UBUNTU: Ubuntu-4.15.0-96.97

[mirror_ubuntu-bionic-kernel.git] / kernel / fork.c

/*
 *  linux/kernel/fork.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

/*
 *  'fork.c' contains the help-routines for the 'fork' system call
 * (see also entry.S and others).
 * Fork is rather simple, once you get the hang of it, but the memory
 * management can be a bitch. See 'mm/memory.c': 'copy_page_range()'
 */

#include <linux/slab.h>
#include <linux/sched/autogroup.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/user.h>
#include <linux/sched/numa_balancing.h>
#include <linux/sched/stat.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/sched/cputime.h>
#include <linux/rtmutex.h>
#include <linux/init.h>
#include <linux/unistd.h>
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/completion.h>
#include <linux/personality.h>
#include <linux/mempolicy.h>
#include <linux/sem.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/iocontext.h>
#include <linux/key.h>
#include <linux/binfmts.h>
#include <linux/mman.h>
#include <linux/mmu_notifier.h>
#include <linux/hmm.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/vmacache.h>
#include <linux/nsproxy.h>
#include <linux/capability.h>
#include <linux/cpu.h>
#include <linux/cgroup.h>
#include <linux/security.h>
#include <linux/hugetlb.h>
#include <linux/seccomp.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
#include <linux/jiffies.h>
#include <linux/futex.h>
#include <linux/compat.h>
#include <linux/kthread.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/rcupdate.h>
#include <linux/ptrace.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
#include <linux/proc_fs.h>
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/ksm.h>
#include <linux/acct.h>
#include <linux/userfaultfd_k.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/freezer.h>
#include <linux/delayacct.h>
#include <linux/taskstats_kern.h>
#include <linux/random.h>
#include <linux/tty.h>
#include <linux/blkdev.h>
#include <linux/fs_struct.h>
#include <linux/magic.h>
#include <linux/perf_event.h>
#include <linux/posix-timers.h>
#include <linux/user-return-notifier.h>
#include <linux/oom.h>
#include <linux/khugepaged.h>
#include <linux/signalfd.h>
#include <linux/uprobes.h>
#include <linux/aio.h>
#include <linux/compiler.h>
#include <linux/sysctl.h>
#include <linux/kcov.h>
#include <linux/livepatch.h>
#include <linux/thread_info.h>

#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>

#include <trace/events/sched.h>

#define CREATE_TRACE_POINTS
#include <trace/events/task.h>
#ifdef CONFIG_USER_NS
extern int unprivileged_userns_clone;
#else
#define unprivileged_userns_clone 0
#endif

/*
 * Minimum number of threads to boot the kernel
 */
#define MIN_THREADS 20

/*
 * Maximum number of threads
 */
#define MAX_THREADS FUTEX_TID_MASK

/*
 * Protected counters by write_lock_irq(&tasklist_lock)
 */
unsigned long total_forks;      /* Handle normal Linux uptimes. */
int nr_threads;                 /* The idle threads do not count.. */

int max_threads;                /* tunable limit on nr_threads */

DEFINE_PER_CPU(unsigned long, process_counts) = 0;

__cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */

#ifdef CONFIG_PROVE_RCU
int lockdep_tasklist_lock_is_held(void)
{
        return lockdep_is_held(&tasklist_lock);
}
EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held);
#endif /* #ifdef CONFIG_PROVE_RCU */

int nr_processes(void)
{
        int cpu;
        int total = 0;

        for_each_possible_cpu(cpu)
                total += per_cpu(process_counts, cpu);

        return total;
}

void __weak arch_release_task_struct(struct task_struct *tsk)
{
}

#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
static struct kmem_cache *task_struct_cachep;

static inline struct task_struct *alloc_task_struct_node(int node)
{
        return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node);
}

static inline void free_task_struct(struct task_struct *tsk)
{
        kmem_cache_free(task_struct_cachep, tsk);
}
#endif

#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR

/*
 * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
 * kmemcache based allocator.
 */
# if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)

#ifdef CONFIG_VMAP_STACK
/*
 * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB
 * flush.  Try to minimize the number of calls by caching stacks.
 */
#define NR_CACHED_STACKS 2
static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]);

static int free_vm_stack_cache(unsigned int cpu)
{
        struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu);
        int i;

        for (i = 0; i < NR_CACHED_STACKS; i++) {
                struct vm_struct *vm_stack = cached_vm_stacks[i];

                if (!vm_stack)
                        continue;

                vfree(vm_stack->addr);
                cached_vm_stacks[i] = NULL;
        }

        return 0;
}
#endif

static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
{
#ifdef CONFIG_VMAP_STACK
        void *stack;
        int i;

        for (i = 0; i < NR_CACHED_STACKS; i++) {
                struct vm_struct *s;

                s = this_cpu_xchg(cached_stacks[i], NULL);

                if (!s)
                        continue;

                /* Clear stale pointers from reused stack. */
                memset(s->addr, 0, THREAD_SIZE);

                tsk->stack_vm_area = s;
                tsk->stack = s->addr;
                return s->addr;
        }

        stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN,
                                     VMALLOC_START, VMALLOC_END,
                                     THREADINFO_GFP,
                                     PAGE_KERNEL,
                                     0, node, __builtin_return_address(0));

        /*
         * We can't call find_vm_area() in interrupt context, and
         * free_thread_stack() can be called in interrupt context,
         * so cache the vm_struct.
         */
        if (stack) {
                tsk->stack_vm_area = find_vm_area(stack);
                tsk->stack = stack;
        }
        return stack;
#else
        struct page *page = alloc_pages_node(node, THREADINFO_GFP,
                                             THREAD_SIZE_ORDER);

        if (likely(page)) {
                tsk->stack = page_address(page);
                return tsk->stack;
        }
        return NULL;
#endif
}

static inline void free_thread_stack(struct task_struct *tsk)
{
#ifdef CONFIG_VMAP_STACK
        if (task_stack_vm_area(tsk)) {
                int i;

                for (i = 0; i < NR_CACHED_STACKS; i++) {
                        if (this_cpu_cmpxchg(cached_stacks[i],
                                        NULL, tsk->stack_vm_area) != NULL)
                                continue;

                        return;
                }

                vfree_atomic(tsk->stack);
                return;
        }
#endif

        __free_pages(virt_to_page(tsk->stack), THREAD_SIZE_ORDER);
}
# else
static struct kmem_cache *thread_stack_cache;

static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
                                                  int node)
{
        unsigned long *stack;
        stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
        tsk->stack = stack;
        return stack;
}

static void free_thread_stack(struct task_struct *tsk)
{
        kmem_cache_free(thread_stack_cache, tsk->stack);
}

void thread_stack_cache_init(void)
{
        thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE,
                                              THREAD_SIZE, 0, NULL);
        BUG_ON(thread_stack_cache == NULL);
}
# endif
#endif

/* SLAB cache for signal_struct structures (tsk->signal) */
static struct kmem_cache *signal_cachep;

/* SLAB cache for sighand_struct structures (tsk->sighand) */
struct kmem_cache *sighand_cachep;

/* SLAB cache for files_struct structures (tsk->files) */
struct kmem_cache *files_cachep;

/* SLAB cache for fs_struct structures (tsk->fs) */
struct kmem_cache *fs_cachep;

/* SLAB cache for vm_area_struct structures */
static struct kmem_cache *vm_area_cachep;

/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;

struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
{
        struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);

        if (vma) {
                vma->vm_mm = mm;
                INIT_LIST_HEAD(&vma->anon_vma_chain);
        }
        return vma;
}

struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
{
        struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);

        if (new) {
                *new = *orig;
                INIT_LIST_HEAD(&new->anon_vma_chain);
        }
        return new;
}

void vm_area_free(struct vm_area_struct *vma)
{
        kmem_cache_free(vm_area_cachep, vma);
}

static void account_kernel_stack(struct task_struct *tsk, int account)
{
        void *stack = task_stack_page(tsk);
        struct vm_struct *vm = task_stack_vm_area(tsk);

        BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);

        if (vm) {
                int i;

                BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);

                for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
                        mod_zone_page_state(page_zone(vm->pages[i]),
                                            NR_KERNEL_STACK_KB,
                                            PAGE_SIZE / 1024 * account);
                }

