/**
* zfcp_unit_enqueue - enqueue unit to unit list of a port.
* @port: pointer to port where unit is added
* @fcp_lun: FCP LUN of unit to be enqueued
* Returns: pointer to enqueued unit on success, ERR_PTR on error
*
* Sets up some unit internal structures and creates sysfs entry.
*/
struct zfcp_unit *zfcp_unit_enqueue(struct zfcp_port *port, u64 fcp_lun)
{
struct zfcp_unit *unit;
int retval = -ENOMEM;
get_device(&port->dev);
unit = zfcp_get_unit_by_lun(port, fcp_lun);
if (unit) {
put_device(&unit->dev);
retval = -EEXIST;
goto err_out;
}
unit = kzalloc(sizeof(struct zfcp_unit), GFP_KERNEL);
if (!unit)
goto err_out;
unit->port = port;
unit->fcp_lun = fcp_lun;
unit->dev.parent = &port->dev;
unit->dev.release = zfcp_unit_release;
if (dev_set_name(&unit->dev, "0x%016llx",
(unsigned long long) fcp_lun)) {
kfree(unit);
goto err_out;
}
retval = -EINVAL;
INIT_WORK(&unit->scsi_work, zfcp_scsi_scan);
spin_lock_init(&unit->latencies.lock);
unit->latencies.write.channel.min = 0xFFFFFFFF;
unit->latencies.write.fabric.min = 0xFFFFFFFF;
unit->latencies.read.channel.min = 0xFFFFFFFF;
unit->latencies.read.fabric.min = 0xFFFFFFFF;
unit->latencies.cmd.channel.min = 0xFFFFFFFF;
unit->latencies.cmd.fabric.min = 0xFFFFFFFF;
if (device_register(&unit->dev)) {
put_device(&unit->dev);
goto err_out;
}
if (sysfs_create_group(&unit->dev.kobj, &zfcp_sysfs_unit_attrs))
goto err_out_put;
write_lock_irq(&port->unit_list_lock);
list_add_tail(&unit->list, &port->unit_list);
write_unlock_irq(&port->unit_list_lock);
atomic_set_mask(ZFCP_STATUS_COMMON_RUNNING, &unit->status);
return unit;
err_out_put:
device_unregister(&unit->dev);
err_out:
put_device(&port->dev);
return ERR_PTR(retval);
}
static int ptrace_attach(struct task_struct *task)
{
bool wait_trap = false;
int retval;
audit_ptrace(task);
retval = -EPERM;
if (unlikely(task->flags & PF_KTHREAD))
goto out;
if (same_thread_group(task, current))
goto out;
/*
* Protect exec's credential calculations against our interference;
* interference; SUID, SGID and LSM creds get determined differently
* under ptrace.
*/
retval = -ERESTARTNOINTR;
if (mutex_lock_interruptible(&task->signal->cred_guard_mutex))
goto out;
task_lock(task);
retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH);
task_unlock(task);
if (retval)
goto unlock_creds;
write_lock_irq(&tasklist_lock);
retval = -EPERM;
if (unlikely(task->exit_state))
goto unlock_tasklist;
if (task->ptrace)
goto unlock_tasklist;
task->ptrace = PT_PTRACED;
if (task_ns_capable(task, CAP_SYS_PTRACE))
task->ptrace |= PT_PTRACE_CAP;
__ptrace_link(task, current);
send_sig_info(SIGSTOP, SEND_SIG_FORCED, task);
spin_lock(&task->sighand->siglock);
/*
* If the task is already STOPPED, set GROUP_STOP_PENDING and
* TRAPPING, and kick it so that it transits to TRACED. TRAPPING
* will be cleared if the child completes the transition or any
* event which clears the group stop states happens. We'll wait
* for the transition to complete before returning from this
* function.
*
* This hides STOPPED -> RUNNING -> TRACED transition from the
* attaching thread but a different thread in the same group can
* still observe the transient RUNNING state. IOW, if another
* thread's WNOHANG wait(2) on the stopped tracee races against
* ATTACH, the wait(2) may fail due to the transient RUNNING.
*
* The following task_is_stopped() test is safe as both transitions
* in and out of STOPPED are protected by siglock.
*/
if (task_is_stopped(task)) {
task->group_stop |= GROUP_STOP_PENDING | GROUP_STOP_TRAPPING;
signal_wake_up(task, 1);
wait_trap = true;
}
spin_unlock(&task->sighand->siglock);
retval = 0;
unlock_tasklist:
write_unlock_irq(&tasklist_lock);
unlock_creds:
mutex_unlock(&task->signal->cred_guard_mutex);
out:
if (wait_trap)
wait_event(current->signal->wait_chldexit,
!(task->group_stop & GROUP_STOP_TRAPPING));
return retval;
}
/*-------------------------------------------------------------------------
* bproc_masq_wait
*/
int masq_wait(pid_t pid, int options, struct siginfo *infop,
unsigned int * stat_addr, struct rusage * ru) {
int result, lpid, status;
struct bproc_krequest_t *req;
struct bproc_rsyscall_msg_t *msg;
struct bproc_wait_resp_t *resp_msg;
struct task_struct *child;
/* XXX to be 100% semantically correct, we need to verify_area
* here on stat_addr and ru here... */
req = bpr_rsyscall1(BPROC_SYS_WAIT);
if (!req){
printk("bproc: masq: sys_wait: out of memory.\n");
return -ENOMEM;
}
msg = (struct bproc_rsyscall_msg_t *) bproc_msg(req);
msg->arg[0] = pid;
msg->arg[1] = options;
if (bpr_rsyscall2(BPROC_MASQ_MASTER(current), req, 1) != 0) {
bproc_put_req(req);
return -EIO;
}
resp_msg = bproc_msg(req->response);
result = resp_msg->hdr.result;
status = resp_msg->status;
if (stat_addr) put_user(status, stat_addr);
if (ru) {
/* Only a few elements of the rusage structure are provided by
* Linux. Also, convert the times back to the HZ
* representation. */
struct rusage ru_tmp;
memset(&ru_tmp, 0, sizeof(ru_tmp));
ru_tmp.ru_utime.tv_sec = resp_msg->utime/HZ;
ru_tmp.ru_utime.tv_usec = (resp_msg->utime*(1000000/HZ))%1000000;
ru_tmp.ru_stime.tv_sec = resp_msg->stime/HZ;
ru_tmp.ru_stime.tv_usec = (resp_msg->stime*(1000000/HZ))%1000000;
ru_tmp.ru_minflt = resp_msg->minflt;
ru_tmp.ru_majflt = resp_msg->majflt;
ru_tmp.ru_nswap = resp_msg->nswap;
copy_to_user(ru, &ru_tmp, sizeof(ru_tmp));
}
bproc_put_req(req);
if (result > 0 && (status & 0xff) != 0x7f) {
/* It's possible that the process we waited on was actually
* local. We need to make sure and get it out of this process
* tree too. If it's not, we need to down the non local child
* count by one... */
write_lock_irq(&tasklist_lock);
child = masq_find_task_by_pid(BPROC_MASQ_MASTER(current), result);
if (child)
lpid = child->pid;
else {
lpid = 0;
current->bproc.nlchild--;
}
write_unlock_irq(&tasklist_lock);
if (lpid) {
/* Do all of this as a kernel call to avoid re-entering
* this whole mess... */
set_bit(BPROC_FLAG_KCALL, ¤t->bproc.flag);
if (k_wait4(lpid, options & ~WNOHANG, NULL, NULL, NULL) == -1) {
printk(KERN_ERR "bproc: masq: local wait failed on %d (%d)\n",
lpid, result);
#if 0
/* This probably isn't correct. If we fail to wait,
* that probably means that somebody else picked it
* up. */
write_lock_irq(&tasklist_lock);
current->bproc.nlchild--;
write_unlock_irq(&tasklist_lock);
#endif
}
}
}
return result;
}
/*
* Send signals to all our closest relatives so that they know
* to properly mourn us..
*/
static void exit_notify(void)
{
struct task_struct * p, *t;
forget_original_parent(current);
/*
* Check to see if any process groups have become orphaned
* as a result of our exiting, and if they have any stopped
* jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2)
*
* Case i: Our father is in a different pgrp than we are
* and we were the only connection outside, so our pgrp
* is about to become orphaned.
*/
t = current->p_pptr;
if ((t->pgrp != current->pgrp) &&
(t->session == current->session) &&
will_become_orphaned_pgrp(current->pgrp, current) &&
has_stopped_jobs(current->pgrp)) {
kill_pg(current->pgrp,SIGHUP,1);
kill_pg(current->pgrp,SIGCONT,1);
}
/* Let father know we died
*
* Thread signals are configurable, but you aren't going to use
* that to send signals to arbitary processes.
* That stops right now.
*
* If the parent exec id doesn't match the exec id we saved
* when we started then we know the parent has changed security
* domain.
*
* If our self_exec id doesn't match our parent_exec_id then
* we have changed execution domain as these two values started
* the same after a fork.
*
*/
if(current->exit_signal != SIGCHLD &&
( current->parent_exec_id != t->self_exec_id ||
current->self_exec_id != current->parent_exec_id)
&& !capable(CAP_KILL))
current->exit_signal = SIGCHLD;
notify_parent(current, current->exit_signal);
/*
* This loop does two things:
*
* A. Make init inherit all the child processes
* B. Check to see if any process groups have become orphaned
* as a result of our exiting, and if they have any stopped
* jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2)
*/
write_lock_irq(&tasklist_lock);
while (current->p_cptr != NULL) {
p = current->p_cptr;
current->p_cptr = p->p_osptr;
p->p_ysptr = NULL;
p->flags &= ~(PF_PTRACED|PF_TRACESYS);
p->p_pptr = p->p_opptr;
p->p_osptr = p->p_pptr->p_cptr;
if (p->p_osptr)
p->p_osptr->p_ysptr = p;
p->p_pptr->p_cptr = p;
if (p->state == TASK_ZOMBIE)
notify_parent(p, p->exit_signal);
/*
* process group orphan check
* Case ii: Our child is in a different pgrp
* than we are, and it was the only connection
* outside, so the child pgrp is now orphaned.
