diff options
Diffstat (limited to 'init/main.c')
| -rw-r--r-- | init/main.c | 825 |
1 files changed, 500 insertions, 325 deletions
diff --git a/init/main.c b/init/main.c index 99ce94930b0..e8ae1fef090 100644 --- a/init/main.c +++ b/init/main.c @@ -9,29 +9,30 @@ * Simplified starting of init: Michael A. Griffith <grif@acm.org> */ +#define DEBUG /* Enable initcall_debug */ + #include <linux/types.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/kernel.h> #include <linux/syscalls.h> +#include <linux/stackprotector.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/delay.h> -#include <linux/utsname.h> #include <linux/ioport.h> #include <linux/init.h> -#include <linux/smp_lock.h> #include <linux/initrd.h> -#include <linux/hdreg.h> #include <linux/bootmem.h> +#include <linux/acpi.h> #include <linux/tty.h> -#include <linux/gfp.h> #include <linux/percpu.h> #include <linux/kmod.h> +#include <linux/vmalloc.h> #include <linux/kernel_stat.h> #include <linux/start_kernel.h> #include <linux/security.h> -#include <linux/workqueue.h> +#include <linux/smp.h> #include <linux/profile.h> #include <linux/rcupdate.h> #include <linux/moduleparam.h> @@ -49,15 +50,34 @@ #include <linux/rmap.h> #include <linux/mempolicy.h> #include <linux/key.h> -#include <linux/unwind.h> #include <linux/buffer_head.h> +#include <linux/page_cgroup.h> #include <linux/debug_locks.h> +#include <linux/debugobjects.h> #include <linux/lockdep.h> +#include <linux/kmemleak.h> #include <linux/pid_namespace.h> #include <linux/device.h> #include <linux/kthread.h> #include <linux/sched.h> #include <linux/signal.h> +#include <linux/idr.h> +#include <linux/kgdb.h> +#include <linux/ftrace.h> +#include <linux/async.h> +#include <linux/kmemcheck.h> +#include <linux/sfi.h> +#include <linux/shmem_fs.h> +#include <linux/slab.h> +#include <linux/perf_event.h> +#include <linux/file.h> +#include <linux/ptrace.h> +#include <linux/blkdev.h> +#include <linux/elevator.h> +#include <linux/sched_clock.h> +#include <linux/context_tracking.h> +#include <linux/random.h> +#include <linux/list.h> #include <asm/io.h> #include <asm/bugs.h> @@ -69,40 +89,25 @@ #include <asm/smp.h> #endif -/* - * This is one of the first .c files built. Error out early if we have compiler - * trouble. - */ - -#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 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 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); -#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 +/* + * Debug helper: via this flag we know that we are in 'early bootup code' + * where only the boot processor is running with IRQ disabled. This means + * two things - IRQ must not be enabled before the flag is cleared and some + * operations which are not allowed with IRQ disabled are allowed while the + * flag is set. + */ +bool early_boot_irqs_disabled __read_mostly; -enum system_states system_state; +enum system_states system_state __read_mostly; EXPORT_SYMBOL(system_state); /* @@ -113,8 +118,7 @@ EXPORT_SYMBOL(system_state); 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); +void (*__initdata late_time_init)(void); /* Untouched command line saved by arch-specific code. */ char __initdata boot_command_line[COMMAND_LINE_SIZE]; @@ -122,50 +126,18 @@ char __initdata boot_command_line[COMMAND_LINE_SIZE]; char *saved_command_line; /* Command line for parameter parsing */ static char *static_command_line; +/* Command line for per-initcall parameter parsing */ +static char *initcall_command_line; static char *execute_command; static char *ramdisk_execute_command; -#ifdef CONFIG_SMP -/* Setup configured maximum number of CPUs to activate */ -unsigned int __initdata setup_max_cpus = NR_CPUS; - /* - * Setup routine for controlling SMP activation - * - * Command-line option of "nosmp" or "maxcpus=0" will disable SMP - * activation entirely (the MPS table probe still happens, though). - * - * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer - * greater than 0, limits the maximum number of CPUs activated in - * SMP mode to <NUM>. + * Used to generate warnings if static_key manipulation functions are used + * before jump_label_init is called. */ -#ifndef CONFIG_X86_IO_APIC -static inline void disable_ioapic_setup(void) {}; -#endif - -static int __init nosmp(char *str) -{ - setup_max_cpus = 0; - disable_ioapic_setup(); - return 0; -} - -early_param("nosmp", nosmp); - -static int __init maxcpus(char *str) -{ - get_option(&str, &setup_max_cpus); - if (setup_max_cpus == 0) - disable_ioapic_setup(); - - return 0; -} - -early_param("maxcpus", maxcpus); -#else -#define setup_max_cpus NR_CPUS -#endif +bool static_key_initialized __read_mostly = false; +EXPORT_SYMBOL_GPL(static_key_initialized); /* * If set, this is an indication to the drivers that reset the underlying @@ -187,21 +159,21 @@ static int __init set_reset_devices(char *str) __setup("reset_devices", set_reset_devices); -static char * argv_init[MAX_INIT_ARGS+2] = { "init", NULL, }; -char * envp_init[MAX_INIT_ENVS+2] = { "HOME=/", "TERM=linux", NULL, }; +static const char * argv_init[MAX_INIT_ARGS+2] = { "init", NULL, }; +const char * envp_init[MAX_INIT_ENVS+2] = { "HOME=/", "TERM=linux", NULL, }; static const char *panic_later, *panic_param; -extern struct obs_kernel_param __setup_start[], __setup_end[]; +extern const struct obs_kernel_param __setup_start[], __setup_end[]; static int __init obsolete_checksetup(char *line) { - struct obs_kernel_param *p; + const struct obs_kernel_param *p; int had_early_param = 0; p = __setup_start; do { int n = strlen(p->str); - if (!strncmp(line, p->str, n)) { + if (parameqn(line, p->str, n)) { if (p->early) { /* Already done in parse_early_param? * (Needs exact match on param part). @@ -210,8 +182,8 @@ static int __init obsolete_checksetup(char *line) if (line[n] == '\0' || line[n] == '=') had_early_param = 1; } else if (!p->setup_func) { - printk(KERN_WARNING "Parameter %s is obsolete," - " ignored\n", p->str); + pr_warn("Parameter %s is obsolete, ignored\n", + p->str); return 1; } else if (p->setup_func(line + n)) return 1; @@ -232,13 +204,13 @@ EXPORT_SYMBOL(loops_per_jiffy); static int __init debug_kernel(char *str) { - console_loglevel = 10; + console_loglevel = CONSOLE_LOGLEVEL_DEBUG; return 0; } static int __init quiet_kernel(char *str) { - console_loglevel = 4; + console_loglevel = CONSOLE_LOGLEVEL_QUIET; return 0; } @@ -247,19 +219,26 @@ early_param("quiet", quiet_kernel); static int __init loglevel(char *str) { - get_option(&str, &console_loglevel); - return 0; + int newlevel; + + /* + * Only update loglevel value when a correct setting was passed, + * to prevent blind crashes (when loglevel being set to 0) that + * are quite hard to debug + */ + if (get_option(&str, &newlevel)) { + console_loglevel = newlevel; + return 0; + } + + return -EINVAL; } early_param("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. */ +static int __init repair_env_string(char *param, char *val, const char *unused) { - /* Change NUL term back to "=", to make "param" the whole string. */ if (val) { /* param=val or param="val"? */ if (val == param+strlen(param)+1) @@ -271,19 +250,45 @@ static int __init unknown_bootoption(char *param, char *val) } else BUG(); } + return 0; +} + +/* Anything after -- gets handed straight to init. */ +static int __init set_init_arg(char *param, char *val, const char *unused) +{ + unsigned int i; + + if (panic_later) + return 0; + + repair_env_string(param, val, unused); + + for (i = 0; argv_init[i]; i++) { + if (i == MAX_INIT_ARGS) { + panic_later = "init"; + panic_param = param; + return 0; + } + } + argv_init[i] = param; + return 0; +} + +/* + * Unknown boot options get handed to init, unless they look like + * unused parameters (modprobe will find them in /proc/cmdline). + */ +static int __init unknown_bootoption(char *param, char *val, const char *unused) +{ + repair_env_string(param, val, unused); /* Handle obsolete-style parameters */ if (obsolete_checksetup(param)) return 0; - /* - * Preemptive maintenance for "why didn't my misspelled command - * line work?" - */ - if (strchr(param, '.') && (!val || strchr(param, '.') < val)) { - printk(KERN_ERR "Unknown boot option `%s': ignoring\n", param); + /* Unused module parameter. */ + if (strchr(param, '.') && (!val || strchr(param, '.') < val)) return 0; - } if (panic_later) return 0; @@ -293,7 +298,7 @@ static int __init unknown_bootoption(char *param, char *val) unsigned int i; for (i = 0; envp_init[i]; i++) { if (i == MAX_INIT_ENVS) { - panic_later = "Too many boot env vars at `%s'"; + panic_later = "env"; panic_param = param; } if (!strncmp(param, envp_init[i], val - param)) @@ -305,7 +310,7 @@ static int __init unknown_bootoption(char *param, char *val) unsigned int i; for (i = 0; argv_init[i]; i++) { if (i == MAX_INIT_ARGS) { - panic_later = "Too many boot init vars at `%s'"; + panic_later = "init"; panic_param = param; } } @@ -314,10 +319,6 @@ 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; @@ -348,7 +349,7 @@ static int __init rdinit_setup(char *str) __setup("rdinit=", rdinit_setup); #ifndef CONFIG_SMP - +static const unsigned int setup_max_cpus = NR_CPUS; #ifdef CONFIG_X86_LOCAL_APIC static void __init smp_init(void) { @@ -358,52 +359,8 @@ static void __init smp_init(void) #define smp_init() do { } while (0) #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 - -#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA -unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; - -EXPORT_SYMBOL(__per_cpu_offset); - -static void __init setup_per_cpu_areas(void) -{ - unsigned long size, i; - char *ptr; - unsigned long nr_possible_cpus = num_possible_cpus(); - - /* Copy section for each CPU (we discard the original) */ - 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; - memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start); - ptr += size; - } -} -#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ - -/* Called by boot processor to activate the rest. */ -static void __init smp_init(void) -{ - unsigned int cpu; - - /* FIXME: This should be done in userspace --RR */ - for_each_present_cpu(cpu) { - if (num_online_cpus() >= setup_max_cpus) - break; - 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(setup_max_cpus); -} - #endif /* @@ -414,8 +371,11 @@ static void __init smp_init(void) */ static void __init setup_command_line(char *command_line) { - saved_command_line = alloc_bootmem(strlen (boot_command_line)+1); - static_command_line = alloc_bootmem(strlen (command_line)+1); + saved_command_line = + memblock_virt_alloc(strlen(boot_command_line) + 1, 0); + initcall_command_line = + memblock_virt_alloc(strlen(boot_command_line) + 1, 0); + static_command_line = memblock_virt_alloc(strlen(command_line) + 1, 0); strcpy (saved_command_line, boot_command_line); strcpy (static_command_line, command_line); } @@ -429,49 +389,59 @@ static void __init setup_command_line(char *command_line) * gcc-3.4 accidentally inlines this function, so use noinline. */ -static void noinline __init_refok rest_init(void) - __releases(kernel_lock) +static __initdata DECLARE_COMPLETION(kthreadd_done); + +static noinline void __init_refok rest_init(void) { int pid; - kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND); + rcu_scheduler_starting(); + /* + * We need to spawn init first so that it obtains pid 1, however + * the init task will end up wanting to create kthreads, which, if + * we schedule it before we create kthreadd, will OOPS. + */ + kernel_thread(kernel_init, NULL, CLONE_FS); numa_default_policy(); pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES); - kthreadd_task = find_task_by_pid(pid); - unlock_kernel(); + rcu_read_lock(); + kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns); + rcu_read_unlock(); + complete(&kthreadd_done); /* * The boot idle thread must execute schedule() * at least once to get things moving: */ init_idle_bootup_task(current); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); - + schedule_preempt_disabled(); /* Call into cpu_idle with preempt disabled */ - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } /* Check for early params. */ -static int __init do_early_param(char *param, char *val) +static int __init do_early_param(char *param, char *val, const char *unused) { - struct obs_kernel_param *p; + const struct obs_kernel_param *p; for (p = __setup_start; p < __setup_end; p++) { - if ((p->early && strcmp(param, p->str) == 0) || + if ((p->early && parameq(param, p->str)) || (strcmp(param, "console") == 0 && strcmp(p->str, "earlycon") == 0) ) { if (p->setup_func(val) != 0) - printk(KERN_WARNING - "Malformed early option '%s'\n", param); + pr_warn("Malformed early option '%s'\n", param); } } /* We accept everything at this stage. */ return 0; } +void __init parse_early_options(char *cmdline) +{ + parse_args("early options", cmdline, NULL, 0, 0, 0, do_early_param); +} + /* Arch code calls this early on, or if not, just before other parsing. */ void __init parse_early_param(void) { @@ -483,7 +453,7 @@ void __init parse_early_param(void) /* All fall through to do_early_param. */ strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE); - parse_args("early options", tmp_cmdline, NULL, 0, do_early_param); + parse_early_options(tmp_cmdline); done = 1; } @@ -495,50 +465,102 @@ 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); + set_cpu_online(cpu, true); + set_cpu_active(cpu, true); + set_cpu_present(cpu, true); + set_cpu_possible(cpu, true); } -void __init __attribute__((weak)) smp_setup_processor_id(void) +void __init __weak smp_setup_processor_id(void) { } -asmlinkage void __init start_kernel(void) +# if THREAD_SIZE >= PAGE_SIZE +void __init __weak thread_info_cache_init(void) { - char * command_line; - extern struct kernel_param __start___param[], __stop___param[]; +} +#endif - smp_setup_processor_id(); +/* + * Set up kernel memory allocators + */ +static void __init mm_init(void) +{ + /* + * page_cgroup requires contiguous pages, + * bigger than MAX_ORDER unless SPARSEMEM. + */ + page_cgroup_init_flatmem(); + mem_init(); + kmem_cache_init(); + percpu_init_late(); + pgtable_init(); + vmalloc_init(); +} + +asmlinkage __visible void __init start_kernel(void) +{ + char * command_line, *after_dashes; + extern const struct kernel_param __start___param[], __stop___param[]; /* * Need to run as early as possible, to initialize the * lockdep hash: */ - unwind_init(); lockdep_init(); + smp_setup_processor_id(); + debug_objects_early_init(); + + /* + * Set up the the initial canary ASAP: + */ + boot_init_stack_canary(); + cgroup_init_early(); local_irq_disable(); - early_boot_irqs_off(); - early_init_irq_lock_class(); + early_boot_irqs_disabled = true; /* * Interrupts are still disabled. Do necessary setups, then * enable them */ - lock_kernel(); - tick_init(); boot_cpu_init(); page_address_init(); - printk(KERN_NOTICE); - printk(linux_banner); + pr_notice("%s", linux_banner); setup_arch(&command_line); + mm_init_cpumask(&init_mm); setup_command_line(command_line); - unwind_setup(); + setup_nr_cpu_ids(); setup_per_cpu_areas(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ + build_all_zonelists(NULL, NULL); + page_alloc_init(); + + pr_notice("Kernel command line: %s\n", boot_command_line); + parse_early_param(); + after_dashes = parse_args("Booting kernel", + static_command_line, __start___param, + __stop___param - __start___param, + -1, -1, &unknown_bootoption); + if (after_dashes) + parse_args("Setting init args", after_dashes, NULL, 0, -1, -1, + set_init_arg); + + jump_label_init(); + + /* + * These use large bootmem allocations and must precede + * kmem_cache_init() + */ + setup_log_buf(0); + pidhash_init(); + vfs_caches_init_early(); + sort_main_extable(); + trap_init(); + mm_init(); + /* * Set up the scheduler prior starting any interrupts (such as the * timer interrupt). Full topology setup happens at smp_init() @@ -550,34 +572,32 @@ asmlinkage void __init start_kernel(void) * fragile until we cpu_idle() for the first time. */ preempt_disable(); - build_all_zonelists(); - page_alloc_init(); - printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line); - parse_early_param(); - parse_args("Booting kernel", static_command_line, __start___param, - __stop___param - __start___param, - &unknown_bootoption); - if (!irqs_disabled()) { - printk(KERN_WARNING "start_kernel(): bug: interrupts were " - "enabled *very* early, fixing it\n"); + if (WARN(!irqs_disabled(), "Interrupts were enabled *very* early, fixing