linux/kernel/fork.c
David Rientjes a63d83f427 oom: badness heuristic rewrite
This a complete rewrite of the oom killer's badness() heuristic which is
used to determine which task to kill in oom conditions.  The goal is to
make it as simple and predictable as possible so the results are better
understood and we end up killing the task which will lead to the most
memory freeing while still respecting the fine-tuning from userspace.

Instead of basing the heuristic on mm->total_vm for each task, the task's
rss and swap space is used instead.  This is a better indication of the
amount of memory that will be freeable if the oom killed task is chosen
and subsequently exits.  This helps specifically in cases where KDE or
GNOME is chosen for oom kill on desktop systems instead of a memory
hogging task.

The baseline for the heuristic is a proportion of memory that each task is
currently using in memory plus swap compared to the amount of "allowable"
memory.  "Allowable," in this sense, means the system-wide resources for
unconstrained oom conditions, the set of mempolicy nodes, the mems
attached to current's cpuset, or a memory controller's limit.  The
proportion is given on a scale of 0 (never kill) to 1000 (always kill),
roughly meaning that if a task has a badness() score of 500 that the task
consumes approximately 50% of allowable memory resident in RAM or in swap
space.

The proportion is always relative to the amount of "allowable" memory and
not the total amount of RAM systemwide so that mempolicies and cpusets may
operate in isolation; they shall not need to know the true size of the
machine on which they are running if they are bound to a specific set of
nodes or mems, respectively.

Root tasks are given 3% extra memory just like __vm_enough_memory()
provides in LSMs.  In the event of two tasks consuming similar amounts of
memory, it is generally better to save root's task.

Because of the change in the badness() heuristic's baseline, it is also
necessary to introduce a new user interface to tune it.  It's not possible
to redefine the meaning of /proc/pid/oom_adj with a new scale since the
ABI cannot be changed for backward compatability.  Instead, a new tunable,
/proc/pid/oom_score_adj, is added that ranges from -1000 to +1000.  It may
be used to polarize the heuristic such that certain tasks are never
considered for oom kill while others may always be considered.  The value
is added directly into the badness() score so a value of -500, for
example, means to discount 50% of its memory consumption in comparison to
other tasks either on the system, bound to the mempolicy, in the cpuset,
or sharing the same memory controller.

/proc/pid/oom_adj is changed so that its meaning is rescaled into the
units used by /proc/pid/oom_score_adj, and vice versa.  Changing one of
these per-task tunables will rescale the value of the other to an
equivalent meaning.  Although /proc/pid/oom_adj was originally defined as
a bitshift on the badness score, it now shares the same linear growth as
/proc/pid/oom_score_adj but with different granularity.  This is required
so the ABI is not broken with userspace applications and allows oom_adj to
be deprecated for future removal.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-08-09 20:45:02 -07:00

1754 lines
42 KiB
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/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/fs.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/swap.h>
#include <linux/syscalls.h>
#include <linux/jiffies.h>
#include <linux/tracehook.h>
#include <linux/futex.h>
#include <linux/compat.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/profile.h>
#include <linux/rmap.h>
#include <linux/ksm.h>
#include <linux/acct.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/proc_fs.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 <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <trace/events/sched.h>
/*
* 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;
}
#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
# define alloc_task_struct() kmem_cache_alloc(task_struct_cachep, GFP_KERNEL)
# define free_task_struct(tsk) kmem_cache_free(task_struct_cachep, (tsk))
static struct kmem_cache *task_struct_cachep;
#endif
#ifndef __HAVE_ARCH_THREAD_INFO_ALLOCATOR
static inline struct thread_info *alloc_thread_info(struct task_struct *tsk)
{
#ifdef CONFIG_DEBUG_STACK_USAGE
gfp_t mask = GFP_KERNEL | __GFP_ZERO;
#else
gfp_t mask = GFP_KERNEL;
#endif
return (struct thread_info *)__get_free_pages(mask, THREAD_SIZE_ORDER);
}
static inline void free_thread_info(struct thread_info *ti)
{
free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
}
#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 */
struct kmem_cache *vm_area_cachep;
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
static void account_kernel_stack(struct thread_info *ti, int account)
{
struct zone *zone = page_zone(virt_to_page(ti));
mod_zone_page_state(zone, NR_KERNEL_STACK, account);
}
void free_task(struct task_struct *tsk)
{
prop_local_destroy_single(&tsk->dirties);
account_kernel_stack(tsk->stack, -1);
free_thread_info(tsk->stack);
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);
static inline void free_signal_struct(struct signal_struct *sig)
{
taskstats_tgid_free(sig);
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);
exit_creds(tsk);
delayacct_tsk_free(tsk);
put_signal_struct(tsk->signal);
if (!profile_handoff_task(tsk))
free_task(tsk);
}
/*
* macro override instead of weak attribute alias, to workaround
* gcc 4.1.0 and 4.1.1 bugs with weak attribute and empty functions.
