per signal_struct coredumps

Current coredumps are mixed up with the exit code, the signal handling
code and with the ptrace code in was they are much more complicated than
necessary and difficult to follow.

This series of changes starts with ptrace_stop and cleans it up,
making it easier to follow what is happening in ptrace_stop.
Then cleans up the exec interactions with coredumps.
Then cleans up the coredump interactions with exit.
Then the coredump interactions with the signal handling code is clean
up.

The first and last changes are bug fixes for minor bugs.

I believe the fact that vfork followed by execve can kill the process
the called vfork if exec fails is sufficient justification to change
the userspace visible behavior.

In previous conversations it was suggested that some of these cleanups
did not stand on their own.  I think I have managed to organize things
so all of their patches stand on their own.

Which means that if for some reason the last change needs to be reverted
we can still keep the gains from the other changes.

Eric W. Biederman (6):
      signal: Remove the bogus sigkill_pending in ptrace_stop
      ptrace: Remove the unnecessary arguments from arch_ptrace_stop
      exec: Check for a pending fatal signal instead of core_state
      exit: Factor coredump_exit_mm out of exit_mm
      coredump:  Don't perform any cleanups before dumping core
      coredump: Limit coredumps to a single thread group

 arch/ia64/include/asm/ptrace.h  |  4 +-
 arch/sparc/include/asm/ptrace.h |  8 ++--
 fs/binfmt_elf.c                 |  4 +-
 fs/binfmt_elf_fdpic.c           |  2 +-
 fs/coredump.c                   | 88 ++++++-----------------------------------
 fs/exec.c                       | 14 +++----
 fs/proc/array.c                 |  6 +--
 include/linux/mm_types.h        | 13 ------
 include/linux/ptrace.h          | 22 +++++------
 include/linux/sched.h           |  1 +
 include/linux/sched/signal.h    | 13 ++++++
 kernel/exit.c                   | 76 +++++++++++++++++++----------------
 kernel/fork.c                   |  4 +-
 kernel/signal.c                 | 49 ++++-------------------
 mm/debug.c                      |  4 +-
 mm/oom_kill.c                   |  6 +--
 16 files changed, 106 insertions(+), 208 deletions(-)

Link: https://lkml.kernel.org/r/87v92qx2c6.fsf@disp2133
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

3 files changed, 49 insertions, 80 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 91a43e57a32e..2b355e926c13 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -339,6 +339,46 @@ kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
 	}
 }
 
+static void coredump_task_exit(struct task_struct *tsk)
+{
+	struct core_state *core_state;
+
+	/*
+	 * Serialize with any possible pending coredump.
+	 * We must hold siglock around checking core_state
+	 * and setting PF_POSTCOREDUMP.  The core-inducing thread
+	 * will increment ->nr_threads for each thread in the
+	 * group without PF_POSTCOREDUMP set.
+	 */
+	spin_lock_irq(&tsk->sighand->siglock);
+	tsk->flags |= PF_POSTCOREDUMP;
+	core_state = tsk->signal->core_state;
+	spin_unlock_irq(&tsk->sighand->siglock);
+	if (core_state) {
+		struct core_thread self;
+
+		self.task = current;
+		if (self.task->flags & PF_SIGNALED)
+			self.next = xchg(&core_state->dumper.next, &self);
+		else
+			self.task = NULL;
+		/*
+		 * Implies mb(), the result of xchg() must be visible
+		 * to core_state->dumper.
+		 */
+		if (atomic_dec_and_test(&core_state->nr_threads))
+			complete(&core_state->startup);
+
+		for (;;) {
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			if (!self.task) /* see coredump_finish() */
+				break;
+			freezable_schedule();
+		}
+		__set_current_state(TASK_RUNNING);
+	}
+}
+
 #ifdef CONFIG_MEMCG
 /*
  * A task is exiting.   If it owned this mm, find a new owner for the mm.
@@ -434,47 +474,12 @@ assign_new_owner:
 static void exit_mm(void)
 {
 	struct mm_struct *mm = current->mm;
-	struct core_state *core_state;
 
