Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull exec/proc updates from Eric Biederman:
 "This contains two significant pieces of work: the work to sort out
  proc_flush_task, and the work to solve a deadlock between strace and
  exec.

  Fixing proc_flush_task so that it no longer requires a persistent
  mount makes improvements to proc possible. The removal of the
  persistent mount solves an old regression that that caused the hidepid
  mount option to only work on remount not on mount. The regression was
  found and reported by the Android folks. This further allows Alexey
  Gladkov's work making proc mount options specific to an individual
  mount of proc to move forward.

  The work on exec starts solving a long standing issue with exec that
  it takes mutexes of blocking userspace applications, which makes exec
  extremely deadlock prone. For the moment this adds a second mutex with
  a narrower scope that handles all of the easy cases. Which makes the
  tricky cases easy to spot. With a little luck the code to solve those
  deadlocks will be ready by next merge window"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (25 commits)
  signal: Extend exec_id to 64bits
  pidfd: Use new infrastructure to fix deadlocks in execve
  perf: Use new infrastructure to fix deadlocks in execve
  proc: io_accounting: Use new infrastructure to fix deadlocks in execve
  proc: Use new infrastructure to fix deadlocks in execve
  kernel/kcmp.c: Use new infrastructure to fix deadlocks in execve
  kernel: doc: remove outdated comment cred.c
  mm: docs: Fix a comment in process_vm_rw_core
  selftests/ptrace: add test cases for dead-locks
  exec: Fix a deadlock in strace
  exec: Add exec_update_mutex to replace cred_guard_mutex
  exec: Move exec_mmap right after de_thread in flush_old_exec
  exec: Move cleanup of posix timers on exec out of de_thread
  exec: Factor unshare_sighand out of de_thread and call it separately
  exec: Only compute current once in flush_old_exec
  pid: Improve the comment about waiting in zap_pid_ns_processes
  proc: Remove the now unnecessary internal mount of proc
  uml: Create a private mount of proc for mconsole
  uml: Don't consult current to find the proc_mnt in mconsole_proc
  proc: Use a list of inodes to flush from proc
  ...

arch/um/drivers/mconsole_kern.c

@@ -36,6 +36,8 @@
 #include "mconsole_kern.h"
 #include <os.h>
 
+static struct vfsmount *proc_mnt = NULL;
+
 static int do_unlink_socket(struct notifier_block *notifier,
 			    unsigned long what, void *data)
 {
@@ -123,7 +125,7 @@ void mconsole_log(struct mc_request *req)
 
 void mconsole_proc(struct mc_request *req)
 {
-	struct vfsmount *mnt = task_active_pid_ns(current)->proc_mnt;
+	struct vfsmount *mnt = proc_mnt;
 	char *buf;
 	int len;
 	struct file *file;
@@ -134,6 +136,10 @@ void mconsole_proc(struct mc_request *req)
 	ptr += strlen("proc");
 	ptr = skip_spaces(ptr);
 
+	if (!mnt) {
+		mconsole_reply(req, "Proc not available", 1, 0);
+		goto out;
+	}
 	file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY, 0);
 	if (IS_ERR(file)) {
 		mconsole_reply(req, "Failed to open file", 1, 0);
@@ -683,6 +689,24 @@ void mconsole_stack(struct mc_request *req)
 	with_console(req, stack_proc, to);
 }
 
+static int __init mount_proc(void)
+{
+	struct file_system_type *proc_fs_type;
+	struct vfsmount *mnt;
+
+	proc_fs_type = get_fs_type("proc");
+	if (!proc_fs_type)
+		return -ENODEV;
+
+	mnt = kern_mount(proc_fs_type);
+	put_filesystem(proc_fs_type);
+	if (IS_ERR(mnt))
+		return PTR_ERR(mnt);
+
+	proc_mnt = mnt;
+	return 0;
+}
+
 /*
  * Changed by mconsole_setup, which is __setup, and called before SMP is
  * active.
@@ -696,6 +720,8 @@ static int __init mconsole_init(void)
 	int err;
 	char file[UNIX_PATH_MAX];
 
+	mount_proc();
+
 	if (umid_file_name("mconsole", file, sizeof(file)))
 		return -1;
 	snprintf(mconsole_socket_name, sizeof(file), "%s", file);

fs/exec.c

@@ -1036,16 +1036,26 @@ ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len)
 }
 EXPORT_SYMBOL(read_code);
 
+/*
+ * Maps the mm_struct mm into the current task struct.
+ * On success, this function returns with the mutex
+ * exec_update_mutex locked.
+ */
 static int exec_mmap(struct mm_struct *mm)
 {
 	struct task_struct *tsk;
 	struct mm_struct *old_mm, *active_mm;
+	int ret;
 
 	/* Notify parent that we're no longer interested in the old VM */
 	tsk = current;
 	old_mm = current->mm;
 	exec_mm_release(tsk, old_mm);
 
+	ret = mutex_lock_killable(&tsk->signal->exec_update_mutex);
+	if (ret)
+		return ret;
+
 	if (old_mm) {
 		sync_mm_rss(old_mm);
 		/*
@@ -1057,9 +1067,11 @@ static int exec_mmap(struct mm_struct *mm)
 		down_read(&old_mm->mmap_sem);
 		if (unlikely(old_mm->core_state)) {
 			up_read(&old_mm->mmap_sem);
+			mutex_unlock(&tsk->signal->exec_update_mutex);
 			return -EINTR;
 		}
 	}
+
 	task_lock(tsk);
 	active_mm = tsk->active_mm;
 	membarrier_exec_mmap(mm);
@@ -1215,10 +1227,22 @@ static int de_thread(struct task_struct *tsk)
 	/* we have changed execution domain */
 	tsk->exit_signal = SIGCHLD;
 
