aboutsummaryrefslogtreecommitdiff
path: root/kernel/fork.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/fork.c')
-rw-r--r--kernel/fork.c222
1 files changed, 115 insertions, 107 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index 987b28a1f01..6a13c46cd87 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -28,6 +28,8 @@
#include <linux/mman.h>
#include <linux/mmu_notifier.h>
#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
#include <linux/nsproxy.h>
#include <linux/capability.h>
#include <linux/cpu.h>
@@ -71,6 +73,7 @@
#include <linux/signalfd.h>
#include <linux/uprobes.h>
#include <linux/aio.h>
+#include <linux/compiler.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -147,15 +150,15 @@ void __weak arch_release_thread_info(struct thread_info *ti)
static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
int node)
{
- struct page *page = alloc_pages_node(node, THREADINFO_GFP_ACCOUNTED,
- THREAD_SIZE_ORDER);
+ struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
+ THREAD_SIZE_ORDER);
return page ? page_address(page) : NULL;
}
static inline void free_thread_info(struct thread_info *ti)
{
- free_memcg_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER);
+ free_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER);
}
# else
static struct kmem_cache *thread_info_cache;
@@ -237,6 +240,7 @@ void __put_task_struct(struct task_struct *tsk)
WARN_ON(atomic_read(&tsk->usage));
WARN_ON(tsk == current);
+ task_numa_free(tsk);
security_task_free(tsk);
exit_creds(tsk);
delayacct_tsk_free(tsk);
@@ -283,7 +287,7 @@ void __init fork_init(unsigned long mempages)
init_task.signal->rlim[RLIMIT_NPROC];
}
-int __attribute__((weak)) arch_dup_task_struct(struct task_struct *dst,
+int __weak arch_dup_task_struct(struct task_struct *dst,
struct task_struct *src)
{
*dst = *src;
@@ -351,7 +355,6 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
struct rb_node **rb_link, *rb_parent;
int retval;
unsigned long charge;
- struct mempolicy *pol;
uprobe_start_dup_mmap();
down_write(&oldmm->mmap_sem);
@@ -364,9 +367,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
mm->locked_vm = 0;
mm->mmap = NULL;
- mm->mmap_cache = NULL;
- mm->free_area_cache = oldmm->mmap_base;
- mm->cached_hole_size = ~0UL;
+ mm->vmacache_seqnum = 0;
mm->map_count = 0;
cpumask_clear(mm_cpumask(mm));
mm->mm_rb = RB_ROOT;
@@ -402,11 +403,9 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
goto fail_nomem;
*tmp = *mpnt;
INIT_LIST_HEAD(&tmp->anon_vma_chain);
- pol = mpol_dup(vma_policy(mpnt));
- retval = PTR_ERR(pol);
- if (IS_ERR(pol))
+ retval = vma_dup_policy(mpnt, tmp);
+ if (retval)
goto fail_nomem_policy;
- vma_set_policy(tmp, pol);
tmp->vm_mm = mm;
if (anon_vma_fork(tmp, mpnt))
goto fail_nomem_anon_vma_fork;
@@ -474,7 +473,7 @@ out:
uprobe_end_dup_mmap();
return retval;
fail_nomem_anon_vma_fork:
- mpol_put(pol);
+ mpol_put(vma_policy(tmp));
fail_nomem_policy:
kmem_cache_free(vm_area_cachep, tmp);
fail_nomem:
@@ -524,7 +523,7 @@ static void mm_init_aio(struct mm_struct *mm)
{
#ifdef CONFIG_AIO
spin_lock_init(&mm->ioctx_lock);
- INIT_HLIST_HEAD(&mm->ioctx_list);
+ mm->ioctx_table = NULL;
#endif
}
@@ -534,19 +533,23 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
atomic_set(&mm->mm_count, 1);
init_rwsem(&mm->mmap_sem);
INIT_LIST_HEAD(&mm->mmlist);
- mm->flags = (current->mm) ?
- (current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
mm->core_state = NULL;
- mm->nr_ptes = 0;
+ atomic_long_set(&mm->nr_ptes, 0);
memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
spin_lock_init(&mm->page_table_lock);
- mm->free_area_cache = TASK_UNMAPPED_BASE;
- mm->cached_hole_size = ~0UL;
mm_init_aio(mm);
mm_init_owner(mm, p);
+ clear_tlb_flush_pending(mm);
- if (likely(!mm_alloc_pgd(mm))) {
+ if (current->mm) {
+ mm->flags = current->mm->flags & MMF_INIT_MASK;
+ mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK;
+ } else {
+ mm->flags = default_dump_filter;
mm->def_flags = 0;
+ }
+
+ if (likely(!mm_alloc_pgd(mm))) {
mmu_notifier_mm_init(mm);
return mm;
}
@@ -567,7 +570,7 @@ static void check_mm(struct mm_struct *mm)
"mm:%p idx:%d val:%ld\n", mm, i, x);
}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
VM_BUG_ON(mm->pmd_huge_pte);
#endif
}
@@ -806,14 +809,11 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
* Allocate a new mm structure and copy contents from the
* mm structure of the passed in task structure.