                /* All stack pages belong to the same memcg. */
                mod_memcg_page_state(vm->pages[0], MEMCG_KERNEL_STACK_KB,
                                     account * (THREAD_SIZE / 1024));
        } else {
                /*
                 * All stack pages are in the same zone and belong to the
                 * same memcg.
                 */
                struct page *first_page = virt_to_page(stack);

                mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
                                    THREAD_SIZE / 1024 * account);

                mod_memcg_page_state(first_page, MEMCG_KERNEL_STACK_KB,
                                     account * (THREAD_SIZE / 1024));
        }
}

static void release_task_stack(struct task_struct *tsk)
{
        if (WARN_ON(tsk->state != TASK_DEAD))
                return;  /* Better to leak the stack than to free prematurely */

        account_kernel_stack(tsk, -1);
        free_thread_stack(tsk);
        tsk->stack = NULL;
#ifdef CONFIG_VMAP_STACK
        tsk->stack_vm_area = NULL;
#endif
}

#ifdef CONFIG_THREAD_INFO_IN_TASK
void put_task_stack(struct task_struct *tsk)
{
        if (atomic_dec_and_test(&tsk->stack_refcount))
                release_task_stack(tsk);
}
#endif

void free_task(struct task_struct *tsk)
{
#ifndef CONFIG_THREAD_INFO_IN_TASK
        /*
         * The task is finally done with both the stack and thread_info,
         * so free both.
         */
        release_task_stack(tsk);
#else
        /*
         * If the task had a separate stack allocation, it should be gone
         * by now.
         */
        WARN_ON_ONCE(atomic_read(&tsk->stack_refcount) != 0);
#endif
        rt_mutex_debug_task_free(tsk);
        ftrace_graph_exit_task(tsk);
        put_seccomp_filter(tsk);
        arch_release_task_struct(tsk);
        if (tsk->flags & PF_KTHREAD)
                free_kthread_struct(tsk);
        free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);

static inline void free_signal_struct(struct signal_struct *sig)
{
        taskstats_tgid_free(sig);
        sched_autogroup_exit(sig);
        /*
         * __mmdrop is not safe to call from softirq context on x86 due to
         * pgd_dtor so postpone it to the async context
         */
        if (sig->oom_mm)
                mmdrop_async(sig->oom_mm);
        kmem_cache_free(signal_cachep, sig);
}

static inline void put_signal_struct(struct signal_struct *sig)
{
        if (atomic_dec_and_test(&sig->sigcnt))
                free_signal_struct(sig);
}

void __put_task_struct(struct task_struct *tsk)
{
        WARN_ON(!tsk->exit_state);
        WARN_ON(atomic_read(&tsk->usage));
        WARN_ON(tsk == current);

        cgroup_free(tsk);
        task_numa_free(tsk, true);
        security_task_free(tsk);
        exit_creds(tsk);
        delayacct_tsk_free(tsk);
        put_signal_struct(tsk->signal);

        if (!profile_handoff_task(tsk))
                free_task(tsk);
}
EXPORT_SYMBOL_GPL(__put_task_struct);

void __init __weak arch_task_cache_init(void) { }

/*
 * set_max_threads
 */
static void set_max_threads(unsigned int max_threads_suggested)
{
        u64 threads;

        /*
         * The number of threads shall be limited such that the thread
         * structures may only consume a small part of the available memory.
         */
        if (fls64(totalram_pages) + fls64(PAGE_SIZE) > 64)
                threads = MAX_THREADS;
        else
                threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE,
                                    (u64) THREAD_SIZE * 8UL);

        if (threads > max_threads_suggested)
                threads = max_threads_suggested;

        max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS);
}

#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
/* Initialized by the architecture: */
int arch_task_struct_size __read_mostly;
#endif

void __init fork_init(void)
{
        int i;
#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
#ifndef ARCH_MIN_TASKALIGN
#define ARCH_MIN_TASKALIGN      0
#endif
        int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN);

        /* create a slab on which task_structs can be allocated */
        task_struct_cachep = kmem_cache_create("task_struct",
                        arch_task_struct_size, align,
                        SLAB_PANIC|SLAB_ACCOUNT, NULL);
#endif

        /* do the arch specific task caches init */
        arch_task_cache_init();

        set_max_threads(MAX_THREADS);

        init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2;
        init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2;
        init_task.signal->rlim[RLIMIT_SIGPENDING] =
                init_task.signal->rlim[RLIMIT_NPROC];

        for (i = 0; i < UCOUNT_COUNTS; i++) {
                init_user_ns.ucount_max[i] = max_threads/2;
        }

#ifdef CONFIG_VMAP_STACK
        cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
                          NULL, free_vm_stack_cache);
#endif

        lockdep_init_task(&init_task);
}

int __weak arch_dup_task_struct(struct task_struct *dst,
                                               struct task_struct *src)
{
        *dst = *src;
        return 0;
}

void set_task_stack_end_magic(struct task_struct *tsk)
{
        unsigned long *stackend;

        stackend = end_of_stack(tsk);
        *stackend = STACK_END_MAGIC;    /* for overflow detection */
}

static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
{
        struct task_struct *tsk;
        unsigned long *stack;
        struct vm_struct *stack_vm_area;
        int err;

        if (node == NUMA_NO_NODE)
                node = tsk_fork_get_node(orig);
        tsk = alloc_task_struct_node(node);
        if (!tsk)
                return NULL;

        stack = alloc_thread_stack_node(tsk, node);
        if (!stack)
                goto free_tsk;

        stack_vm_area = task_stack_vm_area(tsk);

        err = arch_dup_task_struct(tsk, orig);

        /*
         * arch_dup_task_struct() clobbers the stack-related fields.  Make
         * sure they're properly initialized before using any stack-related
         * functions again.
         */
        tsk->stack = stack;
#ifdef CONFIG_VMAP_STACK
        tsk->stack_vm_area = stack_vm_area;
#endif
#ifdef CONFIG_THREAD_INFO_IN_TASK
        atomic_set(&tsk->stack_refcount, 1);
#endif

        if (err)
                goto free_stack;

#ifdef CONFIG_SECCOMP
        /*
         * We must handle setting up seccomp filters once we're under
         * the sighand lock in case orig has changed between now and
         * then. Until then, filter must be NULL to avoid messing up
         * the usage counts on the error path calling free_task.
         */
        tsk->seccomp.filter = NULL;
#endif

        setup_thread_stack(tsk, orig);
        clear_user_return_notifier(tsk);
        clear_tsk_need_resched(tsk);
        set_task_stack_end_magic(tsk);

#ifdef CONFIG_CC_STACKPROTECTOR
        tsk->stack_canary = get_random_canary();
#endif

        /*
         * One for us, one for whoever does the "release_task()" (usually
         * parent)
         */
        atomic_set(&tsk->usage, 2);
#ifdef CONFIG_BLK_DEV_IO_TRACE
        tsk->btrace_seq = 0;
#endif
        tsk->splice_pipe = NULL;
        tsk->task_frag.page = NULL;
        tsk->wake_q.next = NULL;

        account_kernel_stack(tsk, 1);

        kcov_task_init(tsk);

#ifdef CONFIG_FAULT_INJECTION
        tsk->fail_nth = 0;
#endif

        return tsk;

free_stack:
        free_thread_stack(tsk);
free_tsk:
        free_task_struct(tsk);
        return NULL;
}

#ifdef CONFIG_MMU
static __latent_entropy int dup_mmap(struct mm_struct *mm,
                                        struct mm_struct *oldmm)
{
        struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
        struct rb_node **rb_link, *rb_parent;
        int retval;
        unsigned long charge;
        LIST_HEAD(uf);

        uprobe_start_dup_mmap();
        if (down_write_killable(&oldmm->mmap_sem)) {
                retval = -EINTR;
                goto fail_uprobe_end;
        }
        flush_cache_dup_mm(oldmm);
        uprobe_dup_mmap(oldmm, mm);
        /*
         * Not linked in yet - no deadlock potential:
         */
        down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);

        /* No ordering required: file already has been exposed. */
        RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));

        mm->total_vm = oldmm->total_vm;
        mm->data_vm = oldmm->data_vm;
        mm->exec_vm = oldmm->exec_vm;
        mm->stack_vm = oldmm->stack_vm;

        rb_link = &mm->mm_rb.rb_node;
        rb_parent = NULL;
        pprev = &mm->mmap;
        retval = ksm_fork(mm, oldmm);
        if (retval)
                goto out;
        retval = khugepaged_fork(mm, oldmm);
        if (retval)
                goto out;

        prev = NULL;
        for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
                struct file *file;

                if (mpnt->vm_flags & VM_DONTCOPY) {
                        vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
                        continue;
                }
                charge = 0;
                /*
                 * Don't duplicate many vmas if we've been oom-killed (for
                 * example)
                 */
                if (fatal_signal_pending(current)) {
                        retval = -EINTR;
                        goto out;
                }
                if (mpnt->vm_flags & VM_ACCOUNT) {
                        unsigned long len = vma_pages(mpnt);

