#include <linux/ptrace.h>
#include <linux/mount.h>
#include <linux/audit.h>
+#include <linux/memcontrol.h>
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/acct.h>
#include <linux/taskstats_kern.h>
#include <linux/random.h>
#include <linux/tty.h>
+#include <linux/proc_fs.h>
+#include <linux/blkdev.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
void __put_task_struct(struct task_struct *tsk)
{
- WARN_ON(!(tsk->exit_state & (EXIT_DEAD | EXIT_ZOMBIE)));
+ WARN_ON(!tsk->exit_state);
WARN_ON(atomic_read(&tsk->usage));
WARN_ON(tsk == current);
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
ARCH_MIN_TASKALIGN, SLAB_PANIC, 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
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;
return NULL;
}
- *tsk = *orig;
+ err = arch_dup_task_struct(tsk, orig);
+ if (err)
+ goto out;
+
tsk->stack = ti;
err = prop_local_init_single(&tsk->dirties);
- if (err) {
- free_thread_info(ti);
- free_task_struct(tsk);
- return NULL;
- }
+ if (err)
+ goto out;
setup_thread_stack(tsk, orig);
#endif
tsk->splice_pipe = NULL;
return tsk;
+
+out:
+ free_thread_info(ti);
+ free_task_struct(tsk);
+ return NULL;
}
#ifdef CONFIG_MMU
-static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
+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;
if (!tmp)
goto fail_nomem;
*tmp = *mpnt;
- pol = mpol_copy(vma_policy(mpnt));
+ pol = mpol_dup(vma_policy(mpnt));
retval = PTR_ERR(pol);
if (IS_ERR(pol))
goto fail_nomem_policy;
static inline void mm_free_pgd(struct mm_struct * mm)
{
- pgd_free(mm->pgd);
+ pgd_free(mm, mm->pgd);
}
#else
#define dup_mmap(mm, oldmm) (0)
#include <linux/init_task.h>
-static struct mm_struct * mm_init(struct mm_struct * mm)
+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);
mm->ioctx_list = NULL;
mm->free_area_cache = TASK_UNMAPPED_BASE;
mm->cached_hole_size = ~0UL;
+ mm_init_owner(mm, p);
if (likely(!mm_alloc_pgd(mm))) {
mm->def_flags = 0;
return mm;
}
+
free_mm(mm);
return NULL;
}
mm = allocate_mm();
if (mm) {
memset(mm, 0, sizeof(*mm));
- mm = mm_init(mm);
+ mm = mm_init(mm, current);
}
return mm;
}
* is dropped: either by a lazy thread or by
* mmput. Free the page directory and the mm.
*/
-void fastcall __mmdrop(struct mm_struct *mm)
+void __mmdrop(struct mm_struct *mm)
{
BUG_ON(mm == &init_mm);
mm_free_pgd(mm);
destroy_context(mm);
free_mm(mm);
}
+EXPORT_SYMBOL_GPL(__mmdrop);
/*
* Decrement the use count and release all resources for an mm.
