aboutsummaryrefslogtreecommitdiff
path: root/kernel/fork.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/fork.c')
-rw-r--r--kernel/fork.c208
1 files changed, 163 insertions, 45 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index 11c5c8ab827c..17921b0390b4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -12,6 +12,16 @@
*/
#include <linux/slab.h>
+#include <linux/sched/autogroup.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/coredump.h>
+#include <linux/sched/user.h>
+#include <linux/sched/numa_balancing.h>
+#include <linux/sched/stat.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
+#include <linux/sched/cputime.h>
+#include <linux/rtmutex.h>
#include <linux/init.h>
#include <linux/unistd.h>
#include <linux/module.h>
@@ -55,6 +65,7 @@
#include <linux/rmap.h>
#include <linux/ksm.h>
#include <linux/acct.h>
+#include <linux/userfaultfd_k.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/freezer.h>
@@ -76,6 +87,7 @@
#include <linux/compiler.h>
#include <linux/sysctl.h>
#include <linux/kcov.h>
+#include <linux/livepatch.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -167,6 +179,24 @@ void __weak arch_release_thread_stack(unsigned long *stack)
*/
#define NR_CACHED_STACKS 2
static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]);
+
+static int free_vm_stack_cache(unsigned int cpu)
+{
+ struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu);
+ int i;
+
+ for (i = 0; i < NR_CACHED_STACKS; i++) {
+ struct vm_struct *vm_stack = cached_vm_stacks[i];
+
+ if (!vm_stack)
+ continue;
+
+ vfree(vm_stack->addr);
+ cached_vm_stacks[i] = NULL;
+ }
+
+ return 0;
+}
#endif
static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
@@ -175,23 +205,21 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
void *stack;
int i;
- local_irq_disable();
for (i = 0; i < NR_CACHED_STACKS; i++) {
- struct vm_struct *s = this_cpu_read(cached_stacks[i]);
+ struct vm_struct *s;
+
+ s = this_cpu_xchg(cached_stacks[i], NULL);
if (!s)
continue;
- this_cpu_write(cached_stacks[i], NULL);
tsk->stack_vm_area = s;
- local_irq_enable();
return s->addr;
}
- local_irq_enable();
stack = __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE,
VMALLOC_START, VMALLOC_END,
- THREADINFO_GFP | __GFP_HIGHMEM,
+ THREADINFO_GFP,
PAGE_KERNEL,
0, node, __builtin_return_address(0));
@@ -215,19 +243,15 @@ static inline void free_thread_stack(struct task_struct *tsk)
{
#ifdef CONFIG_VMAP_STACK
if (task_stack_vm_area(tsk)) {
- unsigned long flags;
int i;
- local_irq_save(flags);
for (i = 0; i < NR_CACHED_STACKS; i++) {
- if (this_cpu_read(cached_stacks[i]))
+ if (this_cpu_cmpxchg(cached_stacks[i],
+ NULL, tsk->stack_vm_area) != NULL)
continue;
- this_cpu_write(cached_stacks[i], tsk->stack_vm_area);
- local_irq_restore(flags);
return;
}
- local_irq_restore(flags);
vfree_atomic(tsk->stack);
return;
@@ -296,8 +320,8 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
}
/* All stack pages belong to the same memcg. */
- memcg_kmem_update_page_stat(vm->pages[0], MEMCG_KERNEL_STACK_KB,
- account * (THREAD_SIZE / 1024));
+ mod_memcg_page_state(vm->pages[0], MEMCG_KERNEL_STACK_KB,
+ account * (THREAD_SIZE / 1024));
} else {
/*
* All stack pages are in the same zone and belong to the
@@ -308,8 +332,8 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
THREAD_SIZE / 1024 * account);