                        if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
                                goto fail_nomem;
                        charge = len;
                }
                tmp = vm_area_dup(mpnt);
                if (!tmp)
                        goto fail_nomem;
                retval = vma_dup_policy(mpnt, tmp);
                if (retval)
                        goto fail_nomem_policy;
                tmp->vm_mm = mm;
                retval = dup_userfaultfd(tmp, &uf);
                if (retval)
                        goto fail_nomem_anon_vma_fork;
                if (tmp->vm_flags & VM_WIPEONFORK) {
                        /* VM_WIPEONFORK gets a clean slate in the child. */
                        tmp->anon_vma = NULL;
                        if (anon_vma_prepare(tmp))
                                goto fail_nomem_anon_vma_fork;
                } else if (anon_vma_fork(tmp, mpnt))
                        goto fail_nomem_anon_vma_fork;
                tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
                tmp->vm_next = tmp->vm_prev = NULL;
                file = tmp->vm_file;
                if (file) {
                        struct inode *inode = file_inode(file);
                        struct address_space *mapping = file->f_mapping;

                        vma_get_file(tmp);
                        if (tmp->vm_flags & VM_DENYWRITE)
                                atomic_dec(&inode->i_writecount);
                        i_mmap_lock_write(mapping);
                        if (tmp->vm_flags & VM_SHARED)
                                atomic_inc(&mapping->i_mmap_writable);
                        flush_dcache_mmap_lock(mapping);
                        /* insert tmp into the share list, just after mpnt */
                        vma_interval_tree_insert_after(tmp, mpnt,
                                        &mapping->i_mmap);
                        flush_dcache_mmap_unlock(mapping);
                        i_mmap_unlock_write(mapping);
                }

                /*
                 * Clear hugetlb-related page reserves for children. This only
                 * affects MAP_PRIVATE mappings. Faults generated by the child
                 * are not guaranteed to succeed, even if read-only
                 */
                if (is_vm_hugetlb_page(tmp))
                        reset_vma_resv_huge_pages(tmp);

                /*
                 * Link in the new vma and copy the page table entries.
                 */
                *pprev = tmp;
                pprev = &tmp->vm_next;
                tmp->vm_prev = prev;
                prev = tmp;

                __vma_link_rb(mm, tmp, rb_link, rb_parent);
                rb_link = &tmp->vm_rb.rb_right;
                rb_parent = &tmp->vm_rb;

                mm->map_count++;
                if (!(tmp->vm_flags & VM_WIPEONFORK))
                        retval = copy_page_range(mm, oldmm, mpnt);

                if (tmp->vm_ops && tmp->vm_ops->open)
                        tmp->vm_ops->open(tmp);

                if (retval)
                        goto out;
        }
        /* a new mm has just been created */
        retval = arch_dup_mmap(oldmm, mm);
out:
        up_write(&mm->mmap_sem);
        flush_tlb_mm(oldmm);
        up_write(&oldmm->mmap_sem);
        dup_userfaultfd_complete(&uf);
fail_uprobe_end:
        uprobe_end_dup_mmap();
        return retval;
fail_nomem_anon_vma_fork:
        mpol_put(vma_policy(tmp));
fail_nomem_policy:
        vm_area_free(tmp);
fail_nomem:
        retval = -ENOMEM;
        vm_unacct_memory(charge);
        goto out;
}

static inline int mm_alloc_pgd(struct mm_struct *mm)
{
        mm->pgd = pgd_alloc(mm);
        if (unlikely(!mm->pgd))
                return -ENOMEM;
        return 0;
}

static inline void mm_free_pgd(struct mm_struct *mm)
{
        pgd_free(mm, mm->pgd);
}
#else
static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
{
        down_write(&oldmm->mmap_sem);
        RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
        up_write(&oldmm->mmap_sem);
        return 0;
}
#define mm_alloc_pgd(mm)        (0)
#define mm_free_pgd(mm)
#endif /* CONFIG_MMU */

__cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock);

#define allocate_mm()   (kmem_cache_alloc(mm_cachep, GFP_KERNEL))
#define free_mm(mm)     (kmem_cache_free(mm_cachep, (mm)))

static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT;

static int __init coredump_filter_setup(char *s)
{
        default_dump_filter =
                (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) &
                MMF_DUMP_FILTER_MASK;
        return 1;
}

__setup("coredump_filter=", coredump_filter_setup);

#include <linux/init_task.h>

static void mm_init_aio(struct mm_struct *mm)
{
#ifdef CONFIG_AIO
        spin_lock_init(&mm->ioctx_lock);
        mm->ioctx_table = NULL;
#endif
}

static __always_inline void mm_clear_owner(struct mm_struct *mm,
                                           struct task_struct *p)
{
#ifdef CONFIG_MEMCG
        if (mm->owner == p)
                WRITE_ONCE(mm->owner, NULL);
#endif
}

static void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
{
#ifdef CONFIG_MEMCG
        mm->owner = p;
#endif
}

static void mm_init_uprobes_state(struct mm_struct *mm)
{
#ifdef CONFIG_UPROBES
        mm->uprobes_state.xol_area = NULL;
#endif
}

static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
        struct user_namespace *user_ns)
{
        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;
        mm_pgtables_bytes_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);
        RCU_INIT_POINTER(mm->exe_file, NULL);
        mmu_notifier_mm_init(mm);
        hmm_mm_init(mm);
        init_tlb_flush_pending(mm);
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
        mm->pmd_huge_pte = NULL;
#endif
        mm_init_uprobes_state(mm);

        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;

        mm->user_ns = get_user_ns(user_ns);
        return mm;

fail_nocontext:
        mm_free_pgd(mm);
fail_nopgd:
        free_mm(mm);
        return NULL;
}

static void check_mm(struct mm_struct *mm)
{
        int i;

        for (i = 0; i < NR_MM_COUNTERS; i++) {
                long x = atomic_long_read(&mm->rss_stat.count[i]);

                if (unlikely(x))
                        printk(KERN_ALERT "BUG: Bad rss-counter state "
                                          "mm:%p idx:%d val:%ld\n", mm, i, x);
        }

        if (mm_pgtables_bytes(mm))
                pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n",
                                mm_pgtables_bytes(mm));

#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
        VM_BUG_ON_MM(mm->pmd_huge_pte, mm);
#endif
}

/*
 * 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));
        return mm_init(mm, current, current_user_ns());
}

/*
 * Called when the last reference to the mm
 * is dropped: either by a lazy thread or by
 * mmput. Free the page directory and the mm.
 */
void __mmdrop(struct mm_struct *mm)
{
        BUG_ON(mm == &init_mm);
        mm_free_pgd(mm);
        destroy_context(mm);
        hmm_mm_destroy(mm);
        mmu_notifier_mm_destroy(mm);
        check_mm(mm);
        put_user_ns(mm->user_ns);
        free_mm(mm);
}
EXPORT_SYMBOL_GPL(__mmdrop);

static inline void __mmput(struct mm_struct *mm)
{
        VM_BUG_ON(atomic_read(&mm->mm_users));

        uprobe_clear_state(mm);
        exit_aio(mm);
        ksm_exit(mm);
        khugepaged_exit(mm); /* must run before exit_mmap */
        exit_mmap(mm);
        mm_put_huge_zero_page(mm);
        set_mm_exe_file(mm, NULL);
        if (!list_empty(&mm->mmlist)) {
                spin_lock(&mmlist_lock);
                list_del(&mm->mmlist);
                spin_unlock(&mmlist_lock);
        }
        if (mm->binfmt)
                module_put(mm->binfmt->module);
        mmdrop(mm);
}

/*
 * Decrement the use count and release all resources for an mm.
 */
void mmput(struct mm_struct *mm)
{
        might_sleep();

        if (atomic_dec_and_test(&mm->mm_users))
                __mmput(mm);
}
EXPORT_SYMBOL_GPL(mmput);

#ifdef CONFIG_MMU
static void mmput_async_fn(struct work_struct *work)
{
        struct mm_struct *mm = container_of(work, struct mm_struct,
                                            async_put_work);

        __mmput(mm);
}

void mmput_async(struct mm_struct *mm)
{
        if (atomic_dec_and_test(&mm->mm_users)) {
                INIT_WORK(&mm->async_put_work, mmput_async_fn);
                schedule_work(&mm->async_put_work);
        }
}
#endif