*/
#ifndef arch_task_cache_init
#define arch_task_cache_init()
#endif
void __init fork_init(unsigned long mempages)
{
#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
#ifndef ARCH_MIN_TASKALIGN
#define ARCH_MIN_TASKALIGN L1_CACHE_BYTES
#endif
/* create a slab on which task_structs can be allocated */
task_struct_cachep =
kmem_cache_create("task_struct", sizeof(struct task_struct),
ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL);
#endif
/* do the arch specific task caches init */
arch_task_cache_init();
/*
* The default maximum number of threads is set to a safe
* value: the thread structures can take up at most half
* of memory.
*/
max_threads = mempages / (8 * THREAD_SIZE / PAGE_SIZE);
/*
* we need to allow at least 20 threads to boot a system
*/
if(max_threads < 20)
max_threads = 20;
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];
}
int __attribute__((weak)) arch_dup_task_struct(struct task_struct *dst,
struct task_struct *src)
{
*dst = *src;
return 0;
}
static struct task_struct *dup_task_struct(struct task_struct *orig)
{
struct task_struct *tsk;
struct thread_info *ti;
unsigned long *stackend;
int err;
prepare_to_copy(orig);
tsk = alloc_task_struct();
if (!tsk)
return NULL;
ti = alloc_thread_info(tsk);
if (!ti) {
free_task_struct(tsk);
return NULL;
}
err = arch_dup_task_struct(tsk, orig);
if (err)
goto out;
tsk->stack = ti;
err = prop_local_init_single(&tsk->dirties);
if (err)
goto out;
setup_thread_stack(tsk, orig);
clear_user_return_notifier(tsk);
stackend = end_of_stack(tsk);
*stackend = STACK_END_MAGIC; /* for overflow detection */
#ifdef CONFIG_CC_STACKPROTECTOR
tsk->stack_canary = get_random_int();
#endif
/* One for us, one for whoever does the "release_task()" (usually parent) */
atomic_set(&tsk->usage,2);
atomic_set(&tsk->fs_excl, 0);
#ifdef CONFIG_BLK_DEV_IO_TRACE
tsk->btrace_seq = 0;
#endif
tsk->splice_pipe = NULL;
account_kernel_stack(ti, 1);
return tsk;
out:
free_thread_info(ti);
free_task_struct(tsk);
return NULL;
}
#ifdef CONFIG_MMU
static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
{
struct vm_area_struct *mpnt, *tmp, **pprev;
struct rb_node **rb_link, *rb_parent;
int retval;
unsigned long charge;
struct mempolicy *pol;
down_write(&oldmm->mmap_sem);
flush_cache_dup_mm(oldmm);
/*
* Not linked in yet - no deadlock potential:
*/
down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
mm->locked_vm = 0;
mm->mmap = NULL;
mm->mmap_cache = NULL;
mm->free_area_cache = oldmm->mmap_base;
mm->cached_hole_size = ~0UL;
mm->map_count = 0;
cpumask_clear(mm_cpumask(mm));
mm->mm_rb = RB_ROOT;
rb_link = &mm->mm_rb.rb_node;
rb_parent = NULL;
pprev = &mm->mmap;
retval = ksm_fork(mm, oldmm);
if (retval)
goto out;
for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
struct file *file;
if (mpnt->vm_flags & VM_DONTCOPY) {
long pages = vma_pages(mpnt);
mm->total_vm -= pages;
vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
-pages);
continue;
}
charge = 0;
if (mpnt->vm_flags & VM_ACCOUNT) {
unsigned int len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
if (security_vm_enough_memory(len))
goto fail_nomem;
charge = len;
}
tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
if (!tmp)
goto fail_nomem;
*tmp = *mpnt;
INIT_LIST_HEAD(&tmp->anon_vma_chain);
pol = mpol_dup(vma_policy(mpnt));
retval = PTR_ERR(pol);
if (IS_ERR(pol))
goto fail_nomem_policy;
vma_set_policy(tmp, pol);
if (anon_vma_fork(tmp, mpnt))
goto fail_nomem_anon_vma_fork;
tmp->vm_flags &= ~VM_LOCKED;
tmp->vm_mm = mm;
tmp->vm_next = NULL;
file = tmp->vm_file;