-#ifdef CONFIG_POSIX_TIMERS
-	exit_itimers(sig);
-	flush_itimer_signals();
-#endif
+	BUG_ON(!thread_group_leader(tsk));
+	return 0;
+
+killed:
+	/* protects against exit_notify() and __exit_signal() */
+	read_lock(&tasklist_lock);
+	sig->group_exit_task = NULL;
+	sig->notify_count = 0;
+	read_unlock(&tasklist_lock);
+	return -EAGAIN;
+}
+
+
+static int unshare_sighand(struct task_struct *me)
+{
+	struct sighand_struct *oldsighand = me->sighand;
 
 	if (refcount_read(&oldsighand->count) != 1) {
 		struct sighand_struct *newsighand;
@@ -1236,23 +1260,13 @@ static int de_thread(struct task_struct *tsk)
 
 		write_lock_irq(&tasklist_lock);
 		spin_lock(&oldsighand->siglock);
-		rcu_assign_pointer(tsk->sighand, newsighand);
+		rcu_assign_pointer(me->sighand, newsighand);
 		spin_unlock(&oldsighand->siglock);
 		write_unlock_irq(&tasklist_lock);
 
 		__cleanup_sighand(oldsighand);
 	}
-
-	BUG_ON(!thread_group_leader(tsk));
 	return 0;
-
-killed:
-	/* protects against exit_notify() and __exit_signal() */
-	read_lock(&tasklist_lock);
-	sig->group_exit_task = NULL;
-	sig->notify_count = 0;
-	read_unlock(&tasklist_lock);
-	return -EAGAIN;
 }
 
 char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk)
@@ -1286,13 +1300,13 @@ void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec)
  */
 int flush_old_exec(struct linux_binprm * bprm)
 {
+	struct task_struct *me = current;
 	int retval;
 
 	/*
-	 * Make sure we have a private signal table and that
-	 * we are unassociated from the previous thread group.
+	 * Make this the only thread in the thread group.
 	 */
-	retval = de_thread(current);
+	retval = de_thread(me);
 	if (retval)
 		goto out;
 
@@ -1312,18 +1326,31 @@ int flush_old_exec(struct linux_binprm * bprm)
 		goto out;
 
 	/*
-	 * After clearing bprm->mm (to mark that current is using the
-	 * prepared mm now), we have nothing left of the original
+	 * After setting bprm->called_exec_mmap (to mark that current is
+	 * using the prepared mm now), we have nothing left of the original
 	 * process. If anything from here on returns an error, the check
 	 * in search_binary_handler() will SEGV current.
 	 */
+	bprm->called_exec_mmap = 1;
 	bprm->mm = NULL;
 
+#ifdef CONFIG_POSIX_TIMERS
+	exit_itimers(me->signal);
+	flush_itimer_signals();
+#endif
+
+	/*
+	 * Make the signal table private.
+	 */
+	retval = unshare_sighand(me);
+	if (retval)
+		goto out;
+
 	set_fs(USER_DS);
-	current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD |
+	me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD |
 					PF_NOFREEZE | PF_NO_SETAFFINITY);
 	flush_thread();
-	current->personality &= ~bprm->per_clear;
+	me->personality &= ~bprm->per_clear;
 
 	/*
 	 * We have to apply CLOEXEC before we change whether the process is
@@ -1331,7 +1358,7 @@ int flush_old_exec(struct linux_binprm * bprm)
 	 * trying to access the should-be-closed file descriptors of a process
 	 * undergoing exec(2).
 	 */
-	do_close_on_exec(current->files);
+	do_close_on_exec(me->files);
 	return 0;
 
 out:
@@ -1412,7 +1439,7 @@ void setup_new_exec(struct linux_binprm * bprm)
 
 	/* An exec changes our domain. We are no longer part of the thread
 	   group */
-	current->self_exec_id++;
+	WRITE_ONCE(current->self_exec_id, current->self_exec_id + 1);
 	flush_signal_handlers(current, 0);
 }
 EXPORT_SYMBOL(setup_new_exec);
@@ -1450,6 +1477,8 @@ static void free_bprm(struct linux_binprm *bprm)
 {
 	free_arg_pages(bprm);
 	if (bprm->cred) {
+		if (bprm->called_exec_mmap)
+			mutex_unlock(&current->signal->exec_update_mutex);
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
@@ -1499,6 +1528,7 @@ void install_exec_creds(struct linux_binprm *bprm)
 	 * credentials; any time after this it may be unlocked.
 	 */
 	security_bprm_committed_creds(bprm);
+	mutex_unlock(&current->signal->exec_update_mutex);
 	mutex_unlock(&current->signal->cred_guard_mutex);
 }
 EXPORT_SYMBOL(install_exec_creds);
@@ -1690,7 +1720,7 @@ int search_binary_handler(struct linux_binprm *bprm)
 
 		read_lock(&binfmt_lock);
 		put_binfmt(fmt);
-		if (retval < 0 && !bprm->mm) {
+		if (retval < 0 && bprm->called_exec_mmap) {
 			/* we got to flush_old_exec() and failed after it */
 			read_unlock(&binfmt_lock);
 			force_sigsegv(SIGSEGV);

fs/proc/base.c

@@ -405,11 +405,11 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
 
 static int lock_trace(struct task_struct *task)
 {
-	int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+	int err = mutex_lock_killable(&task->signal->exec_update_mutex);
 	if (err)
 		return err;
 	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
-		mutex_unlock(&task->signal->cred_guard_mutex);
+		mutex_unlock(&task->signal->exec_update_mutex);
 		return -EPERM;
 	}
 	return 0;
@@ -417,7 +417,7 @@ static int lock_trace(struct task_struct *task)
 
 static void unlock_trace(struct task_struct *task)
 {
-	mutex_unlock(&task->signal->cred_guard_mutex);
+	mutex_unlock(&task->signal->exec_update_mutex);
 }
 