/**
 * set_mm_exe_file - change a reference to the mm's executable file
 *
 * This changes mm's executable file (shown as symlink /proc/[pid]/exe).
 *
 * Main users are mmput() and sys_execve(). Callers prevent concurrent
 * invocations: in mmput() nobody alive left, in execve task is single
 * threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the
 * mm->exe_file, but does so without using set_mm_exe_file() in order
 * to do avoid the need for any locks.
 */
void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
{
        struct file *old_exe_file;

        /*
         * It is safe to dereference the exe_file without RCU as
         * this function is only called if nobody else can access
         * this mm -- see comment above for justification.
         */
        old_exe_file = rcu_dereference_raw(mm->exe_file);

        if (new_exe_file)
                get_file(new_exe_file);
        rcu_assign_pointer(mm->exe_file, new_exe_file);
        if (old_exe_file)
                fput(old_exe_file);
}

/**
 * get_mm_exe_file - acquire a reference to the mm's executable file
 *
 * Returns %NULL if mm has no associated executable file.
 * User must release file via fput().
 */
struct file *get_mm_exe_file(struct mm_struct *mm)
{
        struct file *exe_file;

        rcu_read_lock();
        exe_file = rcu_dereference(mm->exe_file);
        if (exe_file && !get_file_rcu(exe_file))
                exe_file = NULL;
        rcu_read_unlock();
        return exe_file;
}
EXPORT_SYMBOL(get_mm_exe_file);

/**
 * get_task_exe_file - acquire a reference to the task's executable file
 *
 * Returns %NULL if task's mm (if any) has no associated executable file or
 * this is a kernel thread with borrowed mm (see the comment above get_task_mm).
 * User must release file via fput().
 */
struct file *get_task_exe_file(struct task_struct *task)
{
        struct file *exe_file = NULL;
        struct mm_struct *mm;

        task_lock(task);
        mm = task->mm;
        if (mm) {
                if (!(task->flags & PF_KTHREAD))
                        exe_file = get_mm_exe_file(mm);
        }
        task_unlock(task);
        return exe_file;
}
EXPORT_SYMBOL(get_task_exe_file);

/**
 * get_task_mm - acquire a reference to the task's mm
 *
 * Returns %NULL if the task has no mm.  Checks PF_KTHREAD (meaning
 * this kernel workthread has transiently adopted a user mm with use_mm,
 * to do its AIO) is not set and if so returns a reference to it, after
 * bumping up the use count.  User must release the mm via mmput()
 * after use.  Typically used by /proc and ptrace.
 */
struct mm_struct *get_task_mm(struct task_struct *task)
{
        struct mm_struct *mm;

        task_lock(task);
        mm = task->mm;
        if (mm) {
                if (task->flags & PF_KTHREAD)
                        mm = NULL;
                else
                        mmget(mm);
        }
        task_unlock(task);
        return mm;
}
EXPORT_SYMBOL_GPL(get_task_mm);

struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
{
        struct mm_struct *mm;
        int err;

        err =  mutex_lock_killable(&task->signal->cred_guard_mutex);
        if (err)
                return ERR_PTR(err);

        mm = get_task_mm(task);
        if (mm && mm != current->mm &&
                        !ptrace_may_access(task, mode)) {
                mmput(mm);
                mm = ERR_PTR(-EACCES);
        }
        mutex_unlock(&task->signal->cred_guard_mutex);

        return mm;
}

static void complete_vfork_done(struct task_struct *tsk)
{
        struct completion *vfork;

        task_lock(tsk);
        vfork = tsk->vfork_done;
        if (likely(vfork)) {
                tsk->vfork_done = NULL;
                complete(vfork);
        }
        task_unlock(tsk);
}

static int wait_for_vfork_done(struct task_struct *child,
                                struct completion *vfork)
{
        int killed;

        freezer_do_not_count();
        killed = wait_for_completion_killable(vfork);
        freezer_count();

        if (killed) {
                task_lock(child);
                child->vfork_done = NULL;
                task_unlock(child);
        }

        put_task_struct(child);
        return killed;
}

/* Please note the differences between mmput and mm_release.
 * mmput is called whenever we stop holding onto a mm_struct,
 * error success whatever.
 *
 * mm_release is called after a mm_struct has been removed
 * from the current process.
 *
 * This difference is important for error handling, when we
 * only half set up a mm_struct for a new process and need to restore
 * the old one.  Because we mmput the new mm_struct before
 * restoring the old one. . .
 * Eric Biederman 10 January 1998
 */
static void mm_release(struct task_struct *tsk, struct mm_struct *mm)
{
        uprobe_free_utask(tsk);

        /* Get rid of any cached register state */
        deactivate_mm(tsk, mm);

        /*
         * Signal userspace if we're not exiting with a core dump
         * because we want to leave the value intact for debugging
         * purposes.
         */
        if (tsk->clear_child_tid) {
                if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
                    atomic_read(&mm->mm_users) > 1) {
                        /*
                         * We don't check the error code - if userspace has
                         * not set up a proper pointer then tough luck.
                         */
                        put_user(0, tsk->clear_child_tid);
                        sys_futex(tsk->clear_child_tid, FUTEX_WAKE,
                                        1, NULL, NULL, 0);
                }
                tsk->clear_child_tid = NULL;
        }

        /*
         * All done, finally we can wake up parent and return this mm to him.
         * Also kthread_stop() uses this completion for synchronization.
         */
        if (tsk->vfork_done)
                complete_vfork_done(tsk);
}

void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm)
{
        futex_exit_release(tsk);
        mm_release(tsk, mm);
}

void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm)
{
        futex_exec_release(tsk);
        mm_release(tsk, mm);
}

/*
 * Allocate a new mm structure and copy contents from the
 * mm structure of the passed in task structure.
 */
static struct mm_struct *dup_mm(struct task_struct *tsk)
{
        struct mm_struct *mm, *oldmm = current->mm;
        int err;

        mm = allocate_mm();
        if (!mm)
                goto fail_nomem;

        memcpy(mm, oldmm, sizeof(*mm));

        if (!mm_init(mm, tsk, mm->user_ns))
                goto fail_nomem;

        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;
        mm_init_owner(mm, NULL);
        mmput(mm);

fail_nomem:
        return NULL;
}

static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
{
        struct mm_struct *mm, *oldmm;
        int retval;

        tsk->min_flt = tsk->maj_flt = 0;
        tsk->nvcsw = tsk->nivcsw = 0;
#ifdef CONFIG_DETECT_HUNG_TASK
        tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw;
#endif

        tsk->mm = NULL;
        tsk->active_mm = NULL;

        /*
         * Are we cloning a kernel thread?
         *
         * We need to steal a active VM for that..
         */
        oldmm = current->mm;
        if (!oldmm)
                return 0;

        /* initialize the new vmacache entries */
        vmacache_flush(tsk);

        if (clone_flags & CLONE_VM) {
                mmget(oldmm);
                mm = oldmm;
                goto good_mm;
        }

        retval = -ENOMEM;
        mm = dup_mm(tsk);
        if (!mm)
                goto fail_nomem;

good_mm:
        tsk->mm = mm;
        tsk->active_mm = mm;
        return 0;

fail_nomem:
        return retval;
}

static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
{
        struct fs_struct *fs = current->fs;
        if (clone_flags & CLONE_FS) {
                /* tsk->fs is already what we want */
                spin_lock(&fs->lock);
                if (fs->in_exec) {
                        spin_unlock(&fs->lock);
                        return -EAGAIN;
                }
                fs->users++;
                spin_unlock(&fs->lock);
                return 0;
        }
        tsk->fs = copy_fs_struct(fs);
        if (!tsk->fs)
                return -ENOMEM;
        return 0;
}

static int copy_files(unsigned long clone_flags, struct task_struct *tsk)
{
        struct files_struct *oldf, *newf;
        int error = 0;