*/
if ((p->pgrp != current->pgrp) &&
(p->session == current->session)) {
int pgrp = p->pgrp;
write_unlock_irq(&tasklist_lock);
if (is_orphaned_pgrp(pgrp) && has_stopped_jobs(pgrp)) {
kill_pg(pgrp,SIGHUP,1);
kill_pg(pgrp,SIGCONT,1);
}
write_lock_irq(&tasklist_lock);
}
}
write_unlock_irq(&tasklist_lock);
if (current->leader)
disassociate_ctty(1);
}
unsigned long hp_sdc_put(void)
{
hp_sdc_transaction *curr;
uint8_t act;
int idx, curridx;
int limit = 0;
write_lock(&hp_sdc.lock);
/* If i8042 buffers are full, we cannot do anything that
requires output, so we skip to the administrativa. */
if (hp_sdc.ibf) {
hp_sdc_status_in8();
if (hp_sdc.ibf)
goto finish;
}
anew:
/* See if we are in the middle of a sequence. */
if (hp_sdc.wcurr < 0)
hp_sdc.wcurr = 0;
read_lock_irq(&hp_sdc.rtq_lock);
if (hp_sdc.rcurr == hp_sdc.wcurr)
hp_sdc.wcurr++;
read_unlock_irq(&hp_sdc.rtq_lock);
if (hp_sdc.wcurr >= HP_SDC_QUEUE_LEN)
hp_sdc.wcurr = 0;
curridx = hp_sdc.wcurr;
if (hp_sdc.tq[curridx] != NULL)
goto start;
while (++curridx != hp_sdc.wcurr) {
if (curridx >= HP_SDC_QUEUE_LEN) {
curridx = -1; /* Wrap to top */
continue;
}
read_lock_irq(&hp_sdc.rtq_lock);
if (hp_sdc.rcurr == curridx) {
read_unlock_irq(&hp_sdc.rtq_lock);
continue;
}
read_unlock_irq(&hp_sdc.rtq_lock);
if (hp_sdc.tq[curridx] != NULL)
break; /* Found one. */
}
if (curridx == hp_sdc.wcurr) { /* There's nothing queued to do. */
curridx = -1;
}
hp_sdc.wcurr = curridx;
start:
/* Check to see if the interrupt mask needs to be set. */
if (hp_sdc.set_im) {
hp_sdc_status_out8(hp_sdc.im | HP_SDC_CMD_SET_IM);
hp_sdc.set_im = 0;
goto finish;
}
if (hp_sdc.wcurr == -1)
goto done;
curr = hp_sdc.tq[curridx];
idx = curr->actidx;
if (curr->actidx >= curr->endidx) {
hp_sdc.tq[curridx] = NULL;
/* Interleave outbound data between the transactions. */
hp_sdc.wcurr++;
if (hp_sdc.wcurr >= HP_SDC_QUEUE_LEN)
hp_sdc.wcurr = 0;
goto finish;
}
act = curr->seq[idx];
idx++;
if (curr->idx >= curr->endidx) {
if (act & HP_SDC_ACT_DEALLOC)
kfree(curr);
hp_sdc.tq[curridx] = NULL;
/* Interleave outbound data between the transactions. */
hp_sdc.wcurr++;
if (hp_sdc.wcurr >= HP_SDC_QUEUE_LEN)
hp_sdc.wcurr = 0;
goto finish;
}
while (act & HP_SDC_ACT_PRECMD) {
if (curr->idx != idx) {
idx++;
act &= ~HP_SDC_ACT_PRECMD;
break;
}
hp_sdc_status_out8(curr->seq[idx]);
curr->idx++;
/* act finished? */
if ((act & HP_SDC_ACT_DURING) == HP_SDC_ACT_PRECMD)
goto actdone;
/* skip quantity field if data-out sequence follows. */
if (act & HP_SDC_ACT_DATAOUT)
curr->idx++;
goto finish;
}
if (act & HP_SDC_ACT_DATAOUT) {
int qty;
qty = curr->seq[idx];
idx++;
if (curr->idx - idx < qty) {
hp_sdc_data_out8(curr->seq[curr->idx]);
curr->idx++;
/* act finished? */
if (curr->idx - idx >= qty &&
(act & HP_SDC_ACT_DURING) == HP_SDC_ACT_DATAOUT)
goto actdone;
goto finish;
}
idx += qty;
act &= ~HP_SDC_ACT_DATAOUT;
} else
while (act & HP_SDC_ACT_DATAREG) {
int mask;
uint8_t w7[4];
mask = curr->seq[idx];
if (idx != curr->idx) {
idx++;
idx += !!(mask & 1);
idx += !!(mask & 2);
idx += !!(mask & 4);
idx += !!(mask & 8);
act &= ~HP_SDC_ACT_DATAREG;
break;
}
w7[0] = (mask & 1) ? curr->seq[++idx] : hp_sdc.r7[0];
w7[1] = (mask & 2) ? curr->seq[++idx] : hp_sdc.r7[1];
w7[2] = (mask & 4) ? curr->seq[++idx] : hp_sdc.r7[2];
w7[3] = (mask & 8) ? curr->seq[++idx] : hp_sdc.r7[3];
if (hp_sdc.wi > 0x73 || hp_sdc.wi < 0x70 ||
w7[hp_sdc.wi - 0x70] == hp_sdc.r7[hp_sdc.wi - 0x70]) {
int i = 0;
/* Need to point the write index register */
while (i < 4 && w7[i] == hp_sdc.r7[i])
i++;
if (i < 4) {
hp_sdc_status_out8(HP_SDC_CMD_SET_D0 + i);
hp_sdc.wi = 0x70 + i;
goto finish;
}
idx++;
if ((act & HP_SDC_ACT_DURING) == HP_SDC_ACT_DATAREG)
goto actdone;
curr->idx = idx;
act &= ~HP_SDC_ACT_DATAREG;
break;
}
hp_sdc_data_out8(w7[hp_sdc.wi - 0x70]);
hp_sdc.r7[hp_sdc.wi - 0x70] = w7[hp_sdc.wi - 0x70];
hp_sdc.wi++; /* write index register autoincrements */
{
int i = 0;
while ((i < 4) && w7[i] == hp_sdc.r7[i])
i++;
if (i >= 4) {
curr->idx = idx + 1;
if ((act & HP_SDC_ACT_DURING) ==
HP_SDC_ACT_DATAREG)
goto actdone;
}
}
goto finish;
}
/* We don't go any further in the command if there is a pending read,
because we don't want interleaved results. */
read_lock_irq(&hp_sdc.rtq_lock);
if (hp_sdc.rcurr >= 0) {
read_unlock_irq(&hp_sdc.rtq_lock);
goto finish;
}
read_unlock_irq(&hp_sdc.rtq_lock);
if (act & HP_SDC_ACT_POSTCMD) {
uint8_t postcmd;
/* curr->idx should == idx at this point. */
postcmd = curr->seq[idx];
curr->idx++;
if (act & HP_SDC_ACT_DATAIN) {
/* Start a new read */
hp_sdc.rqty = curr->seq[curr->idx];
do_gettimeofday(&hp_sdc.rtv);
curr->idx++;
/* Still need to lock here in case of spurious irq. */
write_lock_irq(&hp_sdc.rtq_lock);
hp_sdc.rcurr = curridx;
write_unlock_irq(&hp_sdc.rtq_lock);
hp_sdc_status_out8(postcmd);
goto finish;
}
hp_sdc_status_out8(postcmd);
goto actdone;
}
actdone:
if (act & HP_SDC_ACT_SEMAPHORE)
up(curr->act.semaphore);
else if (act & HP_SDC_ACT_CALLBACK)
curr->act.irqhook(0,NULL,0,0);
if (curr->idx >= curr->endidx) { /* This transaction is over. */
if (act & HP_SDC_ACT_DEALLOC)
kfree(curr);
hp_sdc.tq[curridx] = NULL;
} else {
curr->actidx = idx + 1;
curr->idx = idx + 2;
}
/* Interleave outbound data between the transactions. */
hp_sdc.wcurr++;
if (hp_sdc.wcurr >= HP_SDC_QUEUE_LEN)
hp_sdc.wcurr = 0;
finish:
/* If by some quirk IBF has cleared and our ISR has run to
see that that has happened, do it all again. */
if (!hp_sdc.ibf && limit++ < 20)
goto anew;
done:
if (hp_sdc.wcurr >= 0)
tasklet_schedule(&hp_sdc.task);
write_unlock(&hp_sdc.lock);
return 0;
}
/*
* 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.
*/
struct task_struct *copy_process(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
int retval;
struct task_struct *p = NULL;
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;
retval = -EAGAIN;
if (atomic_read(&p->user->processes) >=
p->rlim[RLIMIT_NPROC].rlim_cur) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
p->user != &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(p->thread_info->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;
copy_flags(clone_flags, p);
if (clone_flags & CLONE_IDLETASK)
p->pid = 0;
else {
p->pid = alloc_pidmap();
if (p->pid == -1)
goto bad_fork_cleanup;
}
retval = -EFAULT;
if (clone_flags & CLONE_PARENT_SETTID)
if (put_user(p->pid, parent_tidptr))
goto bad_fork_cleanup;
p->proc_dentry = NULL;
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
init_waitqueue_head(&p->wait_chldexit);
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
spin_lock_init(&p->proc_lock);
clear_tsk_thread_flag(p, TIF_SIGPENDING);
init_sigpending(&p->pending);
p->it_real_value = p->it_virt_value = p->it_prof_value = 0;
p->it_real_incr = p->it_virt_incr = p->it_prof_incr = 0;
init_timer(&p->real_timer);
p->real_timer.data = (unsigned long) p;
p->utime = p->stime = 0;
p->cutime = p->cstime = 0;
p->lock_depth = -1; /* -1 = no lock */
p->start_time = get_jiffies_64();
p->security = NULL;
p->io_context = NULL;
p->audit_context = NULL;
#ifdef CONFIG_NUMA
p->mempolicy = mpol_copy(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
goto bad_fork_cleanup;
}
#endif
retval = -ENOMEM;
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_namespace(clone_flags, p)))
goto bad_fork_cleanup_mm;
retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
if (retval)
goto bad_fork_cleanup_namespace;
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;
/*
* Syscall tracing should be turned off in the child regardless
* of CLONE_PTRACE.
*/
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
/* Our parent execution domain becomes current domain
These must match for thread signalling to apply */
p->parent_exec_id = p->self_exec_id;
/* ok, now we should be set up.. */
p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
p->pdeath_signal = 0;
/* Perform scheduler related setup */
sched_fork(p);
/*
* Ok, make it visible to the rest of the system.
* We dont wake it up yet.
*/
p->tgid = p->pid;
p->group_leader = p;
INIT_LIST_HEAD(&p->ptrace_children);
INIT_LIST_HEAD(&p->ptrace_list);
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
/*
* Check for pending SIGKILL! The new thread should not be allowed
* to slip out of an OOM kill. (or normal SIGKILL.)
*/
if (sigismember(¤t->pending.signal, SIGKILL)) {
write_unlock_irq(&tasklist_lock);
retval = -EINTR;
goto bad_fork_cleanup_namespace;
}
/* CLONE_PARENT re-uses the old parent */
if (clone_flags & CLONE_PARENT)
p->real_parent = current->real_parent;
else
p->real_parent = current;
p->parent = p->real_parent;
if (clone_flags & CLONE_THREAD) {
spin_lock(¤t->sighand->siglock);
/*
* Important: if an exit-all has been started then
* do not create this new thread - the whole thread
* group is supposed to exit anyway.
*/
if (current->signal->group_exit) {
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -EAGAIN;
goto bad_fork_cleanup_namespace;
}
p->tgid = current->tgid;
p->group_leader = current->group_leader;
if (current->signal->group_stop_count > 0) {
/*
* There is an all-stop in progress for the group.
* We ourselves will stop as soon as we check signals.
* Make the new thread part of that group stop too.