if (file) {
struct inode *inode = file->f_path.dentry->d_inode;
struct address_space *mapping = file->f_mapping;
get_file(file);
if (tmp->vm_flags & VM_DENYWRITE)
atomic_dec(&inode->i_writecount);
spin_lock(&mapping->i_mmap_lock);
if (tmp->vm_flags & VM_SHARED)
mapping->i_mmap_writable++;
tmp->vm_truncate_count = mpnt->vm_truncate_count;
flush_dcache_mmap_lock(mapping);
/* insert tmp into the share list, just after mpnt */
vma_prio_tree_add(tmp, mpnt);
flush_dcache_mmap_unlock(mapping);
spin_unlock(&mapping->i_mmap_lock);
}
/*
* 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;
__vma_link_rb(mm, tmp, rb_link, rb_parent);
rb_link = &tmp->vm_rb.rb_right;
rb_parent = &tmp->vm_rb;
mm->map_count++;
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 */
arch_dup_mmap(oldmm, mm);
retval = 0;
out:
up_write(&mm->mmap_sem);
flush_tlb_mm(oldmm);
up_write(&oldmm->mmap_sem);
return retval;
fail_nomem_anon_vma_fork:
mpol_put(pol);
fail_nomem_policy:
kmem_cache_free(vm_area_cachep, 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
#define dup_mmap(mm, oldmm) (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);
INIT_HLIST_HEAD(&mm->ioctx_list);
#endif
}
static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
{
atomic_set(&mm->mm_users, 1);
atomic_set(&mm->mm_count, 1);
init_rwsem(&mm->mmap_sem);
INIT_LIST_HEAD(&mm->mmlist);
mm->flags = (current->mm) ?
(current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
mm->core_state = NULL;
mm->nr_ptes = 0;
memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
spin_lock_init(&mm->page_table_lock);
mm->free_area_cache = TASK_UNMAPPED_BASE;
mm->cached_hole_size = ~0UL;
mm_init_aio(mm);
mm_init_owner(mm, p);
if (likely(!mm_alloc_pgd(mm))) {
mm->def_flags = 0;
mmu_notifier_mm_init(mm);
return 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) {
memset(mm, 0, sizeof(*mm));
mm = mm_init(mm, current);
}
return mm;
}
/*
* 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);
mmu_notifier_mm_destroy(mm);
free_mm(mm);
}
EXPORT_SYMBOL_GPL(__mmdrop);
/*
* 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)) {
exit_aio(mm);
ksm_exit(mm);
exit_mmap(mm);
set_mm_exe_file(mm, NULL);
if (!list_empty(&mm->mmlist)) {
spin_lock(&mmlist_lock);
list_del(&mm->mmlist);
spin_unlock(&mmlist_lock);
}
put_swap_token(mm);
if (mm->binfmt)
module_put(mm->binfmt->module);
mmdrop(mm);
}
}
EXPORT_SYMBOL_GPL(mmput);
/**
* 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
atomic_inc(&mm->mm_users);
}
task_unlock(task);
return mm;
}
EXPORT_SYMBOL_GPL(get_task_mm);
/* 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
*/
void mm_release(struct task_struct *tsk, struct mm_struct *mm)
{
struct completion *vfork_done = tsk->vfork_done;
/* Get rid of any futexes when releasing the mm */
#ifdef CONFIG_FUTEX
if (unlikely(tsk->robust_list)) {
exit_robust_list(tsk);
tsk->robust_list = NULL;
}
#ifdef CONFIG_COMPAT
if (unlikely(tsk->compat_robust_list)) {
compat_exit_robust_list(tsk);
tsk->compat_robust_list = NULL;
}
#endif
if (unlikely(!list_empty(&tsk->pi_state_list)))
exit_pi_state_list(tsk);
#endif
/* Get rid of any cached register state */
deactivate_mm(tsk, mm);
/* notify parent sleeping on vfork() */
if (vfork_done) {
tsk->vfork_done = NULL;
complete(vfork_done);
}
/*
* If we're exiting normally, clear a user-space tid field if
* requested. We leave this alone when dying by signal, to leave
* the value intact in a core dump, and to save the unnecessary
* trouble otherwise. Userland only wants this done for a sys_exit.