        /*
         * A background process may not have any files ...
         */
        oldf = current->files;
        if (!oldf)
                goto out;

        if (clone_flags & CLONE_FILES) {
                atomic_inc(&oldf->count);
                goto out;
        }

        newf = dup_fd(oldf, &error);
        if (!newf)
                goto out;

        tsk->files = newf;
        error = 0;
out:
        return error;
}

static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
{
#ifdef CONFIG_BLOCK
        struct io_context *ioc = current->io_context;
        struct io_context *new_ioc;

        if (!ioc)
                return 0;
        /*
         * Share io context with parent, if CLONE_IO is set
         */
        if (clone_flags & CLONE_IO) {
                ioc_task_link(ioc);
                tsk->io_context = ioc;
        } else if (ioprio_valid(ioc->ioprio)) {
                new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE);
                if (unlikely(!new_ioc))
                        return -ENOMEM;

                new_ioc->ioprio = ioc->ioprio;
                put_io_context(new_ioc);
        }
#endif
        return 0;
}

static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
{
        struct sighand_struct *sig;

        if (clone_flags & CLONE_SIGHAND) {
                atomic_inc(&current->sighand->count);
                return 0;
        }
        sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
        rcu_assign_pointer(tsk->sighand, sig);
        if (!sig)
                return -ENOMEM;

        atomic_set(&sig->count, 1);
        spin_lock_irq(&current->sighand->siglock);
        memcpy(sig->action, current->sighand->action, sizeof(sig->action));
        spin_unlock_irq(&current->sighand->siglock);
        return 0;
}

void __cleanup_sighand(struct sighand_struct *sighand)
{
        if (atomic_dec_and_test(&sighand->count)) {
                signalfd_cleanup(sighand);
                /*
                 * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it
                 * without an RCU grace period, see __lock_task_sighand().
                 */
                kmem_cache_free(sighand_cachep, sighand);
        }
}

#ifdef CONFIG_POSIX_TIMERS
/*
 * Initialize POSIX timer handling for a thread group.
 */
static void posix_cpu_timers_init_group(struct signal_struct *sig)
{
        unsigned long cpu_limit;

        cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
        if (cpu_limit != RLIM_INFINITY) {
                sig->cputime_expires.prof_exp = cpu_limit * NSEC_PER_SEC;
                sig->cputimer.running = true;
        }

        /* The timer lists. */
        INIT_LIST_HEAD(&sig->cpu_timers[0]);
        INIT_LIST_HEAD(&sig->cpu_timers[1]);
        INIT_LIST_HEAD(&sig->cpu_timers[2]);
}
#else
static inline void posix_cpu_timers_init_group(struct signal_struct *sig) { }
#endif

static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
{
        struct signal_struct *sig;

        if (clone_flags & CLONE_THREAD)
                return 0;

        sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL);
        tsk->signal = sig;
        if (!sig)
                return -ENOMEM;

        sig->nr_threads = 1;
        atomic_set(&sig->live, 1);
        atomic_set(&sig->sigcnt, 1);

        /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
        sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
        tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);

        init_waitqueue_head(&sig->wait_chldexit);
        sig->curr_target = tsk;
        init_sigpending(&sig->shared_pending);
        seqlock_init(&sig->stats_lock);
        prev_cputime_init(&sig->prev_cputime);

#ifdef CONFIG_POSIX_TIMERS
        INIT_LIST_HEAD(&sig->posix_timers);
        hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
        sig->real_timer.function = it_real_fn;
#endif

        task_lock(current->group_leader);
        memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
        task_unlock(current->group_leader);

        posix_cpu_timers_init_group(sig);

        tty_audit_fork(sig);
        sched_autogroup_fork(sig);

        sig->oom_score_adj = current->signal->oom_score_adj;
        sig->oom_score_adj_min = current->signal->oom_score_adj_min;

        mutex_init(&sig->cred_guard_mutex);

        return 0;
}

static void copy_seccomp(struct task_struct *p)
{
#ifdef CONFIG_SECCOMP
        /*
         * Must be called with sighand->lock held, which is common to
         * all threads in the group. Holding cred_guard_mutex is not
         * needed because this new task is not yet running and cannot
         * be racing exec.
         */
        assert_spin_locked(&current->sighand->siglock);

        /* Ref-count the new filter user, and assign it. */
        get_seccomp_filter(current);
        p->seccomp = current->seccomp;

        /*
         * Explicitly enable no_new_privs here in case it got set
         * between the task_struct being duplicated and holding the
         * sighand lock. The seccomp state and nnp must be in sync.
         */
        if (task_no_new_privs(current))
                task_set_no_new_privs(p);

        /*
         * If the parent gained a seccomp mode after copying thread
         * flags and between before we held the sighand lock, we have
         * to manually enable the seccomp thread flag here.
         */
        if (p->seccomp.mode != SECCOMP_MODE_DISABLED)
                set_tsk_thread_flag(p, TIF_SECCOMP);
#endif
}

SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
{
        current->clear_child_tid = tidptr;

        return task_pid_vnr(current);
}

static void rt_mutex_init_task(struct task_struct *p)
{
        raw_spin_lock_init(&p->pi_lock);
#ifdef CONFIG_RT_MUTEXES
        p->pi_waiters = RB_ROOT_CACHED;
        p->pi_top_task = NULL;
        p->pi_blocked_on = NULL;
#endif
}

#ifdef CONFIG_POSIX_TIMERS
/*
 * Initialize POSIX timer handling for a single task.
 */
static void posix_cpu_timers_init(struct task_struct *tsk)
{
        tsk->cputime_expires.prof_exp = 0;
        tsk->cputime_expires.virt_exp = 0;
        tsk->cputime_expires.sched_exp = 0;
        INIT_LIST_HEAD(&tsk->cpu_timers[0]);
        INIT_LIST_HEAD(&tsk->cpu_timers[1]);
        INIT_LIST_HEAD(&tsk->cpu_timers[2]);
}
#else
static inline void posix_cpu_timers_init(struct task_struct *tsk) { }
#endif

static inline void
init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
{
         task->pids[type].pid = pid;
}

static inline void rcu_copy_process(struct task_struct *p)
{
#ifdef CONFIG_PREEMPT_RCU
        p->rcu_read_lock_nesting = 0;
        p->rcu_read_unlock_special.s = 0;
        p->rcu_blocked_node = NULL;
        INIT_LIST_HEAD(&p->rcu_node_entry);
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TASKS_RCU
        p->rcu_tasks_holdout = false;
        INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
        p->rcu_tasks_idle_cpu = -1;
#endif /* #ifdef CONFIG_TASKS_RCU */
}

static void __delayed_free_task(struct rcu_head *rhp)
{
        struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);

        free_task(tsk);
}

static __always_inline void delayed_free_task(struct task_struct *tsk)
{
        if (IS_ENABLED(CONFIG_MEMCG))
                call_rcu(&tsk->rcu, __delayed_free_task);
        else
                free_task(tsk);
}

/*
 * This creates a new process as a copy of the old one,
 * but does not actually start it yet.
 *
 * It copies the registers, and all the appropriate
 * parts of the process environment (as per the clone
 * flags). The actual kick-off is left to the caller.
 */
static __latent_entropy struct task_struct *copy_process(
                                        unsigned long clone_flags,
                                        unsigned long stack_start,
                                        unsigned long stack_size,
                                        int __user *child_tidptr,
                                        struct pid *pid,
                                        int trace,
                                        unsigned long tls,
                                        int node)
{
        int retval;
        struct task_struct *p;

        if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
                return ERR_PTR(-EINVAL);

        if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS))
                return ERR_PTR(-EINVAL);

        if ((clone_flags & CLONE_NEWUSER) && !unprivileged_userns_clone)
                if (!capable(CAP_SYS_ADMIN))
                        return ERR_PTR(-EPERM);

        /*
         * Thread groups must share signals as well, and detached threads
         * can only be started up within the thread group.
         */
        if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
                return ERR_PTR(-EINVAL);

        /*
         * Shared signal handlers imply shared VM. By way of the above,
         * thread groups also imply shared VM. Blocking this case allows
         * for various simplifications in other code.
         */
        if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
                return ERR_PTR(-EINVAL);

        /*
         * Siblings of global init remain as zombies on exit since they are
         * not reaped by their parent (swapper). To solve this and to avoid
         * multi-rooted process trees, prevent global and container-inits
         * from creating siblings.
         */
        if ((clone_flags & CLONE_PARENT) &&
                                current->signal->flags & SIGNAL_UNKILLABLE)
                return ERR_PTR(-EINVAL);

        /*
         * If the new process will be in a different pid or user namespace
         * do not allow it to share a thread group with the forking task.
         */
        if (clone_flags & CLONE_THREAD) {
                if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
                    (task_active_pid_ns(current) !=
                                current->nsproxy->pid_ns_for_children))
                        return ERR_PTR(-EINVAL);
        }

        retval = -ENOMEM;
        p = dup_task_struct(current, node);
        if (!p)
                goto fork_out;

        /*
         * This _must_ happen before we call free_task(), i.e. before we jump
         * to any of the bad_fork_* labels. This is to avoid freeing
         * p->set_child_tid which is (ab)used as a kthread's data pointer for
         * kernel threads (PF_KTHREAD).
         */
        p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
        /*
         * Clear TID on mm_release()?
         */
        p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL;

        ftrace_graph_init_task(p);

        rt_mutex_init_task(p);

#ifdef CONFIG_PROVE_LOCKING
        DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
        DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
        retval = -EAGAIN;
        if (atomic_read(&p->real_cred->user->processes) >=
                        task_rlimit(p, RLIMIT_NPROC)) {
                if (p->real_cred->user != INIT_USER &&
                    !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
                        goto bad_fork_free;
        }
        current->flags &= ~PF_NPROC_EXCEEDED;

        retval = copy_creds(p, clone_flags);
        if (retval < 0)
                goto bad_fork_free;

        /*
         * If multiple threads are within copy_process(), then this check
         * triggers too late. This doesn't hurt, the check is only there
         * to stop root fork bombs.
         */
        retval = -EAGAIN;
        if (nr_threads >= max_threads)
                goto bad_fork_cleanup_count;

        delayacct_tsk_init(p);  /* Must remain after dup_task_struct() */
        p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE);
        p->flags |= PF_FORKNOEXEC;
        INIT_LIST_HEAD(&p->children);
        INIT_LIST_HEAD(&p->sibling);
        rcu_copy_process(p);
        p->vfork_done = NULL;
        spin_lock_init(&p->alloc_lock);

        init_sigpending(&p->pending);

        p->utime = p->stime = p->gtime = 0;
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
        p->utimescaled = p->stimescaled = 0;
#endif
        prev_cputime_init(&p->prev_cputime);

#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
        seqcount_init(&p->vtime.seqcount);
        p->vtime.starttime = 0;
        p->vtime.state = VTIME_INACTIVE;
#endif

#if defined(SPLIT_RSS_COUNTING)
        memset(&p->rss_stat, 0, sizeof(p->rss_stat));
#endif

        p->default_timer_slack_ns = current->timer_slack_ns;

        task_io_accounting_init(&p->ioac);
        acct_clear_integrals(p);

        posix_cpu_timers_init(p);

        p->io_context = NULL;
        p->audit_context = NULL;
        cgroup_fork(p);
#ifdef CONFIG_NUMA
        p->mempolicy = mpol_dup(p->mempolicy);
        if (IS_ERR(p->mempolicy)) {
                retval = PTR_ERR(p->mempolicy);
                p->mempolicy = NULL;
                goto bad_fork_cleanup_threadgroup_lock;
        }
#endif
#ifdef CONFIG_CPUSETS
        p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
        p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
        seqcount_init(&p->mems_allowed_seq);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
        p->irq_events = 0;
        p->hardirqs_enabled = 0;
        p->hardirq_enable_ip = 0;
        p->hardirq_enable_event = 0;
        p->hardirq_disable_ip = _THIS_IP_;
        p->hardirq_disable_event = 0;
        p->softirqs_enabled = 1;
        p->softirq_enable_ip = _THIS_IP_;
        p->softirq_enable_event = 0;
        p->softirq_disable_ip = 0;
        p->softirq_disable_event = 0;
        p->hardirq_context = 0;
        p->softirq_context = 0;
#endif

        p->pagefault_disabled = 0;

#ifdef CONFIG_LOCKDEP
        p->lockdep_depth = 0; /* no locks held yet */
        p->curr_chain_key = 0;
        p->lockdep_recursion = 0;
        lockdep_init_task(p);
#endif

#ifdef CONFIG_DEBUG_MUTEXES
        p->blocked_on = NULL; /* not blocked yet */
#endif
#ifdef CONFIG_BCACHE
        p->sequential_io        = 0;
        p->sequential_io_avg    = 0;
#endif
#ifdef CONFIG_SECURITY
        p->security = NULL;
#endif

        /* Perform scheduler related setup. Assign this task to a CPU. */
        retval = sched_fork(clone_flags, p);
        if (retval)
                goto bad_fork_cleanup_policy;

        retval = perf_event_init_task(p);
        if (retval)
                goto bad_fork_cleanup_policy;
        retval = audit_alloc(p);
        if (retval)
                goto bad_fork_cleanup_perf;
        /* copy all the process information */
        shm_init_task(p);
        retval = security_task_alloc(p, clone_flags);
        if (retval)
                goto bad_fork_cleanup_audit;
        retval = copy_semundo(clone_flags, p);
        if (retval)
                goto bad_fork_cleanup_security;
        retval = copy_files(clone_flags, p);
        if (retval)
                goto bad_fork_cleanup_semundo;
        retval = copy_fs(clone_flags, p);
        if (retval)
                goto bad_fork_cleanup_files;
        retval = copy_sighand(clone_flags, p);
        if (retval)
                goto bad_fork_cleanup_fs;
        retval = copy_signal(clone_flags, p);
        if (retval)
                goto bad_fork_cleanup_sighand;
        retval = copy_mm(clone_flags, p);
        if (retval)
                goto bad_fork_cleanup_signal;
        retval = copy_namespaces(clone_flags, p);
        if (retval)
                goto bad_fork_cleanup_mm;
        retval = copy_io(clone_flags, p);
        if (retval)
                goto bad_fork_cleanup_namespaces;
        retval = copy_thread_tls(clone_flags, stack_start, stack_size, p, tls);
        if (retval)
                goto bad_fork_cleanup_io;

        if (pid != &init_struct_pid) {
                pid = alloc_pid(p->nsproxy->pid_ns_for_children);
                if (IS_ERR(pid)) {
                        retval = PTR_ERR(pid);
                        goto bad_fork_cleanup_thread;
                }
        }

#ifdef CONFIG_BLOCK
        p->plug = NULL;
#endif
        futex_init_task(p);

        /*
         * sigaltstack should be cleared when sharing the same VM
         */
        if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
                sas_ss_reset(p);

        /*
         * Syscall tracing and stepping should be turned off in the
         * child regardless of CLONE_PTRACE.
         */
        user_disable_single_step(p);
        clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
        clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
        clear_all_latency_tracing(p);

        /* ok, now we should be set up.. */
        p->pid = pid_nr(pid);
        if (clone_flags & CLONE_THREAD) {
                p->exit_signal = -1;
                p->group_leader = current->group_leader;
                p->tgid = current->tgid;
        } else {
                if (clone_flags & CLONE_PARENT)
                        p->exit_signal = current->group_leader->exit_signal;
                else
                        p->exit_signal = (clone_flags & CSIGNAL);
                p->group_leader = p;
                p->tgid = p->pid;
        }

        p->nr_dirtied = 0;
        p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
        p->dirty_paused_when = 0;

        p->pdeath_signal = 0;
        INIT_LIST_HEAD(&p->thread_group);
        p->task_works = NULL;

        cgroup_threadgroup_change_begin(current);
        /*
         * Ensure that the cgroup subsystem policies allow the new process to be
         * forked. It should be noted the the new process's css_set can be changed
         * between here and cgroup_post_fork() if an organisation operation is in
         * progress.
         */
        retval = cgroup_can_fork(p);
        if (retval)
                goto bad_fork_free_pid;

        /*
         * From this point on we must avoid any synchronous user-space
         * communication until we take the tasklist-lock. In particular, we do
         * not want user-space to be able to predict the process start-time by
         * stalling fork(2) after we recorded the start_time but before it is
         * visible to the system.
         */

        p->start_time = ktime_get_ns();
        p->real_start_time = ktime_get_boot_ns();

        /*
         * Make it visible to the rest of the system, but dont wake it up yet.
         * Need tasklist lock for parent etc handling!
         */
        write_lock_irq(&tasklist_lock);

        /* CLONE_PARENT re-uses the old parent */
        if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
                p->real_parent = current->real_parent;
                p->parent_exec_id = current->parent_exec_id;
        } else {
                p->real_parent = current;
                p->parent_exec_id = current->self_exec_id;
        }

        klp_copy_process(p);

        spin_lock(&current->sighand->siglock);

        /*
         * Copy seccomp details explicitly here, in case they were changed
         * before holding sighand lock.
         */
        copy_seccomp(p);

