NTPL线程创建流程
这里是用户调用API的入口的地方：
int
__pthread_create_2_1 (newthread, attr, start_routine, arg)
pthread_t *newthread;
const pthread_attr_t *attr;
void *(*start_routine) (void *);
void *arg;
{
STACK_VARIABLES;
const struct pthread_attr *iattr = (struct pthread_attr *) attr;
struct pthread_attr default_attr;
bool free_cpuset = false;
if (iattr == NULL)
{
lll_lock (__default_pthread_attr_lock, LLL_PRIVATE);
default_attr = __default_pthread_attr;
size_t cpusetsize = default_attr.cpusetsize;
if (cpusetsize > 0)
{
cpu_set_t *cpuset;
if (__glibc_likely (__libc_use_alloca (cpusetsize)))
cpuset = __alloca (cpusetsize);
else
{
cpuset = malloc (cpusetsize);
if (cpuset == NULL)
{
lll_unlock (__default_pthread_attr_lock, LLL_PRIVATE);
return ENOMEM;
}
free_cpuset = true;
}
memcpy (cpuset, default_attr.cpuset, cpusetsize);
default_attr.cpuset = cpuset;
}
lll_unlock (__default_pthread_attr_lock, LLL_PRIVATE);
iattr = &default_attr;
}
struct pthread *pd = NULL;
int err = ALLOCATE_STACK (iattr, &pd);
int retval = 0;
if (__glibc_unlikely (err != 0))
/* Something went wrong. Maybe a parameter of the attributes is
invalid or we could not allocate memory. Note we have to
translate error codes. */
{
retval = err == ENOMEM ? EAGAIN : err;
goto out;
}
/* Initialize the TCB. All initializations with zero should be
performed in 'get_cached_stack'. This way we avoid doing this if
the stack freshly allocated with 'mmap'. */
#if TLS_TCB_AT_TP
/* Reference to the TCB itself. */
pd->header.self = pd;
/* Self-reference for TLS. */
pd->header.tcb = pd;
#endif
/* Store the address of the start routine and the parameter. Since
we do not start the function directly the stillborn thread will
get the information from its thread descriptor. */
pd->start_routine = start_routine;
pd->arg = arg;
/* Copy the thread attribute flags. */
struct pthread *self = THREAD_SELF;
pd->flags = ((iattr->flags & ~(ATTR_FLAG_SCHED_SET | ATTR_FLAG_POLICY_SET))
| (self->flags & (ATTR_FLAG_SCHED_SET | ATTR_FLAG_POLICY_SET)));
/* Initialize the field for the ID of the thread which is waiting
for us. This is a self-reference in case the thread is created
detached. */
pd->joinid = iattr->flags & ATTR_FLAG_DETACHSTATE ? pd : NULL;
/* The debug events are inherited from the parent. */
pd->eventbuf = self->eventbuf;
/* Copy the parent's scheduling parameters. The flags will say what
is valid and what is not. */
pd->schedpolicy = self->schedpolicy;
pd->schedparam = self->schedparam;
/* Copy the stack guard canary. */
#ifdef THREAD_COPY_STACK_GUARD
THREAD_COPY_STACK_GUARD (pd);
#endif
/* Copy the pointer guard value. */
#ifdef THREAD_COPY_POINTER_GUARD
THREAD_COPY_POINTER_GUARD (pd);
#endif
/* Verify the sysinfo bits were copied in allocate_stack if needed. */
#ifdef NEED_DL_SYSINFO
CHECK_THREAD_SYSINFO (pd);
#endif
/* Inform start_thread (above) about cancellation state that might
translate into inherited signal state. */
pd->parent_cancelhandling = THREAD_GETMEM (THREAD_SELF, cancelhandling);
/* Determine scheduling parameters for the thread. */
if (__builtin_expect ((iattr->flags & ATTR_FLAG_NOTINHERITSCHED) != 0, 0)
&& (iattr->flags & (ATTR_FLAG_SCHED_SET | ATTR_FLAG_POLICY_SET)) != 0)
{
