/* Set the cred info into the current task */
void
crset(cred_t * cr)
{
#if defined(STRUCT_TASK_STRUCT_HAS_CRED)
struct cred *new_creds;
/* If our current task doesn't have identical real and effective
* credentials, commit_cred won't let us change them, so we just
* bail here.
*/
if (current->cred != current->real_cred)
return;
new_creds = prepare_creds();
/* Drop the reference to group_info - we'll overwrite it in afs_copy_creds */
put_group_info(new_creds->group_info);
afs_copy_creds(new_creds, current_cred());
commit_creds(new_creds);
#else
struct group_info *old_info;
current->fsuid = afs_cr_uid(cr);
current->uid = afs_cr_ruid(cr);
current->fsgid = afs_cr_gid(cr);
current->gid = afs_cr_rgid(cr);
get_group_info(afs_cr_group_info(cr));
task_lock(current);
old_info = current->group_info;
current->group_info = afs_cr_group_info(cr);
task_unlock(current);
put_group_info(old_info);
#endif
}
asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
{
int i = 0;
/*
* SMP: Nobody else can change our grouplist. Thus we are
* safe.
*/
if (gidsetsize < 0)
return -EINVAL;
/* no need to grab task_lock here; it cannot change */
get_group_info(current->group_info);
i = current->group_info->ngroups;
if (gidsetsize) {
if (i > gidsetsize) {
i = -EINVAL;
goto out;
}
if (groups_to_user(grouplist, current->group_info)) {
i = -EFAULT;
goto out;
}
}
out:
put_group_info(current->group_info);
return i;
}
int in_egroup_p(gid_t grp)
{
int retval = 1;
if (grp != current->egid) {
get_group_info(current->group_info);
retval = groups_search(current->group_info, grp);
put_group_info(current->group_info);
}
return retval;
}
/*
* Return an array of supplemental gids. The returned address is safe
* to use as long as the caller has taken a reference with crhold().
* The caller is responsible for releasing the reference with crfree().
*/
gid_t *
crgetgroups(const cred_t *cr)
{
struct group_info *gi;
gid_t *gids;
gi = get_group_info(cr->group_info);
gids = gi->blocks[0];
put_group_info(gi);
return gids;
}
void
crfree(cred_t * cr)
{
#if defined(STRUCT_TASK_STRUCT_HAS_CRED)
put_cred(cr);
#else
if (atomic_dec_and_test(&cr->cr_ref)) {
put_group_info(afs_cr_group_info(cr));
kfree(cr);
}
#endif
}
/* Check if the passed gid is available is in supplied credential. */
int
groupmember(gid_t gid, const cred_t *cr)
{
struct group_info *gi;
int rc;
gi = get_group_info(cr->group_info);
rc = cr_groups_search(cr->group_info, gid);
put_group_info(gi);
return rc;
}
/* Return the number of supplemental groups */
int
crgetngroups(const cred_t *cr)
{
struct group_info *gi;
int rc;
gi = get_group_info(cr->group_info);
rc = gi->ngroups;
put_group_info(gi);
return rc;
}
void __put_task_struct(struct task_struct *tsk)
{
WARN_ON(!(tsk->state & (TASK_DEAD | TASK_ZOMBIE)));
WARN_ON(atomic_read(&tsk->usage));
WARN_ON(tsk == current);
if (unlikely(tsk->audit_context))
audit_free(tsk);
security_task_free(tsk);
free_uid(tsk->user);
put_group_info(tsk->group_info);
free_task(tsk);
}
static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *p)
{
struct group_info *group_info;
int g;
struct fdtable *fdt = NULL;
pid_t ppid, tpid;
rcu_read_lock();
ppid = pid_alive(p) ?
