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  kernel: doc: remove outdated comment cred.c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
  ...

5 files changed, 118 insertions, 161 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index c7c64272b0fa..74f948a6b621 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -405,11 +405,11 @@ print0:
 
 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,
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 6da18316d209..1e730ea1dcd6 100644
--- a/fs/proc/inode.c
+++ b/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;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 41587276798e..9e294f0290e5 100644
--- a/fs/proc/internal.h
+++ b/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 *);
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index c75bb4632ed1..b6f5d459b087 100644
--- a/fs/proc/proc_sysctl.c
+++ b/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);
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 608233dfd29c..2633f10446c3 100644
--- a/fs/proc/root.c
+++ b/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);
-}