*/
current->signal->group_stop_count++;
set_tsk_thread_flag(p, TIF_SIGPENDING);
}
spin_unlock(¤t->sighand->siglock);
}
SET_LINKS(p);
if (p->ptrace & PT_PTRACED)
__ptrace_link(p, current->parent);
attach_pid(p, PIDTYPE_PID, p->pid);
if (thread_group_leader(p)) {
attach_pid(p, PIDTYPE_TGID, p->tgid);
attach_pid(p, PIDTYPE_PGID, process_group(p));
attach_pid(p, PIDTYPE_SID, p->signal->session);
if (p->pid)
__get_cpu_var(process_counts)++;
} else
link_pid(p, p->pids + PIDTYPE_TGID, &p->group_leader->pids[PIDTYPE_TGID].pid);
nr_threads++;
write_unlock_irq(&tasklist_lock);
retval = 0;
fork_out:
if (retval)
return ERR_PTR(retval);
return p;
bad_fork_cleanup_namespace:
exit_namespace(p);
bad_fork_cleanup_mm:
exit_mm(p);
if (p->active_mm)
mmdrop(p->active_mm);
bad_fork_cleanup_signal:
exit_signal(p);
bad_fork_cleanup_sighand:
exit_sighand(p);
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_free(p->mempolicy);
#endif
bad_fork_cleanup:
if (p->pid > 0)
free_pidmap(p->pid);
if (p->binfmt)
module_put(p->binfmt->module);
bad_fork_cleanup_put_domain:
module_put(p->thread_info->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);
goto fork_out;
}
static void vcc_remove_socket(struct sock *sk)
{
write_lock_irq(&vcc_sklist_lock);
sk_del_node_init(sk);
write_unlock_irq(&vcc_sklist_lock);
}
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);
if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
return ERR_PTR(-EINVAL);
if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
return ERR_PTR(-EINVAL);
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;
}
current->flags &= ~PF_NPROC_EXCEEDED;
retval = copy_creds(p, clone_flags);
if (retval < 0)
goto bad_fork_free;
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);
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 = p->stime = p->gtime = 0;
p->utimescaled = p->stimescaled = 0;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
p->prev_utime = p->prev_stime = 0;
#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);
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;
if (clone_flags & CLONE_THREAD)
threadgroup_change_begin(current);
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_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;
#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;
p->curr_chain_key = 0;
p->lockdep_recursion = 0;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL;
p->blocked_by = NULL;
p->blocked_since = 0;
#endif
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
p->memcg_batch.do_batch = 0;
p->memcg_batch.memcg = NULL;
#endif
sched_fork(p);
retval = perf_event_init_task(p);
if (retval)
goto bad_fork_cleanup_policy;
retval = audit_alloc(p);
if (retval)
goto bad_fork_cleanup_policy;
retval = copy_semundo(clone_flags, p);
if (retval)
goto bad_fork_cleanup_audit;
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(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;
}
p->pid = pid_nr(pid);
p->tgid = p->pid;
if (clone_flags & CLONE_THREAD)
p->tgid = current->tgid;
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL;
#ifdef CONFIG_BLOCK
p->plug = NULL;
#endif
#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
if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
p->sas_ss_sp = p->sas_ss_size = 0;
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);
if (clone_flags & CLONE_THREAD)
p->exit_signal = -1;
else if (clone_flags & CLONE_PARENT)
p->exit_signal = current->group_leader->exit_signal;
else
p->exit_signal = (clone_flags & CSIGNAL);
p->pdeath_signal = 0;
p->exit_state = 0;
p->nr_dirtied = 0;
p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
p->dirty_paused_when = 0;
p->group_leader = p;
INIT_LIST_HEAD(&p->thread_group);
cgroup_fork_callbacks(p);
cgroup_callbacks_done = 1;
write_lock_irq(&tasklist_lock);
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);
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) {
current->signal->nr_threads++;
atomic_inc(¤t->signal->live);
atomic_inc(¤t->signal->sigcnt);
p->group_leader = current->group_leader;
list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
}
if (likely(p->pid)) {
ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
if (thread_group_leader(p)) {
if (is_child_reaper(pid))
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);
__this_cpu_inc(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);
if (clone_flags & CLONE_THREAD)
threadgroup_change_end(current);
perf_event_fork(p);
trace_task_newtask(p, clone_flags);
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:
if (unlikely(clone_flags & CLONE_NEWPID))
pid_ns_release_proc(p->nsproxy->pid_ns);
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);
bad_fork_cleanup_files:
exit_files(p);
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
if (clone_flags & CLONE_THREAD)
threadgroup_change_end(current);
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);
}
asmlinkage long sys_wait4(pid_t pid,unsigned int * stat_addr, int options, struct rusage * ru)
{
int flag, retval;
DECLARE_WAITQUEUE(wait, current);
struct task_struct *tsk;
if (options & ~(WNOHANG|WUNTRACED|__WNOTHREAD|__WCLONE|__WALL))
return -EINVAL;
add_wait_queue(¤t->wait_chldexit,&wait);
repeat:
flag = 0;
current->state = TASK_INTERRUPTIBLE;
read_lock(&tasklist_lock);
tsk = current;
do {
struct task_struct *p;
for (p = tsk->p_cptr ; p ; p = p->p_osptr) {
if (pid>0) {
if (p->pid != pid)
continue;
} else if (!pid) {
if (p->pgrp != current->pgrp)
continue;
} else if (pid != -1) {
if (p->pgrp != -pid)
continue;
}
/* Wait for all children (clone and not) if __WALL is set;
* otherwise, wait for clone children *only* if __WCLONE is
* set; otherwise, wait for non-clone children *only*. (Note:
* A "clone" child here is one that reports to its parent
* using a signal other than SIGCHLD.) */
if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0))
&& !(options & __WALL))
continue;
flag = 1;
switch (p->state) {
case TASK_STOPPED:
if (!p->exit_code)
continue;
if (!(options & WUNTRACED) && !(p->ptrace & PT_PTRACED))
continue;
read_unlock(&tasklist_lock);
retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
if (!retval && stat_addr)
retval = put_user((p->exit_code << 8) | 0x7f, stat_addr);
if (!retval) {
p->exit_code = 0;
retval = p->pid;
}
goto end_wait4;
case TASK_ZOMBIE:
current->times.tms_cutime += p->times.tms_utime + p->times.tms_cutime;
current->times.tms_cstime += p->times.tms_stime + p->times.tms_cstime;
read_unlock(&tasklist_lock);
retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
if (!retval && stat_addr)
retval = put_user(p->exit_code, stat_addr);
if (retval)
goto end_wait4;
retval = p->pid;
if (p->p_opptr != p->p_pptr) {
write_lock_irq(&tasklist_lock);
REMOVE_LINKS(p);
p->p_pptr = p->p_opptr;
SET_LINKS(p);
do_notify_parent(p, SIGCHLD);
write_unlock_irq(&tasklist_lock);
} else
release_task(p);
goto end_wait4;
default:
continue;
}
}
if (options & __WNOTHREAD)
break;
tsk = next_thread(tsk);
} while (tsk != current);
read_unlock(&tasklist_lock);
if (flag) {
retval = 0;
if (options & WNOHANG)
goto end_wait4;
retval = -ERESTARTSYS;
if (signal_pending(current))
goto end_wait4;
schedule();
goto repeat;
}
retval = -ECHILD;
end_wait4:
current->state = TASK_RUNNING;
remove_wait_queue(¤t->wait_chldexit,&wait);
return retval;
}
static void ib_cache_update(struct ib_device *device,
u8 port)
{
struct ib_port_attr *tprops = NULL;
struct ib_pkey_cache *pkey_cache = NULL, *old_pkey_cache;
struct ib_gid_cache *gid_cache = NULL, *old_gid_cache;
int i, j;
int ret;
union ib_gid gid, empty_gid;
u16 pkey;
tprops = kmalloc(sizeof *tprops, GFP_KERNEL);
if (!tprops)
return;
ret = ib_query_port(device, port, tprops);
if (ret) {
printk(KERN_WARNING "ib_query_port failed (%d) for %s\n",
ret, device->name);
goto err;
}
pkey_cache = kmalloc(sizeof *pkey_cache + tprops->pkey_tbl_len *
sizeof *pkey_cache->entry, GFP_KERNEL);
if (!pkey_cache)
goto err;
pkey_cache->table_len = 0;
gid_cache = kmalloc(sizeof *gid_cache + tprops->gid_tbl_len *
sizeof *gid_cache->entry, GFP_KERNEL);
if (!gid_cache)
goto err;
gid_cache->table_len = 0;
for (i = 0, j = 0; i < tprops->pkey_tbl_len; ++i) {
ret = ib_query_pkey(device, port, i, &pkey);
if (ret) {
printk(KERN_WARNING "ib_query_pkey failed (%d) for %s (index %d)\n",
ret, device->name, i);
goto err;
}
/* pkey 0xffff must be the default pkeyand 0x0000 must be the invalid
* pkey per IBTA spec */
if (pkey) {
pkey_cache->entry[j].index = i;
pkey_cache->entry[j++].pkey = pkey;
}
}
pkey_cache->table_len = j;
memset(&empty_gid, 0, sizeof empty_gid);
for (i = 0, j = 0; i < tprops->gid_tbl_len; ++i) {
ret = ib_query_gid(device, port, i, &gid);
if (ret) {
printk(KERN_WARNING "ib_query_gid failed (%d) for %s (index %d)\n",
ret, device->name, i);
goto err;
}
/* if the lower 8 bytes the device GID entry is all 0,
* our entry is a blank, invalid entry...
* depending on device, the upper 8 bytes might or might
* not be prefilled with a valid subnet prefix, so
* don't rely on them for determining a valid gid
* entry
*/
if (memcmp(&gid + 8, &empty_gid + 8, sizeof gid - 8)) {
gid_cache->entry[j].index = i;
gid_cache->entry[j++].gid = gid;
}
}
gid_cache->table_len = j;
old_pkey_cache = pkey_cache;
pkey_cache = kmalloc(sizeof *pkey_cache + old_pkey_cache->table_len *
sizeof *pkey_cache->entry, GFP_KERNEL);
if (!pkey_cache)
pkey_cache = old_pkey_cache;
else {
pkey_cache->table_len = old_pkey_cache->table_len;
memcpy(&pkey_cache->entry[0], &old_pkey_cache->entry[0],
pkey_cache->table_len * sizeof *pkey_cache->entry);
kfree(old_pkey_cache);
}
old_gid_cache = gid_cache;
gid_cache = kmalloc(sizeof *gid_cache + old_gid_cache->table_len *
sizeof *gid_cache->entry, GFP_KERNEL);
if (!gid_cache)
gid_cache = old_gid_cache;
else {
gid_cache->table_len = old_gid_cache->table_len;
memcpy(&gid_cache->entry[0], &old_gid_cache->entry[0],
gid_cache->table_len * sizeof *gid_cache->entry);
kfree(old_gid_cache);
}
write_lock_irq(&device->cache.lock);
old_pkey_cache = device->cache.pkey_cache[port - start_port(device)];
old_gid_cache = device->cache.gid_cache [port - start_port(device)];
device->cache.pkey_cache[port - start_port(device)] = pkey_cache;
device->cache.gid_cache [port - start_port(device)] = gid_cache;
device->cache.lmc_cache[port - start_port(device)] = tprops->lmc;
write_unlock_irq(&device->cache.lock);
kfree(old_pkey_cache);
kfree(old_gid_cache);
kfree(tprops);
return;
err:
kfree(pkey_cache);
kfree(gid_cache);
kfree(tprops);
}
/*
* Adjust the time obtained from the CMOS to be UTC time instead of
* local time.