task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
tpid = 0;
if (pid_alive(p)) {
struct task_struct *tracer = tracehook_tracer_task(p);
if (tracer)
tpid = task_pid_nr_ns(tracer, ns);
}
seq_printf(m,
"State:\t%s\n"
"Tgid:\t%d\n"
"Pid:\t%d\n"
"PPid:\t%d\n"
"TracerPid:\t%d\n"
"Uid:\t%d\t%d\t%d\t%d\n"
"Gid:\t%d\t%d\t%d\t%d\n",
get_task_state(p),
task_tgid_nr_ns(p, ns),
pid_nr_ns(pid, ns),
ppid, tpid,
p->uid, p->euid, p->suid, p->fsuid,
p->gid, p->egid, p->sgid, p->fsgid);
task_lock(p);
if (p->files)
fdt = files_fdtable(p->files);
seq_printf(m,
"FDSize:\t%d\n"
"Groups:\t",
fdt ? fdt->max_fds : 0);
rcu_read_unlock();
group_info = p->group_info;
get_group_info(group_info);
task_unlock(p);
for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++)
seq_printf(m, "%d ", GROUP_AT(group_info, g));
put_group_info(group_info);
seq_printf(m, "\n");
}
void
crfree(cred_t * cr)
{
if (cr->cr_ref > 1) {
cr->cr_ref--;
return;
}
#if defined(AFS_LINUX26_ENV)
put_group_info(cr->cr_group_info);
#endif
kfree(cr);
}
void __put_task_struct(struct task_struct *tsk)
{
WARN_ON(!tsk->exit_state);
WARN_ON(atomic_read(&tsk->usage));
WARN_ON(tsk == current);
security_task_free(tsk);
free_uid(tsk->user);
put_group_info(tsk->group_info);
delayacct_tsk_free(tsk);
if (!profile_handoff_task(tsk))
free_task(tsk);
}
SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
{
struct group_info *group_info;
int retval;
if (!nsown_capable(CAP_SETGID))
return -EPERM;
if ((unsigned)gidsetsize > NGROUPS_MAX)
return -EINVAL;
group_info = groups_alloc(gidsetsize);
if (!group_info)
return -ENOMEM;
retval = groups16_from_user(group_info, grouplist);
if (retval) {
put_group_info(group_info);
return retval;
}
retval = set_current_groups(group_info);
put_group_info(group_info);
return retval;
}
void __put_task_struct(struct task_struct *tsk)
{
WARN_ON(!(tsk->exit_state & (EXIT_DEAD | EXIT_ZOMBIE)));
WARN_ON(atomic_read(&tsk->usage));
WARN_ON(tsk == current);
if (unlikely(tsk->audit_context))
audit_free(tsk);
security_task_free(tsk);
free_uid(tsk->user);
put_group_info(tsk->group_info);
if (!profile_handoff_task(tsk))
free_task(tsk);
}
asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist)
{
struct group_info *group_info;
int retval;
if (!capable(CAP_SETGID))
return -EPERM;
if ((unsigned)gidsetsize > NGROUPS_MAX)
return -EINVAL;
group_info = groups_alloc(gidsetsize);
if (!group_info)
return -ENOMEM;
retval = groups16_from_user(group_info, grouplist);
if (retval) {
put_group_info(group_info);
return retval;
}
retval = set_current_groups(group_info);
put_group_info(group_info);
return retval;
}
static void mdt_identity_entry_free(struct upcall_cache *cache,
struct upcall_cache_entry *entry)
{
struct md_identity *identity = &entry->u.identity;
if (identity->mi_ginfo) {
put_group_info(identity->mi_ginfo);
identity->mi_ginfo = NULL;
}
if (identity->mi_nperms) {
LASSERT(identity->mi_perms);
OBD_FREE(identity->mi_perms,
identity->mi_nperms * sizeof(struct md_perm));
identity->mi_nperms = 0;
}
}
static inline char * task_state(struct task_struct *p, char *buffer)
{
struct group_info *group_info;
int g;
struct fdtable *fdt = NULL;
read_lock(&tasklist_lock);
buffer += sprintf(buffer,
"State:\t%s\n"
"SleepAVG:\t%lu%%\n"