it\n")) local_irq_disable(); - } - sort_main_extable(); - trap_init(); + idr_init_cache(); rcu_init(); + tick_nohz_init(); + context_tracking_init(); + radix_tree_init(); + /* init some links before init_ISA_irqs() */ + early_irq_init(); init_IRQ(); - pidhash_init(); + tick_init(); init_timers(); hrtimers_init(); softirq_init(); timekeeping_init(); time_init(); + sched_clock_postinit(); + perf_event_init(); profile_init(); - if (!irqs_disabled()) - printk("start_kernel(): bug: interrupts were enabled early\n"); - early_boot_irqs_on(); + call_function_init(); + WARN(!irqs_disabled(), "Interrupts were enabled early\n"); + early_boot_irqs_disabled = false; local_irq_enable(); + 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 @@ -585,7 +605,8 @@ asmlinkage void __init start_kernel(void) */ console_init(); if (panic_later) - panic(panic_later, panic_param); + panic("Too many boot %s vars at `%s'", panic_later, + panic_param); lockdep_info(); @@ -598,45 +619,46 @@ 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) { - printk(KERN_CRIT "initrd overwritten (0x%08lx < 0x%08lx) - " - "disabling it.\n",initrd_start,min_low_pfn << PAGE_SHIFT); + 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 - vfs_caches_init_early(); - cpuset_init_early(); - mem_init(); - enable_debug_pagealloc(); - cpu_hotplug_init(); - kmem_cache_init(); + 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(); - pgtable_cache_init(); - prio_tree_init(); anon_vma_init(); + acpi_early_init(); #ifdef CONFIG_X86 - if (efi_enabled) + if (efi_enabled(EFI_RUNTIME_SERVICES)) efi_enter_virtual_mode(); #endif - fork_init(num_physpages); +#ifdef CONFIG_X86_ESPFIX64 + /* Should be run before the first non-init thread is created */ + init_espfix_bsp(); +#endif + thread_info_cache_init(); + cred_init(); + fork_init(totalram_pages); proc_caches_init(); buffer_init(); - unnamed_dev_init(); key_init(); security_init(); - vfs_caches_init(num_physpages); - radix_tree_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(); @@ -644,81 +666,202 @@ asmlinkage void __init start_kernel(void) 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(); } -static int __initdata initcall_debug; - -static int __init initcall_debug_setup(char *str) +/* Call all constructor functions linked into the kernel. */ +static void __init do_ctors(void) { - initcall_debug = 1; - return 1; +#ifdef CONFIG_CONSTRUCTORS + ctor_fn_t *fn = (ctor_fn_t *) __ctors_start; + + for (; fn < (ctor_fn_t *) __ctors_end; fn++) + (*fn)(); +#endif } -__setup("initcall_debug", initcall_debug_setup); -extern initcall_t __initcall_start[], __initcall_end[]; +bool initcall_debug; +core_param(initcall_debug, initcall_debug, bool, 0644); -static void __init do_initcalls(void) +#ifdef CONFIG_KALLSYMS +struct blacklist_entry { + struct list_head next; + char *buf; +}; + +static __initdata_or_module LIST_HEAD(blacklisted_initcalls); + +static int __init initcall_blacklist(char *str) { - initcall_t *call; - int count = preempt_count(); + char *str_entry; + struct blacklist_entry *entry; - for (call = __initcall_start; call < __initcall_end; call++) { - ktime_t t0, t1, delta; - 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"); - t0 = ktime_get(); + /* str argument is a comma-separated list of functions */ + do { + str_entry = strsep(&str, ","); + if (str_entry) { + pr_debug("blacklisting initcall %s\n", str_entry); + entry = alloc_bootmem(sizeof(*entry)); + entry->buf = alloc_bootmem(strlen(str_entry) + 1); + strcpy(entry->buf, str_entry); + list_add(&entry->next, &blacklisted_initcalls); } + } while (str_entry); + + return 0; +} - result = (*call)(); +static bool __init_or_module initcall_blacklisted(initcall_t fn) +{ + struct list_head *tmp; + struct blacklist_entry *entry; + char *fn_name; + + fn_name = kasprintf(GFP_KERNEL, "%pf", fn); + if (!fn_name) + return false; + + list_for_each(tmp, &blacklisted_initcalls) { + entry = list_entry(tmp, struct blacklist_entry, next); + if (!strcmp(fn_name, entry->buf)) { + pr_debug("initcall %s blacklisted\n", fn_name); + kfree(fn_name); + return true; + } + } - if (initcall_debug) { - t1 = ktime_get(); - delta = ktime_sub(t1, t0); + kfree(fn_name); + return false; +} +#else +static int __init initcall_blacklist(char *str) +{ + pr_warn("initcall_blacklist requires CONFIG_KALLSYMS\n"); + return 0; +} - printk("initcall 0x%p", *call); - print_fn_descriptor_symbol(": %s()", - (unsigned long) *call); - printk(" returned %d.