 #ifdef CONFIG_STACKTRACE
@@ -1834,11 +1834,25 @@ void task_dump_owner(struct task_struct *task, umode_t mode,
 	*rgid = gid;
 }
 
+void proc_pid_evict_inode(struct proc_inode *ei)
+{
+	struct pid *pid = ei->pid;
+
+	if (S_ISDIR(ei->vfs_inode.i_mode)) {
+		spin_lock(&pid->wait_pidfd.lock);
+		hlist_del_init_rcu(&ei->sibling_inodes);
+		spin_unlock(&pid->wait_pidfd.lock);
+	}
+
+	put_pid(pid);
+}
+
 struct inode *proc_pid_make_inode(struct super_block * sb,
 				  struct task_struct *task, umode_t mode)
 {
 	struct inode * inode;
 	struct proc_inode *ei;
+	struct pid *pid;
 
 	/* We need a new inode */
 
@@ -1856,10 +1870,18 @@ struct inode *proc_pid_make_inode(struct super_block * sb,
 	/*
 	 * grab the reference to task.
 	 */
-	ei->pid = get_task_pid(task, PIDTYPE_PID);
-	if (!ei->pid)
+	pid = get_task_pid(task, PIDTYPE_PID);
+	if (!pid)
 		goto out_unlock;
 
+	/* Let the pid remember us for quick removal */
+	ei->pid = pid;
+	if (S_ISDIR(mode)) {
+		spin_lock(&pid->wait_pidfd.lock);
+		hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes);
+		spin_unlock(&pid->wait_pidfd.lock);
+	}
+
 	task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
 	security_task_to_inode(task, inode);
 
@@ -2861,7 +2883,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
 	unsigned long flags;
 	int result;
 
-	result = mutex_lock_killable(&task->signal->cred_guard_mutex);
+	result = mutex_lock_killable(&task->signal->exec_update_mutex);
 	if (result)
 		return result;
 
@@ -2897,7 +2919,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
 	result = 0;
 
 out_unlock:
-	mutex_unlock(&task->signal->cred_guard_mutex);
+	mutex_unlock(&task->signal->exec_update_mutex);
 	return result;
 }
 
@@ -3230,90 +3252,29 @@ static const struct inode_operations proc_tgid_base_inode_operations = {
 	.permission	= proc_pid_permission,
 };
 
-static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
-{
-	struct dentry *dentry, *leader, *dir;
-	char buf[10 + 1];
-	struct qstr name;
-
-	name.name = buf;
-	name.len = snprintf(buf, sizeof(buf), "%u", pid);
-	/* no ->d_hash() rejects on procfs */
-	dentry = d_hash_and_lookup(mnt->mnt_root, &name);
-	if (dentry) {
-		d_invalidate(dentry);
-		dput(dentry);
-	}
-
-	if (pid == tgid)
-		return;
-
-	name.name = buf;
-	name.len = snprintf(buf, sizeof(buf), "%u", tgid);
-	leader = d_hash_and_lookup(mnt->mnt_root, &name);
-	if (!leader)
-		goto out;
-
-	name.name = "task";
-	name.len = strlen(name.name);
-	dir = d_hash_and_lookup(leader, &name);
-	if (!dir)
-		goto out_put_leader;
-
-	name.name = buf;
-	name.len = snprintf(buf, sizeof(buf), "%u", pid);
-	dentry = d_hash_and_lookup(dir, &name);
-	if (dentry) {
-		d_invalidate(dentry);
-		dput(dentry);
-	}
-
-	dput(dir);
-out_put_leader:
-	dput(leader);
-out:
-	return;
-}
-
 /**
- * proc_flush_task -  Remove dcache entries for @task from the /proc dcache.
- * @task: task that should be flushed.
+ * proc_flush_pid -  Remove dcache entries for @pid from the /proc dcache.
+ * @pid: pid that should be flushed.
  *
- * When flushing dentries from proc, one needs to flush them from global
- * proc (proc_mnt) and from all the namespaces' procs this task was seen
- * in. This call is supposed to do all of this job.
- *
- * Looks in the dcache for
- * /proc/@pid
- * /proc/@tgid/task/@pid
- * if either directory is present flushes it and all of it'ts children
- * from the dcache.
+ * This function walks a list of inodes (that belong to any proc
+ * filesystem) that are attached to the pid and flushes them from
+ * the dentry cache.
  *
  * It is safe and reasonable to cache /proc entries for a task until
  * that task exits.  After that they just clog up the dcache with
  * useless entries, possibly causing useful dcache entries to be
- * flushed instead.  This routine is proved to flush those useless
- * dcache entries at process exit time.
+ * flushed instead.  This routine is provided to flush those useless
+ * dcache entries when a process is reaped.
  *
  * NOTE: This routine is just an optimization so it does not guarantee
- *       that no dcache entries will exist at process exit time it
- *       just makes it very unlikely that any will persist.
+ *       that no dcache entries will exist after a process is reaped
+ *       it just makes it very unlikely that any will persist.
  */
 