"Tgid:\t%d\n"
"Pid:\t%d\n"
"PPid:\t%d\n"
"TracerPid:\t%d\n"
"Uid:\t%d\t%d\t%d\t%d\n"
"Gid:\t%d\t%d\t%d\t%d\n",
get_task_state(p),
(p->sleep_avg/1024)*100/(1020000000/1024),
p->tgid,
p->pid, pid_alive(p) ? p->group_leader->real_parent->tgid : 0,
pid_alive(p) && p->ptrace ? p->parent->pid : 0,
p->uid, p->euid, p->suid, p->fsuid,
p->gid, p->egid, p->sgid, p->fsgid);
read_unlock(&tasklist_lock);
task_lock(p);
rcu_read_lock();
if (p->files)
fdt = files_fdtable(p->files);
buffer += sprintf(buffer,
"FDSize:\t%d\n"
"Groups:\t",
fdt ? fdt->max_fds : 0);
rcu_read_unlock();
group_info = p->group_info;
get_group_info(group_info);
task_unlock(p);
for (g = 0; g < min(group_info->ngroups,NGROUPS_SMALL); g++)
buffer += sprintf(buffer, "%d ", GROUP_AT(group_info,g));
put_group_info(group_info);
buffer += sprintf(buffer, "\n");
return buffer;
}
/* Check if the passed gid is available is in supplied credential. */
int
groupmember(gid_t gid, const cred_t *cr)
{
int lock, rc;
lock = (cr != current);
if (lock)
task_lock((struct task_struct *)cr);
get_group_info(cr->group_info);
rc = cr_groups_search(cr->group_info, gid);
put_group_info(cr->group_info);
if (lock)
task_unlock((struct task_struct *)cr);
return rc;
}
/*
* Use the SETCLIENTID credential
*/
static struct rpc_cred *
nfsd4_lookupcred(struct nfs4_client *clp, int taskflags)
{
struct auth_cred acred;
struct rpc_clnt *clnt = clp->cl_callback.cb_client;
struct rpc_cred *ret;
get_group_info(clp->cl_cred.cr_group_info);
acred.uid = clp->cl_cred.cr_uid;
acred.gid = clp->cl_cred.cr_gid;
acred.group_info = clp->cl_cred.cr_group_info;
dprintk("NFSD: looking up %s cred\n",
clnt->cl_auth->au_ops->au_name);
ret = rpcauth_lookup_credcache(clnt->cl_auth, &acred, taskflags);
put_group_info(clp->cl_cred.cr_group_info);
return ret;
}
/* Return the number of supplemental groups */
int
crgetngroups(const cred_t *cr)
{
int lock, rc;
lock = (cr != current);
if (lock)
task_lock((struct task_struct *)cr);
get_group_info(cr->group_info);
rc = cr->group_info->ngroups;
put_group_info(cr->group_info);
if (lock)
task_unlock((struct task_struct *)cr);
return rc;
}
static inline void task_state(struct seq_file *m, struct pid *pid,
struct task_struct *p)
{
struct group_info *group_info;
int g;
struct fdtable *fdt = NULL;
rcu_read_lock();
seq_printf(m,
"State:\t%s\n"
"SleepAVG:\t%lu%%\n"
"Tgid:\t%d\n"
"Pid:\t%d\n"
"PPid:\t%d\n"
"TracerPid:\t%d\n"
"Uid:\t%d\t%d\t%d\t%d\n"
"Gid:\t%d\t%d\t%d\t%d\n",
get_task_state(p),
(p->sleep_avg/1024)*100/(1020000000/1024),
p->tgid, p->pid,
pid_alive(p) ? rcu_dereference(p->real_parent)->tgid : 0,
pid_alive(p) && p->ptrace ? rcu_dereference(p->parent)->pid : 0,
p->uid, p->euid, p->suid, p->fsuid,
p->gid, p->egid, p->sgid, p->fsgid);
task_lock(p);
if (p->files)
fdt = files_fdtable(p->files);
seq_printf(m,
"FDSize:\t%d\n"
"Groups:\t",
fdt ? fdt->max_fds : 0);
rcu_read_unlock();
group_info = p->group_info;
get_group_info(group_info);
task_unlock(p);
for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++)
seq_printf(m, "%d ", GROUP_AT(group_info, g));
put_group_info(group_info);
seq_printf(m, "\n");
}
/*
* Return an array of supplemental gids. The returned address is safe
* to use as long as the caller has taken a reference with crhold().