*
* This is ugly, but preferable to the alternatives. Otherwise we
* would either need to write a program to do it in /etc/rc (and risk
* confusion if the program gets run more than once; it would also be
* hard to make the program warp the clock precisely n hours) or
* compile in the timezone information into the kernel. Bad, bad....
*
* - TYT, 1992-01-01
*
* The best thing to do is to keep the CMOS clock in universal time (UTC)
* as real UNIX machines always do it. This avoids all headaches about
* daylight saving times and warping kernel clocks.
*/
inline static void warp_clock(void)
{
write_lock_irq(&xtime_lock);
xtime.tv_sec += sys_tz.tz_minuteswest * 60;
write_unlock_irq(&xtime_lock);
}
/*
* 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 task_t *copy_process(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr,
int pid)
{
int retval;
struct task_struct *p = NULL;
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;
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 != &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(p->thread_info->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;
copy_flags(clone_flags, p);
p->pid = pid;
retval = -EFAULT;
if (clone_flags & CLONE_PARENT_SETTID)
if (put_user(p->pid, parent_tidptr))
goto bad_fork_cleanup;
p->proc_dentry = NULL;
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
spin_lock_init(&p->proc_lock);
clear_tsk_thread_flag(p, TIF_SIGPENDING);
init_sigpending(&p->pending);
p->utime = cputime_zero;
p->stime = cputime_zero;
p->sched_time = 0;
p->rchar = 0; /* I/O counter: bytes read */
p->wchar = 0; /* I/O counter: bytes written */
p->syscr = 0; /* I/O counter: read syscalls */
p->syscw = 0; /* I/O counter: write syscalls */
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->security = NULL;
p->io_context = NULL;
p->io_wait = NULL;
p->audit_context = NULL;
#ifdef CONFIG_NUMA
p->mempolicy = mpol_copy(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
goto bad_fork_cleanup;
}
#endif
p->tgid = p->pid;
if (clone_flags & CLONE_THREAD)
p->tgid = current->tgid;
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_namespace(clone_flags, p)))
goto bad_fork_cleanup_keys;
retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
if (retval)
goto bad_fork_cleanup_namespace;
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;
/*
* Syscall tracing should be turned off in the child regardless
* of CLONE_PTRACE.
*/
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
/* Our parent execution domain becomes current domain
These must match for thread signalling to apply */
p->parent_exec_id = p->self_exec_id;
/* 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;
/* Perform scheduler related setup */
sched_fork(p);
/*
* Ok, make it visible to the rest of the system.
* We dont wake it up yet.
*/
p->group_leader = p;
INIT_LIST_HEAD(&p->ptrace_children);
INIT_LIST_HEAD(&p->ptrace_list);
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
/*
* The task hasn't been attached yet, so cpus_allowed mask cannot
* have changed. The cpus_allowed mask of the parent may have
* changed after it was copied first time, and it may then move to
* another CPU - so we re-copy it here and set the child's CPU to
* the parent's CPU. This avoids alot of nasty races.
*/
p->cpus_allowed = current->cpus_allowed;
set_task_cpu(p, smp_processor_id());
/*
* Check for pending SIGKILL! The new thread should not be allowed
* to slip out of an OOM kill. (or normal SIGKILL.)
*/
if (sigismember(¤t->pending.signal, SIGKILL)) {
write_unlock_irq(&tasklist_lock);
retval = -EINTR;
goto bad_fork_cleanup_namespace;
}
/* CLONE_PARENT re-uses the old parent */
if (clone_flags & (CLONE_PARENT|CLONE_THREAD))
p->real_parent = current->real_parent;
else
p->real_parent = current;
p->parent = p->real_parent;
if (clone_flags & CLONE_THREAD) {
spin_lock(¤t->sighand->siglock);
/*
* Important: if an exit-all has been started then
* do not create this new thread - the whole thread
* group is supposed to exit anyway.
*/
if (current->signal->flags & SIGNAL_GROUP_EXIT) {
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -EAGAIN;
goto bad_fork_cleanup_namespace;
}
p->group_leader = current->group_leader;
if (current->signal->group_stop_count > 0) {
/*
* There is an all-stop in progress for the group.
* We ourselves will stop as soon as we check signals.
* Make the new thread part of that group stop too.
*/
current->signal->group_stop_count++;
set_tsk_thread_flag(p, TIF_SIGPENDING);
}
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);
}
spin_unlock(¤t->sighand->siglock);
}
SET_LINKS(p);
if (unlikely(p->ptrace & PT_PTRACED))
__ptrace_link(p, current->parent);
cpuset_fork(p);
attach_pid(p, PIDTYPE_PID, p->pid);
attach_pid(p, PIDTYPE_TGID, p->tgid);
if (thread_group_leader(p)) {
attach_pid(p, PIDTYPE_PGID, process_group(p));
attach_pid(p, PIDTYPE_SID, p->signal->session);
if (p->pid)
__get_cpu_var(process_counts)++;
}
nr_threads++;
total_forks++;
write_unlock_irq(&tasklist_lock);
retval = 0;
fork_out:
if (retval)
return ERR_PTR(retval);
return p;
bad_fork_cleanup_namespace:
exit_namespace(p);
bad_fork_cleanup_keys:
exit_keys(p);
bad_fork_cleanup_mm:
if (p->mm)
mmput(p->mm);
bad_fork_cleanup_signal:
exit_signal(p);
bad_fork_cleanup_sighand:
exit_sighand(p);
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_free(p->mempolicy);
#endif
bad_fork_cleanup:
if (p->binfmt)
module_put(p->binfmt->module);
bad_fork_cleanup_put_domain:
module_put(p->thread_info->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);
goto fork_out;
}
long sys_ptrace(long request, pid_t pid, long addr, long data)
{
struct task_struct *child;
long ret;
lock_kernel();
ret = -EPERM;
if (request == PTRACE_TRACEME) {
/* are we already being traced? */
if (current->ptrace & PT_PTRACED)
goto out;
/* set the ptrace bit in the process flags. */
current->ptrace |= PT_PTRACED;
ret = 0;
goto out;
}
ret = -ESRCH;
read_lock(&tasklist_lock);
child = find_task_by_pid(pid);
if (child)
get_task_struct(child);
read_unlock(&tasklist_lock);
if (!child)
goto out;
ret = -EPERM;
if (pid == 1) /* no messing around with init! */
goto out_tsk;
if (request == PTRACE_ATTACH) {
if (child == current)
goto out_tsk;
if ((!child->dumpable ||
(current->uid != child->euid) ||
(current->uid != child->suid) ||
(current->uid != child->uid) ||
(current->gid != child->egid) ||
(current->gid != child->sgid) ||
(!cap_issubset(child->cap_permitted, current->cap_permitted)) ||
(current->gid != child->gid)) && !capable(CAP_SYS_PTRACE))
goto out_tsk;
/* the same process cannot be attached many times */
if (child->ptrace & PT_PTRACED)
goto out_tsk;
child->ptrace |= PT_PTRACED;
if (child->p_pptr != current) {
unsigned long flags;
write_lock_irqsave(&tasklist_lock, flags);
REMOVE_LINKS(child);
child->p_pptr = current;
SET_LINKS(child);
write_unlock_irqrestore(&tasklist_lock, flags);
}
send_sig(SIGSTOP, child, 1);
ret = 0;
goto out_tsk;
}
ret = -ESRCH;
if (!(child->ptrace & PT_PTRACED))
goto out_tsk;
if (child->state != TASK_STOPPED) {
if (request != PTRACE_KILL)
goto out_tsk;
}
if (child->p_pptr != current)
goto out_tsk;
switch (request) {
case PTRACE_PEEKTEXT: /* read word at location addr. */
case PTRACE_PEEKDATA: {
unsigned long tmp;
int copied;
copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
ret = -EIO;
if (copied != sizeof(tmp))
goto out_tsk;
ret = put_user(tmp,(unsigned long *) data);
goto out_tsk;
}
/* when I and D space are separate, this will have to be fixed. */
case PTRACE_POKETEXT: /* write the word at location addr. */
case PTRACE_POKEDATA:
ret = 0;
if (access_process_vm(child, addr, &data, sizeof(data), 1) == sizeof(data))
goto out_tsk;
ret = -EIO;
goto out_tsk;
/* Read the word at location addr in the USER area. This will need
to change when the kernel no longer saves all regs on a syscall. */
case PTRACE_PEEKUSR: {
unsigned long tmp;
ret = -EIO;
if ((addr & 3) || (unsigned long) addr >= sizeof(struct pt_regs))
goto out_tsk;
tmp = *(unsigned long *) ((char *) task_regs(child) + addr);
ret = put_user(tmp, (unsigned long *) data);
goto out_tsk;
}
/* Write the word at location addr in the USER area. This will need
to change when the kernel no longer saves all regs on a syscall.
FIXME. There is a problem at the moment in that r3-r18 are only
saved if the process is ptraced on syscall entry, and even then
those values are overwritten by actual register values on syscall
exit. */
case PTRACE_POKEUSR:
ret = -EIO;
if ((addr & 3) || (unsigned long) addr >= sizeof(struct pt_regs))
goto out_tsk;
/* XXX This test probably needs adjusting. We probably want to
* allow writes to some bits of PSW, and may want to block writes
* to (some) space registers. Some register values written here
* may be ignored in entry.S:syscall_restore_rfi; e.g. iaoq is
* written with r31/r31+4, and not with the values in pt_regs.
*/
/* Allow writing of gr1-gr31, fr*, sr*, iasq*, iaoq*, sar */
if (addr == PT_PSW || (addr > PT_IAOQ1 && addr != PT_SAR))
goto out_tsk;
*(unsigned long *) ((char *) task_regs(child) + addr) = data;
ret = 0;
goto out_tsk;
case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
case PTRACE_CONT:
ret = -EIO;
if ((unsigned long) data > _NSIG)
goto out_tsk;
child->ptrace &= ~(PT_SINGLESTEP|PT_BLOCKSTEP);
if (request == PTRACE_SYSCALL)
child->ptrace |= PT_TRACESYS;
else
child->ptrace &= ~PT_TRACESYS;
child->exit_code = data;
goto out_wake_notrap;
case PTRACE_KILL:
/*
* make the child exit. Best I can do is send it a
* sigkill. perhaps it should be put in the status
* that it wants to exit.