*/
-struct mm_struct *dup_mm(struct task_struct *tsk)
+static struct mm_struct *dup_mm(struct task_struct *tsk)
{
struct mm_struct *mm, *oldmm = current->mm;
int err;
- if (!oldmm)
- return NULL;
-
mm = allocate_mm();
if (!mm)
goto fail_nomem;
@@ -821,12 +821,9 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
memcpy(mm, oldmm, sizeof(*mm));
mm_init_cpumask(mm);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
mm->pmd_huge_pte = NULL;
#endif
-#ifdef CONFIG_NUMA_BALANCING
- mm->first_nid = NUMA_PTE_SCAN_INIT;
-#endif
if (!mm_init(mm, tsk))
goto fail_nomem;
@@ -888,6 +885,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
if (!oldmm)
return 0;
+ /* initialize the new vmacache entries */
+ vmacache_flush(tsk);
+
if (clone_flags & CLONE_VM) {
atomic_inc(&oldmm->mm_users);
mm = oldmm;
@@ -1044,6 +1044,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
sig->nr_threads = 1;
atomic_set(&sig->live, 1);
atomic_set(&sig->sigcnt, 1);
+
+ /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
+ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
+ tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);
+
init_waitqueue_head(&sig->wait_chldexit);
sig->curr_target = tsk;
init_sigpending(&sig->shared_pending);
@@ -1076,15 +1081,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
return 0;
}
-static void copy_flags(unsigned long clone_flags, struct task_struct *p)
-{
- unsigned long new_flags = p->flags;
-
- new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
- new_flags |= PF_FORKNOEXEC;
- p->flags = new_flags;
-}
-
SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
{
current->clear_child_tid = tidptr;
@@ -1096,17 +1092,19 @@ static void rt_mutex_init_task(struct task_struct *p)
{
raw_spin_lock_init(&p->pi_lock);
#ifdef CONFIG_RT_MUTEXES
- plist_head_init(&p->pi_waiters);
+ p->pi_waiters = RB_ROOT;
+ p->pi_waiters_leftmost = NULL;
p->pi_blocked_on = NULL;
+ p->pi_top_task = NULL;
#endif
}
-#ifdef CONFIG_MM_OWNER
+#ifdef CONFIG_MEMCG
void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
{
mm->owner = p;
}
-#endif /* CONFIG_MM_OWNER */
+#endif /* CONFIG_MEMCG */
/*
* Initialize POSIX timer handling for a single task.
@@ -1121,6 +1119,12 @@ static void posix_cpu_timers_init(struct task_struct *tsk)
INIT_LIST_HEAD(&tsk->cpu_timers[2]);
}
+static inline void
+init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
+{
+ task->pids[type].pid = pid;
+}
+
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
@@ -1171,12 +1175,16 @@ static struct task_struct *copy_process(unsigned long clone_flags,
return ERR_PTR(-EINVAL);
/*
- * If the new process will be in a different pid namespace
- * don't allow the creation of threads.
+ * 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_VM|CLONE_NEWPID)) &&
- (task_active_pid_ns(current) != current->nsproxy->pid_ns))
- return ERR_PTR(-EINVAL);
+ 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)
@@ -1199,8 +1207,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
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)
+ if (p->real_cred->user != INIT_USER &&
+ !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
goto bad_fork_free;
}
current->flags &= ~PF_NPROC_EXCEEDED;
@@ -1221,9 +1229,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
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);
+ 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);
@@ -1267,9 +1275,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
- goto bad_fork_cleanup_cgroup;
+ goto bad_fork_cleanup_threadgroup_lock;
}
- mpol_fix_fork_child_flag(p);
#endif
#ifdef CONFIG_CPUSETS
p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
@@ -1310,7 +1317,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
- sched_fork(p);
+ retval = sched_fork(clone_flags, p);
+ if (retval)
+ goto bad_fork_cleanup_policy;
retval = perf_event_init_task(p);
if (retval)
@@ -1349,16 +1358,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
if (pid != &init_struct_pid) {
retval = -ENOMEM;
- pid = alloc_pid(p->nsproxy->pid_ns);
+ pid = alloc_pid(p->nsproxy->pid_ns_for_children);
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()?