* The caller is responsible for releasing the reference with crfree().
*/
gid_t *
crgetgroups(const cred_t *cr)
{
gid_t *gids;
int lock;
lock = (cr != current);
if (lock)
task_lock((struct task_struct *)cr);
get_group_info(cr->group_info);
gids = cr->group_info->blocks[0];
put_group_info(cr->group_info);
if (lock)
task_unlock((struct task_struct *)cr);
return gids;
}
/* Set the cred info into the current task */
void
crset(cred_t * cr)
{
#if defined(STRUCT_TASK_HAS_CRED)
struct cred *new_creds;
new_creds = prepare_creds();
new_creds->fsuid = cr->cr_uid;
new_creds->uid = cr->cr_ruid;
new_creds->fsgid = cr->cr_gid;
new_creds->gid = cr->cr_rgid;
#else
current->fsuid = cr->cr_uid;
current->uid = cr->cr_ruid;
current->fsgid = cr->cr_gid;
current->gid = cr->cr_rgid;
#endif
#if defined(AFS_LINUX26_ENV)
{
struct group_info *old_info;
/* using set_current_groups() will sort the groups */
get_group_info(cr->cr_group_info);
task_lock(current);
#if defined(STRUCT_TASK_HAS_CRED)
old_info = current->cred->group_info;
new_creds->group_info = cr->cr_group_info;
commit_creds(new_creds);
#else
old_info = current->group_info;
current->group_info = cr->cr_group_info;
#endif
task_unlock(current);
put_group_info(old_info);
}
#else
memcpy(current->groups, cr->cr_groups, NGROUPS * sizeof(gid_t));
current->ngroups = cr->cr_ngroups;
#endif
}
void mdt_exit_ucred(struct mdt_thread_info *info)
{
struct lu_ucred *uc = mdt_ucred(info);
struct mdt_device *mdt = info->mti_mdt;
LASSERT(uc != NULL);
if (uc->uc_valid != UCRED_INIT) {
uc->uc_suppgids[0] = uc->uc_suppgids[1] = -1;
if (uc->uc_ginfo) {
put_group_info(uc->uc_ginfo);
uc->uc_ginfo = NULL;
}
if (uc->uc_identity) {
mdt_identity_put(mdt->mdt_identity_cache,
uc->uc_identity);
uc->uc_identity = NULL;
}
uc->uc_valid = UCRED_INIT;
}
}
/* validate and set current->group_info */
int set_current_groups(struct group_info *group_info)
{
int retval;
struct group_info *old_info;
retval = security_task_setgroups(group_info);
if (retval)
return retval;
groups_sort(group_info);
get_group_info(group_info);
task_lock(current);
old_info = current->group_info;
current->group_info = group_info;
task_unlock(current);
put_group_info(old_info);
return 0;
}
asmlinkage long sys_getgroups16(int gidsetsize, old_gid_t __user *grouplist)
{
int i = 0;
if (gidsetsize < 0)
return -EINVAL;
get_group_info(current->group_info);
i = current->group_info->ngroups;
if (gidsetsize) {
if (i > gidsetsize) {
i = -EINVAL;
goto out;
}
if (groups16_to_user(grouplist, current->group_info)) {
i = -EFAULT;
goto out;
}
}
out:
put_group_info(current->group_info);
return i;
}
/*
* 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->it_real_value = 0;
p->it_real_incr = 0;
p->it_virt_value = cputime_zero;
p->it_virt_incr = cputime_zero;
p->it_prof_value = cputime_zero;
p->it_prof_incr = cputime_zero;
init_timer(&p->real_timer);
p->real_timer.data = (unsigned long) p;
p->utime = cputime_zero;
p->stime = cputime_zero;
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->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);
}
spin_unlock(¤t->sighand->siglock);
}
SET_LINKS(p);
if (unlikely(p->ptrace & PT_PTRACED))
__ptrace_link(p, current->parent);
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;
}
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
*
* It copies the registers, and all the appropriate
* parts of the process environment (as per the clone
* flags). The actual kick-off is left to the caller.