\n", result); +static bool __init_or_module initcall_blacklisted(initcall_t fn) +{ + return false; +} +#endif +__setup("initcall_blacklist=", initcall_blacklist); - printk("initcall 0x%p ran for %Ld msecs: ", - *call, (unsigned long long)delta.tv64 >> 20); - print_fn_descriptor_symbol("%s()\n", - (unsigned long) *call); - } +static int __init_or_module do_one_initcall_debug(initcall_t fn) +{ + ktime_t calltime, delta, rettime; + unsigned long long duration; + int ret; + + printk(KERN_DEBUG "calling %pF @ %i\n", fn, task_pid_nr(current)); + calltime = ktime_get(); + ret = fn(); + rettime = ktime_get(); + delta = ktime_sub(rettime, calltime); + duration = (unsigned long long) ktime_to_ns(delta) >> 10; + printk(KERN_DEBUG "initcall %pF returned %d after %lld usecs\n", + fn, ret, duration); + + return ret; +} - 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); - } +int __init_or_module do_one_initcall(initcall_t fn) +{ + int count = preempt_count(); + int ret; + char msgbuf[64]; + + if (initcall_blacklisted(fn)) + return -EPERM; + + if (initcall_debug) + ret = do_one_initcall_debug(fn); + else + ret = fn(); + + msgbuf[0] = 0; + + if (preempt_count() != count) { + sprintf(msgbuf, "preemption imbalance "); + preempt_count_set(count); } + if (irqs_disabled()) { + strlcat(msgbuf, "disabled interrupts ", sizeof(msgbuf)); + local_irq_enable(); + } + WARN(msgbuf[0], "initcall %pF returned with %s\n", fn, msgbuf); + + return ret; +} + + +extern initcall_t __initcall_start[]; +extern initcall_t __initcall0_start[]; +extern initcall_t __initcall1_start[]; +extern initcall_t __initcall2_start[]; +extern initcall_t __initcall3_start[]; +extern initcall_t __initcall4_start[]; +extern initcall_t __initcall5_start[]; +extern initcall_t __initcall6_start[]; +extern initcall_t __initcall7_start[]; +extern initcall_t __initcall_end[]; + +static initcall_t *initcall_levels[] __initdata = { + __initcall0_start, + __initcall1_start, + __initcall2_start, + __initcall3_start, + __initcall4_start, + __initcall5_start, + __initcall6_start, + __initcall7_start, + __initcall_end, +}; + +/* Keep these in sync with initcalls in include/linux/init.h */ +static char *initcall_level_names[] __initdata = { + "early", + "core", + "postcore", + "arch", + "subsys", + "fs", + "device", + "late", +}; + +static void __init do_initcall_level(int level) +{ + extern const struct kernel_param __start___param[], __stop___param[]; + initcall_t *fn; + + strcpy(initcall_command_line, saved_command_line); + parse_args(initcall_level_names[level], + initcall_command_line, __start___param, + __stop___param - __start___param, + level, level, + &repair_env_string); + + for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++) + do_one_initcall(*fn); +} - /* Make sure there is no pending stuff from the initcall sequence */ - flush_scheduled_work(); +static void __init do_initcalls(void) +{ + int level; + + for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++) + do_initcall_level(level); } /* @@ -730,60 +873,80 @@ static void __init do_initcalls(void) */ static void __init do_basic_setup(void) { - /* drivers will send hotplug events */ - init_workqueues(); + cpuset_init_smp(); usermodehelper_init(); + shmem_init(); driver_init(); init_irq_proc(); + do_ctors(); + usermodehelper_enable(); do_initcalls(); + random_int_secret_init(); } -static int __initdata nosoftlockup; - -static int __init nosoftlockup_setup(char *str) +static void __init do_pre_smp_initcalls(void) { - nosoftlockup = 1; - return 1; + initcall_t *fn; + + for (fn = __initcall_start; fn < __initcall0_start; fn++) + do_one_initcall(*fn); } -__setup("nosoftlockup", nosoftlockup_setup); -static void __init do_pre_smp_initcalls(void) +/* + * This function requests modules which should be loaded by