@@ -1375,7 +1379,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
INIT_LIST_HEAD(&p->pi_state_list);
p->pi_state_cache = NULL;
#endif
- uprobe_copy_process(p);
/*
* sigaltstack should be cleared when sharing the same VM
*/
@@ -1394,29 +1397,32 @@ static struct task_struct *copy_process(unsigned long clone_flags,
clear_all_latency_tracing(p);
/* ok, now we should be set up.. */
- if (clone_flags & CLONE_THREAD)
+ p->pid = pid_nr(pid);
+ 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->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;
- /*
- * Ok, make it visible to the rest of the system.
- * We dont wake it up yet.
- */
- p->group_leader = p;
+ p->pdeath_signal = 0;
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
- /* Need tasklist lock for parent etc handling! */
+ /*
+ * 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 */
@@ -1446,18 +1452,14 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto bad_fork_free_pid;
}
- if (clone_flags & CLONE_THREAD) {
- current->signal->nr_threads++;
- atomic_inc(&current->signal->live);
- atomic_inc(&current->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);
+ 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;
@@ -1465,19 +1467,29 @@ static struct task_struct *copy_process(unsigned long clone_flags,
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);
+ attach_pid(p, PIDTYPE_PGID);
+ attach_pid(p, PIDTYPE_SID);
__this_cpu_inc(process_counts);
+ } else {
+ current->signal->nr_threads++;
+ atomic_inc(&current->signal->live);
+ atomic_inc(&current->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, pid);
+ attach_pid(p, PIDTYPE_PID);
nr_threads++;
}
total_forks++;
spin_unlock(&current->sighand->siglock);
+ syscall_tracepoint_update(p);
write_unlock_irq(&tasklist_lock);
+
proc_fork_connector(p);
cgroup_post_fork(p);
if (clone_flags & CLONE_THREAD)
@@ -1485,6 +1497,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
perf_event_fork(p);
trace_task_newtask(p, clone_flags);
+ uprobe_copy_process(p, clone_flags);
return p;
@@ -1516,11 +1529,10 @@ bad_fork_cleanup_policy:
perf_event_free_task(p);
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
-bad_fork_cleanup_cgroup:
+bad_fork_cleanup_threadgroup_lock:
#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:
@@ -1542,7 +1554,7 @@ static inline void init_idle_pids(struct pid_link *links)
}
}
-struct task_struct * __cpuinit fork_idle(int cpu)
+struct task_struct *fork_idle(int cpu)
{
struct task_struct *task;
task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0);
@@ -1571,15 +1583,6 @@ long do_fork(unsigned long clone_flags,
long nr;
/*
- * Do some preliminary argument and permissions checking before we
- * actually start allocating stuff
- */
- if (clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) {
- if (clone_flags & (CLONE_THREAD|CLONE_PARENT))
- return -EINVAL;
- }
-
- /*
* 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
@@ -1605,10 +1608,12 @@ long do_fork(unsigned long clone_flags,
*/
if (!IS_ERR(p)) {
struct completion vfork;
+ struct pid *pid;
trace_sched_process_fork(current, p);
- nr = task_pid_vnr(p);
+ pid = get_task_pid(p, PIDTYPE_PID);
+ nr = pid_vnr(pid);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
@@ -1623,12 +1628,14 @@ long do_fork(unsigned long clone_flags,
/* forking complete and child started to run, tell ptracer */
if (unlikely(trace))
- ptrace_event(trace, nr);
+ ptrace_event_pid(trace, pid);
if (clone_flags & CLONE_VFORK) {
if (!wait_for_vfork_done(p, &vfork))
- ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
+ ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
}
+
+ put_pid(pid);
} else {
nr = PTR_ERR(p);
}
@@ -1651,7 +1658,7 @@ SYSCALL_DEFINE0(fork)
return do_fork(SIGCHLD, 0, 0, NULL, NULL);
#else
/* can not support in nommu mode */
- return(-EINVAL);
+ return -EINVAL;
#endif
}
#endif
@@ -1659,7 +1666,7 @@ SYSCALL_DEFINE0(fork)
#ifdef __ARCH_WANT_SYS_VFORK
SYSCALL_DEFINE0(vfork)
{
- return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0,
+ return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0,
0, NULL, NULL);
}
#endif
@@ -1675,6 +1682,12 @@ 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,
@@ -1814,11 +1827,6 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
if (unshare_flags & CLONE_NEWUSER)
unshare_flags |= CLONE_THREAD | CLONE_FS;
/*
- * If unsharing a pid namespace must also unshare the thread.
- */
- if (unshare_flags & CLONE_NEWPID)
- unshare_flags |= CLONE_THREAD;
- /*
* If unsharing a thread from a thread group, must also unshare vm.
*/
if (unshare_flags & CLONE_THREAD)
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 08:04:43 +0000