*/
static struct task_struct *copy_process(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *child_tidptr,
struct pid *pid,
int trace)
{
int retval;
struct task_struct *p;
int cgroup_callbacks_done = 0;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
/*
* Thread groups must share signals as well, and detached threads
* can only be started up within the thread group.
*/
if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
return ERR_PTR(-EINVAL);
/*
* Shared signal handlers imply shared VM. By way of the above,
* thread groups also imply shared VM. Blocking this case allows
* for various simplifications in other code.
*/
if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
return ERR_PTR(-EINVAL);
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
retval = -ENOMEM;
p = dup_task_struct(current);
if (!p)
goto fork_out;
rt_mutex_init_task(p);
#ifdef CONFIG_PROVE_LOCKING
DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
retval = -EAGAIN;
if (atomic_read(&p->user->processes) >=
p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
p->user != current->nsproxy->user_ns->root_user)
goto bad_fork_free;
}
atomic_inc(&p->user->__count);
atomic_inc(&p->user->processes);
get_group_info(p->group_info);
/*
* If multiple threads are within copy_process(), then this check
* triggers too late. This doesn't hurt, the check is only there
* to stop root fork bombs.
*/
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
if (!try_module_get(task_thread_info(p)->exec_domain->module))
goto bad_fork_cleanup_count;
if (p->binfmt && !try_module_get(p->binfmt->module))
goto bad_fork_cleanup_put_domain;
p->did_exec = 0;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
copy_flags(clone_flags, p);
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
#ifdef CONFIG_PREEMPT_RCU
p->rcu_read_lock_nesting = 0;
p->rcu_flipctr_idx = 0;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
clear_tsk_thread_flag(p, TIF_SIGPENDING);
init_sigpending(&p->pending);
p->utime = cputime_zero;
p->stime = cputime_zero;
p->gtime = cputime_zero;
p->utimescaled = cputime_zero;
p->stimescaled = cputime_zero;
p->prev_utime = cputime_zero;
p->prev_stime = cputime_zero;
#ifdef CONFIG_DETECT_SOFTLOCKUP
p->last_switch_count = 0;
p->last_switch_timestamp = 0;
#endif
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
p->it_virt_expires = cputime_zero;
p->it_prof_expires = cputime_zero;
p->it_sched_expires = 0;
INIT_LIST_HEAD(&p->cpu_timers[0]);
INIT_LIST_HEAD(&p->cpu_timers[1]);
INIT_LIST_HEAD(&p->cpu_timers[2]);
p->lock_depth = -1; /* -1 = no lock */
do_posix_clock_monotonic_gettime(&p->start_time);
p->real_start_time = p->start_time;
monotonic_to_bootbased(&p->real_start_time);
#ifdef CONFIG_SECURITY
p->security = NULL;
#endif
p->cap_bset = current->cap_bset;
p->io_context = NULL;
p->audit_context = NULL;
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
goto bad_fork_cleanup_cgroup;
}
mpol_fix_fork_child_flag(p);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
p->irq_events = 0;
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
p->hardirqs_enabled = 1;
#else
p->hardirqs_enabled = 0;
#endif
p->hardirq_enable_ip = 0;
p->hardirq_enable_event = 0;
p->hardirq_disable_ip = _THIS_IP_;
p->hardirq_disable_event = 0;
