X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=init%2Fmain.c;h=16ca1ee071c4f11a7e784ae9ed1a620c2231e87e;hb=3f5ec13696fd4a33bde42f385406cbb1d3cc96fd;hp=a20a5138211f8146a3854e750a55c6f14dd487d4;hpb=b04c3afb2b6e2f902b41bb62b73684d92d7e6c34;p=safe%2Fjmp%2Flinux-2.6 diff --git a/init/main.c b/init/main.c index a20a513..16ca1ee 100644 --- a/init/main.c +++ b/init/main.c @@ -22,15 +22,16 @@ #include #include #include -#include #include #include #include #include #include +#include #include #include #include +#include #include #include #include @@ -39,7 +40,10 @@ #include #include #include +#include #include +#include +#include #include #include #include @@ -48,10 +52,18 @@ #include #include #include +#include #include +#include #include #include #include +#include +#include +#include +#include +#include +#include #include #include @@ -66,34 +78,21 @@ /* * 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__ < 3) || (__GNUC__ == 3 && __GNUC_MINOR__ < 2) -#error Sorry, your GCC is too old. It builds incorrect kernels. -#endif #if __GNUC__ == 4 && __GNUC_MINOR__ == 1 && __GNUC_PATCHLEVEL__ == 0 #warning gcc-4.1.0 is known to miscompile the kernel. A different compiler version is recommended. #endif -static int init(void *); +static int kernel_init(void *); extern void init_IRQ(void); extern void fork_init(unsigned long); extern void mca_init(void); extern void sbus_init(void); -extern void sysctl_init(void); -extern void signals_init(void); -extern void pidhash_init(void); -extern void pidmap_init(void); extern void prio_tree_init(void); extern void radix_tree_init(void); extern void free_initmem(void); -extern void prepare_namespace(void); #ifdef CONFIG_ACPI extern void acpi_early_init(void); #else @@ -131,20 +130,9 @@ static char *static_command_line; static char *execute_command; static char *ramdisk_execute_command; +#ifdef CONFIG_SMP /* Setup configured maximum number of CPUs to activate */ -static unsigned int max_cpus = NR_CPUS; - -/* - * If set, this is an indication to the drivers that reset the underlying - * device before going ahead with the initialization otherwise driver might - * rely on the BIOS and skip the reset operation. - * - * This is useful if kernel is booting in an unreliable environment. - * For ex. kdump situaiton where previous kernel has crashed, BIOS has been - * skipped and devices will be in unknown state. - */ -unsigned int reset_devices; -EXPORT_SYMBOL(reset_devices); +unsigned int __initdata setup_max_cpus = NR_CPUS; /* * Setup routine for controlling SMP activation @@ -156,21 +144,44 @@ EXPORT_SYMBOL(reset_devices); * greater than 0, limits the maximum number of CPUs activated in * SMP mode to . */ +#ifndef CONFIG_X86_IO_APIC +static inline void disable_ioapic_setup(void) {}; +#endif + static int __init nosmp(char *str) { - max_cpus = 0; - return 1; + setup_max_cpus = 0; + disable_ioapic_setup(); + return 0; } -__setup("nosmp", nosmp); +early_param("nosmp", nosmp); static int __init maxcpus(char *str) { - get_option(&str, &max_cpus); - return 1; + get_option(&str, &setup_max_cpus); + if (setup_max_cpus == 0) + disable_ioapic_setup(); + + return 0; } -__setup("maxcpus=", maxcpus); +early_param("maxcpus", maxcpus); +#else +#define setup_max_cpus NR_CPUS +#endif + +/* + * If set, this is an indication to the drivers that reset the underlying + * device before going ahead with the initialization otherwise driver might + * rely on the BIOS and skip the reset operation. + * + * This is useful if kernel is booting in an unreliable environment. + * For ex. kdump situaiton where previous kernel has crashed, BIOS has been + * skipped and devices will be in unknown state. + */ +unsigned int reset_devices; +EXPORT_SYMBOL(reset_devices); static int __init set_reset_devices(char *str) { @@ -225,30 +236,26 @@ EXPORT_SYMBOL(loops_per_jiffy); static int __init debug_kernel(char *str) { - if (*str) - return 0; console_loglevel = 