*/
if (child->state == TASK_ZOMBIE) /* already dead */
goto out_tsk;
child->exit_code = SIGKILL;
goto out_wake_notrap;
case PTRACE_SINGLEBLOCK:
ret = -EIO;
if ((unsigned long) data > _NSIG)
goto out_tsk;
child->ptrace &= ~(PT_TRACESYS|PT_SINGLESTEP);
child->ptrace |= PT_BLOCKSTEP;
child->exit_code = data;
/* Enable taken branch trap. */
pa_psw(child)->r = 0;
pa_psw(child)->t = 1;
pa_psw(child)->h = 0;
pa_psw(child)->l = 0;
goto out_wake;
case PTRACE_SINGLESTEP:
ret = -EIO;
if ((unsigned long) data > _NSIG)
goto out_tsk;
child->ptrace &= ~(PT_TRACESYS|PT_BLOCKSTEP);
child->ptrace |= PT_SINGLESTEP;
child->exit_code = data;
if (pa_psw(child)->n) {
struct siginfo si;
/* Nullified, just crank over the queue. */
task_regs(child)->iaoq[0] = task_regs(child)->iaoq[1];
task_regs(child)->iasq[0] = task_regs(child)->iasq[1];
task_regs(child)->iaoq[1] = task_regs(child)->iaoq[0] + 4;
pa_psw(child)->n = 0;
pa_psw(child)->x = 0;
pa_psw(child)->y = 0;
pa_psw(child)->z = 0;
pa_psw(child)->b = 0;
pa_psw(child)->r = 0;
pa_psw(child)->t = 0;
pa_psw(child)->h = 0;
pa_psw(child)->l = 0;
/* Don't wake up the child, but let the
parent know something happened. */
si.si_code = TRAP_TRACE;
si.si_addr = (void *) (task_regs(child)->iaoq[0] & ~3);
si.si_signo = SIGTRAP;
si.si_errno = 0;
force_sig_info(SIGTRAP, &si, child);
//notify_parent(child, SIGCHLD);
//ret = 0;
goto out_wake;
}
/* Enable recovery counter traps. The recovery counter
* itself will be set to zero on a task switch. If the
* task is suspended on a syscall then the syscall return
* path will overwrite the recovery counter with a suitable
* value such that it traps once back in user space. We
* disable interrupts in the childs PSW here also, to avoid
* interrupts while the recovery counter is decrementing.
*/
pa_psw(child)->r = 1;
pa_psw(child)->t = 0;
pa_psw(child)->h = 0;
pa_psw(child)->l = 0;
/* give it a chance to run. */
goto out_wake;
case PTRACE_DETACH:
ret = -EIO;
if ((unsigned long) data > _NSIG)
goto out_tsk;
child->ptrace &= ~(PT_PTRACED|PT_TRACESYS|PT_SINGLESTEP|PT_BLOCKSTEP);
child->exit_code = data;
write_lock_irq(&tasklist_lock);
REMOVE_LINKS(child);
child->p_pptr = child->p_opptr;
SET_LINKS(child);
write_unlock_irq(&tasklist_lock);
goto out_wake_notrap;
default:
ret = -EIO;
goto out_tsk;
}
out_wake_notrap:
/* make sure the trap bits are not set */
pa_psw(child)->r = 0;
pa_psw(child)->t = 0;
pa_psw(child)->h = 0;
pa_psw(child)->l = 0;
out_wake:
wake_up_process(child);
ret = 0;
out_tsk:
free_task_struct(child);
out:
unlock_kernel();
return ret;
}
/**
* zfcp_adapter_enqueue - enqueue a new adapter to the list
* @ccw_device: pointer to the struct cc_device
*
* Returns: 0 if a new adapter was successfully enqueued
* -ENOMEM if alloc failed
* Enqueues an adapter at the end of the adapter list in the driver data.
* All adapter internal structures are set up.
* Proc-fs entries are also created.
* locks: config_sema must be held to serialise changes to the adapter list
*/
int zfcp_adapter_enqueue(struct ccw_device *ccw_device)
{
struct zfcp_adapter *adapter;
/*
* Note: It is safe to release the list_lock, as any list changes
* are protected by the config_sema, which must be held to get here
*/
adapter = kzalloc(sizeof(struct zfcp_adapter), GFP_KERNEL);
if (!adapter)
return -ENOMEM;
ccw_device->handler = NULL;
adapter->ccw_device = ccw_device;
atomic_set(&adapter->refcount, 0);
if (zfcp_qdio_allocate(adapter))
goto qdio_allocate_failed;
if (zfcp_allocate_low_mem_buffers(adapter))
goto failed_low_mem_buffers;
if (zfcp_reqlist_alloc(adapter))
goto failed_low_mem_buffers;
if (zfcp_adapter_debug_register(adapter))
goto debug_register_failed;
init_waitqueue_head(&adapter->remove_wq);
init_waitqueue_head(&adapter->erp_thread_wqh);
init_waitqueue_head(&adapter->erp_done_wqh);
INIT_LIST_HEAD(&adapter->port_list_head);
INIT_LIST_HEAD(&adapter->erp_ready_head);
INIT_LIST_HEAD(&adapter->erp_running_head);
spin_lock_init(&adapter->req_list_lock);
spin_lock_init(&adapter->hba_dbf_lock);
spin_lock_init(&adapter->san_dbf_lock);
spin_lock_init(&adapter->scsi_dbf_lock);
spin_lock_init(&adapter->rec_dbf_lock);
spin_lock_init(&adapter->req_q_lock);
rwlock_init(&adapter->erp_lock);
rwlock_init(&adapter->abort_lock);
sema_init(&adapter->erp_ready_sem, 0);
INIT_WORK(&adapter->stat_work, _zfcp_status_read_scheduler);
INIT_WORK(&adapter->scan_work, _zfcp_scan_ports_later);
/* mark adapter unusable as long as sysfs registration is not complete */
atomic_set_mask(ZFCP_STATUS_COMMON_REMOVE, &adapter->status);
dev_set_drvdata(&ccw_device->dev, adapter);
if (sysfs_create_group(&ccw_device->dev.kobj,
&zfcp_sysfs_adapter_attrs))
goto sysfs_failed;
write_lock_irq(&zfcp_data.config_lock);
atomic_clear_mask(ZFCP_STATUS_COMMON_REMOVE, &adapter->status);
list_add_tail(&adapter->list, &zfcp_data.adapter_list_head);
write_unlock_irq(&zfcp_data.config_lock);
zfcp_fc_nameserver_init(adapter);
return 0;
sysfs_failed:
zfcp_adapter_debug_unregister(adapter);
debug_register_failed:
dev_set_drvdata(&ccw_device->dev, NULL);
kfree(adapter->req_list);
failed_low_mem_buffers:
zfcp_free_low_mem_buffers(adapter);
qdio_allocate_failed:
zfcp_qdio_free(adapter);
kfree(adapter);
return -ENOMEM;
}
/**
* zfcp_port_enqueue - enqueue port to port list of adapter
* @adapter: adapter where remote port is added
* @wwpn: WWPN of the remote port to be enqueued
* @status: initial status for the port
* @d_id: destination id of the remote port to be enqueued
* Returns: pointer to enqueued port on success, ERR_PTR on error
*
* All port internal structures are set up and the sysfs entry is generated.
* d_id is used to enqueue ports with a well known address like the Directory
* Service for nameserver lookup.
*/
struct zfcp_port *zfcp_port_enqueue(struct zfcp_adapter *adapter, u64 wwpn,
u32 status, u32 d_id)
{
struct zfcp_port *port;
int retval = -ENOMEM;
kref_get(&adapter->ref);
port = zfcp_get_port_by_wwpn(adapter, wwpn);
if (port) {
put_device(&port->dev);
retval = -EEXIST;
goto err_out;
}
port = kzalloc(sizeof(struct zfcp_port), GFP_KERNEL);
if (!port)
goto err_out;
rwlock_init(&port->unit_list_lock);
INIT_LIST_HEAD(&port->unit_list);
INIT_WORK(&port->gid_pn_work, zfcp_fc_port_did_lookup);
INIT_WORK(&port->test_link_work, zfcp_fc_link_test_work);
INIT_WORK(&port->rport_work, zfcp_scsi_rport_work);
port->adapter = adapter;
port->d_id = d_id;
port->wwpn = wwpn;
port->rport_task = RPORT_NONE;
port->dev.parent = &adapter->ccw_device->dev;
port->dev.release = zfcp_port_release;
if (dev_set_name(&port->dev, "0x%016llx", (unsigned long long)wwpn)) {
kfree(port);
goto err_out;
}
retval = -EINVAL;
if (device_register(&port->dev)) {
put_device(&port->dev);
goto err_out;
}
if (sysfs_create_group(&port->dev.kobj,
&zfcp_sysfs_port_attrs))
goto err_out_put;
write_lock_irq(&adapter->port_list_lock);
list_add_tail(&port->list, &adapter->port_list);
write_unlock_irq(&adapter->port_list_lock);
atomic_set_mask(status | ZFCP_STATUS_COMMON_RUNNING, &port->status);
return port;
err_out_put:
device_unregister(&port->dev);
err_out:
zfcp_ccw_adapter_put(adapter);
return ERR_PTR(retval);
}
static void ib_cache_update(struct ib_device *device,
u8 port)
{
struct ib_port_attr *tprops = NULL;
struct ib_pkey_cache *pkey_cache = NULL, *old_pkey_cache;
struct ib_gid_cache *gid_cache = NULL, *old_gid_cache;
int i;
int ret;
tprops = kmalloc(sizeof *tprops, GFP_KERNEL);
if (!tprops)
return;
ret = ib_query_port(device, port, tprops);
if (ret) {
printk(KERN_WARNING "ib_query_port failed (%d) for %s\n",
ret, device->name);
goto err;
}
pkey_cache = kmalloc(sizeof *pkey_cache + tprops->pkey_tbl_len *
sizeof *pkey_cache->table, GFP_KERNEL);
if (!pkey_cache)
goto err;
pkey_cache->table_len = tprops->pkey_tbl_len;
gid_cache = kmalloc(sizeof *gid_cache + tprops->gid_tbl_len *
sizeof *gid_cache->table, GFP_KERNEL);
if (!gid_cache)
goto err;
gid_cache->table_len = tprops->gid_tbl_len;
for (i = 0; i < pkey_cache->table_len; ++i) {
ret = ib_query_pkey(device, port, i, pkey_cache->table + i);
if (ret) {
printk(KERN_WARNING "ib_query_pkey failed (%d) for %s (index %d)\n",
ret, device->name, i);
goto err;
}
}
for (i = 0; i < gid_cache->table_len; ++i) {
ret = ib_query_gid(device, port, i, gid_cache->table + i);
if (ret) {
printk(KERN_WARNING "ib_query_gid failed (%d) for %s (index %d)\n",
ret, device->name, i);
goto err;
}
}
write_lock_irq(&device->cache.lock);
old_pkey_cache = device->cache.pkey_cache[port - start_port(device)];
old_gid_cache = device->cache.gid_cache [port - start_port(device)];
device->cache.pkey_cache[port - start_port(device)] = pkey_cache;
device->cache.gid_cache [port - start_port(device)] = gid_cache;
device->cache.lmc_cache[port - start_port(device)] = tprops->lmc;
write_unlock_irq(&device->cache.lock);
kfree(old_pkey_cache);
kfree(old_gid_cache);
kfree(tprops);
return;
err:
kfree(pkey_cache);
kfree(gid_cache);
kfree(tprops);
}
/**
* write_one_page - write out a single page and optionally wait on I/O
* @page: the page to write
* @wait: if true, wait on writeout
*
* The page must be locked by the caller and will be unlocked upon return.
