/*
* Allocate a new mm structure and copy contents from the
* mm structure of the passed in task structure.
*/
struct mm_struct *dup_mm(struct task_struct *tsk)
{
struct mm_struct *mm, *oldmm = current->mm;
int err;
if (!oldmm)
return NULL;
mm = allocate_mm();
if (!mm)
goto fail_nomem;
memcpy(mm, oldmm, sizeof(*mm));
mm_init_cpumask(mm);
/* Initializing for Swap token stuff */
mm->token_priority = 0;
mm->last_interval = 0;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
mm->pmd_huge_pte = NULL;
#endif
if (!mm_init(mm, tsk))
goto fail_nomem;
if (init_new_context(tsk, mm))
goto fail_nocontext;
dup_mm_exe_file(oldmm, mm);
err = dup_mmap(mm, oldmm);
if (err)
goto free_pt;
mm->hiwater_rss = get_mm_rss(mm);
mm->hiwater_vm = mm->total_vm;
if (mm->binfmt && !try_module_get(mm->binfmt->module))
goto free_pt;
return mm;
free_pt:
/* don't put binfmt in mmput, we haven't got module yet */
mm->binfmt = NULL;
mmput(mm);
fail_nomem:
return NULL;
fail_nocontext:
/*
* If init_new_context() failed, we cannot use mmput() to free the mm
* because it calls destroy_context()
*/
mm_free_pgd(mm);
free_mm(mm);
return NULL;
}
struct mm_struct *dup_mm(struct task_struct *tsk)
{
struct mm_struct *mm, *oldmm = current->mm;
int err;
if (!oldmm)
return NULL;
mm = allocate_mm();
if (!mm)
goto fail_nomem;
memcpy(mm, oldmm, sizeof(*mm));
mm_init_cpumask(mm);
mm->token_priority = 0;
mm->last_interval = 0;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
mm->pmd_huge_pte = NULL;
#endif
if (!mm_init(mm, tsk))
goto fail_nomem;
if (init_new_context(tsk, mm))
goto fail_nocontext;
dup_mm_exe_file(oldmm, mm);
err = dup_mmap(mm, oldmm);
if (err)
goto free_pt;
mm->hiwater_rss = get_mm_rss(mm);
mm->hiwater_vm = mm->total_vm;
if (mm->binfmt && !try_module_get(mm->binfmt->module))
goto free_pt;
return mm;
free_pt:
mm->binfmt = NULL;
mmput(mm);
fail_nomem:
return NULL;
fail_nocontext:
mm_free_pgd(mm);
free_mm(mm);
return NULL;
}
/*
* Allocate and initialize an mm_struct.
*/
struct mm_struct *mm_alloc(void)
{
struct mm_struct *mm;
mm = allocate_mm();
if (!mm)
return NULL;
memset(mm, 0, sizeof(*mm));
mm_init_cpumask(mm);
return mm_init(mm, current);
}
static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
{
mm->mmap = NULL;
mm->mm_rb = RB_ROOT;
mm->vmacache_seqnum = 0;
atomic_set(&mm->mm_users, 1);
atomic_set(&mm->mm_count, 1);
init_rwsem(&mm->mmap_sem);
INIT_LIST_HEAD(&mm->mmlist);
mm->core_state = NULL;
atomic_long_set(&mm->nr_ptes, 0);
mm_nr_pmds_init(mm);
mm->map_count = 0;
mm->locked_vm = 0;
mm->pinned_vm = 0;
memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
spin_lock_init(&mm->page_table_lock);
mm_init_cpumask(mm);
mm_init_aio(mm);
mm_init_owner(mm, p);
mmu_notifier_mm_init(mm);
clear_tlb_flush_pending(mm);
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
mm->pmd_huge_pte = NULL;
#endif
if (current->mm) {
mm->flags = current->mm->flags & MMF_INIT_MASK;
mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK;
} else {
mm->flags = default_dump_filter;
mm->def_flags = 0;
}
if (mm_alloc_pgd(mm))
goto fail_nopgd;
if (init_new_context(p, mm))
goto fail_nocontext;
return mm;
fail_nocontext:
mm_free_pgd(mm);
fail_nopgd:
free_mm(mm);
return NULL;
}
static bool __init efi_virtmap_init(void)
{
efi_memory_desc_t *md;
bool systab_found;
efi_mm.pgd = pgd_alloc(&efi_mm);
mm_init_cpumask(&efi_mm);
init_new_context(NULL, &efi_mm);
systab_found = false;
for_each_efi_memory_desc(md) {
phys_addr_t phys = md->phys_addr;
int ret;
if (!(md->attribute & EFI_MEMORY_RUNTIME))
continue;
if (md->virt_addr == 0)
return false;
ret = efi_create_mapping(&efi_mm, md);
if (ret) {
pr_warn(" EFI remap %pa: failed to create mapping (%d)\n",
&phys, ret);
return false;
}
/*
* If this entry covers the address of the UEFI system table,
* calculate and record its virtual address.
