Merge branch 'signal-for-v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull signal/exit/ptrace updates from Eric Biederman:
 "This set of changes deletes some dead code, makes a lot of cleanups
  which hopefully make the code easier to follow, and fixes bugs found
  along the way.

  The end-game which I have not yet reached yet is for fatal signals
  that generate coredumps to be short-circuit deliverable from
  complete_signal, for force_siginfo_to_task not to require changing
  userspace configured signal delivery state, and for the ptrace stops
  to always happen in locations where we can guarantee on all
  architectures that the all of the registers are saved and available on
  the stack.

  Removal of profile_task_ext, profile_munmap, and profile_handoff_task
  are the big successes for dead code removal this round.

  A bunch of small bug fixes are included, as most of the issues
  reported were small enough that they would not affect bisection so I
  simply added the fixes and did not fold the fixes into the changes
  they were fixing.

  There was a bug that broke coredumps piped to systemd-coredump. I
  dropped the change that caused that bug and replaced it entirely with
  something much more restrained. Unfortunately that required some
  rebasing.

  Some successes after this set of changes: There are few enough calls
  to do_exit to audit in a reasonable amount of time. The lifetime of
  struct kthread now matches the lifetime of struct task, and the
  pointer to struct kthread is no longer stored in set_child_tid. The
  flag SIGNAL_GROUP_COREDUMP is removed. The field group_exit_task is
  removed. Issues where task->exit_code was examined with
  signal->group_exit_code should been examined were fixed.

  There are several loosely related changes included because I am
  cleaning up and if I don't include them they will probably get lost.

  The original postings of these changes can be found at:
     https://lkml.kernel.org/r/87a6ha4zsd.fsf@email.froward.int.ebiederm.org
     https://lkml.kernel.org/r/87bl1kunjj.fsf@email.froward.int.ebiederm.org
     https://lkml.kernel.org/r/87r19opkx1.fsf_-_@email.froward.int.ebiederm.org

  I trimmed back the last set of changes to only the obviously correct
  once. Simply because there was less time for review than I had hoped"

* 'signal-for-v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (44 commits)
  ptrace/m68k: Stop open coding ptrace_report_syscall
  ptrace: Remove unused regs argument from ptrace_report_syscall
  ptrace: Remove second setting of PT_SEIZED in ptrace_attach
  taskstats: Cleanup the use of task->exit_code
  exit: Use the correct exit_code in /proc/<pid>/stat
  exit: Fix the exit_code for wait_task_zombie
  exit: Coredumps reach do_group_exit
  exit: Remove profile_handoff_task
  exit: Remove profile_task_exit & profile_munmap
  signal: clean up kernel-doc comments
  signal: Remove the helper signal_group_exit
  signal: Rename group_exit_task group_exec_task
  coredump: Stop setting signal->group_exit_task
  signal: Remove SIGNAL_GROUP_COREDUMP
  signal: During coredumps set SIGNAL_GROUP_EXIT in zap_process
  signal: Make coredump handling explicit in complete_signal
  signal: Have prepare_signal detect coredumps using signal->core_state
  signal: Have the oom killer detect coredumps using signal->core_state
  exit: Move force_uaccess back into do_exit
  exit: Guarantee make_task_dead leaks the tsk when calling do_task_exit
  ...

12 files changed, 32 insertions, 27 deletions

diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 1060164b984a..68ed29cff7e8 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1139,7 +1139,7 @@ next_pdu:
 	}
 
 	memalloc_noreclaim_restore(noreclaim_flag);
-	module_put_and_exit(0);
+	module_put_and_kthread_exit(0);
 }
 
 /*
diff --git a/fs/coredump.c b/fs/coredump.c
index a6b3c196cdef..7dece20b162b 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -347,13 +347,13 @@ out:
 	return ispipe;
 }
 
-static int zap_process(struct task_struct *start, int exit_code, int flags)
+static int zap_process(struct task_struct *start, int exit_code)
 {
 	struct task_struct *t;
 	int nr = 0;
 
 	/* ignore all signals except SIGKILL, see prepare_signal() */
-	start->signal->flags = SIGNAL_GROUP_COREDUMP | flags;
+	start->signal->flags = SIGNAL_GROUP_EXIT;
 	start->signal->group_exit_code = exit_code;
 	start->signal->group_stop_count = 0;
 