if (atomic_dec_and_test(&mm->mm_users)) {
exit_aio(mm);
exit_mmap(mm);
+ set_mm_exe_file(mm, NULL);
if (!list_empty(&mm->mmlist)) {
spin_lock(&mmlist_lock);
list_del(&mm->mmlist);
* 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 *dup_mm(struct task_struct *tsk)
{
struct mm_struct *mm, *oldmm = current->mm;
int err;
mm->token_priority = 0;
mm->last_interval = 0;
- if (!mm_init(mm))
+ if (!mm_init(mm, tsk))
goto fail_nomem;
if (init_new_context(tsk, mm))
goto fail_nocontext;
+ dup_mm_exe_file(oldmm, mm);
+
err = dup_mmap(mm, oldmm);
if (err)
goto free_pt;
return retval;
}
-static inline struct fs_struct *__copy_fs_struct(struct fs_struct *old)
+static struct fs_struct *__copy_fs_struct(struct fs_struct *old)
{
struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL);
/* We don't need to lock fs - think why ;-) */
rwlock_init(&fs->lock);
fs->umask = old->umask;
read_lock(&old->lock);
- fs->rootmnt = mntget(old->rootmnt);
- fs->root = dget(old->root);
- fs->pwdmnt = mntget(old->pwdmnt);
- fs->pwd = dget(old->pwd);
- if (old->altroot) {
- fs->altrootmnt = mntget(old->altrootmnt);
- fs->altroot = dget(old->altroot);
+ fs->root = old->root;
+ path_get(&old->root);
+ fs->pwd = old->pwd;
+ path_get(&old->pwd);
+ if (old->altroot.dentry) {
+ fs->altroot = old->altroot;
+ path_get(&old->altroot);
} else {
- fs->altrootmnt = NULL;
- fs->altroot = NULL;
+ fs->altroot.mnt = NULL;
+ fs->altroot.dentry = NULL;
}
read_unlock(&old->lock);
}
EXPORT_SYMBOL_GPL(copy_fs_struct);
-static inline int copy_fs(unsigned long clone_flags, struct task_struct * tsk)
+static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
{
if (clone_flags & CLONE_FS) {
atomic_inc(¤t->fs->count);
goto out;
}
- /*
- * Note: we may be using current for both targets (See exec.c)
- * This works because we cache current->files (old) as oldf. Don't
- * break this.
- */
- tsk->files = NULL;
newf = dup_fd(oldf, &error);
if (!newf)
goto out;
return error;
}
-/*
- * 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(void)
+static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
{
- struct files_struct *files = current->files;
- int rc;
-
- BUG_ON(!files);
+#ifdef CONFIG_BLOCK
+ struct io_context *ioc = current->io_context;
- /* This can race but the race causes us to copy when we don't
- need to and drop the copy */
- if(atomic_read(&files->count) == 1)
- {
- atomic_inc(&files->count);
+ 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;
}
- rc = copy_files(0, current);
- if(rc)
- current->files = files;
- return rc;
+#endif
+ return 0;
}
-EXPORT_SYMBOL(unshare_files);
-
-static inline int copy_sighand(unsigned long clone_flags, struct task_struct * tsk)
+static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
{
struct sighand_struct *sig;
kmem_cache_free(sighand_cachep, sighand);
}
-static inline int copy_signal(unsigned long clone_flags, struct task_struct * tsk)
+static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
{
struct signal_struct *sig;
int ret;
sig->group_exit_code = 0;
sig->group_exit_task = NULL;
sig->group_stop_count = 0;
- sig->curr_target = NULL;
+ 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->it_real_incr.tv64 = 0;
sig->real_timer.function = it_real_fn;
- sig->tsk = tsk;
sig->it_virt_expires = cputime_zero;
sig->it_virt_incr = cputime_zero;
kmem_cache_free(signal_cachep, sig);
}
-static inline void cleanup_signal(struct task_struct *tsk)
+static void cleanup_signal(struct task_struct *tsk)
{
struct signal_struct *sig = tsk->signal;
__cleanup_signal(sig);
}