- memcg_kmem_update_page_stat(first_page, MEMCG_KERNEL_STACK_KB,
- account * (THREAD_SIZE / 1024));
+ mod_memcg_page_state(first_page, MEMCG_KERNEL_STACK_KB,
+ account * (THREAD_SIZE / 1024));
}
}
@@ -432,11 +456,13 @@ void __init fork_init(void)
int i;
#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
#ifndef ARCH_MIN_TASKALIGN
-#define ARCH_MIN_TASKALIGN L1_CACHE_BYTES
+#define ARCH_MIN_TASKALIGN 0
#endif
+ int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN);
+
/* create a slab on which task_structs can be allocated */
task_struct_cachep = kmem_cache_create("task_struct",
- arch_task_struct_size, ARCH_MIN_TASKALIGN,
+ arch_task_struct_size, align,
SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, NULL);
#endif
@@ -453,6 +479,11 @@ void __init fork_init(void)
for (i = 0; i < UCOUNT_COUNTS; i++) {
init_user_ns.ucount_max[i] = max_threads/2;
}
+
+#ifdef CONFIG_VMAP_STACK
+ cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
+ NULL, free_vm_stack_cache);
+#endif
}
int __weak arch_dup_task_struct(struct task_struct *dst,
@@ -523,7 +554,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
set_task_stack_end_magic(tsk);
#ifdef CONFIG_CC_STACKPROTECTOR
- tsk->stack_canary = get_random_int();
+ tsk->stack_canary = get_random_canary();
#endif
/*
@@ -542,6 +573,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
kcov_task_init(tsk);
+#ifdef CONFIG_FAULT_INJECTION
+ tsk->fail_nth = 0;
+#endif
+
return tsk;
free_stack:
@@ -559,6 +594,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
struct rb_node **rb_link, *rb_parent;
int retval;
unsigned long charge;
+ LIST_HEAD(uf);
uprobe_start_dup_mmap();
if (down_write_killable(&oldmm->mmap_sem)) {
@@ -615,12 +651,13 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
if (retval)
goto fail_nomem_policy;
tmp->vm_mm = mm;
+ retval = dup_userfaultfd(tmp, &uf);
+ if (retval)
+ goto fail_nomem_anon_vma_fork;
if (anon_vma_fork(tmp, mpnt))
goto fail_nomem_anon_vma_fork;
- tmp->vm_flags &=
- ~(VM_LOCKED|VM_LOCKONFAULT|VM_UFFD_MISSING|VM_UFFD_WP);
+ tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
tmp->vm_next = tmp->vm_prev = NULL;
- tmp->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
file = tmp->vm_file;
if (file) {
struct inode *inode = file_inode(file);
@@ -676,6 +713,7 @@ out:
up_write(&mm->mmap_sem);
flush_tlb_mm(oldmm);
up_write(&oldmm->mmap_sem);
+ dup_userfaultfd_complete(&uf);
fail_uprobe_end:
uprobe_end_dup_mmap();
return retval;
@@ -994,7 +1032,7 @@ struct mm_struct *get_task_mm(struct task_struct *task)
if (task->flags & PF_KTHREAD)
mm = NULL;
else
- atomic_inc(&mm->mm_users);
+ mmget(mm);
}
task_unlock(task);
return mm;
@@ -1182,7 +1220,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
vmacache_flush(tsk);
if (clone_flags & CLONE_VM) {
- atomic_inc(&oldmm->mm_users);
+ mmget(oldmm);
mm = oldmm;
goto good_mm;
}
@@ -1297,13 +1335,14 @@ void __cleanup_sighand(struct sighand_struct *sighand)
if (atomic_dec_and_test(&sighand->count)) {
signalfd_cleanup(sighand);
/*
- * sighand_cachep is SLAB_DESTROY_BY_RCU so we can free it
+ * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it
* without an RCU grace period, see __lock_task_sighand().
*/
kmem_cache_free(sighand_cachep, sighand);
}
}
+#ifdef CONFIG_POSIX_TIMERS
/*
* Initialize POSIX timer handling for a thread group.