p->softirqs_enabled = 1;
p->softirq_enable_ip = _THIS_IP_;
p->softirq_enable_event = 0;
p->softirq_disable_ip = 0;
p->softirq_disable_event = 0;
p->hardirq_context = 0;
p->softirq_context = 0;
#endif
#ifdef CONFIG_LOCKDEP
p->lockdep_depth = 0; /* no locks held yet */
p->curr_chain_key = 0;
p->lockdep_recursion = 0;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags);
if ((retval = security_task_alloc(p)))
goto bad_fork_cleanup_policy;
if ((retval = audit_alloc(p)))
goto bad_fork_cleanup_security;
/* copy all the process information */
if ((retval = copy_semundo(clone_flags, p)))
goto bad_fork_cleanup_audit;
if ((retval = copy_files(clone_flags, p)))
goto bad_fork_cleanup_semundo;
if ((retval = copy_fs(clone_flags, p)))
goto bad_fork_cleanup_files;
if ((retval = copy_sighand(clone_flags, p)))
goto bad_fork_cleanup_fs;
if ((retval = copy_signal(clone_flags, p)))
goto bad_fork_cleanup_sighand;
if ((retval = copy_mm(clone_flags, p)))
goto bad_fork_cleanup_signal;
if ((retval = copy_keys(clone_flags, p)))
goto bad_fork_cleanup_mm;
if ((retval = copy_namespaces(clone_flags, p)))
goto bad_fork_cleanup_keys;
if ((retval = copy_io(clone_flags, p)))
goto bad_fork_cleanup_namespaces;
retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
if (retval)
goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
retval = -ENOMEM;
pid = alloc_pid(task_active_pid_ns(p));
if (!pid)
goto bad_fork_cleanup_io;
if (clone_flags & CLONE_NEWPID) {
retval = pid_ns_prepare_proc(task_active_pid_ns(p));
if (retval < 0)
goto bad_fork_free_pid;
}
}
p->pid = pid_nr(pid);
p->tgid = p->pid;
if (clone_flags & CLONE_THREAD)
p->tgid = current->tgid;
if (current->nsproxy != p->nsproxy) {
retval = ns_cgroup_clone(p, pid);
if (retval)
goto bad_fork_free_pid;
}
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
/*
* Clear TID on mm_release()?
*/
p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
#ifdef CONFIG_FUTEX
p->robust_list = NULL;
#ifdef CONFIG_COMPAT
p->compat_robust_list = NULL;
#endif
INIT_LIST_HEAD(&p->pi_state_list);
p->pi_state_cache = NULL;
#endif
/*
* sigaltstack should be cleared when sharing the same VM
*/
if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
p->sas_ss_sp = p->sas_ss_size = 0;
/*
* Syscall tracing should be turned off in the child regardless
* of CLONE_PTRACE.
*/
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
clear_all_latency_tracing(p);
/* ok, now we should be set up.. */
p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
p->pdeath_signal = 0;
p->exit_state = 0;
/*
* Ok, make it visible to the rest of the system.
* We dont wake it up yet.
*/
p->group_leader = p;
INIT_LIST_HEAD(&p->thread_group);
/* Now that the task is set up, run cgroup callbacks if
* necessary. We need to run them before the task is visible
* on the tasklist. */
cgroup_fork_callbacks(p);
cgroup_callbacks_done = 1;
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
/*
* The task hasn't been attached yet, so its cpus_allowed mask will
* not be changed, nor will its assigned CPU.
*
* The cpus_allowed mask of the parent may have changed after it was
* copied first time - so re-copy it here, then check the child's CPU
* to ensure it is on a valid CPU (and if not, just force it back to
* parent's CPU). This avoids alot of nasty races.