*
* write_one_page() returns a negative error code if I/O failed.
*/
int write_one_page(struct page *page, int wait)
{
struct address_space *mapping = page->mapping;
int ret = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 1,
};
BUG_ON(!PageLocked(page));
if (wait)
wait_on_page_writeback(page);
if (clear_page_dirty_for_io(page)) {
page_cache_get(page);
ret = mapping->a_ops->writepage(page, &wbc);
if (ret == 0 && wait) {
wait_on_page_writeback(page);
if (PageError(page))
ret = -EIO;
}
page_cache_release(page);
} else {
unlock_page(page);
}
return ret;
}
EXPORT_SYMBOL(write_one_page);
/*
* For address_spaces which do not use buffers nor write back.
*/
int __set_page_dirty_no_writeback(struct page *page)
{
if (!PageDirty(page))
SetPageDirty(page);
return 0;
}
/*
* For address_spaces which do not use buffers. Just tag the page as dirty in
* its radix tree.
*
* This is also used when a single buffer is being dirtied: we want to set the
* page dirty in that case, but not all the buffers. This is a "bottom-up"
* dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
*
* Most callers have locked the page, which pins the address_space in memory.
* But zap_pte_range() does not lock the page, however in that case the
* mapping is pinned by the vma's ->vm_file reference.
*
* We take care to handle the case where the page was truncated from the
* mapping by re-checking page_mapping() insode tree_lock.
*/
int __set_page_dirty_nobuffers(struct page *page)
{
if (!TestSetPageDirty(page)) {
struct address_space *mapping = page_mapping(page);
struct address_space *mapping2;
if (!mapping)
return 1;
write_lock_irq(&mapping->tree_lock);
mapping2 = page_mapping(page);
if (mapping2) { /* Race with truncate? */
BUG_ON(mapping2 != mapping);
WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
if (mapping_cap_account_dirty(mapping)) {
__inc_zone_page_state(page, NR_FILE_DIRTY);
task_io_account_write(PAGE_CACHE_SIZE);
}
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
write_unlock_irq(&mapping->tree_lock);
if (mapping->host) {
/* !PageAnon && !swapper_space */
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
return 1;
}
return 0;
}
EXPORT_SYMBOL(__set_page_dirty_nobuffers);
/*
* When a writepage implementation decides that it doesn't want to write this
* page for some reason, it should redirty the locked page via
* redirty_page_for_writepage() and it should then unlock the page and return 0
*/
int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
{
wbc->pages_skipped++;
return __set_page_dirty_nobuffers(page);
}
asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
{
struct task_struct *p;
int err = -EINVAL;
if (!pid)
pid = current->pid;
if (!pgid)
pgid = pid;
if (pgid < 0)
return -EINVAL;
/* From this point forward we keep holding onto the tasklist lock
* so that our parent does not change from under us. -DaveM
*/
write_lock_irq(&tasklist_lock);
err = -ESRCH;
p = find_task_by_pid(pid);
if (!p)
goto out;
err = -EINVAL;
if (!thread_group_leader(p))
goto out;
if (p->parent == current || p->real_parent == current) {
err = -EPERM;
if (p->signal->session != current->signal->session)
goto out;
err = -EACCES;
if (p->did_exec)
goto out;
} else {
err = -ESRCH;
if (p != current)
goto out;
}
err = -EPERM;
if (p->signal->leader)
goto out;
if (pgid != pid) {
struct task_struct *p;
do_each_task_pid(pgid, PIDTYPE_PGID, p) {
if (p->signal->session == current->signal->session)
goto ok_pgid;
} while_each_task_pid(pgid, PIDTYPE_PGID, p);
goto out;
}
ok_pgid:
err = security_task_setpgid(p, pgid);
if (err)
goto out;
if (process_group(p) != pgid) {
detach_pid(p, PIDTYPE_PGID);
p->signal->pgrp = pgid;
attach_pid(p, PIDTYPE_PGID, pgid);
}
err = 0;
out:
/* All paths lead to here, thus we are safe. -DaveM */
write_unlock_irq(&tasklist_lock);
return err;
}
void vcc_insert_socket(struct sock *sk)
{
write_lock_irq(&vcc_sklist_lock);
__vcc_insert_socket(sk);
write_unlock_irq(&vcc_sklist_lock);
}
/**
* zfcp_unit_enqueue - enqueue unit to unit list of a port.
* @port: pointer to port where unit is added
* @fcp_lun: FCP LUN of unit to be enqueued
* Returns: pointer to enqueued unit on success, ERR_PTR on error
* Locks: config_sema must be held to serialize changes to the unit list
*
* Sets up some unit internal structures and creates sysfs entry.
*/
struct zfcp_unit *zfcp_unit_enqueue(struct zfcp_port *port, u64 fcp_lun)
{
struct zfcp_unit *unit;
unit = kzalloc(sizeof(struct zfcp_unit), GFP_KERNEL);
if (!unit)
return ERR_PTR(-ENOMEM);
atomic_set(&unit->refcount, 0);
init_waitqueue_head(&unit->remove_wq);
unit->port = port;
unit->fcp_lun = fcp_lun;
dev_set_name(&unit->sysfs_device, "0x%016llx",
(unsigned long long) fcp_lun);
unit->sysfs_device.parent = &port->sysfs_device;
unit->sysfs_device.release = zfcp_sysfs_unit_release;
dev_set_drvdata(&unit->sysfs_device, unit);
/* mark unit unusable as long as sysfs registration is not complete */
atomic_set_mask(ZFCP_STATUS_COMMON_REMOVE, &unit->status);
spin_lock_init(&unit->latencies.lock);
unit->latencies.write.channel.min = 0xFFFFFFFF;
unit->latencies.write.fabric.min = 0xFFFFFFFF;
unit->latencies.read.channel.min = 0xFFFFFFFF;
unit->latencies.read.fabric.min = 0xFFFFFFFF;
unit->latencies.cmd.channel.min = 0xFFFFFFFF;
unit->latencies.cmd.fabric.min = 0xFFFFFFFF;
read_lock_irq(&zfcp_data.config_lock);
if (zfcp_get_unit_by_lun(port, fcp_lun)) {
read_unlock_irq(&zfcp_data.config_lock);
goto err_out_free;
}
read_unlock_irq(&zfcp_data.config_lock);
if (device_register(&unit->sysfs_device))
goto err_out_free;
if (sysfs_create_group(&unit->sysfs_device.kobj,
&zfcp_sysfs_unit_attrs)) {
device_unregister(&unit->sysfs_device);
return ERR_PTR(-EIO);
}
zfcp_unit_get(unit);
write_lock_irq(&zfcp_data.config_lock);
list_add_tail(&unit->list, &port->unit_list_head);
atomic_clear_mask(ZFCP_STATUS_COMMON_REMOVE, &unit->status);
atomic_set_mask(ZFCP_STATUS_COMMON_RUNNING, &unit->status);
write_unlock_irq(&zfcp_data.config_lock);
zfcp_port_get(port);
return unit;
err_out_free:
kfree(unit);
return ERR_PTR(-EINVAL);
}
/*
* This needs some heavy checking ...
* I just haven't the stomach for it. I also don't fully
* understand sessions/pgrp etc. Let somebody who does explain it.
*
* OK, I think I have the protection semantics right.... this is really
* only important on a multi-user system anyway, to make sure one user
* can't send a signal to a process owned by another. -TYT, 12/12/91
*
* Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
* LBT 04.03.94
*/
asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
{
struct task_struct *p;
struct task_struct *group_leader = current->group_leader;
int err = -EINVAL;
struct pid_namespace *ns;
if (!pid)
pid = task_pid_vnr(group_leader);
if (!pgid)
pgid = pid;
if (pgid < 0)
return -EINVAL;
/* From this point forward we keep holding onto the tasklist lock
* so that our parent does not change from under us. -DaveM
*/
ns = current->nsproxy->pid_ns;
write_lock_irq(&tasklist_lock);
err = -ESRCH;
p = find_task_by_pid_ns(pid, ns);
if (!p)
goto out;
err = -EINVAL;
if (!thread_group_leader(p))
goto out;
if (p->real_parent->tgid == group_leader->tgid) {
err = -EPERM;
if (task_session(p) != task_session(group_leader))
goto out;
err = -EACCES;
if (p->did_exec)
goto out;
} else {
err = -ESRCH;
if (p != group_leader)
goto out;
}
err = -EPERM;
if (p->signal->leader)
goto out;
if (pgid != pid) {
struct task_struct *g;
g = find_task_by_pid_type_ns(PIDTYPE_PGID, pgid, ns);
if (!g || task_session(g) != task_session(group_leader))
goto out;
}
err = security_task_setpgid(p, pgid);
if (err)
goto out;
if (task_pgrp_nr_ns(p, ns) != pgid) {
struct pid *pid;
detach_pid(p, PIDTYPE_PGID);
pid = find_vpid(pgid);
attach_pid(p, PIDTYPE_PGID, pid);
set_task_pgrp(p, pid_nr(pid));
}
err = 0;
out:
/* All paths lead to here, thus we are safe. -DaveM */
write_unlock_irq(&tasklist_lock);
return err;
}
/**
* zfcp_port_enqueue - enqueue port to port list of adapter
* @adapter: adapter where remote port is added
* @wwpn: WWPN of the remote port to be enqueued
* @status: initial status for the port
* @d_id: destination id of the remote port to be enqueued
* Returns: pointer to enqueued port on success, ERR_PTR on error
* Locks: config_sema must be held to serialize changes to the port list
*
* All port internal structures are set up and the sysfs entry is generated.
* d_id is used to enqueue ports with a well known address like the Directory
* Service for nameserver lookup.