*/
@@ -1313,7 +1352,7 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
if (cpu_limit != RLIM_INFINITY) {
- sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit);
+ sig->cputime_expires.prof_exp = cpu_limit * NSEC_PER_SEC;
sig->cputimer.running = true;
}
@@ -1322,6 +1361,9 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
INIT_LIST_HEAD(&sig->cpu_timers[1]);
INIT_LIST_HEAD(&sig->cpu_timers[2]);
}
+#else
+static inline void posix_cpu_timers_init_group(struct signal_struct *sig) { }
+#endif
static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
{
@@ -1346,11 +1388,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
init_waitqueue_head(&sig->wait_chldexit);
sig->curr_target = tsk;
init_sigpending(&sig->shared_pending);
- INIT_LIST_HEAD(&sig->posix_timers);
seqlock_init(&sig->stats_lock);
prev_cputime_init(&sig->prev_cputime);
#ifdef CONFIG_POSIX_TIMERS
+ INIT_LIST_HEAD(&sig->posix_timers);
hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
sig->real_timer.function = it_real_fn;
#endif
@@ -1367,9 +1409,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
sig->oom_score_adj = current->signal->oom_score_adj;
sig->oom_score_adj_min = current->signal->oom_score_adj_min;
- sig->has_child_subreaper = current->signal->has_child_subreaper ||
- current->signal->is_child_subreaper;
-
mutex_init(&sig->cred_guard_mutex);
return 0;
@@ -1421,10 +1460,12 @@ static void rt_mutex_init_task(struct task_struct *p)
#ifdef CONFIG_RT_MUTEXES
p->pi_waiters = RB_ROOT;
p->pi_waiters_leftmost = NULL;
+ p->pi_top_task = NULL;
p->pi_blocked_on = NULL;
#endif
}
+#ifdef CONFIG_POSIX_TIMERS
/*
* Initialize POSIX timer handling for a single task.
*/
@@ -1437,6 +1478,9 @@ static void posix_cpu_timers_init(struct task_struct *tsk)
INIT_LIST_HEAD(&tsk->cpu_timers[1]);
INIT_LIST_HEAD(&tsk->cpu_timers[2]);
}
+#else
+static inline void posix_cpu_timers_init(struct task_struct *tsk) { }
+#endif
static inline void
init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
@@ -1444,6 +1488,21 @@ init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
task->pids[type].pid = pid;
}
+static inline void rcu_copy_process(struct task_struct *p)
+{
+#ifdef CONFIG_PREEMPT_RCU
+ p->rcu_read_lock_nesting = 0;
+ p->rcu_read_unlock_special.s = 0;
+ p->rcu_blocked_node = NULL;
+ INIT_LIST_HEAD(&p->rcu_node_entry);
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
+#ifdef CONFIG_TASKS_RCU
+ p->rcu_tasks_holdout = false;
+ INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
+ p->rcu_tasks_idle_cpu = -1;
+#endif /* #ifdef CONFIG_TASKS_RCU */
+}
+
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
@@ -1516,6 +1575,18 @@ static __latent_entropy struct task_struct *copy_process(
if (!p)
goto fork_out;
+ /*
+ * This _must_ happen before we call free_task(), i.e. before we jump
+ * to any of the bad_fork_* labels. This is to avoid freeing
+ * p->set_child_tid which is (ab)used as a kthread's data pointer for
+ * kernel threads (PF_KTHREAD).
+ */
+ 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;
+
ftrace_graph_init_task(p);
rt_mutex_init_task(p);
@@ -1564,9 +1635,9 @@ static __latent_entropy struct task_struct *copy_process(
prev_cputime_init(&p->prev_cputime);
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
- seqcount_init(&p->vtime_seqcount);
- p->vtime_snap = 0;
- p->vtime_snap_whence = VTIME_INACTIVE;
+ seqcount_init(&p->vtime.seqcount);
+ p->vtime.starttime = 0;
+ p->vtime.state = VTIME_INACTIVE;
#endif
#if defined(SPLIT_RSS_COUNTING)
@@ -1643,9 +1714,12 @@ static __latent_entropy struct task_struct *copy_process(
goto bad_fork_cleanup_perf;
/* copy all the process information */
shm_init_task(p);
- retval = copy_semundo(clone_flags, p);
+ retval = security_task_alloc(p, clone_flags);
if (retval)
goto bad_fork_cleanup_audit;
+ retval = copy_semundo(clone_flags, p);
+ if (retval)
+ goto bad_fork_cleanup_security;
retval = copy_files(clone_flags, p);
if (retval)
goto bad_fork_cleanup_semundo;