/* Use the scheduling parameters the user provided. */
if (iattr->flags & ATTR_FLAG_POLICY_SET)
{
pd->schedpolicy = iattr->schedpolicy;
pd->flags |= ATTR_FLAG_POLICY_SET;
}
if (iattr->flags & ATTR_FLAG_SCHED_SET)
{
/* The values were validated in pthread_attr_setschedparam. */
pd->schedparam = iattr->schedparam;
pd->flags |= ATTR_FLAG_SCHED_SET;
}
if ((pd->flags & (ATTR_FLAG_SCHED_SET | ATTR_FLAG_POLICY_SET))
!= (ATTR_FLAG_SCHED_SET | ATTR_FLAG_POLICY_SET))
collect_default_sched (pd);
}
/* Pass the descriptor to the caller. */
*newthread = (pthread_t) pd;
LIBC_PROBE (pthread_create, 4, newthread, attr, start_routine, arg);
/* One more thread. We cannot have the thread do this itself, since it
might exist but not have been scheduled yet by the time we've returned
and need to check the value to behave correctly. We must do it before
creating the thread, in case it does get scheduled first and then
might mistakenly think it was the only thread. In the failure case,
we momentarily store a false value; this doesn't matter because there
is no kosher thing a signal handler interrupting us right here can do
that cares whether the thread count is correct. */
atomic_increment (&__nptl_nthreads);
bool thread_ran = false;
/* Start the thread. */
if (__glibc_unlikely (report_thread_creation (pd)))
{
/* Create the thread. We always create the thread stopped
so that it does not get far before we tell the debugger. */
retval = create_thread (pd, iattr, true, STACK_VARIABLES_ARGS,
&thread_ran);
if (retval == 0)
{
/* create_thread should have set this so that the logic below can
test it. */
assert (pd->stopped_start);
/* Now fill in the information about the new thread in
the newly created thread's data structure. We cannot let
the new thread do this since we don't know whether it was
already scheduled when we send the event. */
pd->eventbuf.eventnum = TD_CREATE;
pd->eventbuf.eventdata = pd;
/* Enqueue the descriptor. */
do
pd->nextevent = __nptl_last_event;
while (atomic_compare_and_exchange_bool_acq (&__nptl_last_event,
pd, pd->nextevent)
!= 0);
/* Now call the function which signals the event. */
__nptl_create_event ();
}
}
else
retval = create_thread (pd, iattr, false, STACK_VARIABLES_ARGS,
&thread_ran);
if (__glibc_unlikely (retval != 0))
{
/* If thread creation "failed", that might mean that the thread got
created and ran a little--short of running user code--but then
create_thread cancelled it. In that case, the thread will do all
its own cleanup just like a normal thread exit after a successful
creation would do. */
if (thread_ran)
assert (pd->stopped_start);
else
{
/* Oops, we lied for a second. */
atomic_decrement (&__nptl_nthreads);
/* Perhaps a thread wants to change the IDs and is waiting for this
stillborn thread. */
if (__glibc_unlikely (atomic_exchange_acq (&pd->setxid_futex, 0)
== -2))
lll_futex_wake (&pd->setxid_futex, 1, LLL_PRIVATE);
/* Free the resources. */
__deallocate_stack (pd);
}
/* We have to translate error codes. */
if (retval == ENOMEM)
retval = EAGAIN;
}
else
{
if (pd->stopped_start)
/* The thread blocked on this lock either because we're doing TD_CREATE
event reporting, or for some other reason that create_thread chose.