*/
if (tsk->clear_child_tid) {
if (!(tsk->flags & PF_SIGNALED) &&
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;
}
}
/*
* 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));
/* Initializing for Swap token stuff */
mm->token_priority = 0;
mm->last_interval = 0;
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;
}
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;
if (clone_flags & CLONE_VM) {
atomic_inc(&oldmm->mm_users);
mm = oldmm;
goto good_mm;
}
retval = -ENOMEM;
mm = dup_mm(tsk);
if (!mm)
goto fail_nomem;
good_mm:
/* Initializing for Swap token stuff */
mm->token_priority = 0;
mm->last_interval = 0;
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 */
write_lock(&fs->lock);
if (fs->in_exec) {
write_unlock(&fs->lock);
return -EAGAIN;
}
fs->users++;
write_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;
if (!ioc)
return 0;
/*
* Share io context with parent, if CLONE_IO is set
*/
if (clone_flags & CLONE_IO) {
tsk->io_context = ioc_task_link(ioc);
if (unlikely(!tsk->io_context))
return -ENOMEM;
} else if (ioprio_valid(ioc->ioprio)) {
tsk->io_context = alloc_io_context(GFP_KERNEL, -1);
if (unlikely(!tsk->io_context))
return -ENOMEM;
tsk->io_context->ioprio = ioc->ioprio;
}
#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);
memcpy(sig->action, current->sighand->action, sizeof(sig->action));
return 0;
}
void __cleanup_sighand(struct sighand_struct *sighand)
{
if (atomic_dec_and_test(&sighand->count))
kmem_cache_free(sighand_cachep, sighand);
}
/*
* Initialize POSIX timer handling for a thread group.
*/
static void posix_cpu_timers_init_group(struct signal_struct *sig)
{
unsigned long cpu_limit;
/* Thread group counters. */
thread_group_cputime_init(sig);
cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
if (cpu_limit != RLIM_INFINITY) {
sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit);
sig->cputimer.running = 1;
}
/* The timer lists. */
INIT_LIST_HEAD(&sig->cpu_timers[0]);
INIT_LIST_HEAD(&sig->cpu_timers[1]);
INIT_LIST_HEAD(&sig->cpu_timers[2]);
}
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);
init_waitqueue_head(&sig->wait_chldexit);
if (clone_flags & CLONE_NEWPID)
sig->flags |= SIGNAL_UNKILLABLE;
sig->curr_target = tsk;
init_sigpending(&sig->shared_pending);
INIT_LIST_HEAD(&sig->posix_timers);
hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
sig->real_timer.function = it_real_fn;
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);
sig->oom_adj = current->signal->oom_adj;
sig->oom_score_adj = current->signal->oom_score_adj;
return 0;
}
static void copy_flags(unsigned long clone_flags, struct task_struct *p)
{
unsigned long new_flags = p->flags;
new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
new_flags |= PF_FORKNOEXEC;
new_flags |= PF_STARTING;
p->flags = new_flags;
clear_freeze_flag(p);
}
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
plist_head_init_raw(&p->pi_waiters, &p->pi_lock);
p->pi_blocked_on = NULL;
#endif
}
#ifdef CONFIG_MM_OWNER
void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
{
mm->owner = p;
}
#endif /* CONFIG_MM_OWNER */
/*
* Initialize POSIX timer handling for a single task.