 	exit_mm_release(current, mm);
 	if (!mm)
 		return;
 	sync_mm_rss(mm);
-	/*
-	 * Serialize with any possible pending coredump.
-	 * We must hold mmap_lock around checking core_state
-	 * and clearing tsk->mm.  The core-inducing thread
-	 * will increment ->nr_threads for each thread in the
-	 * group with ->mm != NULL.
-	 */
 	mmap_read_lock(mm);
-	core_state = mm->core_state;
-	if (core_state) {
-		struct core_thread self;
-
-		mmap_read_unlock(mm);
-
-		self.task = current;
-		if (self.task->flags & PF_SIGNALED)
-			self.next = xchg(&core_state->dumper.next, &self);
-		else
-			self.task = NULL;
-		/*
-		 * Implies mb(), the result of xchg() must be visible
-		 * to core_state->dumper.
-		 */
-		if (atomic_dec_and_test(&core_state->nr_threads))
-			complete(&core_state->startup);
-
-		for (;;) {
-			set_current_state(TASK_UNINTERRUPTIBLE);
-			if (!self.task) /* see coredump_finish() */
-				break;
-			freezable_schedule();
-		}
-		__set_current_state(TASK_RUNNING);
-		mmap_read_lock(mm);
-	}
 	mmgrab(mm);
 	BUG_ON(mm != current->active_mm);
 	/* more a memory barrier than a real lock */
@@ -762,6 +767,7 @@ void __noreturn do_exit(long code)
 	profile_task_exit(tsk);
 	kcov_task_exit(tsk);
 
+	coredump_task_exit(tsk);
 	ptrace_event(PTRACE_EVENT_EXIT, code);
 
 	validate_creds_for_do_exit(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index 38681ad44c76..c8adb76982f7 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1044,7 +1044,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	seqcount_init(&mm->write_protect_seq);
 	mmap_init_lock(mm);
 	INIT_LIST_HEAD(&mm->mmlist);
-	mm->core_state = NULL;
 	mm_pgtables_bytes_init(mm);
 	mm->map_count = 0;
 	mm->locked_vm = 0;
@@ -1392,8 +1391,7 @@ static void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 	 * purposes.
 	 */
 	if (tsk->clear_child_tid) {
-		if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
-		    atomic_read(&mm->mm_users) > 1) {
+		if (atomic_read(&mm->mm_users) > 1) {
 			/*
 			 * We don't check the error code - if userspace has
 			 * not set up a proper pointer then tough luck.
diff --git a/kernel/signal.c b/kernel/signal.c
index 952741f6d0f9..b0db80acc6ef 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2158,40 +2158,6 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
 	spin_unlock_irqrestore(&sighand->siglock, flags);
 }
 
-static inline bool may_ptrace_stop(void)
-{
-	if (!likely(current->ptrace))
-		return false;
-	/*
-	 * Are we in the middle of do_coredump?
-	 * If so and our tracer is also part of the coredump stopping
-	 * is a deadlock situation, and pointless because our tracer
-	 * is dead so don't allow us to stop.
-	 * If SIGKILL was already sent before the caller unlocked
-	 * ->siglock we must see ->core_state != NULL. Otherwise it
-	 * is safe to enter schedule().
-	 *
-	 * This is almost outdated, a task with the pending SIGKILL can't
-	 * block in TASK_TRACED. But PTRACE_EVENT_EXIT can be reported
-	 * after SIGKILL was already dequeued.
-	 */
-	if (unlikely(current->mm->core_state) &&
-	    unlikely(current->mm == current->parent->mm))
-		return false;
-
-	return true;
-}
-
-/*
- * Return non-zero if there is a SIGKILL that should be waking us up.
- * Called with the siglock held.
- */
-static bool sigkill_pending(struct task_struct *tsk)
-{
-	return sigismember(&tsk->pending.signal, SIGKILL) ||
-	       sigismember(&tsk->signal->shared_pending.signal, SIGKILL);
-}
-
 /*
  * This must be called with current->sighand->siglock held.
  *
@@ -2209,7 +2175,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t
 {
 	bool gstop_done = false;
 
-	if (arch_ptrace_stop_needed(exit_code, info)) {
+	if (arch_ptrace_stop_needed()) {
 		/*
 		 * The arch code has something special to do before a
 		 * ptrace stop.  This is allowed to block, e.g. for faults
@@ -2217,17 +2183,16 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t
 		 * calling arch_ptrace_stop, so we must release it now.
 		 * To preserve proper semantics, we must do this before
 		 * any signal bookkeeping like checking group_stop_count.
-		 * Meanwhile, a SIGKILL could come in before we retake the
-		 * siglock.  That must prevent us from sleeping in TASK_TRACED.
-		 * So after regaining the lock, we must check for SIGKILL.
 		 */
 		spin_unlock_irq(&current->sighand->siglock);
-		arch_ptrace_stop(exit_code, info);
+		arch_ptrace_stop();
 		spin_lock_irq(&current->sighand->siglock);
-		if (sigkill_pending(current))
-			return;
 	}
 
+	/*
+	 * schedule() will not sleep if there is a pending signal that
+	 * can awaken the task.
+	 */
 	set_special_state(TASK_TRACED);
 
 	/*
@@ -2273,7 +2238,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t
 
 	spin_unlock_irq(&current->sighand->siglock);
 	read_lock(&tasklist_lock);
-	if (may_ptrace_stop()) {
+	if (likely(current->ptrace)) {
 		/*
 		 * Notify parents of the stop.
 		 *