        /*
         * Process group and session signals need to be delivered to just the
         * parent before the fork or both the parent and the child after the
         * fork. Restart if a signal comes in before we add the new process to
         * it's process group.
         * A fatal signal pending means that current will exit, so the new
         * thread can't slip out of an OOM kill (or normal SIGKILL).
        */
        recalc_sigpending();
        if (signal_pending(current)) {
                retval = -ERESTARTNOINTR;
                goto bad_fork_cancel_cgroup;
        }
        if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) {
                retval = -ENOMEM;
                goto bad_fork_cancel_cgroup;
        }

        if (likely(p->pid)) {
                ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);

                init_task_pid(p, PIDTYPE_PID, pid);
                if (thread_group_leader(p)) {
                        init_task_pid(p, PIDTYPE_PGID, task_pgrp(current));
                        init_task_pid(p, PIDTYPE_SID, task_session(current));

                        if (is_child_reaper(pid)) {
                                ns_of_pid(pid)->child_reaper = p;
                                p->signal->flags |= SIGNAL_UNKILLABLE;
                        }

                        p->signal->leader_pid = pid;
                        p->signal->tty = tty_kref_get(current->signal->tty);
                        /*
                         * Inherit has_child_subreaper flag under the same
                         * tasklist_lock with adding child to the process tree
                         * for propagate_has_child_subreaper optimization.
                         */
                        p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper ||
                                                         p->real_parent->signal->is_child_subreaper;
                        list_add_tail(&p->sibling, &p->real_parent->children);
                        list_add_tail_rcu(&p->tasks, &init_task.tasks);
                        attach_pid(p, PIDTYPE_PGID);
                        attach_pid(p, PIDTYPE_SID);
                        __this_cpu_inc(process_counts);
                } else {
                        current->signal->nr_threads++;
                        atomic_inc(&current->signal->live);
                        atomic_inc(&current->signal->sigcnt);
                        list_add_tail_rcu(&p->thread_group,
                                          &p->group_leader->thread_group);
                        list_add_tail_rcu(&p->thread_node,
                                          &p->signal->thread_head);
                }
                attach_pid(p, PIDTYPE_PID);
                nr_threads++;
        }

        total_forks++;
        spin_unlock(&current->sighand->siglock);
        syscall_tracepoint_update(p);
        write_unlock_irq(&tasklist_lock);

        proc_fork_connector(p);
        cgroup_post_fork(p);
        cgroup_threadgroup_change_end(current);
        perf_event_fork(p);

        trace_task_newtask(p, clone_flags);
        uprobe_copy_process(p, clone_flags);

        return p;

bad_fork_cancel_cgroup:
        spin_unlock(&current->sighand->siglock);
        write_unlock_irq(&tasklist_lock);
        cgroup_cancel_fork(p);
bad_fork_free_pid:
        cgroup_threadgroup_change_end(current);
        if (pid != &init_struct_pid)
                free_pid(pid);
bad_fork_cleanup_thread:
        exit_thread(p);
bad_fork_cleanup_io:
        if (p->io_context)
                exit_io_context(p);
bad_fork_cleanup_namespaces:
        exit_task_namespaces(p);
bad_fork_cleanup_mm:
        if (p->mm) {
                mm_clear_owner(p->mm, p);
                mmput(p->mm);
        }
bad_fork_cleanup_signal:
        if (!(clone_flags & CLONE_THREAD))
                free_signal_struct(p->signal);
bad_fork_cleanup_sighand:
        __cleanup_sighand(p->sighand);
bad_fork_cleanup_fs:
        exit_fs(p); /* blocking */
bad_fork_cleanup_files:
        exit_files(p); /* blocking */
bad_fork_cleanup_semundo:
        exit_sem(p);
bad_fork_cleanup_security:
        security_task_free(p);
bad_fork_cleanup_audit:
        audit_free(p);
bad_fork_cleanup_perf:
        perf_event_free_task(p);
bad_fork_cleanup_policy:
        lockdep_free_task(p);
#ifdef CONFIG_NUMA
        mpol_put(p->mempolicy);
bad_fork_cleanup_threadgroup_lock:
#endif
        delayacct_tsk_free(p);
bad_fork_cleanup_count:
        atomic_dec(&p->cred->user->processes);
        exit_creds(p);
bad_fork_free:
        p->state = TASK_DEAD;
        put_task_stack(p);
        delayed_free_task(p);
fork_out:
        return ERR_PTR(retval);
}

static inline void init_idle_pids(struct pid_link *links)
{
        enum pid_type type;

        for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) {
                INIT_HLIST_NODE(&links[type].node); /* not really needed */
                links[type].pid = &init_struct_pid;
        }
}

struct task_struct *fork_idle(int cpu)
{
        struct task_struct *task;
        task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
                            cpu_to_node(cpu));
        if (!IS_ERR(task)) {
                init_idle_pids(task->pids);
                init_idle(task, cpu);
        }

        return task;
}

/*
 *  Ok, this is the main fork-routine.
 *
 * It copies the process, and if successful kick-starts
 * it and waits for it to finish using the VM if required.
 */
long _do_fork(unsigned long clone_flags,
              unsigned long stack_start,
              unsigned long stack_size,
              int __user *parent_tidptr,
              int __user *child_tidptr,
              unsigned long tls)
{
        struct task_struct *p;
        int trace = 0;
        long nr;

        /*
         * Determine whether and which event to report to ptracer.  When
         * called from kernel_thread or CLONE_UNTRACED is explicitly
         * requested, no event is reported; otherwise, report if the event
         * for the type of forking is enabled.
         */
        if (!(clone_flags & CLONE_UNTRACED)) {
                if (clone_flags & CLONE_VFORK)
                        trace = PTRACE_EVENT_VFORK;
                else if ((clone_flags & CSIGNAL) != SIGCHLD)
                        trace = PTRACE_EVENT_CLONE;
                else
                        trace = PTRACE_EVENT_FORK;

                if (likely(!ptrace_event_enabled(current, trace)))
                        trace = 0;
        }

        p = copy_process(clone_flags, stack_start, stack_size,
                         child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
        add_latent_entropy();
        /*
         * Do this prior waking up the new thread - the thread pointer
         * might get invalid after that point, if the thread exits quickly.
         */
        if (!IS_ERR(p)) {
                struct completion vfork;
                struct pid *pid;

                trace_sched_process_fork(current, p);

                pid = get_task_pid(p, PIDTYPE_PID);
                nr = pid_vnr(pid);

                if (clone_flags & CLONE_PARENT_SETTID)
                        put_user(nr, parent_tidptr);

                if (clone_flags & CLONE_VFORK) {
                        p->vfork_done = &vfork;
                        init_completion(&vfork);
                        get_task_struct(p);
                }

                wake_up_new_task(p);

                /* forking complete and child started to run, tell ptracer */
                if (unlikely(trace))
                        ptrace_event_pid(trace, pid);

                if (clone_flags & CLONE_VFORK) {
                        if (!wait_for_vfork_done(p, &vfork))
                                ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
                }

                put_pid(pid);
        } else {
                nr = PTR_ERR(p);
        }
        return nr;
}

#ifndef CONFIG_HAVE_COPY_THREAD_TLS
/* For compatibility with architectures that call do_fork directly rather than
 * using the syscall entry points below. */
long do_fork(unsigned long clone_flags,
              unsigned long stack_start,
              unsigned long stack_size,
              int __user *parent_tidptr,
              int __user *child_tidptr)
{
        return _do_fork(clone_flags, stack_start, stack_size,
                        parent_tidptr, child_tidptr, 0);
}
#endif

/*
 * Create a kernel thread.
 */
pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
{
        return _do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn,
                (unsigned long)arg, NULL, NULL, 0);
}

#ifdef __ARCH_WANT_SYS_FORK
SYSCALL_DEFINE0(fork)
{
#ifdef CONFIG_MMU
        return _do_fork(SIGCHLD, 0, 0, NULL, NULL, 0);
#else
        /* can not support in nommu mode */
        return -EINVAL;
#endif
}
#endif

#ifdef __ARCH_WANT_SYS_VFORK
SYSCALL_DEFINE0(vfork)
{
        return _do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0,
                        0, NULL, NULL, 0);
}
#endif