-static inline void copy_flags(unsigned long clone_flags, struct task_struct *p)
+static void copy_flags(unsigned long clone_flags, struct task_struct *p)
{
unsigned long new_flags = p->flags;
{
current->clear_child_tid = tidptr;
- return current->pid;
+ return task_pid_vnr(current);
}
-static inline void rt_mutex_init_task(struct task_struct *p)
+static void rt_mutex_init_task(struct task_struct *p)
{
spin_lock_init(&p->pi_lock);
#ifdef CONFIG_RT_MUTEXES
#endif
}
+#ifdef CONFIG_MM_OWNER
+void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
+{
+ mm->owner = p;
+}
+#endif /* CONFIG_MM_OWNER */
+
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
- int __user *parent_tidptr,
int __user *child_tidptr,
struct pid *pid)
{
int retval;
- struct task_struct *p = NULL;
+ struct task_struct *p;
int cgroup_callbacks_done = 0;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
p->did_exec = 0;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
copy_flags(clone_flags, p);
- retval = -EFAULT;
- if (clone_flags & CLONE_PARENT_SETTID)
- if (put_user(p->pid, parent_tidptr))
- goto bad_fork_cleanup_delays_binfmt;
-
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
+#ifdef CONFIG_PREEMPT_RCU
+ p->rcu_read_lock_nesting = 0;
+ p->rcu_flipctr_idx = 0;
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
p->gtime = cputime_zero;
p->utimescaled = cputime_zero;
p->stimescaled = cputime_zero;
+ p->prev_utime = cputime_zero;
+ p->prev_stime = cputime_zero;
+
+#ifdef CONFIG_DETECT_SOFTLOCKUP
+ p->last_switch_count = 0;
+ p->last_switch_timestamp = 0;
+#endif
#ifdef CONFIG_TASK_XACCT
p->rchar = 0; /* I/O counter: bytes read */
#ifdef CONFIG_SECURITY
p->security = NULL;
#endif
+ p->cap_bset = current->cap_bset;
p->io_context = NULL;
p->audit_context = NULL;
cgroup_fork(p);
#ifdef CONFIG_NUMA
- p->mempolicy = mpol_copy(p->mempolicy);
+ p->mempolicy = mpol_dup(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
p->blocked_on = NULL; /* not blocked yet */
#endif
+ /* Perform scheduler related setup. Assign this task to a CPU. */
+ sched_fork(p, clone_flags);
+
if ((retval = security_task_alloc(p)))
goto bad_fork_cleanup_policy;
if ((retval = audit_alloc(p)))
goto bad_fork_cleanup_mm;
if ((retval = copy_namespaces(clone_flags, p)))
goto bad_fork_cleanup_keys;
+ if ((retval = copy_io(clone_flags, p)))
+ goto bad_fork_cleanup_namespaces;
retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
if (retval)
- goto bad_fork_cleanup_namespaces;
+ goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
retval = -ENOMEM;
pid = alloc_pid(task_active_pid_ns(p));
if (!pid)
- goto bad_fork_cleanup_namespaces;
+ goto bad_fork_cleanup_io;
+
+ if (clone_flags & CLONE_NEWPID) {
+ retval = pid_ns_prepare_proc(task_active_pid_ns(p));
+ if (retval < 0)
+ goto bad_fork_free_pid;
+ }
}
p->pid = pid_nr(pid);
#ifdef TIF_SYSCALL_EMU
clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
+ clear_all_latency_tracing(p);
/* Our parent execution domain becomes current domain
These must match for thread signalling to apply */
INIT_LIST_HEAD(&p->ptrace_children);
INIT_LIST_HEAD(&p->ptrace_list);
- /* Perform scheduler related setup. Assign this task to a CPU. */
- sched_fork(p, clone_flags);
-
/* 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. */
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
- /* for sys_ioprio_set(IOPRIO_WHO_PGRP) */
- p->ioprio = current->ioprio;
-
/*
* The task hasn't been attached yet, so its cpus_allowed mask will
* not be changed, nor will its assigned CPU.
* parent's CPU). This avoids alot of nasty races.