@@ -1679,11 +1753,6 @@ static __latent_entropy struct task_struct *copy_process(
}
}
- 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
@@ -1735,7 +1804,7 @@ static __latent_entropy struct task_struct *copy_process(
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
- threadgroup_change_begin(current);
+ cgroup_threadgroup_change_begin(current);
/*
* Ensure that the cgroup subsystem policies allow the new process to be
* forked. It should be noted the the new process's css_set can be changed
@@ -1761,6 +1830,8 @@ static __latent_entropy struct task_struct *copy_process(
p->parent_exec_id = current->self_exec_id;
}
+ klp_copy_process(p);
+
spin_lock(&current->sighand->siglock);
/*
@@ -1779,11 +1850,13 @@ static __latent_entropy struct task_struct *copy_process(
*/
recalc_sigpending();
if (signal_pending(current)) {
- spin_unlock(&current->sighand->siglock);
- write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
goto bad_fork_cancel_cgroup;
}
+ if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) {
+ retval = -ENOMEM;
+ goto bad_fork_cancel_cgroup;
+ }
if (likely(p->pid)) {
ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
@@ -1800,6 +1873,13 @@ static __latent_entropy struct task_struct *copy_process(
p->signal->leader_pid = pid;
p->signal->tty = tty_kref_get(current->signal->tty);
+ /*
+ * Inherit has_child_subreaper flag under the same
+ * tasklist_lock with adding child to the process tree
+ * for propagate_has_child_subreaper optimization.
+ */
+ p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper ||
+ p->real_parent->signal->is_child_subreaper;
list_add_tail(&p->sibling, &p->real_parent->children);
list_add_tail_rcu(&p->tasks, &init_task.tasks);
attach_pid(p, PIDTYPE_PGID);
@@ -1825,7 +1905,7 @@ static __latent_entropy struct task_struct *copy_process(
proc_fork_connector(p);
cgroup_post_fork(p);
- threadgroup_change_end(current);
+ cgroup_threadgroup_change_end(current);
perf_event_fork(p);
trace_task_newtask(p, clone_flags);
@@ -1834,9 +1914,11 @@ static __latent_entropy struct task_struct *copy_process(
return p;
bad_fork_cancel_cgroup:
+ spin_unlock(&current->sighand->siglock);
+ write_unlock_irq(&tasklist_lock);
cgroup_cancel_fork(p);
bad_fork_free_pid:
- threadgroup_change_end(current);
+ cgroup_threadgroup_change_end(current);
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_thread:
@@ -1860,6 +1942,8 @@ bad_fork_cleanup_files:
exit_files(p); /* blocking */
bad_fork_cleanup_semundo:
exit_sem(p);
+bad_fork_cleanup_security:
+ security_task_free(p);
bad_fork_cleanup_audit:
audit_free(p);
bad_fork_cleanup_perf:
@@ -2053,6 +2137,38 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
}
#endif
+void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data)
+{
+ struct task_struct *leader, *parent, *child;
+ int res;
+
+ read_lock(&tasklist_lock);
+ leader = top = top->group_leader;
+down:
+ for_each_thread(leader, parent) {
+ list_for_each_entry(child, &parent->children, sibling) {
+ res = visitor(child, data);
+ if (res) {
+ if (res < 0)
+ goto out;
+ leader = child;
+ goto down;
+ }
+up:
+ ;
+ }
+ }
+
+ if (leader != top) {
+ child = leader;
+ parent = child->real_parent;
+ leader = parent->group_leader;
+ goto up;
+ }
+out:
+ read_unlock(&tasklist_lock);
+}
+
#ifndef ARCH_MIN_MMSTRUCT_ALIGN
#define ARCH_MIN_MMSTRUCT_ALIGN 0
#endif
@@ -2069,7 +2185,7 @@ void __init proc_caches_init(void)
{
sighand_cachep = kmem_cache_create("sighand_cache",
sizeof(struct sighand_struct), 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU|
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
SLAB_NOTRACK|SLAB_ACCOUNT, sighand_ctor);
signal_cachep = kmem_cache_create("signal_cache",
sizeof(struct signal_struct), 0,
@@ -2277,6 +2393,8 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
}
}
+ perf_event_namespaces(current);
+
bad_unshare_cleanup_cred:
if (new_cred)
put_cred(new_cred);
Powered by cgit, Gruvboxed by Blaster4385.