-void proc_flush_task(struct task_struct *task)
+void proc_flush_pid(struct pid *pid)
 {
-	int i;
-	struct pid *pid, *tgid;
-	struct upid *upid;
-
-	pid = task_pid(task);
-	tgid = task_tgid(task);
-
-	for (i = 0; i <= pid->level; i++) {
-		upid = &pid->numbers[i];
-		proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr,
-					tgid->numbers[i].nr);
-	}
+	proc_invalidate_siblings_dcache(&pid->inodes, &pid->wait_pidfd.lock);
+	put_pid(pid);
 }
 
 static struct dentry *proc_pid_instantiate(struct dentry * dentry,

fs/proc/inode.c

@@ -33,21 +33,27 @@ static void proc_evict_inode(struct inode *inode)
 {
 	struct proc_dir_entry *de;
 	struct ctl_table_header *head;
+	struct proc_inode *ei = PROC_I(inode);
 
 	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 
 	/* Stop tracking associated processes */
-	put_pid(PROC_I(inode)->pid);
+	if (ei->pid) {
+		proc_pid_evict_inode(ei);
+		ei->pid = NULL;
+	}
 
 	/* Let go of any associated proc directory entry */
-	de = PDE(inode);
-	if (de)
+	de = ei->pde;
+	if (de) {
 		pde_put(de);
+		ei->pde = NULL;
+	}
 
-	head = PROC_I(inode)->sysctl;
+	head = ei->sysctl;
 	if (head) {
-		RCU_INIT_POINTER(PROC_I(inode)->sysctl, NULL);
+		RCU_INIT_POINTER(ei->sysctl, NULL);
 		proc_sys_evict_inode(inode, head);
 	}
 }
@@ -68,6 +74,7 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
 	ei->pde = NULL;
 	ei->sysctl = NULL;
 	ei->sysctl_entry = NULL;
+	INIT_HLIST_NODE(&ei->sibling_inodes);
 	ei->ns_ops = NULL;
 	return &ei->vfs_inode;
 }
@@ -102,6 +109,62 @@ void __init proc_init_kmemcache(void)
 	BUILD_BUG_ON(sizeof(struct proc_dir_entry) >= SIZEOF_PDE);
 }
 
+void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock)
+{
+	struct inode *inode;
+	struct proc_inode *ei;
+	struct hlist_node *node;
+	struct super_block *old_sb = NULL;
+
+	rcu_read_lock();
+	for (;;) {
+		struct super_block *sb;
+		node = hlist_first_rcu(inodes);
+		if (!node)
+			break;
+		ei = hlist_entry(node, struct proc_inode, sibling_inodes);
+		spin_lock(lock);
+		hlist_del_init_rcu(&ei->sibling_inodes);
+		spin_unlock(lock);
+
+		inode = &ei->vfs_inode;
+		sb = inode->i_sb;
+		if ((sb != old_sb) && !atomic_inc_not_zero(&sb->s_active))
+			continue;
+		inode = igrab(inode);
+		rcu_read_unlock();
+		if (sb != old_sb) {
+			if (old_sb)
+				deactivate_super(old_sb);
+			old_sb = sb;
+		}
+		if (unlikely(!inode)) {
+			rcu_read_lock();
+			continue;
+		}
+
+		if (S_ISDIR(inode->i_mode)) {
+			struct dentry *dir = d_find_any_alias(inode);
+			if (dir) {
+				d_invalidate(dir);
+				dput(dir);
+			}
+		} else {
+			struct dentry *dentry;
+			while ((dentry = d_find_alias(inode))) {
+				d_invalidate(dentry);
+				dput(dentry);
+			}
+		}
+		iput(inode);
+
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+	if (old_sb)
+		deactivate_super(old_sb);
+}
+
 static int proc_show_options(struct seq_file *seq, struct dentry *root)
 {
 	struct super_block *sb = root->d_sb;

fs/proc/internal.h

@@ -91,7 +91,7 @@ struct proc_inode {
 	struct proc_dir_entry *pde;
 	struct ctl_table_header *sysctl;
 	struct ctl_table *sysctl_entry;
-	struct hlist_node sysctl_inodes;
+	struct hlist_node sibling_inodes;
 	const struct proc_ns_operations *ns_ops;
 	struct inode vfs_inode;
 } __randomize_layout;
@@ -158,6 +158,7 @@ extern int proc_pid_statm(struct seq_file *, struct pid_namespace *,
 extern const struct dentry_operations pid_dentry_operations;
 extern int pid_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int proc_setattr(struct dentry *, struct iattr *);
+extern void proc_pid_evict_inode(struct proc_inode *);
 extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t);
 extern void pid_update_inode(struct task_struct *, struct inode *);
 extern int pid_delete_dentry(const struct dentry *);
@@ -210,6 +211,7 @@ extern const struct inode_operations proc_pid_link_inode_operations;
 extern const struct super_operations proc_sops;
 
 void proc_init_kmemcache(void);
+void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock);
 void set_proc_pid_nlink(void);
 extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
 extern void proc_entry_rundown(struct proc_dir_entry *);

fs/proc/proc_sysctl.c

@@ -267,42 +267,9 @@ static void unuse_table(struct ctl_table_header *p)
 			complete(p->unregistering);
 }
 
-static void proc_sys_prune_dcache(struct ctl_table_header *head)
+static void proc_sys_invalidate_dcache(struct ctl_table_header *head)
 {
-	struct inode *inode;
-	struct proc_inode *ei;
-	struct hlist_node *node;
-	struct super_block *sb;
-
-	rcu_read_lock();
-	for (;;) {
-		node = hlist_first_rcu(&head->inodes);
-		if (!node)
-			break;
-		ei = hlist_entry(node, struct proc_inode, sysctl_inodes);
-		spin_lock(&sysctl_lock);
-		hlist_del_init_rcu(&ei->sysctl_inodes);
-		spin_unlock(&sysctl_lock);
-
-		inode = &ei->vfs_inode;
-		sb = inode->i_sb;
-		if (!atomic_inc_not_zero(&sb->s_active))
-			continue;
-		inode = igrab(inode);
-		rcu_read_unlock();
-		if (unlikely(!inode)) {
-			deactivate_super(sb);
-			rcu_read_lock();
-			continue;
-		}
-
-		d_prune_aliases(inode);
-		iput(inode);
-		deactivate_super(sb);
-
-		rcu_read_lock();
-	}
-	rcu_read_unlock();
+	proc_invalidate_siblings_dcache(&head->inodes, &sysctl_lock);
 }
 
 /* called under sysctl_lock, will reacquire if has to wait */
@@ -324,10 +291,10 @@ static void start_unregistering(struct ctl_table_header *p)
 		spin_unlock(&sysctl_lock);
 	}
 	/*
-	 * Prune dentries for unregistered sysctls: namespaced sysctls
+	 * Invalidate dentries for unregistered sysctls: namespaced sysctls
 	 * can have duplicate names and contaminate dcache very badly.
 	 */
-	proc_sys_prune_dcache(p);
+	proc_sys_invalidate_dcache(p);
 	/*
 	 * do not remove from the list until nobody holds it; walking the
 	 * list in do_sysctl() relies on that.
@@ -483,7 +450,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 	}
 	ei->sysctl = head;
 	ei->sysctl_entry = table;
-	hlist_add_head_rcu(&ei->sysctl_inodes, &head->inodes);
+	hlist_add_head_rcu(&ei->sibling_inodes, &head->inodes);
 	head->count++;
 	spin_unlock(&sysctl_lock);
 
@@ -514,7 +481,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head)
 {
 	spin_lock(&sysctl_lock);
-	hlist_del_init_rcu(&PROC_I(inode)->sysctl_inodes);
+	hlist_del_init_rcu(&PROC_I(inode)->sibling_inodes);
 	if (!--head->count)
 		kfree_rcu(head, rcu);
 	spin_unlock(&sysctl_lock);

fs/proc/root.c

@@ -292,39 +292,3 @@ struct proc_dir_entry proc_root = {
 	.subdir		= RB_ROOT,
 	.name		= "/proc",
 };
-
-int pid_ns_prepare_proc(struct pid_namespace *ns)
-{
-	struct proc_fs_context *ctx;
-	struct fs_context *fc;
-	struct vfsmount *mnt;
-
-	fc = fs_context_for_mount(&proc_fs_type, SB_KERNMOUNT);
-	if (IS_ERR(fc))
-		return PTR_ERR(fc);
-
-	if (fc->user_ns != ns->user_ns) {
-		put_user_ns(fc->user_ns);
-		fc->user_ns = get_user_ns(ns->user_ns);
-	}
-
-	ctx = fc->fs_private;
-	if (ctx->pid_ns != ns) {
-		put_pid_ns(ctx->pid_ns);
-		get_pid_ns(ns);
-		ctx->pid_ns = ns;
-	}
-
-	mnt = fc_mount(fc);
-	put_fs_context(fc);
-	if (IS_ERR(mnt))
-		return PTR_ERR(mnt);
-
-	ns->proc_mnt = mnt;
-	return 0;
-}
-
-void pid_ns_release_proc(struct pid_namespace *ns)
-{
-	kern_unmount(ns->proc_mnt);
-}

include/linux/binfmts.h

@@ -44,7 +44,13 @@ struct linux_binprm {
 		 * exec has happened. Used to sanitize execution environment
 		 * and to set AT_SECURE auxv for glibc.
 		 */
-		secureexec:1;
+		secureexec:1,
+		/*
+		 * Set by flush_old_exec, when exec_mmap has been called.
+		 * This is past the point of no return, when the
+		 * exec_update_mutex has been taken.
+		 */
+		called_exec_mmap:1;
 #ifdef __alpha__
 	unsigned int taso:1;
 #endif

include/linux/pid.h

@@ -62,6 +62,7 @@ struct pid
 	unsigned int level;
 	/* lists of tasks that use this pid */
 	struct hlist_head tasks[PIDTYPE_MAX];
+	struct hlist_head inodes;
 	/* wait queue for pidfd notifications */
 	wait_queue_head_t wait_pidfd;
 	struct rcu_head rcu;

include/linux/pid_namespace.h

@@ -33,7 +33,6 @@ struct pid_namespace {
 	unsigned int level;
 	struct pid_namespace *parent;
 #ifdef CONFIG_PROC_FS
-	struct vfsmount *proc_mnt;
 	struct dentry *proc_self;
 	struct dentry *proc_thread_self;
 #endif
@@ -42,7 +41,6 @@ struct pid_namespace {
 #endif
 	struct user_namespace *user_ns;
 	struct ucounts *ucounts;
-	struct work_struct proc_work;
 	kgid_t pid_gid;
 	int hide_pid;
 	int reboot;	/* group exit code if this pidns was rebooted */

include/linux/proc_fs.h

@@ -32,7 +32,7 @@ struct proc_ops {
 typedef int (*proc_write_t)(struct file *, char *, size_t);
 
 extern void proc_root_init(void);
-extern void proc_flush_task(struct task_struct *);
+extern void proc_flush_pid(struct pid *);
 
 extern struct proc_dir_entry *proc_symlink(const char *,
 		struct proc_dir_entry *, const char *);
@@ -105,7 +105,7 @@ static inline void proc_root_init(void)
 {
 }
 
