/*
* 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);
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
retval = -ENOMEM;
p = dup_task_struct(current);
if (!p)
goto fork_out;
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->user->processes) >=
p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
p->user != current->nsproxy->user_ns->root_user)
goto bad_fork_free;
}
atomic_inc(&p->user->__count);
atomic_inc(&p->user->processes);
get_group_info(p->group_info);
/*
* 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.
*/
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;
if (p->binfmt && !try_module_get(p->binfmt->module))
goto bad_fork_cleanup_put_domain;
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);
#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);
clear_tsk_thread_flag(p, TIF_SIGPENDING);
init_sigpending(&p->pending);
p->utime = cputime_zero;
p->stime = cputime_zero;
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
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
p->it_virt_expires = cputime_zero;
p->it_prof_expires = cputime_zero;
p->it_sched_expires = 0;
INIT_LIST_HEAD(&p->cpu_timers[0]);
INIT_LIST_HEAD(&p->cpu_timers[1]);
INIT_LIST_HEAD(&p->cpu_timers[2]);
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);
#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_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
/* 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_security;
/* 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_keys(clone_flags, 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_io;
if (pid != &init_struct_pid) {
retval = -ENOMEM;
pid = alloc_pid(task_active_pid_ns(p));
if (!pid)
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);
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 should be turned off in the child regardless
* of CLONE_PTRACE.
*/
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);
/*
* The task hasn't been attached yet, so its cpus_allowed mask will
* not be changed, nor will its assigned CPU.
*
* The cpus_allowed mask of the parent may have changed after it was
* copied first time - so re-copy it here, then check the child's CPU
* to ensure it is on a valid CPU (and if not, just force it back to
* parent's CPU). This avoids alot of nasty races.
*/
p->cpus_allowed = current->cpus_allowed;
if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
!cpu_online(task_cpu(p))))
set_task_cpu(p, smp_processor_id());
/* 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(¤t->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(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
goto bad_fork_free_pid;
}
if (clone_flags & CLONE_THREAD) {
atomic_inc(¤t->signal->count);
atomic_inc(¤t->signal->live);
p->group_leader = current->group_leader;
list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
if (!cputime_eq(current->signal->it_virt_expires,
cputime_zero) ||
!cputime_eq(current->signal->it_prof_expires,
cputime_zero) ||
current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY ||
!list_empty(¤t->signal->cpu_timers[0]) ||
!list_empty(¤t->signal->cpu_timers[1]) ||
!list_empty(¤t->signal->cpu_timers[2])) {
/*
* Have child wake up on its first tick to check
* for process CPU timers.
*/
p->it_prof_expires = jiffies_to_cputime(1);
}
}
if (likely(p->pid)) {
list_add_tail(&p->sibling, &p->real_parent->children);
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 = current->signal->tty;
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)++;
}
attach_pid(p, PIDTYPE_PID, pid);
nr_threads++;
}
total_forks++;
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
return p;
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:
exit_keys(p);
bad_fork_cleanup_mm:
if (p->mm)
mmput(p->mm);
bad_fork_cleanup_signal:
if (!(clone_flags & CLONE_THREAD))
__cleanup_signal(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_security:
security_task_free(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
#endif
cgroup_exit(p, cgroup_callbacks_done);
delayacct_tsk_free(p);
if (p->binfmt)
module_put(p->binfmt->module);
bad_fork_cleanup_put_domain:
module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
put_group_info(p->group_info);
atomic_dec(&p->user->processes);
free_uid(p->user);
bad_fork_free:
free_task(p);
fork_out:
return ERR_PTR(retval);
}
/* Actual dumper.
*
* This is a two-pass process; first we find the offsets of the bits,
* and then they are actually written out. If we run out of core limit
* we just truncate.