*/
static void posix_cpu_timers_init(struct task_struct *tsk)
{
tsk->cputime_expires.prof_exp = cputime_zero;
tsk->cputime_expires.virt_exp = cputime_zero;
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]);
}
/*
* 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 struct task_struct *copy_process(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *child_tidptr,
struct pid *pid,
int trace)
{
int retval;
struct task_struct *p;
int cgroup_callbacks_done = 0;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
/*
* 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);
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
retval = -ENOMEM;
p = dup_task_struct(current);
if (!p)
goto fork_out;
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 (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
p->real_cred->user != INIT_USER)
goto bad_fork_free;
}
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;
if (!try_module_get(task_thread_info(p)->exec_domain->module))
goto bad_fork_cleanup_count;
p->did_exec = 0;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
copy_flags(clone_flags, p);
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 = cputime_zero;
p->stime = cputime_zero;
p->gtime = cputime_zero;
p->utimescaled = cputime_zero;
p->stimescaled = cputime_zero;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
p->prev_utime = cputime_zero;
p->prev_stime = cputime_zero;
#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->lock_depth = -1; /* -1 = no lock */
do_posix_clock_monotonic_gettime(&p->start_time);
p->real_start_time = p->start_time;
monotonic_to_bootbased(&p->real_start_time);
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_cgroup;
}
mpol_fix_fork_child_flag(p);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
p->irq_events = 0;
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
p->hardirqs_enabled = 1;
#else
p->hardirqs_enabled = 0;
#endif
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
#ifdef CONFIG_LOCKDEP
p->lockdep_depth = 0; /* no locks held yet */
p->curr_chain_key = 0;
p->lockdep_recursion = 0;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
p->memcg_batch.do_batch = 0;
p->memcg_batch.memcg = NULL;
#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags);
retval = perf_event_init_task(p);
if (retval)
goto bad_fork_cleanup_policy;
if ((retval = audit_alloc(p)))
goto bad_fork_cleanup_policy;
/* copy all the process information */
if ((retval = copy_semundo(clone_flags, p)))
goto bad_fork_cleanup_audit;
if ((retval = copy_files(clone_flags, p)))
goto bad_fork_cleanup_semundo;
if ((retval = copy_fs(clone_flags, p)))
goto bad_fork_cleanup_files;
if ((retval = copy_sighand(clone_flags, p)))
goto bad_fork_cleanup_fs;
if ((retval = copy_signal(clone_flags, p)))
goto bad_fork_cleanup_sighand;
if ((retval = copy_mm(clone_flags, p)))
goto bad_fork_cleanup_signal;
if ((retval = copy_namespaces(clone_flags, p)))
goto bad_fork_cleanup_mm;
if ((retval = copy_io(clone_flags, p)))
goto bad_fork_cleanup_namespaces;
retval = copy_thread(clone_flags, stack_start, stack_size, p, regs);
if (retval)
goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
retval = -ENOMEM;
pid = alloc_pid(p->nsproxy->pid_ns);
if (!pid)
goto bad_fork_cleanup_io;
if (clone_flags & CLONE_NEWPID) {
retval = pid_ns_prepare_proc(p->nsproxy->pid_ns);
if (retval < 0)
goto bad_fork_free_pid;
}
}
p->pid = pid_nr(pid);
p->tgid = p->pid;
if (clone_flags & CLONE_THREAD)
p->tgid = current->tgid;
if (current->nsproxy != p->nsproxy) {
retval = ns_cgroup_clone(p, pid);
if (retval)
goto bad_fork_free_pid;
}
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;
#ifdef CONFIG_FUTEX
p->robust_list = NULL;
#ifdef CONFIG_COMPAT
p->compat_robust_list = NULL;
#endif
INIT_LIST_HEAD(&p->pi_state_list);
p->pi_state_cache = NULL;
#endif
/*
* sigaltstack should be cleared when sharing the same VM
*/
if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
p->sas_ss_sp = p->sas_ss_size = 0;
/*
* 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->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
p->pdeath_signal = 0;
p->exit_state = 0;
/*
* Ok, make it visible to the rest of the system.
* We dont wake it up yet.