-static inline void proc_flush_task(struct task_struct *task)
+static inline void proc_flush_pid(struct pid *pid)
 {
 }
 

include/linux/proc_ns.h

@@ -50,16 +50,11 @@ enum {
 
 #ifdef CONFIG_PROC_FS
 
-extern int pid_ns_prepare_proc(struct pid_namespace *ns);
-extern void pid_ns_release_proc(struct pid_namespace *ns);
 extern int proc_alloc_inum(unsigned int *pino);
 extern void proc_free_inum(unsigned int inum);
 
 #else /* CONFIG_PROC_FS */
 
-static inline int pid_ns_prepare_proc(struct pid_namespace *ns) { return 0; }
-static inline void pid_ns_release_proc(struct pid_namespace *ns) {}
-
 static inline int proc_alloc_inum(unsigned int *inum)
 {
 	*inum = 1;

include/linux/sched.h

@@ -945,8 +945,8 @@ struct task_struct {
 	struct seccomp			seccomp;
 
 	/* Thread group tracking: */
-	u32				parent_exec_id;
-	u32				self_exec_id;
+	u64				parent_exec_id;
+	u64				self_exec_id;
 
 	/* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */
 	spinlock_t			alloc_lock;

include/linux/sched/signal.h

@@ -224,7 +224,14 @@ struct signal_struct {
 
 	struct mutex cred_guard_mutex;	/* guard against foreign influences on
 					 * credential calculations
-					 * (notably. ptrace) */
+					 * (notably. ptrace)
+					 * Deprecated do not use in new code.
+					 * Use exec_update_mutex instead.
+					 */
+	struct mutex exec_update_mutex;	/* Held while task_struct is being
+					 * updated during exec, and may have
+					 * inconsistent permissions.
+					 */
 } __randomize_layout;
 
 /*

init/init_task.c

@@ -26,6 +26,7 @@ static struct signal_struct init_signals = {
 	.multiprocess	= HLIST_HEAD_INIT,
 	.rlim		= INIT_RLIMITS,
 	.cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex),
+	.exec_update_mutex = __MUTEX_INITIALIZER(init_signals.exec_update_mutex),
 #ifdef CONFIG_POSIX_TIMERS
 	.posix_timers = LIST_HEAD_INIT(init_signals.posix_timers),
 	.cputimer	= {

kernel/cred.c

@@ -675,8 +675,6 @@ void __init cred_init(void)
  * The caller may change these controls afterwards if desired.
  *
  * Returns the new credentials or NULL if out of memory.
- *
- * Does not take, and does not return holding current->cred_replace_mutex.
  */
 struct cred *prepare_kernel_cred(struct task_struct *daemon)
 {

kernel/events/core.c

@@ -1295,7 +1295,7 @@ static void put_ctx(struct perf_event_context *ctx)
  * function.
  *
  * Lock order:
- *    cred_guard_mutex
+ *    exec_update_mutex
  *	task_struct::perf_event_mutex
  *	  perf_event_context::mutex
  *	    perf_event::child_mutex;
@@ -11425,14 +11425,14 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	if (task) {
-		err = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
+		err = mutex_lock_interruptible(&task->signal->exec_update_mutex);
 		if (err)
 			goto err_task;
 
 		/*
 		 * Reuse ptrace permission checks for now.
 		 *
-		 * We must hold cred_guard_mutex across this and any potential
+		 * We must hold exec_update_mutex across this and any potential
 		 * perf_install_in_context() call for this new event to
 		 * serialize against exec() altering our credentials (and the
 		 * perf_event_exit_task() that could imply).
@@ -11721,7 +11721,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	mutex_unlock(&ctx->mutex);
 
 	if (task) {
-		mutex_unlock(&task->signal->cred_guard_mutex);
+		mutex_unlock(&task->signal->exec_update_mutex);
 		put_task_struct(task);
 	}
 
@@ -11757,7 +11757,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		free_event(event);
 err_cred:
 	if (task)
-		mutex_unlock(&task->signal->cred_guard_mutex);
+		mutex_unlock(&task->signal->exec_update_mutex);
 err_task:
 	if (task)
 		put_task_struct(task);
@@ -12062,7 +12062,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 /*
  * When a child task exits, feed back event values to parent events.
  *
- * Can be called with cred_guard_mutex held when called from
+ * Can be called with exec_update_mutex held when called from
  * install_exec_creds().
  */
 void perf_event_exit_task(struct task_struct *child)

kernel/exit.c

@@ -182,6 +182,7 @@ void put_task_struct_rcu_user(struct task_struct *task)
 void release_task(struct task_struct *p)
 {
 	struct task_struct *leader;
+	struct pid *thread_pid;
 	int zap_leader;
 repeat:
 	/* don't need to get the RCU readlock here - the process is dead and
@@ -190,11 +191,11 @@ void release_task(struct task_struct *p)
 	atomic_dec(&__task_cred(p)->user->processes);
 	rcu_read_unlock();
 