*/
struct zfcp_port *zfcp_port_enqueue(struct zfcp_adapter *adapter, u64 wwpn,
u32 status, u32 d_id)
{
struct zfcp_port *port;
int retval;
port = kzalloc(sizeof(struct zfcp_port), GFP_KERNEL);
if (!port)
return ERR_PTR(-ENOMEM);
init_waitqueue_head(&port->remove_wq);
INIT_LIST_HEAD(&port->unit_list_head);
INIT_WORK(&port->gid_pn_work, zfcp_erp_port_strategy_open_lookup);
port->adapter = adapter;
port->d_id = d_id;
port->wwpn = wwpn;
/* mark port unusable as long as sysfs registration is not complete */
atomic_set_mask(status | ZFCP_STATUS_COMMON_REMOVE, &port->status);
atomic_set(&port->refcount, 0);
dev_set_name(&port->sysfs_device, "0x%016llx",
(unsigned long long)wwpn);
port->sysfs_device.parent = &adapter->ccw_device->dev;
port->sysfs_device.release = zfcp_sysfs_port_release;
dev_set_drvdata(&port->sysfs_device, port);
read_lock_irq(&zfcp_data.config_lock);
if (!(status & ZFCP_STATUS_PORT_NO_WWPN))
if (zfcp_get_port_by_wwpn(adapter, wwpn)) {
read_unlock_irq(&zfcp_data.config_lock);
goto err_out_free;
}
read_unlock_irq(&zfcp_data.config_lock);
if (device_register(&port->sysfs_device))
goto err_out_free;
retval = sysfs_create_group(&port->sysfs_device.kobj,
&zfcp_sysfs_port_attrs);
if (retval) {
device_unregister(&port->sysfs_device);
goto err_out;
}
zfcp_port_get(port);
write_lock_irq(&zfcp_data.config_lock);
list_add_tail(&port->list, &adapter->port_list_head);
atomic_clear_mask(ZFCP_STATUS_COMMON_REMOVE, &port->status);
atomic_set_mask(ZFCP_STATUS_COMMON_RUNNING, &port->status);
write_unlock_irq(&zfcp_data.config_lock);
zfcp_adapter_get(adapter);
return port;
err_out_free:
kfree(port);
err_out:
return ERR_PTR(-EINVAL);
}
asmlinkage int sys_wait4(pid_t pid,unsigned int * stat_addr, int options, struct rusage * ru)
{
int flag, retval;
struct wait_queue wait = { current, NULL };
struct task_struct *p;
if (options & ~(WNOHANG|WUNTRACED|__WCLONE))
return -EINVAL;
add_wait_queue(¤t->wait_chldexit,&wait);
repeat:
flag = 0;
/* The interruptible state must be set before looking at the
children. This because we want to catch any racy exit from
the children as do_exit() may run under us. The following
read_lock will enforce SMP ordering at the CPU level. */
current->state = TASK_INTERRUPTIBLE;
read_lock(&tasklist_lock);
for (p = current->p_cptr ; p ; p = p->p_osptr) {
if (pid>0) {
if (p->pid != pid)
continue;
} else if (!pid) {
if (p->pgrp != current->pgrp)
continue;
} else if (pid != -1) {
if (p->pgrp != -pid)
continue;
}
/* wait for cloned processes iff the __WCLONE flag is set */
if ((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0))
continue;
flag = 1;
switch (p->state) {
case TASK_STOPPED:
if (!p->exit_code)
continue;
if (!(options & WUNTRACED) && !(p->flags & PF_PTRACED))
continue;
read_unlock(&tasklist_lock);
current->state = TASK_RUNNING; /* We *must* do this before touching userspace! */
retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
if (!retval && stat_addr)
retval = put_user((p->exit_code << 8) | 0x7f, stat_addr);
if (!retval) {
p->exit_code = 0;
retval = p->pid;
}
goto end_wait4;
case TASK_ZOMBIE:
current->times.tms_cutime += p->times.tms_utime + p->times.tms_cutime;
current->times.tms_cstime += p->times.tms_stime + p->times.tms_cstime;
read_unlock(&tasklist_lock);
current->state = TASK_RUNNING; /* We *must* do this before touching userspace! */
retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
if (!retval && stat_addr)
retval = put_user(p->exit_code, stat_addr);
if (retval)
goto end_wait4;
retval = p->pid;
if (p->p_opptr != p->p_pptr) {
write_lock_irq(&tasklist_lock);
REMOVE_LINKS(p);
p->p_pptr = p->p_opptr;
SET_LINKS(p);
write_unlock_irq(&tasklist_lock);
notify_parent(p, SIGCHLD);
} else
release(p);
#ifdef DEBUG_PROC_TREE
audit_ptree();
#endif
goto end_wait4;
default:
continue;
}
}
read_unlock(&tasklist_lock);
if (flag) {
retval = 0;
if (options & WNOHANG)
goto end_wait4;
retval = -ERESTARTSYS;
if (signal_pending(current))
goto end_wait4;
schedule();
goto repeat;
}
retval = -ECHILD;
end_wait4:
remove_wait_queue(¤t->wait_chldexit,&wait);
current->state = TASK_RUNNING;
return retval;
}
/* adjtimex mainly allows reading (and writing, if superuser) of
* kernel time-keeping variables. used by xntpd.
*/
int do_adjtimex(struct timex *txc)
{
long ltemp, mtemp, save_adjust;
int result;
/* In order to modify anything, you gotta be super-user! */
if (txc->modes && !capable(CAP_SYS_TIME))
return -EPERM;
/* Now we validate the data before disabling interrupts */
if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT)
/* singleshot must not be used with any other mode bits */
if (txc->modes != ADJ_OFFSET_SINGLESHOT)
return -EINVAL;
if (txc->modes != ADJ_OFFSET_SINGLESHOT && (txc->modes & ADJ_OFFSET))
/* adjustment Offset limited to +- .512 seconds */
if (txc->offset <= - MAXPHASE || txc->offset >= MAXPHASE )
return -EINVAL;
/* if the quartz is off by more than 10% something is VERY wrong ! */
if (txc->modes & ADJ_TICK)
if (txc->tick < 900000/HZ || txc->tick > 1100000/HZ)
return -EINVAL;
write_lock_irq(&xtime_lock);
result = time_state; /* mostly `TIME_OK' */
/* Save for later - semantics of adjtime is to return old value */
save_adjust = time_adjust;
#if 0 /* STA_CLOCKERR is never set yet */
time_status &= ~STA_CLOCKERR; /* reset STA_CLOCKERR */
#endif
/* If there are input parameters, then process them */
if (txc->modes)
{
if (txc->modes & ADJ_STATUS) /* only set allowed bits */
time_status = (txc->status & ~STA_RONLY) |
(time_status & STA_RONLY);
if (txc->modes & ADJ_FREQUENCY) { /* p. 22 */
if (txc->freq > MAXFREQ || txc->freq < -MAXFREQ) {
result = -EINVAL;
goto leave;
}
time_freq = txc->freq - pps_freq;
}
if (txc->modes & ADJ_MAXERROR) {
if (txc->maxerror < 0 || txc->maxerror >= NTP_PHASE_LIMIT) {
result = -EINVAL;
goto leave;
}
time_maxerror = txc->maxerror;
}
if (txc->modes & ADJ_ESTERROR) {
if (txc->esterror < 0 || txc->esterror >= NTP_PHASE_LIMIT) {
result = -EINVAL;
goto leave;
}
time_esterror = txc->esterror;
}
if (txc->modes & ADJ_TIMECONST) { /* p. 24 */
if (txc->constant < 0) { /* NTP v4 uses values > 6 */
result = -EINVAL;
goto leave;
}
time_constant = txc->constant;
}
if (txc->modes & ADJ_OFFSET) { /* values checked earlier */
if (txc->modes == ADJ_OFFSET_SINGLESHOT) {
/* adjtime() is independent from ntp_adjtime() */
time_adjust = txc->offset;
}
else if ( time_status & (STA_PLL | STA_PPSTIME) ) {
ltemp = (time_status & (STA_PPSTIME | STA_PPSSIGNAL)) ==
(STA_PPSTIME | STA_PPSSIGNAL) ?
pps_offset : txc->offset;
/*
* Scale the phase adjustment and
* clamp to the operating range.
*/
if (ltemp > MAXPHASE)
time_offset = MAXPHASE << SHIFT_UPDATE;
else if (ltemp < -MAXPHASE)
time_offset = -(MAXPHASE << SHIFT_UPDATE);
else
time_offset = ltemp << SHIFT_UPDATE;
/*
* Select whether the frequency is to be controlled
* and in which mode (PLL or FLL). Clamp to the operating
* range. Ugly multiply/divide should be replaced someday.
*/
if (time_status & STA_FREQHOLD || time_reftime == 0)
time_reftime = xtime.tv_sec;
mtemp = xtime.tv_sec - time_reftime;
time_reftime = xtime.tv_sec;
if (time_status & STA_FLL) {
if (mtemp >= MINSEC) {
ltemp = (time_offset / mtemp) << (SHIFT_USEC -
SHIFT_UPDATE);
if (ltemp < 0)
time_freq -= -ltemp >> SHIFT_KH;
else
time_freq += ltemp >> SHIFT_KH;
} else /* calibration interval too short (p. 12) */
result = TIME_ERROR;
} else { /* PLL mode */
/*
* 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 *parent_tidptr,
int __user *child_tidptr,
struct pid *pid)
{
int retval;
struct task_struct *p = NULL;
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_TRACE_IRQFLAGS
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 != &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);
p->pid = pid_nr(pid);
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);
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->sched_time = 0;
#ifdef CONFIG_TASK_XACCT
p->rchar = 0; /* I/O counter: bytes read */
p->wchar = 0; /* I/O counter: bytes written */
p->syscr = 0; /* I/O counter: read syscalls */
p->syscw = 0; /* I/O counter: write syscalls */
#endif
task_io_accounting_init(p);
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->security = NULL;
p->io_context = NULL;
p->io_wait = NULL;
p->audit_context = NULL;
cpuset_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_copy(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
goto bad_fork_cleanup_cpuset;
}
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
p->tgid = p->pid;
if (clone_flags & CLONE_THREAD)
p->tgid = current->tgid;
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;
retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
if (retval)
goto bad_fork_cleanup_namespaces;
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;
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;
/*
* 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
/* Our parent execution domain becomes current domain
These must match for thread signalling to apply */
p->parent_exec_id = p->self_exec_id;
/* 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);
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);
/* 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.