Now let it run free. */
lll_unlock (pd->lock, LLL_PRIVATE);
/* We now have for sure more than one thread. The main thread might
not yet have the flag set. No need to set the global variable
again if this is what we use. */
THREAD_SETMEM (THREAD_SELF, header.multiple_threads, 1);
}
out:
if (__glibc_unlikely (free_cpuset))
free (default_attr.cpuset);
return retval;
}
versioned_symbol (libpthread, __pthread_create_2_1, pthread_create, GLIBC_2_1);
然后调用creat_pthread创建线程
static int
create_thread (struct pthread *pd, const struct pthread_attr *attr,
bool stopped_start, STACK_VARIABLES_PARMS, bool *thread_ran)
{
/* Determine whether the newly created threads has to be started
stopped since we have to set the scheduling parameters or set the
affinity. */
if (attr != NULL
&& (__glibc_unlikely (attr->cpuset != NULL)
|| __glibc_unlikely ((attr->flags & ATTR_FLAG_NOTINHERITSCHED) != 0)))
stopped_start = true;
pd->stopped_start = stopped_start;
if (__glibc_unlikely (stopped_start))
/* We make sure the thread does not run far by forcing it to get a
lock. We lock it here too so that the new thread cannot continue
until we tell it to. */
lll_lock (pd->lock, LLL_PRIVATE);
/* We rely heavily on various flags the CLONE function understands:
CLONE_VM, CLONE_FS, CLONE_FILES
These flags select semantics with shared address space and
file descriptors according to what POSIX requires.
CLONE_SIGHAND, CLONE_THREAD
This flag selects the POSIX signal semantics and various
other kinds of sharing (itimers, POSIX timers, etc.).
CLONE_SETTLS
The sixth parameter to CLONE determines the TLS area for the
new thread.
CLONE_PARENT_SETTID
The kernels writes the thread ID of the newly created thread
into the location pointed to by the fifth parameters to CLONE.
Note that it would be semantically equivalent to use
CLONE_CHILD_SETTID but it is be more expensive in the kernel.
CLONE_CHILD_CLEARTID
The kernels clears the thread ID of a thread that has called
sys_exit() in the location pointed to by the seventh parameter
to CLONE.
The termination signal is chosen to be zero which means no signal
is sent. */
const int clone_flags = (CLONE_VM | CLONE_FS | CLONE_FILES | CLONE_SYSVSEM
| CLONE_SIGHAND | CLONE_THREAD
| CLONE_SETTLS | CLONE_PARENT_SETTID
| CLONE_CHILD_CLEARTID
| 0);
TLS_DEFINE_INIT_TP (tp, pd);
if (__glibc_unlikely (ARCH_CLONE (&start_thread, STACK_VARIABLES_ARGS,
clone_flags, pd, &pd->tid, tp, &pd->tid)
== -1))
return errno;
/* It's started now, so if we fail below, we'll have to cancel it
and let it clean itself up. */
*thread_ran = true;
/* Now we have the possibility to set scheduling parameters etc. */
if (attr != NULL)
{
INTERNAL_SYSCALL_DECL (err);
int res;
/* Set the affinity mask if necessary. */
if (attr->cpuset != NULL)
{
assert (stopped_start);
res = INTERNAL_SYSCALL (sched_setaffinity, err, 3, pd->tid,
attr->cpusetsize, attr->cpuset);
if (__glibc_unlikely (INTERNAL_SYSCALL_ERROR_P (res, err)))
err_out:
{
/* The operation failed. We have to kill the thread.
We let the normal cancellation mechanism do the work. */
INTERNAL_SYSCALL_DECL (err2);
(void) INTERNAL_SYSCALL (tgkill, err2, 3,
THREAD_GETMEM (THREAD_SELF, pid),
pd->tid, SIGCANCEL);
return INTERNAL_SYSCALL_ERRNO (res, err);
}
}
/* Set the scheduling parameters. */
if ((attr->flags & ATTR_FLAG_NOTINHERITSCHED) != 0)
{
assert (stopped_start);
res = INTERNAL_SYSCALL (sched_setscheduler, err, 3, pd->tid,
pd->schedpolicy, &pd->schedparam);
if (__glibc_unlikely (INTERNAL_SYSCALL_ERROR_P (res, err)))
goto err_out;
}
}
return 0;
}
然后是用户空间的最后一步，使用汇编做系统调用：（以下针对ARM架构而言）
/* int clone(int (*fn)(void *arg), void *child_stack, int flags, void *arg,
pid_t *ptid, struct user_desc *tls, pid_t *ctid); */
.text
ENTRY(__clone)
@ sanity check args
cmp r0, #0
ite ne
cmpne r1, #0
moveq r0, #-EINVAL
beq PLTJMP(syscall_error)
@ insert the args onto the new stack
str r3, [r1, #-4]!
str r0, [r1, #-4]!