*/
p->cpus_allowed = current->cpus_allowed;
+ p->rt.nr_cpus_allowed = current->rt.nr_cpus_allowed;
if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
!cpu_online(task_cpu(p))))
set_task_cpu(p, smp_processor_id());
__ptrace_link(p, current->parent);
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 = current->signal->tty;
- p->signal->pgrp = task_pgrp_nr(current);
+ set_task_pgrp(p, task_pgrp_nr(current));
set_task_session(p, task_session_nr(current));
attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
attach_pid(p, PIDTYPE_SID, task_session(current));
-
list_add_tail_rcu(&p->tasks, &init_task.tasks);
__get_cpu_var(process_counts)++;
}
bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
+bad_fork_cleanup_io:
+ put_io_context(p->io_context);
bad_fork_cleanup_namespaces:
exit_task_namespaces(p);
bad_fork_cleanup_keys:
security_task_free(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
- mpol_free(p->mempolicy);
+ mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
#endif
cgroup_exit(p, cgroup_callbacks_done);
-bad_fork_cleanup_delays_binfmt:
delayacct_tsk_free(p);
if (p->binfmt)
module_put(p->binfmt->module);
return ERR_PTR(retval);
}
-noinline struct pt_regs * __devinit __attribute__((weak)) idle_regs(struct pt_regs *regs)
+noinline struct pt_regs * __cpuinit __attribute__((weak)) idle_regs(struct pt_regs *regs)
{
memset(regs, 0, sizeof(struct pt_regs));
return regs;
struct task_struct *task;
struct pt_regs regs;
- task = copy_process(CLONE_VM, 0, idle_regs(®s), 0, NULL, NULL,
+ task = copy_process(CLONE_VM, 0, idle_regs(®s), 0, NULL,
&init_struct_pid);
if (!IS_ERR(task))
init_idle(task, cpu);
return task;
}
-static inline int fork_traceflag (unsigned clone_flags)
+static int fork_traceflag(unsigned clone_flags)
{
if (clone_flags & CLONE_UNTRACED)
return 0;
int trace = 0;
long nr;
+ /*
+ * 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);
+ }
+ }
+
if (unlikely(current->ptrace)) {
trace = fork_traceflag (clone_flags);
if (trace)
}
p = copy_process(clone_flags, stack_start, regs, stack_size,
- parent_tidptr, child_tidptr, NULL);
+ child_tidptr, NULL);
/*
* 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;
- nr = pid_nr(task_pid(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;
if (!(clone_flags & CLONE_STOPPED))
wake_up_new_task(p, clone_flags);
else
- p->state = TASK_STOPPED;
+ __set_task_state(p, TASK_STOPPED);
if (unlikely (trace)) {
current->ptrace_message = nr;
* Check constraints on flags passed to the unshare system call and
* force unsharing of additional process context as appropriate.
*/
-static inline void check_unshare_flags(unsigned long *flags_ptr)
+static void check_unshare_flags(unsigned long *flags_ptr)
{
/*
* If unsharing a thread from a thread group, must also
}
/*
- * Unsharing of semundo for tasks created with CLONE_SYSVSEM is not
- * supported yet
- */
-static int unshare_semundo(unsigned long unshare_flags, struct sem_undo_list **new_ulistp)
-{
- if (unshare_flags & CLONE_SYSVSEM)
- return -EINVAL;
-
- 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
struct sighand_struct *new_sigh = NULL;
struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL;
struct files_struct *fd, *new_fd = NULL;
- struct sem_undo_list *new_ulist = NULL;
struct nsproxy *new_nsproxy = NULL;
+ int do_sysvsem = 0;
check_unshare_flags(&unshare_flags);
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_sigh;
if ((err = unshare_fd(unshare_flags, &new_fd)))
goto bad_unshare_cleanup_vm;
- if ((err = unshare_semundo(unshare_flags, &new_ulist)))
- goto bad_unshare_cleanup_fd;
if ((err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
new_fs)))
- goto bad_unshare_cleanup_semundo;
+ goto bad_unshare_cleanup_fd;
- if (new_fs || new_mm || new_fd || new_ulist || new_nsproxy) {
+ 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);
if (new_nsproxy)
put_nsproxy(new_nsproxy);
-bad_unshare_cleanup_semundo:
bad_unshare_cleanup_fd:
if (new_fd)
put_files_struct(new_fd);
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, ©);
+ if (error || !copy) {
+ *displaced = NULL;
+ return error;
+ }
+ *displaced = task->files;
+ task_lock(task);
+ task->files = copy;
+ task_unlock(task);
+ return 0;
+}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff