aboutsummaryrefslogtreecommitdiff
path: root/kernel/fork.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/fork.c')
-rw-r--r--kernel/fork.c132
1 files changed, 110 insertions, 22 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index a070caed5c8e..38681ad44c76 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -425,7 +425,7 @@ static int memcg_charge_kernel_stack(struct task_struct *tsk)
static void release_task_stack(struct task_struct *tsk)
{
- if (WARN_ON(tsk->state != TASK_DEAD))
+ if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD))
return; /* Better to leak the stack than to free prematurely */
account_kernel_stack(tsk, -1);
@@ -446,6 +446,7 @@ void put_task_stack(struct task_struct *tsk)
void free_task(struct task_struct *tsk)
{
+ release_user_cpus_ptr(tsk);
scs_release(tsk);
#ifndef CONFIG_THREAD_INFO_IN_TASK
@@ -470,6 +471,20 @@ void free_task(struct task_struct *tsk)
}
EXPORT_SYMBOL(free_task);
+static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+ struct file *exe_file;
+
+ exe_file = get_mm_exe_file(oldmm);
+ RCU_INIT_POINTER(mm->exe_file, exe_file);
+ /*
+ * We depend on the oldmm having properly denied write access to the
+ * exe_file already.
+ */
+ if (exe_file && deny_write_access(exe_file))
+ pr_warn_once("deny_write_access() failed in %s\n", __func__);
+}
+
#ifdef CONFIG_MMU
static __latent_entropy int dup_mmap(struct mm_struct *mm,
struct mm_struct *oldmm)
@@ -493,7 +508,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING);
/* No ordering required: file already has been exposed. */
- RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+ dup_mm_exe_file(mm, oldmm);
mm->total_vm = oldmm->total_vm;
mm->data_vm = oldmm->data_vm;
@@ -556,12 +571,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
file = tmp->vm_file;
if (file) {
- struct inode *inode = file_inode(file);
struct address_space *mapping = file->f_mapping;
get_file(file);
- if (tmp->vm_flags & VM_DENYWRITE)
- put_write_access(inode);
i_mmap_lock_write(mapping);
if (tmp->vm_flags & VM_SHARED)
mapping_allow_writable(mapping);
@@ -639,7 +651,7 @@ static inline void mm_free_pgd(struct mm_struct *mm)
static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
{
mmap_write_lock(oldmm);
- RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+ dup_mm_exe_file(mm, oldmm);
mmap_write_unlock(oldmm);
return 0;
}
@@ -742,6 +754,7 @@ void __put_task_struct(struct task_struct *tsk)
exit_creds(tsk);
delayacct_tsk_free(tsk);
put_signal_struct(tsk->signal);
+ sched_core_free(tsk);
if (!profile_handoff_task(tsk))
free_task(tsk);
@@ -824,9 +837,14 @@ void __init fork_init(void)
init_task.signal->rlim[RLIMIT_SIGPENDING] =
init_task.signal->rlim[RLIMIT_NPROC];
- for (i = 0; i < UCOUNT_COUNTS; i++)
+ for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++)
init_user_ns.ucount_max[i] = max_threads/2;
+ set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY);
+ set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY);
+ set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY);
+ set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY);
+
#ifdef CONFIG_VMAP_STACK
cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
NULL, free_vm_stack_cache);
@@ -918,6 +936,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
#endif
if (orig->cpus_ptr == &orig->cpus_mask)
tsk->cpus_ptr = &tsk->cpus_mask;
+ dup_user_cpus_ptr(tsk, orig, node);
/*
* One for the user space visible state that goes away when reaped.
@@ -1029,7 +1048,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
mm_pgtables_bytes_init(mm);
mm->map_count = 0;
mm->locked_vm = 0;
- atomic_set(&mm->has_pinned, 0);
atomic64_set(&mm->pinned_vm, 0);
memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
spin_lock_init(&mm->page_table_lock);
@@ -1045,6 +1063,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
mm->pmd_huge_pte = NULL;
#endif
mm_init_uprobes_state(mm);
+ hugetlb_count_init(mm);
if (current->mm) {
mm->flags = current->mm->flags & MMF_INIT_MASK;
@@ -1143,11 +1162,11 @@ void mmput_async(struct mm_struct *mm)
*
* Main users are mmput() and sys_execve(). Callers prevent concurrent
* invocations: in mmput() nobody alive left, in execve task is single
- * threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the
- * mm->exe_file, but does so without using set_mm_exe_file() in order
- * to avoid the need for any locks.
+ * threaded.
+ *
+ * Can only fail if new_exe_file != NULL.
*/
-void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
+int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
{
struct file *old_exe_file;
@@ -1158,11 +1177,73 @@ void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
*/
old_exe_file = rcu_dereference_raw(mm->exe_file);
- if (new_exe_file)
+ if (new_exe_file) {
+ /*
+ * We expect the caller (i.e., sys_execve) to already denied
+ * write access, so this is unlikely to fail.