10; - return 1; + return 0; } static int __init quiet_kernel(char *str) { - if (*str) - return 0; console_loglevel = 4; - return 1; + return 0; } -__setup("debug", debug_kernel); -__setup("quiet", quiet_kernel); +early_param("debug", debug_kernel); +early_param("quiet", quiet_kernel); static int __init loglevel(char *str) { get_option(&str, &console_loglevel); - return 1; + return 0; } -__setup("loglevel=", loglevel); +early_param("loglevel", loglevel); /* * Unknown boot options get handed to init, unless they look like @@ -274,7 +281,7 @@ static int __init unknown_bootoption(char *param, char *val) return 0; /* - * Preemptive maintenance for "why didn't my mispelled command + * Preemptive maintenance for "why didn't my misspelled command * line work?" */ if (strchr(param, '.') && (!val || strchr(param, '.') < val)) { @@ -311,6 +318,10 @@ static int __init unknown_bootoption(char *param, char *val) return 0; } +#ifdef CONFIG_DEBUG_PAGEALLOC +int __read_mostly debug_pagealloc_enabled = 0; +#endif + static int __init init_setup(char *str) { unsigned int i; @@ -352,11 +363,32 @@ static void __init smp_init(void) #endif static inline void setup_per_cpu_areas(void) { } +static inline void setup_nr_cpu_ids(void) { } static inline void smp_prepare_cpus(unsigned int maxcpus) { } #else -#ifdef __GENERIC_PER_CPU +#if NR_CPUS > BITS_PER_LONG +cpumask_t cpu_mask_all __read_mostly = CPU_MASK_ALL; +EXPORT_SYMBOL(cpu_mask_all); +#endif + +/* Setup number of possible processor ids */ +int nr_cpu_ids __read_mostly = NR_CPUS; +EXPORT_SYMBOL(nr_cpu_ids); + +/* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */ +static void __init setup_nr_cpu_ids(void) +{ + int cpu, highest_cpu = 0; + + for_each_possible_cpu(cpu) + highest_cpu = cpu; + + nr_cpu_ids = highest_cpu + 1; +} + +#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); @@ -368,12 +400,8 @@ static void __init setup_per_cpu_areas(void) 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); -#ifdef CONFIG_MODULES - if (size < PERCPU_ENOUGH_ROOM) - size = PERCPU_ENOUGH_ROOM; -#endif - ptr = alloc_bootmem(size * nr_possible_cpus); + size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE); + ptr = alloc_bootmem_pages(size * nr_possible_cpus); for_each_possible_cpu(i) { __per_cpu_offset[i] = ptr - __per_cpu_start; @@ -381,24 +409,31 @@ static void __init setup_per_cpu_areas(void) ptr += size; } } -#endif /* !__GENERIC_PER_CPU */ +#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ /* Called by boot processor to activate the rest. */ static void __init smp_init(void) { - unsigned int i; + unsigned int cpu; + + /* + * Set up the current CPU as possible to migrate to. + * The other ones will be done by cpu_up/cpu_down() + */ + cpu = smp_processor_id(); + cpu_set(cpu, cpu_active_map); /* FIXME: This should be done in userspace --RR */ - for_each_present_cpu(i) { - if (num_online_cpus() >= max_cpus) + for_each_present_cpu(cpu) { + if (num_online_cpus() >= setup_max_cpus) break; - if (!cpu_online(i)) - cpu_up(i); + if (!cpu_online(cpu)) + cpu_up(cpu); } /* Any cleanup work */ printk(KERN_INFO "Brought up %ld CPUs\n", (long)num_online_cpus()); - smp_cpus_done(max_cpus); + smp_cpus_done(setup_max_cpus); } #endif @@ -426,24 +461,29 @@ static void __init setup_command_line(char *command_line) * gcc-3.4 accidentally inlines this function, so use noinline. */ -static void noinline rest_init(void) +static void noinline __init_refok rest_init(void) __releases(kernel_lock) { - kernel_thread(init, NULL, CLONE_FS | CLONE_SIGHAND); + int pid; + + kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND); numa_default_policy(); + pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES); + kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns); unlock_kernel(); /* * The boot idle thread must execute schedule() - * at least one to get things moving: + * at least once to get things moving: */ + init_idle_bootup_task(current); 