*/
static int irix_core_dump(long signr, struct pt_regs *regs, struct file *file, unsigned long limit)
{
int has_dumped = 0;
mm_segment_t fs;
int segs;
int i;
size_t size;
struct vm_area_struct *vma;
struct elfhdr elf;
off_t offset = 0, dataoff;
int numnote = 3;
struct memelfnote notes[3];
struct elf_prstatus prstatus; /* NT_PRSTATUS */
elf_fpregset_t fpu; /* NT_PRFPREG */
struct elf_prpsinfo psinfo; /* NT_PRPSINFO */
/* Count what's needed to dump, up to the limit of coredump size. */
segs = 0;
size = 0;
for (vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) {
if (maydump(vma))
{
int sz = vma->vm_end-vma->vm_start;
if (size+sz >= limit)
break;
else
size += sz;
}
segs++;
}
pr_debug("irix_core_dump: %d segs taking %d bytes\n", segs, size);
/* Set up header. */
memcpy(elf.e_ident, ELFMAG, SELFMAG);
elf.e_ident[EI_CLASS] = ELFCLASS32;
elf.e_ident[EI_DATA] = ELFDATA2LSB;
elf.e_ident[EI_VERSION] = EV_CURRENT;
elf.e_ident[EI_OSABI] = ELF_OSABI;
memset(elf.e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);
elf.e_type = ET_CORE;
elf.e_machine = ELF_ARCH;
elf.e_version = EV_CURRENT;
elf.e_entry = 0;
elf.e_phoff = sizeof(elf);
elf.e_shoff = 0;
elf.e_flags = 0;
elf.e_ehsize = sizeof(elf);
elf.e_phentsize = sizeof(struct elf_phdr);
elf.e_phnum = segs+1; /* Include notes. */
elf.e_shentsize = 0;
elf.e_shnum = 0;
elf.e_shstrndx = 0;
fs = get_fs();
set_fs(KERNEL_DS);
has_dumped = 1;
current->flags |= PF_DUMPCORE;
DUMP_WRITE(&elf, sizeof(elf));
offset += sizeof(elf); /* Elf header. */
offset += (segs+1) * sizeof(struct elf_phdr); /* Program headers. */
/* Set up the notes in similar form to SVR4 core dumps made
* with info from their /proc.
*/
memset(&psinfo, 0, sizeof(psinfo));
memset(&prstatus, 0, sizeof(prstatus));
notes[0].name = "CORE";
notes[0].type = NT_PRSTATUS;
notes[0].datasz = sizeof(prstatus);
notes[0].data = &prstatus;
prstatus.pr_info.si_signo = prstatus.pr_cursig = signr;
prstatus.pr_sigpend = current->pending.signal.sig[0];
prstatus.pr_sighold = current->blocked.sig[0];
psinfo.pr_pid = prstatus.pr_pid = current->pid;
psinfo.pr_ppid = prstatus.pr_ppid = current->parent->pid;
psinfo.pr_pgrp = prstatus.pr_pgrp = task_pgrp_nr(current);
psinfo.pr_sid = prstatus.pr_sid = task_session_nr(current);
if (current->pid == current->tgid) {
/*
* This is the record for the group leader. Add in the
* cumulative times of previous dead threads. This total
* won't include the time of each live thread whose state
* is included in the core dump. The final total reported
* to our parent process when it calls wait4 will include
* those sums as well as the little bit more time it takes
* this and each other thread to finish dying after the
* core dump synchronization phase.