@@ -372,13 +372,13 @@ static int zap_process(struct task_struct *start, int exit_code, int flags)
 static int zap_threads(struct task_struct *tsk,
 			struct core_state *core_state, int exit_code)
 {
+	struct signal_struct *signal = tsk->signal;
 	int nr = -EAGAIN;
 
 	spin_lock_irq(&tsk->sighand->siglock);
-	if (!signal_group_exit(tsk->signal)) {
-		tsk->signal->core_state = core_state;
-		tsk->signal->group_exit_task = tsk;
-		nr = zap_process(tsk, exit_code, 0);
+	if (!(signal->flags & SIGNAL_GROUP_EXIT) && !signal->group_exec_task) {
+		signal->core_state = core_state;
+		nr = zap_process(tsk, exit_code);
 		clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
 		tsk->flags |= PF_DUMPCORE;
 		atomic_set(&core_state->nr_threads, nr);
@@ -426,8 +426,6 @@ static void coredump_finish(bool core_dumped)
 	spin_lock_irq(&current->sighand->siglock);
 	if (core_dumped && !__fatal_signal_pending(current))
 		current->signal->group_exit_code |= 0x80;
-	current->signal->group_exit_task = NULL;
-	current->signal->flags = SIGNAL_GROUP_EXIT;
 	next = current->signal->core_state->dumper.next;
 	current->signal->core_state = NULL;
 	spin_unlock_irq(&current->sighand->siglock);
diff --git a/fs/exec.c b/fs/exec.c
index 537d92c41105..82db656ca709 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1045,7 +1045,7 @@ static int de_thread(struct task_struct *tsk)
 	 * Kill all other threads in the thread group.
 	 */
 	spin_lock_irq(lock);
-	if (signal_group_exit(sig)) {
+	if ((sig->flags & SIGNAL_GROUP_EXIT) || sig->group_exec_task) {
 		/*
 		 * Another group action in progress, just
 		 * return so that the signal is processed.
@@ -1054,7 +1054,7 @@ static int de_thread(struct task_struct *tsk)
 		return -EAGAIN;
 	}
 
-	sig->group_exit_task = tsk;
+	sig->group_exec_task = tsk;
 	sig->notify_count = zap_other_threads(tsk);
 	if (!thread_group_leader(tsk))
 		sig->notify_count--;
@@ -1082,7 +1082,7 @@ static int de_thread(struct task_struct *tsk)
 			write_lock_irq(&tasklist_lock);
 			/*
 			 * Do this under tasklist_lock to ensure that
-			 * exit_notify() can't miss ->group_exit_task
+			 * exit_notify() can't miss ->group_exec_task
 			 */
 			sig->notify_count = -1;
 			if (likely(leader->exit_state))
@@ -1149,7 +1149,7 @@ static int de_thread(struct task_struct *tsk)
 		release_task(leader);
 	}
 
-	sig->group_exit_task = NULL;
+	sig->group_exec_task = NULL;
 	sig->notify_count = 0;
 
 no_thread_group:
@@ -1162,7 +1162,7 @@ no_thread_group:
 killed:
 	/* protects against exit_notify() and __exit_signal() */
 	read_lock(&tasklist_lock);
-	sig->group_exit_task = NULL;
+	sig->group_exec_task = NULL;
 	sig->notify_count = 0;
 	read_unlock(&tasklist_lock);
 	return -EAGAIN;
@@ -1307,6 +1307,8 @@ int begin_new_exec(struct linux_binprm * bprm)
 	 */
 	force_uaccess_begin();
 
+	if (me->flags & PF_KTHREAD)
+		free_kthread_struct(me);
 	me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD |
 					PF_NOFREEZE | PF_NO_SETAFFINITY);
 	flush_thread();
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 5c4f582d6549..a7763127f884 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -670,7 +670,7 @@ loop:
  */
 void io_wq_worker_running(struct task_struct *tsk)
 {
-	struct io_worker *worker = tsk->pf_io_worker;
+	struct io_worker *worker = tsk->worker_private;
 
 	if (!worker)
 		return;
@@ -688,7 +688,7 @@ void io_wq_worker_running(struct task_struct *tsk)
  */
 void io_wq_worker_sleeping(struct task_struct *tsk)
 {
-	struct io_worker *worker = tsk->pf_io_worker;
+	struct io_worker *worker = tsk->worker_private;
 