#ifdef __ARCH_WANT_SYS_CLONE
#ifdef CONFIG_CLONE_BACKWARDS
SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
                 int __user *, parent_tidptr,
                 unsigned long, tls,
                 int __user *, child_tidptr)
#elif defined(CONFIG_CLONE_BACKWARDS2)
SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags,
                 int __user *, parent_tidptr,
                 int __user *, child_tidptr,
                 unsigned long, tls)
#elif defined(CONFIG_CLONE_BACKWARDS3)
SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp,
                int, stack_size,
                int __user *, parent_tidptr,
                int __user *, child_tidptr,
                unsigned long, tls)
#else
SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
                 int __user *, parent_tidptr,
                 int __user *, child_tidptr,
                 unsigned long, tls)
#endif
{
        return _do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr, tls);
}
#endif

void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data)
{
        struct task_struct *leader, *parent, *child;
        int res;

        read_lock(&tasklist_lock);
        leader = top = top->group_leader;
down:
        for_each_thread(leader, parent) {
                list_for_each_entry(child, &parent->children, sibling) {
                        res = visitor(child, data);
                        if (res) {
                                if (res < 0)
                                        goto out;
                                leader = child;
                                goto down;
                        }
up:
                        ;
                }
        }

        if (leader != top) {
                child = leader;
                parent = child->real_parent;
                leader = parent->group_leader;
                goto up;
        }
out:
        read_unlock(&tasklist_lock);
}

#ifndef ARCH_MIN_MMSTRUCT_ALIGN
#define ARCH_MIN_MMSTRUCT_ALIGN 0
#endif

static void sighand_ctor(void *data)
{
        struct sighand_struct *sighand = data;

        spin_lock_init(&sighand->siglock);
        init_waitqueue_head(&sighand->signalfd_wqh);
}

void __init proc_caches_init(void)
{
        sighand_cachep = kmem_cache_create("sighand_cache",
                        sizeof(struct sighand_struct), 0,
                        SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
                        SLAB_ACCOUNT, sighand_ctor);
        signal_cachep = kmem_cache_create("signal_cache",
                        sizeof(struct signal_struct), 0,
                        SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
                        NULL);
        files_cachep = kmem_cache_create("files_cache",
                        sizeof(struct files_struct), 0,
                        SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
                        NULL);
        fs_cachep = kmem_cache_create("fs_cache",
                        sizeof(struct fs_struct), 0,
                        SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
                        NULL);
        /*
         * FIXME! The "sizeof(struct mm_struct)" currently includes the
         * whole struct cpumask for the OFFSTACK case. We could change
         * this to *only* allocate as much of it as required by the
         * maximum number of CPU's we can ever have.  The cpumask_allocation
         * is at the end of the structure, exactly for that reason.
         */
        mm_cachep = kmem_cache_create("mm_struct",
                        sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
                        SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
                        NULL);
        vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT);
        mmap_init();
        nsproxy_cache_init();
}

/*
 * Check constraints on flags passed to the unshare system call.
 */
static int check_unshare_flags(unsigned long unshare_flags)
{
        if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
                                CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
                                CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET|
                                CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP))
                return -EINVAL;
        /*
         * Not implemented, but pretend it works if there is nothing
         * to unshare.  Note that unsharing the address space or the
         * signal handlers also need to unshare the signal queues (aka
         * CLONE_THREAD).
         */
        if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) {
                if (!thread_group_empty(current))
                        return -EINVAL;
        }
        if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) {
                if (atomic_read(&current->sighand->count) > 1)
                        return -EINVAL;
        }
        if (unshare_flags & CLONE_VM) {
                if (!current_is_single_threaded())
                        return -EINVAL;
        }

        return 0;
}

/*
 * Unshare the filesystem structure if it is being shared
 */
static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
{
        struct fs_struct *fs = current->fs;

        if (!(unshare_flags & CLONE_FS) || !fs)
                return 0;

        /* don't need lock here; in the worst case we'll do useless copy */
        if (fs->users == 1)
                return 0;

        *new_fsp = copy_fs_struct(fs);
        if (!*new_fsp)
                return -ENOMEM;

        return 0;
}

/*
 * Unshare file descriptor table if it is being shared
 */
static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
{
        struct files_struct *fd = current->files;
        int error = 0;

        if ((unshare_flags & CLONE_FILES) &&
            (fd && atomic_read(&fd->count) > 1)) {
                *new_fdp = dup_fd(fd, &error);
                if (!*new_fdp)
                        return error;
        }

        return 0;
}

/*
 * unshare allows a process to 'unshare' part of the process
 * context which was originally shared using clone.  copy_*
 * functions used by do_fork() cannot be used here directly
 * because they modify an inactive task_struct that is being
 * constructed. Here we are modifying the current, active,
 * task_struct.
 */
SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
{
        struct fs_struct *fs, *new_fs = NULL;
        struct files_struct *fd, *new_fd = NULL;
        struct cred *new_cred = NULL;
        struct nsproxy *new_nsproxy = NULL;
        int do_sysvsem = 0;
        int err;

        /*
         * If unsharing a user namespace must also unshare the thread group
         * and unshare the filesystem root and working directories.
         */
        if (unshare_flags & CLONE_NEWUSER)
                unshare_flags |= CLONE_THREAD | CLONE_FS;
        /*
         * If unsharing vm, must also unshare signal handlers.
         */
        if (unshare_flags & CLONE_VM)
                unshare_flags |= CLONE_SIGHAND;
        /*
         * If unsharing a signal handlers, must also unshare the signal queues.
         */
        if (unshare_flags & CLONE_SIGHAND)
                unshare_flags |= CLONE_THREAD;
        /*
         * If unsharing namespace, must also unshare filesystem information.
         */
        if (unshare_flags & CLONE_NEWNS)
                unshare_flags |= CLONE_FS;

        if ((unshare_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) {
                err = -EPERM;
                if (!capable(CAP_SYS_ADMIN))
                        goto bad_unshare_out;
        }

        err = check_unshare_flags(unshare_flags);
        if (err)
                goto bad_unshare_out;
        /*
         * CLONE_NEWIPC must also detach from the undolist: after switching
         * to a new ipc namespace, the semaphore arrays from the old
         * namespace are unreachable.
         */
        if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM))
                do_sysvsem = 1;
        err = unshare_fs(unshare_flags, &new_fs);
        if (err)
                goto bad_unshare_out;
        err = unshare_fd(unshare_flags, &new_fd);
        if (err)
                goto bad_unshare_cleanup_fs;
        err = unshare_userns(unshare_flags, &new_cred);
        if (err)
                goto bad_unshare_cleanup_fd;
        err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
                                         new_cred, new_fs);
        if (err)
                goto bad_unshare_cleanup_cred;

        if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) {
                if (do_sysvsem) {
                        /*
                         * CLONE_SYSVSEM is equivalent to sys_exit().
                         */
                        exit_sem(current);
                }
                if (unshare_flags & CLONE_NEWIPC) {
                        /* Orphan segments in old ns (see sem above). */
                        exit_shm(current);
                        shm_init_task(current);
                }

                if (new_nsproxy)
                        switch_task_namespaces(current, new_nsproxy);

                task_lock(current);

                if (new_fs) {
                        fs = current->fs;
                        spin_lock(&fs->lock);
                        current->fs = new_fs;
                        if (--fs->users)
                                new_fs = NULL;
                        else
                                new_fs = fs;
                        spin_unlock(&fs->lock);
                }

                if (new_fd) {
                        fd = current->files;
                        current->files = new_fd;
                        new_fd = fd;
                }

                task_unlock(current);

                if (new_cred) {
                        /* Install the new user namespace */
                        commit_creds(new_cred);
                        new_cred = NULL;
                }
        }

        perf_event_namespaces(current);

bad_unshare_cleanup_cred:
        if (new_cred)
                put_cred(new_cred);
bad_unshare_cleanup_fd:
        if (new_fd)
                put_files_struct(new_fd);

bad_unshare_cleanup_fs:
        if (new_fs)
                free_fs_struct(new_fs);

bad_unshare_out:
        return err;
}

/*
 *      Helper to unshare the files of the current task.
 *      We don't want to expose copy_files internals to
 *      the exec layer of the kernel.
 */

int unshare_files(struct files_struct **displaced)
{
        struct task_struct *task = current;
        struct files_struct *copy = NULL;
        int error;

        error = unshare_fd(CLONE_FILES, &copy);
        if (error || !copy) {
                *displaced = NULL;
                return error;
        }
        *displaced = task->files;
        task_lock(task);
        task->files = copy;
        task_unlock(task);
        return 0;
}

int sysctl_max_threads(struct ctl_table *table, int write,
                       void __user *buffer, size_t *lenp, loff_t *ppos)
{
        struct ctl_table t;
        int ret;
        int threads = max_threads;
        int min = 1;
        int max = MAX_THREADS;

        t = *table;
        t.data = &threads;
        t.extra1 = &min;
        t.extra2 = &max;

        ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
        if (ret || !write)
                return ret;

        max_threads = threads;

        return 0;
}