+ */
+ if (unlikely(deny_write_access(new_exe_file)))
+ return -EACCES;
get_file(new_exe_file);
+ }
rcu_assign_pointer(mm->exe_file, new_exe_file);
- if (old_exe_file)
+ if (old_exe_file) {
+ allow_write_access(old_exe_file);
fput(old_exe_file);
+ }
+ return 0;
+}
+
+/**
+ * replace_mm_exe_file - replace a reference to the mm's executable file
+ *
+ * This changes mm's executable file (shown as symlink /proc/[pid]/exe),
+ * dealing with concurrent invocation and without grabbing the mmap lock in
+ * write mode.
+ *
+ * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE).
+ */
+int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
+{
+ struct vm_area_struct *vma;
+ struct file *old_exe_file;
+ int ret = 0;
+
+ /* Forbid mm->exe_file change if old file still mapped. */
+ old_exe_file = get_mm_exe_file(mm);
+ if (old_exe_file) {
+ mmap_read_lock(mm);
+ for (vma = mm->mmap; vma && !ret; vma = vma->vm_next) {
+ if (!vma->vm_file)
+ continue;
+ if (path_equal(&vma->vm_file->f_path,
+ &old_exe_file->f_path))
+ ret = -EBUSY;
+ }
+ mmap_read_unlock(mm);
+ fput(old_exe_file);
+ if (ret)
+ return ret;
+ }
+
+ /* set the new file, lockless */
+ ret = deny_write_access(new_exe_file);
+ if (ret)
+ return -EACCES;
+ get_file(new_exe_file);
+
+ old_exe_file = xchg(&mm->exe_file, new_exe_file);
+ if (old_exe_file) {
+ /*
+ * Don't race with dup_mmap() getting the file and disallowing
+ * write access while someone might open the file writable.
+ */
+ mmap_read_lock(mm);
+ allow_write_access(old_exe_file);
+ fput(old_exe_file);
+ mmap_read_unlock(mm);
+ }
+ return 0;
}
/**
@@ -1182,7 +1263,6 @@ struct file *get_mm_exe_file(struct mm_struct *mm)
rcu_read_unlock();
return exe_file;
}
-EXPORT_SYMBOL(get_mm_exe_file);
/**
* get_task_exe_file - acquire a reference to the task's executable file
@@ -1205,7 +1285,6 @@ struct file *get_task_exe_file(struct task_struct *task)
task_unlock(task);
return exe_file;
}
-EXPORT_SYMBOL(get_task_exe_file);
/**
* get_task_mm - acquire a reference to the task's mm
@@ -1977,8 +2056,7 @@ static __latent_entropy struct task_struct *copy_process(
DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
retval = -EAGAIN;
- if (atomic_read(&p->real_cred->user->processes) >=
- task_rlimit(p, RLIMIT_NPROC)) {
+ if (is_ucounts_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
if (p->real_cred->user != INIT_USER &&
!capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
goto bad_fork_free;
@@ -1999,7 +2077,7 @@ static __latent_entropy struct task_struct *copy_process(
goto bad_fork_cleanup_count;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
- p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE);
+ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY);
p->flags |= PF_FORKNOEXEC;
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
@@ -2079,6 +2157,7 @@ static __latent_entropy struct task_struct *copy_process(
#endif
#ifdef CONFIG_BPF_SYSCALL
RCU_INIT_POINTER(p->bpf_storage, NULL);
+ p->bpf_ctx = NULL;
#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
@@ -2249,6 +2328,8 @@ static __latent_entropy struct task_struct *copy_process(
klp_copy_process(p);
+ sched_core_fork(p);
+
spin_lock(&current->sighand->siglock);
/*
@@ -2336,6 +2417,7 @@ static __latent_entropy struct task_struct *copy_process(
return p;
bad_fork_cancel_cgroup:
+ sched_core_free(p);
spin_unlock(&current->sighand->siglock);
write_unlock_irq(&tasklist_lock);
cgroup_cancel_fork(p, args);
@@ -2384,10 +2466,10 @@ bad_fork_cleanup_threadgroup_lock:
#endif
delayacct_tsk_free(p);
bad_fork_cleanup_count:
- atomic_dec(&p->cred->user->processes);
+ dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
exit_creds(p);
bad_fork_free:
- p->state = TASK_DEAD;
+ WRITE_ONCE(p->__state, TASK_DEAD);
put_task_stack(p);
delayed_free_task(p);
fork_out:
@@ -2407,7 +2489,7 @@ static inline void init_idle_pids(struct task_struct *idle)
}
}
-struct task_struct *fork_idle(int cpu)
+struct task_struct * __init fork_idle(int cpu)
{
struct task_struct *task;
struct kernel_clone_args args = {
@@ -2997,6 +3079,12 @@ int ksys_unshare(unsigned long unshare_flags)
if (err)
goto bad_unshare_cleanup_cred;
+ if (new_cred) {
+ err = set_cred_ucounts(new_cred);
+ if (err)
+ goto bad_unshare_cleanup_cred;
+ }
+
if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) {
if (do_sysvsem) {
/*