*/
if (efi_system_table >= phys &&
efi_system_table < phys + (md->num_pages * EFI_PAGE_SIZE)) {
efi.systab = (void *)(unsigned long)(efi_system_table -
phys + md->virt_addr);
systab_found = true;
}
}
if (!systab_found) {
pr_err("No virtual mapping found for the UEFI System Table\n");
return false;
}
if (efi_memattr_apply_permissions(&efi_mm, efi_set_mapping_permissions))
return false;
return true;
}
/*
* We need our own copy of the higher levels of the page tables
* because we want to avoid inserting EFI region mappings (EFI_VA_END
* to EFI_VA_START) into the standard kernel page tables. Everything
* else can be shared, see efi_sync_low_kernel_mappings().
*
* We don't want the pgd on the pgd_list and cannot use pgd_alloc() for the
* allocation.
*/
int __init efi_alloc_page_tables(void)
{
pgd_t *pgd, *efi_pgd;
p4d_t *p4d;
pud_t *pud;
gfp_t gfp_mask;
if (efi_enabled(EFI_OLD_MEMMAP))
return 0;
gfp_mask = GFP_KERNEL | __GFP_ZERO;
efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
if (!efi_pgd)
return -ENOMEM;
pgd = efi_pgd + pgd_index(EFI_VA_END);
p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END);
if (!p4d) {
free_page((unsigned long)efi_pgd);
return -ENOMEM;
}
pud = pud_alloc(&init_mm, p4d, EFI_VA_END);
if (!pud) {
if (pgtable_l5_enabled)
free_page((unsigned long) pgd_page_vaddr(*pgd));
free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
return -ENOMEM;
}
efi_mm.pgd = efi_pgd;
mm_init_cpumask(&efi_mm);
init_new_context(NULL, &efi_mm);
return 0;
}
/*
* Allocate a new mm structure and copy contents from the
* mm structure of the passed in task structure.
*/
struct mm_struct *dup_mm(struct task_struct *tsk)
{
struct mm_struct *mm, *oldmm = current->mm;
int err;
if (!oldmm)
return NULL;
mm = allocate_mm();
if (!mm)
goto fail_nomem;
memcpy(mm, oldmm, sizeof(*mm));
mm_init_cpumask(mm);
/* Initializing for Swap token stuff */
mm->token_priority = 0;
mm->last_interval = 0;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
mm->pmd_huge_pte = NULL;
#endif
uprobe_reset_state(mm);
if (!mm_init(mm, tsk))
goto fail_nomem;
if (init_new_context(tsk, mm))
goto fail_nocontext;
dup_mm_exe_file(oldmm, mm);
err = dup_mmap(mm, oldmm);
if (err)
goto free_pt;
#ifdef CONFIG_HOMECACHE
{
/* Reset vm_pid on all vmas. In the new mm_struct, we
* want to switch anything that was associated with
* the parent to be associated with the child, and
* clear everything else.
*/
struct vm_area_struct *mpnt;
down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
for (mpnt = mm->mmap; mpnt; mpnt = mpnt->vm_next) {
if (mpnt->vm_pid == current->pid)
mpnt->vm_pid = tsk->pid;
else
mpnt->vm_pid = 0;
}
up_write(&mm->mmap_sem);
}
#endif
mm->hiwater_rss = get_mm_rss(mm);
mm->hiwater_vm = mm->total_vm;
if (mm->binfmt && !try_module_get(mm->binfmt->module))
goto free_pt;
return mm;
free_pt:
/* don't put binfmt in mmput, we haven't got module yet */
mm->binfmt = NULL;
mmput(mm);
fail_nomem:
return NULL;
fail_nocontext:
/*
* If init_new_context() failed, we cannot use mmput() to free the mm
* because it calls destroy_context()
*/
mm_free_pgd(mm);
free_mm(mm);
return NULL;
}
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();
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_disabled = true;
/*
* Interrupts are still disabled. Do necessary setups, then
* enable them
*/
tick_init();
boot_cpu_init();
page_address_init();
printk(KERN_NOTICE "%s", linux_banner);
setup_arch(&command_line);
mm_init_owner(&init_mm, &init_task);
mm_init_cpumask(&init_mm);
setup_command_line(command_line);
setup_nr_cpu_ids();
setup_per_cpu_areas();
smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
build_all_zonelists(NULL);
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);
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()
* time - but meanwhile we still have a functioning scheduler.
*/
sched_init();
/*
* Disable preemption - early bootup scheduling is extremely
* fragile until we cpu_idle() for the first time.
*/
preempt_disable();
if (!irqs_disabled()) {
printk(KERN_WARNING "start_kernel(): bug: interrupts were "
"enabled *very* early, fixing it\n");
local_irq_disable();
}
idr_init_cache();
perf_event_init();
rcu_init();
radix_tree_init();
/* init some links before init_ISA_irqs() */
early_irq_init();
init_IRQ();
prio_tree_init();
init_timers();
hrtimers_init();
softirq_init();
timekeeping_init();
time_init();
profile_init();
call_function_init();
if (!irqs_disabled())
printk(KERN_CRIT "start_kernel(): bug: interrupts were "
"enabled early\n");
early_boot_irqs_disabled = false;
local_irq_enable();
/* Interrupts are enabled now so all GFP allocations are safe. */
gfp_allowed_mask = __GFP_BITS_MASK;
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) {
printk(KERN_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();
enable_debug_pagealloc();
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_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();
ftrace_init();
/* Do the rest non-__init'ed, we're now alive */
rest_init();
}
