aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/fork.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/fork.c')
-rw-r--r--kernel/fork.c170
1 files changed, 156 insertions, 14 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index 9dcd18aa210b..b4cba953040a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -11,6 +11,7 @@
* management can be a bitch. See 'mm/memory.c': 'copy_page_range()'
*/
+#include <linux/anon_inodes.h>
#include <linux/slab.h>
#include <linux/sched/autogroup.h>
#include <linux/sched/mm.h>
@@ -21,6 +22,7 @@
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/sched/cputime.h>
+#include <linux/seq_file.h>
#include <linux/rtmutex.h>
#include <linux/init.h>
#include <linux/unistd.h>
@@ -815,6 +817,7 @@ void __init fork_init(void)
#endif
lockdep_init_task(&init_task);
+ uprobes_init();
}
int __weak arch_dup_task_struct(struct task_struct *dst,
@@ -952,6 +955,15 @@ static void mm_init_aio(struct mm_struct *mm)
#endif
}
+static __always_inline void mm_clear_owner(struct mm_struct *mm,
+ struct task_struct *p)
+{
+#ifdef CONFIG_MEMCG
+ if (mm->owner == p)
+ WRITE_ONCE(mm->owner, NULL);
+#endif
+}
+
static void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
{
#ifdef CONFIG_MEMCG
@@ -1222,7 +1234,9 @@ static int wait_for_vfork_done(struct task_struct *child,
int killed;
freezer_do_not_count();
+ cgroup_enter_frozen();
killed = wait_for_completion_killable(vfork);
+ cgroup_leave_frozen(false);
freezer_count();
if (killed) {
@@ -1298,13 +1312,20 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
complete_vfork_done(tsk);
}
-/*
- * Allocate a new mm structure and copy contents from the
- * mm structure of the passed in task structure.
+/**
+ * dup_mm() - duplicates an existing mm structure
+ * @tsk: the task_struct with which the new mm will be associated.
+ * @oldmm: the mm to duplicate.
+ *
+ * Allocates a new mm structure and duplicates the provided @oldmm structure
+ * content into it.
+ *
+ * Return: the duplicated mm or NULL on failure.
*/
-static struct mm_struct *dup_mm(struct task_struct *tsk)
+static struct mm_struct *dup_mm(struct task_struct *tsk,
+ struct mm_struct *oldmm)
{
- struct mm_struct *mm, *oldmm = current->mm;
+ struct mm_struct *mm;
int err;
mm = allocate_mm();
@@ -1331,6 +1352,7 @@ static struct mm_struct *dup_mm(struct task_struct *tsk)
free_pt:
/* don't put binfmt in mmput, we haven't got module yet */
mm->binfmt = NULL;
+ mm_init_owner(mm, NULL);
mmput(mm);
fail_nomem:
@@ -1371,7 +1393,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
}
retval = -ENOMEM;
- mm = dup_mm(tsk);
+ mm = dup_mm(tsk, current->mm);
if (!mm)
goto fail_nomem;
@@ -1662,6 +1684,73 @@ static inline void rcu_copy_process(struct task_struct *p)
#endif /* #ifdef CONFIG_TASKS_RCU */
}
+static int pidfd_release(struct inode *inode, struct file *file)
+{
+ struct pid *pid = file->private_data;
+
+ file->private_data = NULL;
+ put_pid(pid);
+ return 0;
+}
+
+#ifdef CONFIG_PROC_FS
+static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
+{
+ struct pid_namespace *ns = proc_pid_ns(file_inode(m->file));
+ struct pid *pid = f->private_data;
+
+ seq_put_decimal_ull(m, "Pid:\t", pid_nr_ns(pid, ns));
+ seq_putc(m, '\n');
+}
+#endif
+
+const struct file_operations pidfd_fops = {
+ .release = pidfd_release,
+#ifdef CONFIG_PROC_FS
+ .show_fdinfo = pidfd_show_fdinfo,
+#endif
+};
+
+/**
+ * pidfd_create() - Create a new pid file descriptor.
+ *
+ * @pid: struct pid that the pidfd will reference
+ *
+ * This creates a new pid file descriptor with the O_CLOEXEC flag set.
+ *
+ * Note, that this function can only be called after the fd table has
+ * been unshared to avoid leaking the pidfd to the new process.
+ *
+ * Return: On success, a cloexec pidfd is returned.
+ * On error, a negative errno number will be returned.
+ */
+static int pidfd_create(struct pid *pid)
+{
+ int fd;
+
+ fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid),
+ O_RDWR | O_CLOEXEC);
+ if (fd < 0)
+ put_pid(pid);
+
+ return fd;
+}
+
+static void __delayed_free_task(struct rcu_head *rhp)
+{
+ struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
+
+ free_task(tsk);
+}
+
+static __always_inline void delayed_free_task(struct task_struct *tsk)
+{
+ if (IS_ENABLED(CONFIG_MEMCG))
+ call_rcu(&tsk->rcu, __delayed_free_task);
+ else
+ free_task(tsk);
+}
+
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
@@ -1674,13 +1763,14 @@ static __latent_entropy struct task_struct *copy_process(
unsigned long clone_flags,
unsigned long stack_start,
unsigned long stack_size,
+ int __user *parent_tidptr,
int __user *child_tidptr,
struct pid *pid,
int trace,
unsigned long tls,
int node)
{
- int retval;
+ int pidfd = -1, retval;
struct task_struct *p;
struct multiprocess_signals delayed;
@@ -1730,6 +1820,31 @@ static __latent_entropy struct task_struct *copy_process(
return ERR_PTR(-EINVAL);
}
+ if (clone_flags & CLONE_PIDFD) {
+ int reserved;
+
+ /*
+ * - CLONE_PARENT_SETTID is useless for pidfds and also
+ * parent_tidptr is used to return pidfds.
