG_BOOT_DELAY + +unsigned int boot_delay = 0; /* msecs delay after each printk during bootup */ +extern long preset_lpj; +unsigned long long printk_delay_msec = 0; /* per msec, based on boot_delay */ + +static int __init boot_delay_setup(char *str) +{ + unsigned long lpj = preset_lpj ? preset_lpj : 1000000; /* some guess */ + unsigned long long loops_per_msec = lpj / 1000 * CONFIG_HZ; + + get_option(&str, &boot_delay); + if (boot_delay > 10 * 1000) + boot_delay = 0; + + printk_delay_msec = loops_per_msec; + printk("boot_delay: %u, preset_lpj: %ld, lpj: %lu, CONFIG_HZ: %d, printk_delay_msec: %llu\n", + boot_delay, preset_lpj, lpj, CONFIG_HZ, printk_delay_msec); + + return 1; +} +__setup("boot_delay=", boot_delay_setup); + +#endif + struct task_struct *child_reaper = &init_task; -extern initcall_t __initcall_start, __initcall_end; +extern initcall_t __initcall_start[], __initcall_end[]; static void __init do_initcalls(void) { initcall_t *call; int count = preempt_count(); - for (call = &__initcall_start; call < &__initcall_end; call++) { - char *msg; + for (call = __initcall_start; call < __initcall_end; call++) { + char *msg = NULL; + char msgbuf[40]; + int result; if (initcall_debug) { - printk(KERN_DEBUG "Calling initcall 0x%p", *call); - print_symbol(": %s()", (unsigned long) *call); + printk("Calling initcall 0x%p", *call); + print_fn_descriptor_symbol(": %s()", + (unsigned long) *call); printk("\n"); } - (*call)(); + result = (*call)(); - msg = NULL; + if (result && result != -ENODEV && initcall_debug) { + sprintf(msgbuf, "error code %d", result); + msg = msgbuf; + } if (preempt_count() != count) { msg = "preemption imbalance"; preempt_count() = count; @@ -528,8 +620,10 @@ static void __init do_initcalls(void) local_irq_enable(); } if (msg) { - printk("error in initcall at 0x%p: " - "returned with %s\n", *call, msg); + printk(KERN_WARNING "initcall at 0x%p", *call); + print_fn_descriptor_symbol(": %s()", + (unsigned long) *call); + printk(": returned with %s\n", msg); } } @@ -546,19 +640,27 @@ static void __init do_initcalls(void) */ static void __init do_basic_setup(void) { + /* drivers will send hotplug events */ + init_workqueues(); + usermodehelper_init(); driver_init(); #ifdef CONFIG_SYSCTL sysctl_init(); #endif - /* Networking initialization needs a process context */ - sock_init(); - - init_workqueues(); do_initcalls(); } +static int __initdata nosoftlockup; + +static int __init nosoftlockup_setup(char *str) +{ + nosoftlockup = 1; + return 1; +} +__setup("nosoftlockup", nosoftlockup_setup); + static void do_pre_smp_initcalls(void) { extern int spawn_ksoftirqd(void); @@ -567,8 +669,9 @@ static void do_pre_smp_initcalls(void) migration_init(); #endif - node_nr_running_init(); spawn_ksoftirqd(); + if (!nosoftlockup) + spawn_softlockup_task(); } static void run_init_process(char *init_filename) @@ -580,6 +683,10 @@ static void run_init_process(char *init_filename) static int init(void * unused) { lock_kernel(); + /* + * init can run on any cpu. + */ + set_cpus_allowed(current, CPU_MASK_ALL); /* * Tell the world that we're going to be the grim * reaper of innocent orphaned children. @@ -590,12 +697,14 @@ static int init(void * unused) */ child_reaper = current; - /* Sets up cpus_possible() */ smp_prepare_cpus(max_cpus); do_pre_smp_initcalls(); smp_init(); + sched_init_smp(); + + cpuset_init_smp(); /* * Do this before initcalls, because some drivers want to access @@ -609,10 +718,14 @@ static int init(void * unused) * check if there is an early userspace init. If yes, let it do all * the work */ - if (sys_access("/init", 0) == 0) - execute_command = "/init"; - else + + if (!ramdisk_execute_command) + ramdisk_execute_command = "/init"; + + if (sys_access((const char __user *) ramdisk_execute_command, 0) != 0) { + ramdisk_execute_command = NULL; prepare_namespace(); + } /* * Ok, we have completed the initial bootup, and @@ -621,24 +734,33 @@ static int init(void * unused) */ free_initmem(); unlock_kernel(); + mark_rodata_ro(); system_state = SYSTEM_RUNNING; + numa_default_policy(); - if (sys_open("/dev/console", O_RDWR, 0) < 0) - printk("Warning: unable to open an initial console.\n"); + if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) + printk(KERN_WARNING "Warning: unable to open an initial console.\n"); (void) sys_dup(0); (void) sys_dup(0); - + + if (ramdisk_execute_command) { + run_init_process(ramdisk_execute_command); + printk(KERN_WARNING "Failed to execute %s\n", + ramdisk_execute_command); + } + /* * We try each of these until one succeeds. * * The Bourne shell can be used instead of init if we are * trying to recover a really broken machine. */ - - if (execute_command) + if (execute_command) { run_init_process(execute_command); - + printk(KERN_WARNING "Failed to execute %s. Attempting " + "defaults...\n", execute_command); + } run_init_process("/sbin/init"); run_init_process("/etc/init"); run_init_process("/bin/init");