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  kernel: doc: remove outdated comment cred.c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

7 files changed, 20 insertions, 13 deletions

diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index b40fc633f3be..a345d9fed3d8 100644
--- a/include/linux/binfmts.h
+++ b/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
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 998ae7d24450..01a0d4e28506 100644
--- a/include/linux/pid.h
+++ b/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;
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 2ed6af88794b..4956e362e55e 100644
--- a/include/linux/pid_namespace.h
+++ b/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 */
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 3dfa92633af3..40a7982b7285 100644
--- a/include/linux/proc_fs.h
+++ b/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)
 {
 }
 
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index adff08bfecf9..6abe85c34681 100644
--- a/include/linux/proc_ns.h
+++ b/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;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5d0d2fc018e9..4418f5cb8324 100644
--- a/include/linux/sched.h
+++ b/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;
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 88050259c466..a29df79540ce 100644
--- a/include/linux/sched/signal.h
+++ b/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;
 
 /*