*/
p->cpus_allowed = current->cpus_allowed;
if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
!cpu_online(task_cpu(p))))
set_task_cpu(p, smp_processor_id());
/* CLONE_PARENT re-uses the old parent */
if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
p->real_parent = current->real_parent;
p->parent_exec_id = current->parent_exec_id;
} else {
p->real_parent = current;
p->parent_exec_id = current->self_exec_id;
}
spin_lock(¤t->sighand->siglock);
/*
* Process group and session signals need to be delivered to just the
* parent before the fork or both the parent and the child after the
* fork. Restart if a signal comes in before we add the new process to
* it's process group.
* A fatal signal pending means that current will exit, so the new
* thread can't slip out of an OOM kill (or normal SIGKILL).
*/
recalc_sigpending();
if (signal_pending(current)) {
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
goto bad_fork_free_pid;
}
if (clone_flags & CLONE_THREAD) {
atomic_inc(¤t->signal->count);
atomic_inc(¤t->signal->live);
p->group_leader = current->group_leader;
list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
if (!cputime_eq(current->signal->it_virt_expires,
cputime_zero) ||
!cputime_eq(current->signal->it_prof_expires,
cputime_zero) ||
current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY ||
!list_empty(¤t->signal->cpu_timers[0]) ||
!list_empty(¤t->signal->cpu_timers[1]) ||
!list_empty(¤t->signal->cpu_timers[2])) {
/*
* Have child wake up on its first tick to check
* for process CPU timers.
*/
p->it_prof_expires = jiffies_to_cputime(1);
}
}
if (likely(p->pid)) {
list_add_tail(&p->sibling, &p->real_parent->children);
tracehook_finish_clone(p, clone_flags, trace);
if (thread_group_leader(p)) {
if (clone_flags & CLONE_NEWPID)
p->nsproxy->pid_ns->child_reaper = p;
p->signal->leader_pid = pid;
p->signal->tty = current->signal->tty;
set_task_pgrp(p, task_pgrp_nr(current));
set_task_session(p, task_session_nr(current));
attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
attach_pid(p, PIDTYPE_SID, task_session(current));
list_add_tail_rcu(&p->tasks, &init_task.tasks);
__get_cpu_var(process_counts)++;
}
attach_pid(p, PIDTYPE_PID, pid);
nr_threads++;
}
total_forks++;
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
return p;
bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_io:
put_io_context(p->io_context);
bad_fork_cleanup_namespaces:
exit_task_namespaces(p);
bad_fork_cleanup_keys:
exit_keys(p);
bad_fork_cleanup_mm:
if (p->mm)
mmput(p->mm);
bad_fork_cleanup_signal:
if (!(clone_flags & CLONE_THREAD))
__cleanup_signal(p->signal);
bad_fork_cleanup_sighand:
__cleanup_sighand(p->sighand);
bad_fork_cleanup_fs:
exit_fs(p); /* blocking */
bad_fork_cleanup_files:
exit_files(p); /* blocking */
bad_fork_cleanup_semundo:
exit_sem(p);
bad_fork_cleanup_audit:
audit_free(p);
bad_fork_cleanup_security:
security_task_free(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
#endif
cgroup_exit(p, cgroup_callbacks_done);
delayacct_tsk_free(p);
if (p->binfmt)
module_put(p->binfmt->module);
bad_fork_cleanup_put_domain:
module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
put_group_info(p->group_info);
atomic_dec(&p->user->processes);
free_uid(p->user);
bad_fork_free:
free_task(p);
fork_out:
return ERR_PTR(retval);
}
/* Free a reference on the credential and group info */
void
crfree(cred_t *cr)
{
put_group_info(cr->group_info);
put_cred((const cred_t *)cr);