-	proc_flush_task(p);
 	cgroup_release(p);
 
 	write_lock_irq(&tasklist_lock);
 	ptrace_release_task(p);
+	thread_pid = get_pid(p->thread_pid);
 	__exit_signal(p);
 
 	/*
@@ -217,6 +218,7 @@ void release_task(struct task_struct *p)
 	}
 
 	write_unlock_irq(&tasklist_lock);
+	proc_flush_pid(thread_pid);
 	release_thread(p);
 	put_task_struct_rcu_user(p);
 

kernel/fork.c

@@ -1224,7 +1224,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 	struct mm_struct *mm;
 	int err;
 
-	err =  mutex_lock_killable(&task->signal->cred_guard_mutex);
+	err =  mutex_lock_killable(&task->signal->exec_update_mutex);
 	if (err)
 		return ERR_PTR(err);
 
@@ -1234,7 +1234,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 		mmput(mm);
 		mm = ERR_PTR(-EACCES);
 	}
-	mutex_unlock(&task->signal->cred_guard_mutex);
+	mutex_unlock(&task->signal->exec_update_mutex);
 
 	return mm;
 }
@@ -1594,6 +1594,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
 
 	mutex_init(&sig->cred_guard_mutex);
+	mutex_init(&sig->exec_update_mutex);
 
 	return 0;
 }

kernel/kcmp.c

@@ -173,8 +173,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
 	/*
 	 * One should have enough rights to inspect task details.
 	 */
-	ret = kcmp_lock(&task1->signal->cred_guard_mutex,
-			&task2->signal->cred_guard_mutex);
+	ret = kcmp_lock(&task1->signal->exec_update_mutex,
+			&task2->signal->exec_update_mutex);
 	if (ret)
 		goto err;
 	if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) ||
@@ -229,8 +229,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
 	}
 
 err_unlock:
-	kcmp_unlock(&task1->signal->cred_guard_mutex,
-		    &task2->signal->cred_guard_mutex);
+	kcmp_unlock(&task1->signal->exec_update_mutex,
+		    &task2->signal->exec_update_mutex);
 err:
 	put_task_struct(task1);
 	put_task_struct(task2);

kernel/pid.c

@@ -144,9 +144,6 @@ void free_pid(struct pid *pid)
 			/* Handle a fork failure of the first process */
 			WARN_ON(ns->child_reaper);
 			ns->pid_allocated = 0;
-			/* fall through */
-		case 0:
-			schedule_work(&ns->proc_work);
 			break;
 		}
 
@@ -257,17 +254,13 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 	 */
 	retval = -ENOMEM;
 
-	if (unlikely(is_child_reaper(pid))) {
-		if (pid_ns_prepare_proc(ns))
-			goto out_free;
-	}
-
 	get_pid_ns(ns);
 	refcount_set(&pid->count, 1);
 	for (type = 0; type < PIDTYPE_MAX; ++type)
 		INIT_HLIST_HEAD(&pid->tasks[type]);
 
 	init_waitqueue_head(&pid->wait_pidfd);
+	INIT_HLIST_HEAD(&pid->inodes);
 
 	upid = pid->numbers + ns->level;
 	spin_lock_irq(&pidmap_lock);
@@ -594,7 +587,7 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd)
 	struct file *file;
 	int ret;
 
-	ret = mutex_lock_killable(&task->signal->cred_guard_mutex);
+	ret = mutex_lock_killable(&task->signal->exec_update_mutex);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -603,7 +596,7 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd)
 	else
 		file = ERR_PTR(-EPERM);
 
-	mutex_unlock(&task->signal->cred_guard_mutex);
+	mutex_unlock(&task->signal->exec_update_mutex);
 
 	return file ?: ERR_PTR(-EBADF);
 }

kernel/pid_namespace.c

@@ -57,12 +57,6 @@ static struct kmem_cache *create_pid_cachep(unsigned int level)
 	return READ_ONCE(*pkc);
 }
 
-static void proc_cleanup_work(struct work_struct *work)
-{
-	struct pid_namespace *ns = container_of(work, struct pid_namespace, proc_work);
-	pid_ns_release_proc(ns);
-}
-
 static struct ucounts *inc_pid_namespaces(struct user_namespace *ns)
 {
 	return inc_ucount(ns, current_euid(), UCOUNT_PID_NAMESPACES);
@@ -114,7 +108,6 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 	ns->user_ns = get_user_ns(user_ns);
 	ns->ucounts = ucounts;
 	ns->pid_allocated = PIDNS_ADDING;
-	INIT_WORK(&ns->proc_work, proc_cleanup_work);
 
 	return ns;
 
@@ -231,20 +224,27 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	} while (rc != -ECHILD);
 