 	if (!worker)
 		return;
@@ -707,7 +707,7 @@ void io_wq_worker_sleeping(struct task_struct *tsk)
 static void io_init_new_worker(struct io_wqe *wqe, struct io_worker *worker,
 			       struct task_struct *tsk)
 {
-	tsk->pf_io_worker = worker;
+	tsk->worker_private = worker;
 	worker->task = tsk;
 	set_cpus_allowed_ptr(tsk, wqe->cpu_mask);
 	tsk->flags |= PF_NO_SETAFFINITY;
diff --git a/fs/io-wq.h b/fs/io-wq.h
index 3709b7c5ec98..dbecd27656c7 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -222,6 +222,6 @@ static inline void io_wq_worker_running(struct task_struct *tsk)
 static inline bool io_wq_current_is_worker(void)
 {
 	return in_task() && (current->flags & PF_IO_WORKER) &&
-		current->pf_io_worker;
+		current->worker_private;
 }
 #endif
diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c
index 2b4d5013dc5d..6da92ecaf66d 100644
--- a/fs/jffs2/background.c
+++ b/fs/jffs2/background.c
@@ -161,5 +161,5 @@ static int jffs2_garbage_collect_thread(void *_c)
 	spin_lock(&c->erase_completion_lock);
 	c->gc_task = NULL;
 	spin_unlock(&c->erase_completion_lock);
-	complete_and_exit(&c->gc_thread_exit, 0);
+	kthread_complete_and_exit(&c->gc_thread_exit, 0);
 }
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 4defefd89cbf..0475c5a5d061 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -185,7 +185,7 @@ lockd(void *vrqstp)
 
 	svc_exit_thread(rqstp);
 
-	module_put_and_exit(0);
+	module_put_and_kthread_exit(0);
 }
 
 static int create_lockd_listener(struct svc_serv *serv, const char *name,
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index c4994c1d4e36..054cc1255fac 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -93,7 +93,7 @@ nfs4_callback_svc(void *vrqstp)
 		svc_process(rqstp);
 	}
 	svc_exit_thread(rqstp);
-	module_put_and_exit(0);
+	module_put_and_kthread_exit(0);
 	return 0;
 }
 
@@ -137,7 +137,7 @@ nfs41_callback_svc(void *vrqstp)
 		}
 	}
 	svc_exit_thread(rqstp);
-	module_put_and_exit(0);
+	module_put_and_kthread_exit(0);
 	return 0;
 }
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index f63dfa01001c..d88b779f9dd0 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2693,6 +2693,6 @@ static int nfs4_run_state_manager(void *ptr)
 	allow_signal(SIGKILL);
 	nfs4_state_manager(clp);
 	nfs_put_client(clp);
-	module_put_and_exit(0);
+	module_put_and_kthread_exit(0);
 	return 0;
 }
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 07193595b8e0..b8c682b62d29 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -1020,7 +1020,7 @@ out:
 	}
 
 	/* Release module */
-	module_put_and_exit(0);
+	module_put_and_kthread_exit(0);
 	return 0;
 }
 
diff --git a/fs/proc/array.c b/fs/proc/array.c
index ff869a66b34e..43a7abde9e42 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -468,6 +468,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	u64 cgtime, gtime;
 	unsigned long rsslim = 0;
 	unsigned long flags;
+	int exit_code = task->exit_code;
 
 	state = *get_task_state(task);
 	vsize = eip = esp = 0;
@@ -531,6 +532,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 			maj_flt += sig->maj_flt;
 			thread_group_cputime_adjusted(task, &utime, &stime);
 			gtime += sig->gtime;
+
+			if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED))
+				exit_code = sig->group_exit_code;
 		}
 
 		sid = task_session_nr_ns(task, ns);
@@ -630,7 +634,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 		seq_puts(m, " 0 0 0 0 0 0 0");
 
 	if (permitted)
-		seq_put_decimal_ll(m, " ", task->exit_code);
+		seq_put_decimal_ll(m, " ", exit_code);
 	else
 		seq_puts(m, " 0");
 
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 65ce0e72e7b9..e20d1484c663 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -155,11 +155,12 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info,
 				int nonblock)
 {
+	enum pid_type type;
 	ssize_t ret;
 	DECLARE_WAITQUEUE(wait, current);
 
 	spin_lock_irq(&current->sighand->siglock);
-	ret = dequeue_signal(current, &ctx->sigmask, info);
+	ret = dequeue_signal(current, &ctx->sigmask, info, &type);
 	switch (ret) {
 	case 0:
 		if (!nonblock)
@@ -174,7 +175,7 @@ static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info
 	add_wait_queue(&current->sighand->signalfd_wqh, &wait);
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
-		ret = dequeue_signal(current, &ctx->sigmask, info);
+		ret = dequeue_signal(current, &ctx->sigmask, info, &type);
 		if (ret != 0)
 			break;
 		if (signal_pending(current)) {