*
* 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;
else
p->real_parent = current;
p->parent = p->real_parent;
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_cleanup_namespaces;
}
if (clone_flags & CLONE_THREAD) {
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)) {
add_parent(p);
if (unlikely(p->ptrace & PT_PTRACED))
__ptrace_link(p, current->parent);
if (thread_group_leader(p)) {
p->signal->tty = current->signal->tty;
p->signal->pgrp = process_group(current);
set_signal_session(p->signal, process_session(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);
return p;
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:
cleanup_signal(p);
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_free(p->mempolicy);
bad_fork_cleanup_cpuset:
#endif
cpuset_exit(p);
bad_fork_cleanup_delays_binfmt:
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);
}
/*
* 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->real_cred->user->processes) >=
p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
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;
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;
p->default_timer_slack_ns = current->timer_slack_ns;
#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);
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
if (unlikely(current->ptrace))
ptrace_fork(p, clone_flags);
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags);
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;
}
}
ftrace_graph_init_task(p);
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_graph;
}
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;
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());
/* 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_graph;
}
if (clone_flags & CLONE_THREAD) {
p->group_leader = current->group_leader;
list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
}
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;
tty_kref_put(p->signal->tty);
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_rcu(&p->tasks, &init_task.tasks);
__get_cpu_var(process_counts)++;
}
attach_pid(p, PIDTYPE_PID, pid);
nr_threads++;
}
#ifdef CONFIG_LTT_LITE
ltt_lite_ev_process(LTT_LITE_EV_PROCESS_FORK, p);
#endif
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_graph:
ftrace_graph_exit_task(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_mm:
if (p->mm)
mmput(p->mm);
bad_fork_cleanup_signal:
cleanup_signal(p);
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:
#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:
atomic_dec(&p->cred->user->processes);
put_cred(p->real_cred);
put_cred(p->cred);
bad_fork_free:
free_task(p);
fork_out:
return ERR_PTR(retval);
}
/*
* 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;
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;
}
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;
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 = p->stime = p->gtime = 0;
p->utimescaled = p->stimescaled = 0;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
p->prev_utime = p->prev_stime = 0;
#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);
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;
if (clone_flags & CLONE_THREAD)
threadgroup_change_begin(current);
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_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;
#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);
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 */
retval = copy_semundo(clone_flags, p);
if (retval)
goto bad_fork_cleanup_audit;
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(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;
}
p->pid = pid_nr(pid);
p->tgid = p->pid;
if (clone_flags & CLONE_THREAD)
p->tgid = current->tgid;
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_BLOCK
p->plug = NULL;
#endif
#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.. */
if (clone_flags & CLONE_THREAD)
p->exit_signal = -1;
else if (clone_flags & CLONE_PARENT)
p->exit_signal = current->group_leader->exit_signal;
else
p->exit_signal = (clone_flags & CSIGNAL);
p->pdeath_signal = 0;
p->exit_state = 0;
p->nr_dirtied = 0;
p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
p->dirty_paused_when = 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);
/* 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(¤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 (likely(p->pid)) {
ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
if (thread_group_leader(p)) {
if (is_child_reaper(pid))
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);
__this_cpu_inc(process_counts);
} else {
current->signal->nr_threads++;
atomic_inc(¤t->signal->live);
atomic_inc(¤t->signal->sigcnt);
p->group_leader = current->group_leader;
list_add_tail_rcu(&p->thread_group,
&p->group_leader->thread_group);
}
attach_pid(p, PIDTYPE_PID, pid);
nr_threads++;
}
total_forks++;
spin_unlock(¤t->sighand->siglock);
syscall_tracepoint_update(p);
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
if (clone_flags & CLONE_THREAD)
threadgroup_change_end(current);
perf_event_fork(p);
trace_task_newtask(p, clone_flags);
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:
if (unlikely(clone_flags & CLONE_NEWPID))
pid_ns_release_proc(p->nsproxy->pid_ns);
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_perf:
perf_event_free_task(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
#endif
if (clone_flags & CLONE_THREAD)
threadgroup_change_end(current);
cgroup_exit(p, 0);
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);
}
/*
* 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.
*/
struct task_struct *copy_process(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int *parent_tidptr,
int *child_tidptr)
{
int retval;
struct task_struct *p = NULL;
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);
if ((clone_flags & CLONE_DETACHED) && !(clone_flags & CLONE_THREAD))
return ERR_PTR(-EINVAL);
if (!(clone_flags & CLONE_DETACHED) && (clone_flags & CLONE_THREAD))
return ERR_PTR(-EINVAL);
retval = -ENOMEM;
p = dup_task_struct(current);
if (!p)
goto fork_out;
p->tux_info = NULL;
retval = -EAGAIN;
/*
* Increment user->__count before the rlimit test so that it would
* be correct if we take the bad_fork_free failure path.
*/
atomic_inc(&p->user->__count);
if (atomic_read(&p->user->processes) >= p->rlim[RLIMIT_NPROC].rlim_cur) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE))
goto bad_fork_free;
}
atomic_inc(&p->user->processes);
/*
* Counter increases are protected by
* the kernel lock so nr_threads can't
* increase under us (but it may decrease).
*/
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
get_exec_domain(p->exec_domain);
if (p->binfmt && p->binfmt->module)
__MOD_INC_USE_COUNT(p->binfmt->module);
p->did_exec = 0;
p->swappable = 0;
p->state = TASK_UNINTERRUPTIBLE;
copy_flags(clone_flags, p);
if (clone_flags & CLONE_IDLETASK)
p->pid = 0;
else {
p->pid = alloc_pidmap();
if (p->pid == -1)
goto bad_fork_cleanup;
}
retval = -EFAULT;
if (clone_flags & CLONE_PARENT_SETTID)
if (put_user(p->pid, parent_tidptr))
goto bad_fork_cleanup;
INIT_LIST_HEAD(&p->run_list);
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
init_waitqueue_head(&p->wait_chldexit);
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
spin_lock_init(&p->switch_lock);
p->sigpending = 0;
init_sigpending(&p->pending);
p->it_real_value = p->it_virt_value = p->it_prof_value = 0;
p->it_real_incr = p->it_virt_incr = p->it_prof_incr = 0;
init_timer(&p->real_timer);
p->real_timer.data = (unsigned long) p;
p->leader = 0; /* session leadership doesn't inherit */
p->tty_old_pgrp = 0;
memset(&p->utime, 0, sizeof(p->utime));
memset(&p->stime, 0, sizeof(p->stime));
memset(&p->cutime, 0, sizeof(p->cutime));
memset(&p->cstime, 0, sizeof(p->cstime));
memset(&p->group_utime, 0, sizeof(p->group_utime));
memset(&p->group_stime, 0, sizeof(p->group_stime));
memset(&p->group_cutime, 0, sizeof(p->group_cutime));
memset(&p->group_cstime, 0, sizeof(p->group_cstime));
#ifdef CONFIG_SMP
memset(&p->per_cpu_utime, 0, sizeof(p->per_cpu_utime));
memset(&p->per_cpu_stime, 0, sizeof(p->per_cpu_stime));
#endif
memset(&p->timing_state, 0, sizeof(p->timing_state));
p->timing_state.type = PROCESS_TIMING_USER;
p->last_sigxcpu = 0;
p->array = NULL;
p->lock_depth = -1; /* -1 = no lock */
p->start_time = jiffies;
retval = -ENOMEM;
/* copy all the process information */
if (copy_files(clone_flags, p))
goto bad_fork_cleanup;
if (copy_fs(clone_flags, p))
goto bad_fork_cleanup_files;
if (copy_sighand(clone_flags, p))
goto bad_fork_cleanup_fs;
if (copy_signal(clone_flags, p))
goto bad_fork_cleanup_sighand;
if (copy_mm(clone_flags, p))
goto bad_fork_cleanup_signal;
if (copy_namespace(clone_flags, p))
goto bad_fork_cleanup_mm;
retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
if (retval)
goto bad_fork_cleanup_namespace;
p->semundo = NULL;
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;
/* Our parent execution domain becomes current domain
These must match for thread signalling to apply */
p->parent_exec_id = p->self_exec_id;
/* ok, now we should be set up.. */
p->swappable = 1;
if (clone_flags & CLONE_DETACHED)
p->exit_signal = -1;
else
p->exit_signal = clone_flags & CSIGNAL;
p->pdeath_signal = 0;
/*
* Share the timeslice between parent and child, thus the
* total amount of pending timeslices in the system doesnt change,
* resulting in more scheduling fairness.
*/
local_irq_disable();
p->time_slice = (current->time_slice + 1) >> 1;
p->first_time_slice = 1;
/*
* The remainder of the first timeslice might be recovered by
* the parent if the child exits early enough.
*/
current->time_slice >>= 1;
p->last_run = jiffies;
if (!current->time_slice) {
/*
* This case is rare, it happens when the parent has only
* a single jiffy left from its timeslice. Taking the
* runqueue lock is not a problem.
*/
current->time_slice = 1;
scheduler_tick(0 /* don't update the time stats */);
}
local_irq_enable();
if ((int)current->time_slice <= 0)
BUG();
if ((int)p->time_slice <= 0)
BUG();
/*
* Ok, add it to the run-queues and make it
* visible to the rest of the system.
*
* Let it rip!
*/
p->tgid = p->pid;
p->group_leader = p;
INIT_LIST_HEAD(&p->ptrace_children);
INIT_LIST_HEAD(&p->ptrace_list);
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
/*
* Check for pending SIGKILL! The new thread should not be allowed
* to slip out of an OOM kill. (or normal SIGKILL.)
*/
if (sigismember(¤t->pending.signal, SIGKILL)) {
write_unlock_irq(&tasklist_lock);
retval = -EINTR;
goto bad_fork_cleanup_namespace;
}
/* CLONE_PARENT re-uses the old parent */
if (clone_flags & (CLONE_PARENT|CLONE_THREAD))
p->real_parent = current->real_parent;
else
p->real_parent = current;
p->parent = p->real_parent;
if (clone_flags & CLONE_THREAD) {
spin_lock(¤t->sighand->siglock);
/*
* Important: if an exit-all has been started then
* do not create this new thread - the whole thread
* group is supposed to exit anyway.
*/
if (current->signal->group_exit) {
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -EINTR;
goto bad_fork_cleanup_namespace;
}
p->tgid = current->tgid;
p->group_leader = current->group_leader;
if (current->signal->group_stop_count > 0) {
/*
* There is an all-stop in progress for the group.
* We ourselves will stop as soon as we check signals.
* Make the new thread part of that group stop too.
*/
current->signal->group_stop_count++;
p->sigpending = 1;
}
spin_unlock(¤t->sighand->siglock);
}
SET_LINKS(p);
if (p->ptrace & PT_PTRACED)
__ptrace_link(p, current->parent);
attach_pid(p, PIDTYPE_PID, p->pid);
if (thread_group_leader(p)) {
attach_pid(p, PIDTYPE_TGID, p->tgid);
attach_pid(p, PIDTYPE_PGID, p->pgrp);
attach_pid(p, PIDTYPE_SID, p->session);
} else {
link_pid(p, p->pids + PIDTYPE_TGID,
&p->group_leader->pids[PIDTYPE_TGID].pid);
}
/* clear controlling tty of new task if parent's was just cleared */
if (!current->tty && p->tty)
p->tty = NULL;
nr_threads++;
write_unlock_irq(&tasklist_lock);
retval = 0;
fork_out:
if (retval)
return ERR_PTR(retval);
return p;
bad_fork_cleanup_namespace:
exit_namespace(p);
bad_fork_cleanup_mm:
exit_mm(p);
if (p->active_mm)
mmdrop(p->active_mm);
bad_fork_cleanup_signal:
exit_signal(p);
bad_fork_cleanup_sighand:
exit_sighand(p);
bad_fork_cleanup_fs:
exit_fs(p); /* blocking */
bad_fork_cleanup_files:
exit_files(p); /* blocking */
bad_fork_cleanup:
if (p->pid > 0)
free_pidmap(p->pid);
put_exec_domain(p->exec_domain);
if (p->binfmt && p->binfmt->module)
__MOD_DEC_USE_COUNT(p->binfmt->module);
bad_fork_cleanup_count:
atomic_dec(&p->user->processes);
bad_fork_free:
p->state = TASK_ZOMBIE; /* debug */
atomic_dec(&p->usage);
put_task_struct(p);
goto fork_out;
}