 	/*
-	 * kernel_wait4() above can't reap the EXIT_DEAD children but we do not
-	 * really care, we could reparent them to the global init. We could
-	 * exit and reap ->child_reaper even if it is not the last thread in
-	 * this pid_ns, free_pid(pid_allocated == 0) calls proc_cleanup_work(),
-	 * pid_ns can not go away until proc_kill_sb() drops the reference.
+	 * kernel_wait4() misses EXIT_DEAD children, and EXIT_ZOMBIE
+	 * process whose parents processes are outside of the pid
+	 * namespace.  Such processes are created with setns()+fork().
+	 *
+	 * If those EXIT_ZOMBIE processes are not reaped by their
+	 * parents before their parents exit, they will be reparented
+	 * to pid_ns->child_reaper.  Thus pidns->child_reaper needs to
+	 * stay valid until they all go away.
+	 *
+	 * The code relies on the the pid_ns->child_reaper ignoring
+	 * SIGCHILD to cause those EXIT_ZOMBIE processes to be
+	 * autoreaped if reparented.
 	 *
-	 * But this ns can also have other tasks injected by setns()+fork().
-	 * Again, ignoring the user visible semantics we do not really need
-	 * to wait until they are all reaped, but they can be reparented to
-	 * us and thus we need to ensure that pid->child_reaper stays valid
-	 * until they all go away. See free_pid()->wake_up_process().
+	 * Semantically it is also desirable to wait for EXIT_ZOMBIE
+	 * processes before allowing the child_reaper to be reaped, as
+	 * that gives the invariant that when the init process of a
+	 * pid namespace is reaped all of the processes in the pid
+	 * namespace are gone.
 	 *
-	 * We rely on ignored SIGCHLD, an injected zombie must be autoreaped
-	 * if reparented.
+	 * Once all of the other tasks are gone from the pid_namespace
+	 * free_pid() will awaken this task.
 	 */
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);

kernel/signal.c

@@ -1931,7 +1931,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 		 * This is only possible if parent == real_parent.
 		 * Check if it has changed security domain.
 		 */
-		if (tsk->parent_exec_id != tsk->parent->self_exec_id)
+		if (tsk->parent_exec_id != READ_ONCE(tsk->parent->self_exec_id))
 			sig = SIGCHLD;
 	}
 

mm/process_vm_access.c

@@ -206,7 +206,7 @@ static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter,
 	if (!mm || IS_ERR(mm)) {
 		rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
 		/*
-		 * Explicitly map EACCES to EPERM as EPERM is a more a
+		 * Explicitly map EACCES to EPERM as EPERM is a more
 		 * appropriate error code for process_vw_readv/writev
 		 */
 		if (rc == -EACCES)

tools/testing/selftests/ptrace/Makefile

 # SPDX-License-Identifier: GPL-2.0-only
-CFLAGS += -iquote../../../../include/uapi -Wall
+CFLAGS += -std=c99 -pthread -iquote../../../../include/uapi -Wall
 
-TEST_GEN_PROGS := get_syscall_info peeksiginfo
+TEST_GEN_PROGS := get_syscall_info peeksiginfo vmaccess
 
 include ../lib.mk

tools/testing/selftests/ptrace/vmaccess.c

+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (c) 2020 Bernd Edlinger <bernd.edlinger@hotmail.de>
+ * All rights reserved.
+ *
+ * Check whether /proc/$pid/mem can be accessed without causing deadlocks
+ * when de_thread is blocked with ->cred_guard_mutex held.
+ */
+
+#include "../kselftest_harness.h"
+#include <stdio.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <signal.h>
+#include <unistd.h>
+#include <sys/ptrace.h>
+
+static void *thread(void *arg)
+{
+	ptrace(PTRACE_TRACEME, 0, 0L, 0L);
+	return NULL;
+}
+
+TEST(vmaccess)
+{
+	int f, pid = fork();
+	char mm[64];
+
+	if (!pid) {
+		pthread_t pt;
+
+		pthread_create(&pt, NULL, thread, NULL);
+		pthread_join(pt, NULL);
+		execlp("true", "true", NULL);
+	}
+
+	sleep(1);
+	sprintf(mm, "/proc/%d/mem", pid);
+	f = open(mm, O_RDONLY);
+	ASSERT_GE(f, 0);
+	close(f);
+	f = kill(pid, SIGCONT);
+	ASSERT_EQ(f, 0);
+}
+
+TEST(attach)
+{
+	int s, k, pid = fork();
+
+	if (!pid) {
+		pthread_t pt;
+
+		pthread_create(&pt, NULL, thread, NULL);
+		pthread_join(pt, NULL);
+		execlp("sleep", "sleep", "2", NULL);
+	}
+
+	sleep(1);
+	k = ptrace(PTRACE_ATTACH, pid, 0L, 0L);
+	ASSERT_EQ(errno, EAGAIN);
+	ASSERT_EQ(k, -1);
+	k = waitpid(-1, &s, WNOHANG);
+	ASSERT_NE(k, -1);
+	ASSERT_NE(k, 0);
+	ASSERT_NE(k, pid);
+	ASSERT_EQ(WIFEXITED(s), 1);
+	ASSERT_EQ(WEXITSTATUS(s), 0);
+	sleep(1);
+	k = ptrace(PTRACE_ATTACH, pid, 0L, 0L);
+	ASSERT_EQ(k, 0);
+	k = waitpid(-1, &s, 0);
+	ASSERT_EQ(k, pid);
+	ASSERT_EQ(WIFSTOPPED(s), 1);
+	ASSERT_EQ(WSTOPSIG(s), SIGSTOP);
+	k = ptrace(PTRACE_DETACH, pid, 0L, 0L);
+	ASSERT_EQ(k, 0);
+	k = waitpid(-1, &s, 0);
+	ASSERT_EQ(k, pid);
+	ASSERT_EQ(WIFEXITED(s), 1);
+	ASSERT_EQ(WEXITSTATUS(s), 0);
+	k = waitpid(-1, NULL, 0);
+	ASSERT_EQ(k, -1);
+	ASSERT_EQ(errno, ECHILD);
+}
+
+TEST_HARNESS_MAIN