+ * - CLONE_DETACHED is blocked so that we can potentially
+ * reuse it later for CLONE_PIDFD.
+ * - CLONE_THREAD is blocked until someone really needs it.
+ */
+ if (clone_flags &
+ (CLONE_DETACHED | CLONE_PARENT_SETTID | CLONE_THREAD))
+ return ERR_PTR(-EINVAL);
+
+ /*
+ * Verify that parent_tidptr is sane so we can potentially
+ * reuse it later.
+ */
+ if (get_user(reserved, parent_tidptr))
+ return ERR_PTR(-EFAULT);
+
+ if (reserved != 0)
+ return ERR_PTR(-EINVAL);
+ }
+
/*
* Force any signals received before this point to be delivered
* before the fork happens. Collect up signals sent to multiple
@@ -1936,6 +2051,22 @@ static __latent_entropy struct task_struct *copy_process(
}
}
+ /*
+ * This has to happen after we've potentially unshared the file
+ * descriptor table (so that the pidfd doesn't leak into the child
+ * if the fd table isn't shared).
+ */
+ if (clone_flags & CLONE_PIDFD) {
+ retval = pidfd_create(pid);
+ if (retval < 0)
+ goto bad_fork_free_pid;
+
+ pidfd = retval;
+ retval = put_user(pidfd, parent_tidptr);
+ if (retval)
+ goto bad_fork_put_pidfd;
+ }
+
#ifdef CONFIG_BLOCK
p->plug = NULL;
#endif
@@ -1962,7 +2093,7 @@ static __latent_entropy struct task_struct *copy_process(
#ifdef TIF_SYSCALL_EMU
clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
- clear_all_latency_tracing(p);
+ clear_tsk_latency_tracing(p);
/* ok, now we should be set up.. */
p->pid = pid_nr(pid);
@@ -1996,7 +2127,7 @@ static __latent_entropy struct task_struct *copy_process(
*/
retval = cgroup_can_fork(p);
if (retval)
- goto bad_fork_free_pid;
+ goto bad_fork_cgroup_threadgroup_change_end;
/*
* From this point on we must avoid any synchronous user-space
@@ -2111,8 +2242,12 @@ bad_fork_cancel_cgroup:
spin_unlock(&current->sighand->siglock);
write_unlock_irq(&tasklist_lock);
cgroup_cancel_fork(p);
-bad_fork_free_pid:
+bad_fork_cgroup_threadgroup_change_end:
cgroup_threadgroup_change_end(current);
+bad_fork_put_pidfd:
+ if (clone_flags & CLONE_PIDFD)
+ ksys_close(pidfd);
+bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_thread:
@@ -2123,8 +2258,10 @@ bad_fork_cleanup_io:
bad_fork_cleanup_namespaces:
exit_task_namespaces(p);
bad_fork_cleanup_mm:
- if (p->mm)
+ if (p->mm) {
+ mm_clear_owner(p->mm, p);
mmput(p->mm);
+ }
bad_fork_cleanup_signal:
if (!(clone_flags & CLONE_THREAD))
free_signal_struct(p->signal);
@@ -2155,7 +2292,7 @@ bad_fork_cleanup_count:
bad_fork_free:
p->state = TASK_DEAD;
put_task_stack(p);
- free_task(p);
+ delayed_free_task(p);
fork_out:
spin_lock_irq(&current->sighand->siglock);
hlist_del_init(&delayed.node);
@@ -2176,7 +2313,7 @@ static inline void init_idle_pids(struct task_struct *idle)
struct task_struct *fork_idle(int cpu)
{
struct task_struct *task;
- task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
+ task = copy_process(CLONE_VM, 0, 0, NULL, NULL, &init_struct_pid, 0, 0,
cpu_to_node(cpu));
if (!IS_ERR(task)) {
init_idle_pids(task);
@@ -2186,6 +2323,11 @@ struct task_struct *fork_idle(int cpu)
return task;
}
+struct mm_struct *copy_init_mm(void)
+{
+ return dup_mm(NULL, &init_mm);
+}
+
/*
* Ok, this is the main fork-routine.
*
@@ -2223,7 +2365,7 @@ long _do_fork(unsigned long clone_flags,
trace = 0;
}
- p = copy_process(clone_flags, stack_start, stack_size,
+ p = copy_process(clone_flags, stack_start, stack_size, parent_tidptr,
child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
add_latent_entropy();
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.