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) @@ -451,7 +491,10 @@ 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->early && strcmp(param, p->str) == 0) || + (strcmp(param, "console") == 0 && + strcmp(p->str, "earlycon") == 0) + ) { if (p->setup_func(val) != 0) printk(KERN_WARNING "Malformed early option '%s'\n", param); @@ -489,7 +532,11 @@ static void __init boot_cpu_init(void) cpu_set(cpu, cpu_possible_map); } -void __init __attribute__((weak)) smp_setup_processor_id(void) +void __init __weak smp_setup_processor_id(void) +{ +} + +void __init __weak thread_info_cache_init(void) { } @@ -506,6 +553,8 @@ asmlinkage void __init start_kernel(void) */ unwind_init(); lockdep_init(); + debug_objects_early_init(); + cgroup_init_early(); local_irq_disable(); early_boot_irqs_off(); @@ -516,14 +565,17 @@ asmlinkage void __init start_kernel(void) * enable them */ lock_kernel(); + tick_init(); boot_cpu_init(); page_address_init(); printk(KERN_NOTICE); printk(linux_banner); setup_arch(&command_line); + mm_init_owner(&init_mm, &init_task); setup_command_line(command_line); unwind_setup(); setup_per_cpu_areas(); + setup_nr_cpu_ids(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ /* @@ -559,6 +611,7 @@ asmlinkage void __init start_kernel(void) softirq_init(); timekeeping_init(); time_init(); + sched_clock_init(); profile_init(); if (!irqs_disabled()) printk("start_kernel(): bug: interrupts were enabled early\n"); @@ -585,16 +638,24 @@ asmlinkage void __init start_kernel(void) #ifdef CONFIG_BLK_DEV_INITRD if (initrd_start && !initrd_below_start_ok && - initrd_start < min_low_pfn << PAGE_SHIFT) { + page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) { printk(KERN_CRIT "initrd overwritten (0x%08lx < 0x%08lx) - " - "disabling it.\n",initrd_start,min_low_pfn << PAGE_SHIFT); + "disabling it.\n", + page_to_pfn(virt_to_page((void *)initrd_start)), + min_low_pfn); initrd_start = 0; } #endif + vmalloc_init(); vfs_caches_init_early(); cpuset_init_early(); + page_cgroup_init(); mem_init(); + enable_debug_pagealloc(); + cpu_hotplug_init(); kmem_cache_init(); + debug_objects_mem_init(); + idr_init_cache(); setup_per_cpu_pageset(); numa_policy_init(); if (late_time_init) @@ -608,10 +669,10 @@ asmlinkage void __init start_kernel(void) if (efi_enabled) efi_enter_virtual_mode(); #endif + thread_info_cache_init(); fork_init(num_physpages); proc_caches_init(); buffer_init(); - unnamed_dev_init(); key_init(); security_init(); vfs_caches_init(num_physpages); @@ -622,6 +683,7 @@ asmlinkage void __init start_kernel(void) #ifdef CONFIG_PROC_FS proc_root_init(); #endif + cgroup_init(); cpuset_init(); taskstats_init_early(); delayacct_init(); @@ -630,59 +692,70 @@ asmlinkage void __init start_kernel(void) acpi_early_init(); /* before LAPIC and SMP init */ + ftrace_init(); + /* Do the rest non-__init'ed, we're now alive */ rest_init(); } -static int __initdata initcall_debug; +static int initcall_debug; +core_param(initcall_debug, initcall_debug, bool, 0644); -static int __init initcall_debug_setup(char *str) +int do_one_initcall(initcall_t fn) { - initcall_debug = 1; - return 1; + int count = preempt_count(); + ktime_t delta; + char msgbuf[64]; + struct boot_trace it; + + if (initcall_debug) { + it.caller = task_pid_nr(current); + printk("calling %pF @ %i\n", fn, it.caller); + it.calltime = ktime_get(); + enable_boot_trace(); + } + + it.result = fn(); + + if (initcall_debug) { + it.rettime = ktime_get(); + delta = ktime_sub(it.rettime, it.calltime); + it.duration = (unsigned long long) delta.tv64 >> 10; + printk("initcall %pF returned %d after %Ld usecs\n", fn, + it.result, it.duration); + trace_boot(&it, fn); + disable_boot_trace(); + } + + msgbuf[0] = 0; + + if (it.result && it.result != -ENODEV && initcall_debug) + sprintf(msgbuf, "error code %d ", it.result); + + if (preempt_count() != count) { + strlcat(msgbuf, "preemption imbalance ", sizeof(msgbuf)); + preempt_count() = count; + } + if (irqs_disabled()) { + strlcat(msgbuf, "disabled interrupts ", sizeof(msgbuf)); + local_irq_enable(); + } + if (msgbuf[0]) { + printk("initcall %pF returned with %s\n", fn, msgbuf); + } + + return it.result; } -__setup("initcall_debug", initcall_debug_setup); -extern initcall_t __initcall_start[], __initcall_end[]; + +extern initcall_t __initcall_start[], __initcall_end[], __early_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 = NULL; - char msgbuf[40]; - int result; - - if (initcall_debug) { - printk("Calling initcall 0x%p", *call); - print_fn_descriptor_symbol(": %s()", - (unsigned long) *call); - printk("\n"); - } - - result = (*call)(); - - if (result && result != -ENODEV && initcall_debug) { - sprintf(msgbuf, "error code %d", result); - msg = msgbuf; - } - if (preempt_count() != count) { - msg = "preemption imbalance"; - preempt_count() = count; - } - if (irqs_disabled()) { - msg = "disabled interrupts"; - local_irq_enable(); - } - if (msg) { - printk(KERN_WARNING "initcall at 0x%p", *call); - print_fn_descriptor_symbol(": %s()", - (unsigned long) *call); - printk(": returned with %s\n", msg); - } - } + for (call = __early_initcall_end; call < __initcall_end; call++) + do_one_initcall(*call); /* Make sure there is no pending stuff from the initcall sequence */ flush_scheduled_work(); @@ -697,31 +770,20 @@ static void __init do_initcalls(void) */ static void __init do_basic_setup(void) { - /* drivers will send hotplug events */ + rcu_init_sched(); /* needed by module_init stage. */ init_workqueues(); usermodehelper_init(); driver_init(); - -#ifdef CONFIG_SYSCTL - sysctl_init(); -#endif -#ifdef CONFIG_PROC_FS init_irq_proc(); -#endif - do_initcalls(); } static void __init do_pre_smp_initcalls(void) { - extern int spawn_ksoftirqd(void); -#ifdef CONFIG_SMP - extern int migration_init(void); + initcall_t *call; - migration_init(); -#endif - spawn_ksoftirqd(); - spawn_softlockup_task(); + for (call = __initcall_start; call < __early_initcall_end; call++) + do_one_initcall(*call); } static void run_init_process(char *init_filename) @@ -730,13 +792,57 @@ static void run_init_process(char *init_filename) kernel_execve(init_filename, argv_init, envp_init); } -static int init(void * unused) +/* This is a non __init function. Force it to be noinline otherwise gcc + * makes it inline to init() and it becomes part of init.text section + */ +static int noinline init_post(void) +{ + free_initmem(); + unlock_kernel(); + mark_rodata_ro(); + system_state = SYSTEM_RUNNING; + numa_default_policy(); + + 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); + + current->signal->flags |= SIGNAL_UNKILLABLE; + + 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) { + 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"); + run_init_process("/bin/sh"); + + panic("No init found. Try passing init= option to kernel."); +} + +static int __init kernel_init(void * unused) { lock_kernel(); /* * init can run on any cpu. */ - set_cpus_allowed(current, CPU_MASK_ALL); + set_cpus_allowed_ptr(current, CPU_MASK_ALL_PTR); /* * Tell the world that we're going to be the grim * reaper of innocent orphaned children. @@ -749,9 +855,10 @@ static int init(void * unused) cad_pid = task_pid(current); - smp_prepare_cpus(max_cpus); + smp_prepare_cpus(setup_max_cpus); do_pre_smp_initcalls(); + start_boot_trace(); smp_init(); sched_init_smp(); @@ -778,39 +885,7 @@ static int init(void * unused) * we're essentially up and running. Get rid of the * initmem segments and start the user-mode stuff.. */ - free_initmem(); - unlock_kernel(); - mark_rodata_ro(); - system_state = SYSTEM_RUNNING; - numa_default_policy(); - - 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) { - 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"); - run_init_process("/bin/sh"); - panic("No init found. Try passing init= option to kernel."); + init_post(); + return 0; }