@ do the system call
@ get flags
mov r0, r2
mov ip, r2
@ new sp is already in r1
push {r4, r7}
cfi_adjust_cfa_offset (8)
cfi_rel_offset (r4, 0)
cfi_rel_offset (r7, 4)
ldr r2, [sp, #8]
ldr r3, [sp, #12]
ldr r4, [sp, #16]
ldr r7, =SYS_ify(clone)
swi 0x0
cfi_endproc
cmp r0, #0
beq 1f
pop {r4, r7}
blt PLTJMP(C_SYMBOL_NAME(__syscall_error))
RETINSTR(, lr)
cfi_startproc
PSEUDO_END (__clone)
在上一步进行系统调用后，就走到内核空间了，根据前面提供的参数和系统调用号，依次会调用到clone、sched_setaffinity、sched_setscheduler等系统服务。以下主要看下clone的具体实现：
#ifdef __ARCH_WANT_SYS_CLONE
#ifdef CONFIG_CLONE_BACKWARDS
SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
int __user *, parent_tidptr,
int, tls_val,
int __user *, child_tidptr)
#elif defined(CONFIG_CLONE_BACKWARDS2)
SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags,
int __user *, parent_tidptr,
int __user *, child_tidptr,
int, tls_val)
#elif defined(CONFIG_CLONE_BACKWARDS3)
SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp,
int, stack_size,
int __user *, parent_tidptr,
int __user *, child_tidptr,
int, tls_val)
#else
SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
int __user *, parent_tidptr,
int __user *, child_tidptr,
int, tls_val)
#endif
{
return do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr);
}
#endif从以上code可以看出来实际通过do_fork函数执行线程的克隆操作，根据传入的flags觉得哪些内容需要克隆。
/*
* Ok, this is the main fork-routine.
*
* It copies the process, and if successful kick-starts
* it and waits for it to finish using the VM if required.
*/
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
long nr;
/*
* Determine whether and which event to report to ptracer. When
* called from kernel_thread or CLONE_UNTRACED is explicitly
* requested, no event is reported; otherwise, report if the event
* for the type of forking is enabled.
*/
if (!(clone_flags & CLONE_UNTRACED)) {
if (clone_flags & CLONE_VFORK)
trace = PTRACE_EVENT_VFORK;
else if ((clone_flags & CSIGNAL) != SIGCHLD)
trace = PTRACE_EVENT_CLONE;
else
trace = PTRACE_EVENT_FORK;
if (likely(!ptrace_event_enabled(current, trace)))
trace = 0;
}
p = copy_process(clone_flags, stack_start, stack_size,
child_tidptr, NULL, trace);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
if (!IS_ERR(p)) {
struct completion vfork;
struct pid *pid;
trace_sched_process_fork(current, p);
pid = get_task_pid(p, PIDTYPE_PID);
nr = pid_vnr(pid);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
get_task_struct(p);
}
wake_up_new_task(p);
/* forking complete and child started to run, tell ptracer */
if (unlikely(trace))
ptrace_event_pid(trace, pid);
if (clone_flags & CLONE_VFORK) {
if (!wait_for_vfork_done(p, &vfork))
ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
}
put_pid(pid);
} else {
nr = PTR_ERR(p);
}
return nr;
}
/*
* 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,
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);
if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|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);
/*
* If the new process will be in a different pid or user namespace
* do not allow it to share a thread group or signal handlers or
* parent with the forking task.