*/
jiffies_to_timeval(current->utime + current->signal->utime,
&prstatus.pr_utime);
jiffies_to_timeval(current->stime + current->signal->stime,
&prstatus.pr_stime);
} else {
jiffies_to_timeval(current->utime, &prstatus.pr_utime);
jiffies_to_timeval(current->stime, &prstatus.pr_stime);
}
jiffies_to_timeval(current->signal->cutime, &prstatus.pr_cutime);
jiffies_to_timeval(current->signal->cstime, &prstatus.pr_cstime);
if (sizeof(elf_gregset_t) != sizeof(struct pt_regs)) {
printk("sizeof(elf_gregset_t) (%d) != sizeof(struct pt_regs) "
"(%d)\n", sizeof(elf_gregset_t), sizeof(struct pt_regs));
} else {
*(struct pt_regs *)&prstatus.pr_reg = *regs;
}
notes[1].name = "CORE";
notes[1].type = NT_PRPSINFO;
notes[1].datasz = sizeof(psinfo);
notes[1].data = &psinfo;
i = current->state ? ffz(~current->state) + 1 : 0;
psinfo.pr_state = i;
psinfo.pr_sname = (i < 0 || i > 5) ? '.' : "RSDZTD"[i];
psinfo.pr_zomb = psinfo.pr_sname == 'Z';
psinfo.pr_nice = task_nice(current);
psinfo.pr_flag = current->flags;
psinfo.pr_uid = current->uid;
psinfo.pr_gid = current->gid;
{
int i, len;
set_fs(fs);
len = current->mm->arg_end - current->mm->arg_start;
len = len >= ELF_PRARGSZ ? ELF_PRARGSZ : len;
(void *) copy_from_user(&psinfo.pr_psargs,
(const char __user *)current->mm->arg_start, len);
for (i = 0; i < len; i++)
if (psinfo.pr_psargs[i] == 0)
psinfo.pr_psargs[i] = ' ';
psinfo.pr_psargs[len] = 0;
set_fs(KERNEL_DS);
}
strlcpy(psinfo.pr_fname, current->comm, sizeof(psinfo.pr_fname));
/* Try to dump the FPU. */
prstatus.pr_fpvalid = dump_fpu(regs, &fpu);
if (!prstatus.pr_fpvalid) {
numnote--;
} else {
notes[2].name = "CORE";
notes[2].type = NT_PRFPREG;
notes[2].datasz = sizeof(fpu);
notes[2].data = &fpu;
}
/* Write notes phdr entry. */
{
struct elf_phdr phdr;
int sz = 0;
for (i = 0; i < numnote; i++)
sz += notesize(¬es[i]);
phdr.p_type = PT_NOTE;
phdr.p_offset = offset;
phdr.p_vaddr = 0;
phdr.p_paddr = 0;
phdr.p_filesz = sz;
phdr.p_memsz = 0;
phdr.p_flags = 0;
phdr.p_align = 0;
offset += phdr.p_filesz;
DUMP_WRITE(&phdr, sizeof(phdr));
}
/* Page-align dumped data. */
dataoff = offset = roundup(offset, PAGE_SIZE);
/* Write program headers for segments dump. */
for (vma = current->mm->mmap, i = 0;
i < segs && vma != NULL; vma = vma->vm_next) {
struct elf_phdr phdr;
size_t sz;
i++;
sz = vma->vm_end - vma->vm_start;
phdr.p_type = PT_LOAD;
phdr.p_offset = offset;
phdr.p_vaddr = vma->vm_start;
phdr.p_paddr = 0;
phdr.p_filesz = maydump(vma) ? sz : 0;
phdr.p_memsz = sz;
offset += phdr.p_filesz;
phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
if (vma->vm_flags & VM_WRITE)
phdr.p_flags |= PF_W;
if (vma->vm_flags & VM_EXEC)
phdr.p_flags |= PF_X;
phdr.p_align = PAGE_SIZE;
DUMP_WRITE(&phdr, sizeof(phdr));
}
for (i = 0; i < numnote; i++)
if (!writenote(¬es[i], file))
goto end_coredump;
set_fs(fs);
DUMP_SEEK(dataoff);
for (i = 0, vma = current->mm->mmap;
i < segs && vma != NULL;
vma = vma->vm_next) {
unsigned long addr = vma->vm_start;
unsigned long len = vma->vm_end - vma->vm_start;
if (!maydump(vma))
continue;
i++;
pr_debug("elf_core_dump: writing %08lx %lx\n", addr, len);
DUMP_WRITE((void __user *)addr, len);
}
if ((off_t) file->f_pos != offset) {
/* Sanity check. */
printk("elf_core_dump: file->f_pos (%ld) != offset (%ld)\n",
(off_t) file->f_pos, offset);
}
end_coredump:
set_fs(fs);
return has_dumped;
}