}
struct rpc_cred *rpc_lookup_machine_cred(void)
{
struct auth_cred acred = {
.uid = RPC_MACHINE_CRED_USERID,
.gid = RPC_MACHINE_CRED_GROUPID,
.machine_cred = 1,
};
dprintk("RPC: looking up machine cred\n");
return generic_auth.au_ops->lookup_cred(&generic_auth, &acred, 0);
}
EXPORT_SYMBOL_GPL(rpc_lookup_machine_cred);
static void
generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred, int lookupflags)
{
struct rpc_auth *auth = task->tk_client->cl_auth;
struct auth_cred *acred = &container_of(cred, struct generic_cred, gc_base)->acred;
struct rpc_cred *ret;
ret = auth->au_ops->lookup_cred(auth, acred, lookupflags);
if (!IS_ERR(ret))
task->tk_msg.rpc_cred = ret;
else
task->tk_status = PTR_ERR(ret);
}
static struct rpc_cred *
generic_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
{
return rpcauth_lookup_credcache(&generic_auth, acred, flags);
}
static struct rpc_cred *
generic_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
{
struct generic_cred *gcred;
gcred = kmalloc(sizeof(*gcred), GFP_KERNEL);
if (gcred == NULL)
return ERR_PTR(-ENOMEM);
rpcauth_init_cred(&gcred->gc_base, acred, &generic_auth, &generic_credops);
gcred->gc_base.cr_flags = 1UL << RPCAUTH_CRED_UPTODATE;
gcred->acred.uid = acred->uid;
gcred->acred.gid = acred->gid;
gcred->acred.group_info = acred->group_info;
if (gcred->acred.group_info != NULL)
get_group_info(gcred->acred.group_info);
gcred->acred.machine_cred = acred->machine_cred;
dprintk("RPC: allocated %s cred %p for uid %d gid %d\n",
gcred->acred.machine_cred ? "machine" : "generic",
gcred, acred->uid, acred->gid);
return &gcred->gc_base;
}
static void
generic_free_cred(struct rpc_cred *cred)
{
struct generic_cred *gcred = container_of(cred, struct generic_cred, gc_base);
dprintk("RPC: generic_free_cred %p\n", gcred);
if (gcred->acred.group_info != NULL)
put_group_info(gcred->acred.group_info);
kfree(gcred);
}
static void
generic_free_cred_callback(struct rcu_head *head)
{
struct rpc_cred *cred = container_of(head, struct rpc_cred, cr_rcu);
generic_free_cred(cred);
}
static void
generic_destroy_cred(struct rpc_cred *cred)
{
call_rcu(&cred->cr_rcu, generic_free_cred_callback);
}
int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
{
struct svc_cred cred = rqstp->rq_cred;
int i;
int flags = nfsexp_flags(rqstp, exp);
int ret;
if (flags & NFSEXP_ALLSQUASH) {
cred.cr_uid = exp->ex_anon_uid;
cred.cr_gid = exp->ex_anon_gid;
cred.cr_group_info = groups_alloc(0);
} else if (flags & NFSEXP_ROOTSQUASH) {
struct group_info *gi;
if (!cred.cr_uid)
cred.cr_uid = exp->ex_anon_uid;
if (!cred.cr_gid)
cred.cr_gid = exp->ex_anon_gid;
gi = groups_alloc(cred.cr_group_info->ngroups);
if (gi)
for (i = 0; i < cred.cr_group_info->ngroups; i++) {
if (!GROUP_AT(cred.cr_group_info, i))
GROUP_AT(gi, i) = exp->ex_anon_gid;
else
GROUP_AT(gi, i) = GROUP_AT(cred.cr_group_info, i);
}
cred.cr_group_info = gi;
} else
get_group_info(cred.cr_group_info);
if (cred.cr_uid != (uid_t) -1)
current->fsuid = cred.cr_uid;
else
current->fsuid = exp->ex_anon_uid;
if (cred.cr_gid != (gid_t) -1)
current->fsgid = cred.cr_gid;
else
current->fsgid = exp->ex_anon_gid;
if (!cred.cr_group_info)
return -ENOMEM;
ret = set_current_groups(cred.cr_group_info);
put_group_info(cred.cr_group_info);
if ((cred.cr_uid)) {
current->cap_effective =
cap_drop_nfsd_set(current->cap_effective);
} else {
current->cap_effective =
cap_raise_nfsd_set(current->cap_effective,
current->cap_permitted);
}
return ret;
}