default and is + * called twice right after initrd is mounted and right before init is + * exec'd. If such modules are on either initrd or rootfs, they will be + * loaded before control is passed to userland. + */ +void __init load_default_modules(void) { - extern int spawn_ksoftirqd(void); - - migration_init(); - spawn_ksoftirqd(); - if (!nosoftlockup) - spawn_softlockup_task(); + load_default_elevator_module(); } -static void run_init_process(char *init_filename) +static int run_init_process(const char *init_filename) { argv_init[0] = init_filename; - kernel_execve(init_filename, argv_init, envp_init); + return do_execve(getname_kernel(init_filename), + (const char __user *const __user *)argv_init, + (const char __user *const __user *)envp_init); } -/* 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) +static int try_to_run_init_process(const char *init_filename) +{ + int ret; + + ret = run_init_process(init_filename); + + if (ret && ret != -ENOENT) { + pr_err("Starting init: %s exists but couldn't execute it (error %d)\n", + init_filename, ret); + } + + return ret; +} + +static noinline void __init kernel_init_freeable(void); + +static int __ref kernel_init(void *unused) { + int ret; + + kernel_init_freeable(); + /* need to finish all async __init code before freeing the memory */ + async_synchronize_full(); 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); + flush_delayed_fput(); if (ramdisk_execute_command) { - run_init_process(ramdisk_execute_command); - printk(KERN_WARNING "Failed to execute %s\n", - ramdisk_execute_command); + ret = run_init_process(ramdisk_execute_command); + if (!ret) + return 0; + pr_err("Failed to execute %s (error %d)\n", + ramdisk_execute_command, ret); } /* @@ -793,48 +956,59 @@ static int noinline init_post(void) * 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); + ret = run_init_process(execute_command); + if (!ret) + return 0; + pr_err("Failed to execute %s (error %d). Attempting defaults...\n", + execute_command, ret); } - run_init_process("/sbin/init"); - run_init_process("/etc/init"); - run_init_process("/bin/init"); - run_init_process("/bin/sh"); + if (!try_to_run_init_process("/sbin/init") || + !try_to_run_init_process("/etc/init") || + !try_to_run_init_process("/bin/init") || + !try_to_run_init_process("/bin/sh")) + return 0; - panic("No init found. Try passing init= option to kernel."); + panic("No working init found. Try passing init= option to kernel. " + "See Linux Documentation/init.txt for guidance."); } -static int __init kernel_init(void * unused) +static noinline void __init kernel_init_freeable(void) { - lock_kernel(); /* - * init can run on any cpu. + * Wait until kthreadd is all set-up. */ - set_cpus_allowed(current, CPU_MASK_ALL); + wait_for_completion(&kthreadd_done); + + /* Now the scheduler is fully set up and can do blocking allocations */ + gfp_allowed_mask = __GFP_BITS_MASK; + /* - * Tell the world that we're going to be the grim - * reaper of innocent orphaned children. - * - * We don't want people to have to make incorrect - * assumptions about where in the task array this - * can be found. + * init can allocate pages on any node */ - init_pid_ns.child_reaper = current; + set_mems_allowed(node_states[N_MEMORY]); + /* + * init can run on any cpu. + */ + set_cpus_allowed_ptr(current, cpu_all_mask); cad_pid = task_pid(current); smp_prepare_cpus(setup_max_cpus); do_pre_smp_initcalls(); + lockup_detector_init(); smp_init(); sched_init_smp(); - cpuset_init_smp(); - do_basic_setup(); + /* Open the /dev/console on the rootfs, this should never fail */ + if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) + pr_err("Warning: unable to open an initial console.\n"); + + (void) sys_dup(0); + (void) sys_dup(0); /* * check if there is an early userspace init. If yes, let it do all * the work @@ -853,6 +1027,7 @@ static int __init kernel_init(void * unused) * we're essentially up and running. Get rid of the * initmem segments and start the user-mode stuff.. */ - init_post(); - return 0; + + /* rootfs is available now, try loading default modules */ + load_default_modules(); } |