*/
if (clone_flags & CLONE_SIGHAND) {
if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
(task_active_pid_ns(current) !=
current->nsproxy->pid_ns_for_children))
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 (p->real_cred->user != INIT_USER &&
!capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
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;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
p->flags |= PF_FORKNOEXEC;
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_NATIVE
p->prev_cputime.utime = p->prev_cputime.stime = 0;
#endif
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
seqlock_init(&p->vtime_seqlock);
p->vtime_snap = 0;
p->vtime_snap_whence = VTIME_SLEEPING;
#endif
#if defined(SPLIT_RSS_COUNTING)
memset(&p->rss_stat, 0, sizeof(p->rss_stat));
#endif
p->default_timer_slack_ns = current->timer_slack_ns;
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
posix_cpu_timers_init(p);
p->start_time = ktime_get_ns();
p->real_start_time = ktime_get_boot_ns();
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_threadgroup_lock;
}
#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;
p->hardirqs_enabled = 0;
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_BCACHE
p->sequential_io = 0;
p->sequential_io_avg = 0;
#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
retval = sched_fork(clone_flags, p);
if (retval)
goto bad_fork_cleanup_policy;
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 */
shm_init_task(p);
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);
if (retval)
goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
retval = -ENOMEM;
pid = alloc_pid(p->nsproxy->pid_ns_for_children);
if (!pid)
goto bad_fork_cleanup_io;
}
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.. */
p->pid = pid_nr(pid);
if (clone_flags & CLONE_THREAD) {
p->exit_signal = -1;
p->group_leader = current->group_leader;
p->tgid = current->tgid;
} else {
if (clone_flags & CLONE_PARENT)
p->exit_signal = current->group_leader->exit_signal;
else
p->exit_signal = (clone_flags & CSIGNAL);
p->group_leader = p;
p->tgid = p->pid;
}
p->nr_dirtied = 0;
p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
p->dirty_paused_when = 0;
p->pdeath_signal = 0;
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
/*
* Make it visible to the rest of the system, but dont wake it up yet.
* 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);
/*
* Copy seccomp details explicitly here, in case they were changed
* before holding sighand lock.
*/
copy_seccomp(p);
/*
* 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);
init_task_pid(p, PIDTYPE_PID, pid);
if (thread_group_leader(p)) {
init_task_pid(p, PIDTYPE_PGID, task_pgrp(current));
init_task_pid(p, PIDTYPE_SID, task_session(current));
if (is_child_reaper(pid)) {
ns_of_pid(pid)->child_reaper = p;
p->signal->flags |= SIGNAL_UNKILLABLE;
}
p->signal->leader_pid = pid;
p->signal->tty = tty_kref_get(current->signal->tty);
list_add_tail(&p->sibling, &p->real_parent->children);
list_add_tail_rcu(&p->tasks, &init_task.tasks);
attach_pid(p, PIDTYPE_PGID);
attach_pid(p, PIDTYPE_SID);
__this_cpu_inc(process_counts);
} else {
current->signal->nr_threads++;
atomic_inc(¤t->signal->live);
atomic_inc(¤t->signal->sigcnt);
list_add_tail_rcu(&p->thread_group,
&p->group_leader->thread_group);
list_add_tail_rcu(&p->thread_node,
&p->signal->thread_head);
}
attach_pid(p, PIDTYPE_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);
uprobe_copy_process(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:
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_threadgroup_lock:
#endif
if (clone_flags & CLONE_THREAD)
threadgroup_change_end(current);
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);
}
新创建的任务加入到CPU的rq队列里面：
/*
* wake_up_new_task - wake up a newly created task for the first time.
*
* This function will do some initial scheduler statistics housekeeping
* that must be done for every newly created context, then puts the task
* on the runqueue and wakes it.
*/
void wake_up_new_task(struct task_struct *p)
{
unsigned long flags;
struct rq *rq;
raw_spin_lock_irqsave(&p->pi_lock, flags);
#ifdef CONFIG_SMP
/*
* Fork balancing, do it here and not earlier because:
* - cpus_allowed can change in the fork path
* - any previously selected cpu might disappear through hotplug
*/
set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
/* Initialize new task's runnable average */
init_task_runnable_average(p);
rq = __task_rq_lock(p);
activate_task(rq, p, 0);
p->on_rq = TASK_ON_RQ_QUEUED;
trace_sched_wakeup_new(p, true);
check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
if (p->sched_class->task_woken)
p->sched_class->task_woken(rq, p);
#endif
task_rq_unlock(rq, p, &flags);
}