*/
p->group_leader = p;
INIT_LIST_HEAD(&p->thread_group);
/* Now that the task is set up, run cgroup callbacks if
* necessary. We need to run them before the task is visible
* on the tasklist. */
cgroup_fork_callbacks(p);
cgroup_callbacks_done = 1;
/* 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;
}
spin_lock(&current->sighand->siglock);
/*
* 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)) {
spin_unlock(&current->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
goto bad_fork_free_pid;
}
if (clone_flags & CLONE_THREAD) {
current->signal->nr_threads++;
atomic_inc(&current->signal->live);
atomic_inc(&current->signal->sigcnt);
p->group_leader = current->group_leader;
list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
}
if (likely(p->pid)) {
tracehook_finish_clone(p, clone_flags, trace);
if (thread_group_leader(p)) {
if (clone_flags & CLONE_NEWPID)
p->nsproxy->pid_ns->child_reaper = p;
p->signal->leader_pid = pid;
p->signal->tty = tty_kref_get(current->signal->tty);
attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
attach_pid(p, PIDTYPE_SID, task_session(current));
list_add_tail(&p->sibling, &p->real_parent->children);
list_add_tail_rcu(&p->tasks, &init_task.tasks);
__get_cpu_var(process_counts)++;
}
attach_pid(p, PIDTYPE_PID, pid);
nr_threads++;
}
total_forks++;
spin_unlock(&current->sighand->siglock);
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
perf_event_fork(p);
return p;
bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
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)
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_audit:
audit_free(p);
bad_fork_cleanup_policy:
perf_event_free_task(p);
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
#endif
cgroup_exit(p, cgroup_callbacks_done);
delayacct_tsk_free(p);
module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
exit_creds(p);
bad_fork_free:
free_task(p);
fork_out:
return ERR_PTR(retval);
}
noinline struct pt_regs * __cpuinit __attribute__((weak)) idle_regs(struct pt_regs *regs)
{
memset(regs, 0, sizeof(struct pt_regs));
return regs;
}
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 * __cpuinit fork_idle(int cpu)
{
struct task_struct *task;
struct pt_regs regs;
task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL,
&init_struct_pid, 0);
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,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
long nr;
/*
* Do some preliminary argument and permissions checking before we
* actually start allocating stuff
*/
if (clone_flags & CLONE_NEWUSER) {
if (clone_flags & CLONE_THREAD)
return -EINVAL;
/* hopefully this check will go away when userns support is
* complete
*/
if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
!capable(CAP_SETGID))
return -EPERM;
}
/*
* We hope to recycle these flags after 2.6.26
*/
if (unlikely(clone_flags & CLONE_STOPPED)) {
static int __read_mostly count = 100;
if (count > 0 && printk_ratelimit()) {
char comm[TASK_COMM_LEN];
count--;
printk(KERN_INFO "fork(): process `%s' used deprecated "
"clone flags 0x%lx\n",
get_task_comm(comm, current),
clone_flags & CLONE_STOPPED);
}
}
/*
* When called from kernel_thread, don't do user tracing stuff.
*/
if (likely(user_mode(regs)))
trace = tracehook_prepare_clone(clone_flags);
p = copy_process(clone_flags, stack_start, regs, stack_size,
child_tidptr, NULL, trace);
/*
* 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;
trace_sched_process_fork(current, p);
nr = task_pid_vnr(p);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
}
audit_finish_fork(p);
tracehook_report_clone(regs, clone_flags, nr, p);
/*
* We set PF_STARTING at creation in case tracing wants to
* use this to distinguish a fully live task from one that
* hasn't gotten to tracehook_report_clone() yet. Now we
* clear it and set the child going.
*/
p->flags &= ~PF_STARTING;
if (unlikely(clone_flags & CLONE_STOPPED)) {
/*
* We'll start up with an immediate SIGSTOP.
*/
sigaddset(&p->pending.signal, SIGSTOP);
set_tsk_thread_flag(p, TIF_SIGPENDING);
__set_task_state(p, TASK_STOPPED);
} else {
wake_up_new_task(p, clone_flags);
}
tracehook_report_clone_complete(trace, regs,
clone_flags, nr, p);
if (clone_flags & CLONE_VFORK) {
freezer_do_not_count();
wait_for_completion(&vfork);
freezer_count();
tracehook_report_vfork_done(p, nr);
}
} else {
nr = PTR_ERR(p);
}
return nr;
}
#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_DESTROY_BY_RCU|
SLAB_NOTRACK, sighand_ctor);
signal_cachep = kmem_cache_create("signal_cache",
sizeof(struct signal_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
files_cachep = kmem_cache_create("files_cache",
sizeof(struct files_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
fs_cachep = kmem_cache_create("fs_cache",
sizeof(struct fs_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
mm_cachep = kmem_cache_create("mm_struct",
sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC);
mmap_init();
}
/*
* Check constraints on flags passed to the unshare system call and
* force unsharing of additional process context as appropriate.
*/
static void check_unshare_flags(unsigned long *flags_ptr)
{
/*
* If unsharing a thread from a thread group, must also
* unshare vm.
*/
if (*flags_ptr & CLONE_THREAD)
*flags_ptr |= CLONE_VM;
/*
* If unsharing vm, must also unshare signal handlers.
*/
if (*flags_ptr & CLONE_VM)
*flags_ptr |= CLONE_SIGHAND;
/*
* If unsharing namespace, must also unshare filesystem information.
*/
if (*flags_ptr & CLONE_NEWNS)
*flags_ptr |= CLONE_FS;
}
/*
* Unsharing of tasks created with CLONE_THREAD is not supported yet
*/
static int unshare_thread(unsigned long unshare_flags)
{
if (unshare_flags & CLONE_THREAD)
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;
}
/*
* Unsharing of sighand is not supported yet
*/
static int unshare_sighand(unsigned long unshare_flags, struct sighand_struct **new_sighp)
{
struct sighand_struct *sigh = current->sighand;
if ((unshare_flags & CLONE_SIGHAND) && atomic_read(&sigh->count) > 1)
return -EINVAL;
else
return 0;
}
/*
* Unshare vm if it is being shared
*/
static int unshare_vm(unsigned long unshare_flags, struct mm_struct **new_mmp)
{
struct mm_struct *mm = current->mm;
if ((unshare_flags & CLONE_VM) &&
(mm && atomic_read(&mm->mm_users) > 1)) {
return -EINVAL;
}
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)
{
int err = 0;
struct fs_struct *fs, *new_fs = NULL;
struct sighand_struct *new_sigh = NULL;
struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL;
struct files_struct *fd, *new_fd = NULL;
struct nsproxy *new_nsproxy = NULL;
int do_sysvsem = 0;
check_unshare_flags(&unshare_flags);
/* Return -EINVAL for all unsupported flags */
err = -EINVAL;
if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET))
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;
if ((err = unshare_thread(unshare_flags)))
goto bad_unshare_out;
if ((err = unshare_fs(unshare_flags, &new_fs)))
goto bad_unshare_cleanup_thread;
if ((err = unshare_sighand(unshare_flags, &new_sigh)))
goto bad_unshare_cleanup_fs;
if ((err = unshare_vm(unshare_flags, &new_mm)))
goto bad_unshare_cleanup_sigh;
if ((err = unshare_fd(unshare_flags, &new_fd)))
goto bad_unshare_cleanup_vm;
if ((err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
new_fs)))
goto bad_unshare_cleanup_fd;
if (new_fs || new_mm || new_fd || do_sysvsem || new_nsproxy) {
if (do_sysvsem) {
/*
* CLONE_SYSVSEM is equivalent to sys_exit().
*/
exit_sem(current);
}
if (new_nsproxy) {
switch_task_namespaces(current, new_nsproxy);
new_nsproxy = NULL;
}
task_lock(current);
if (new_fs) {
fs = current->fs;
write_lock(&fs->lock);
current->fs = new_fs;
if (--fs->users)
new_fs = NULL;
else
new_fs = fs;
write_unlock(&fs->lock);
}
if (new_mm) {
mm = current->mm;
active_mm = current->active_mm;
current->mm = new_mm;
current->active_mm = new_mm;
activate_mm(active_mm, new_mm);
new_mm = mm;
}
if (new_fd) {
fd = current->files;
current->files = new_fd;
new_fd = fd;
}
task_unlock(current);
}
if (new_nsproxy)
put_nsproxy(new_nsproxy);
bad_unshare_cleanup_fd:
if (new_fd)
put_files_struct(new_fd);
bad_unshare_cleanup_vm:
if (new_mm)
mmput(new_mm);
bad_unshare_cleanup_sigh:
if (new_sigh)
if (atomic_dec_and_test(&new_sigh->count))
kmem_cache_free(sighand_cachep, new_sigh);
bad_unshare_cleanup_fs:
if (new_fs)
free_fs_struct(new_fs);
bad_unshare_cleanup_thread:
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;
}