1 files changed, 142 insertions, 78 deletions

diff --git a/kernel/signal.c b/kernel/signal.c
index 07da8def4329..0f39cc1c6ac1 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -20,6 +20,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/rt.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/proc_fs.h>
@@ -398,37 +399,62 @@ void task_join_group_stop(struct task_struct *task)
 	}
 }
 
+static inline struct sigqueue *get_task_cache(struct task_struct *t)
+{
+	struct sigqueue *q = t->sigqueue_cache;
+
+	if (cmpxchg(&t->sigqueue_cache, q, NULL) != q)
+		return NULL;
+	return q;
+}
+
+static inline int put_task_cache(struct task_struct *t, struct sigqueue *q)
+{
+	if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL)
+		return 0;
+	return 1;
+}
+
 /*
  * allocate a new signal queue record
  * - this may be called without locks if and only if t == current, otherwise an
  *   appropriate lock must be held to stop the target task from exiting
  */
 static struct sigqueue *
-__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit)
+__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags,
+		    int override_rlimit, int fromslab)
 {
 	struct sigqueue *q = NULL;
 	struct user_struct *user;
+	int sigpending;
 
 	/*
 	 * Protect access to @t credentials. This can go away when all
 	 * callers hold rcu read lock.
+	 *
+	 * NOTE! A pending signal will hold on to the user refcount,
+	 * and we get/put the refcount only when the sigpending count
+	 * changes from/to zero.
 	 */
 	rcu_read_lock();
-	user = get_uid(__task_cred(t)->user);
-	atomic_inc(&user->sigpending);
+	user = __task_cred(t)->user;
+	sigpending = atomic_inc_return(&user->sigpending);
+	if (sigpending == 1)
+		get_uid(user);
 	rcu_read_unlock();
 
-	if (override_rlimit ||
-	    atomic_read(&user->sigpending) <=
-			task_rlimit(t, RLIMIT_SIGPENDING)) {
-		q = kmem_cache_alloc(sigqueue_cachep, flags);
+	if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) {
+		if (!fromslab)
+			q = get_task_cache(t);
+		if (!q)
+			q = kmem_cache_alloc(sigqueue_cachep, flags);
 	} else {
 		print_dropped_signal(sig);
 	}
 
 	if (unlikely(q == NULL)) {
-		atomic_dec(&user->sigpending);
-		free_uid(user);
+		if (atomic_dec_and_test(&user->sigpending))
+			free_uid(user);
 	} else {
 		INIT_LIST_HEAD(&q->list);
 		q->flags = 0;
@@ -438,15 +464,37 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi
 	return q;
 }
 
+static struct sigqueue *
+__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags,
+		 int override_rlimit)
+{
+	return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0);
+}
+
 static void __sigqueue_free(struct sigqueue *q)
 {
 	if (q->flags & SIGQUEUE_PREALLOC)
 		return;
-	atomic_dec(&q->user->sigpending);
-	free_uid(q->user);
+	if (atomic_dec_and_test(&q->user->sigpending))
+		free_uid(q->user);
 	kmem_cache_free(sigqueue_cachep, q);
 }
 
+static void sigqueue_free_current(struct sigqueue *q)
+{
+	struct user_struct *up;
+
+	if (q->flags & SIGQUEUE_PREALLOC)
+		return;
+
+	up = q->user;
+	if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) {
+		atomic_dec(&up->sigpending);
+		free_uid(up);
+	} else
+		  __sigqueue_free(q);
+}
+
 void flush_sigqueue(struct sigpending *queue)
 {
 	struct sigqueue *q;
@@ -460,6 +508,21 @@ void flush_sigqueue(struct sigpending *queue)
 }
 
 /*
+ * Called from __exit_signal. Flush tsk->pending and
+ * tsk->sigqueue_cache
+ */
+void flush_task_sigqueue(struct task_struct *tsk)
+{
+	struct sigqueue *q;
+
+	flush_sigqueue(&tsk->pending);
+
+	q = get_task_cache(tsk);
+	if (q)
+		kmem_cache_free(sigqueue_cachep, q);
+}
+
+/*
  * Flush all pending signals for this kthread.
  */
 void flush_signals(struct task_struct *t)
@@ -583,7 +646,7 @@ still_pending:
 			(info->si_code == SI_TIMER) &&
 			(info->si_sys_private);
 
-		__sigqueue_free(first);
+		sigqueue_free_current(first);
 	} else {
 		/*
 		 * Ok, it wasn't in the queue.  This must be
@@ -620,6 +683,8 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *in
 	bool resched_timer = false;
 	int signr;
 
+	WARN_ON_ONCE(tsk != current);
+
 	/* We only dequeue private signals from ourselves, we don't let
 	 * signalfd steal them
 	 */
@@ -1287,8 +1352,8 @@ int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p
  * We don't want to have recursive SIGSEGV's etc, for example,
  * that is why we also clear SIGNAL_UNKILLABLE.
  */
-int
-force_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *t)
+static int
+do_force_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *t)
 {
 	unsigned long int flags;
 	int ret, blocked, ignored;
@@ -1317,6 +1382,39 @@ force_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *t)
 	return ret;
 }
 
+int force_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *t)
+{
+/*
+ * On some archs, PREEMPT_RT has to delay sending a signal from a trap
+ * since it can not enable preemption, and the signal code's spin_locks
+ * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will
+ * send the signal on exit of the trap.
+ */
+#ifdef ARCH_RT_DELAYS_SIGNAL_SEND
+	if (in_atomic()) {
+		if (WARN_ON_ONCE(t != current))
+			return 0;
+		if (WARN_ON_ONCE(t->forced_info.si_signo))
+			return 0;
+
+		if (is_si_special(info)) {
+			WARN_ON_ONCE(info != SEND_SIG_PRIV);
+			t->forced_info.si_signo = sig;
+			t->forced_info.si_errno = 0;
+			t->forced_info.si_code = SI_KERNEL;
+			t->forced_info.si_pid = 0;
+			t->forced_info.si_uid = 0;
+		} else {
+			t->forced_info = *info;
+		}
+
+		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
+		return 0;
+	}
+#endif
+	return do_force_sig_info(sig, info, t);
+}
+
 /*
  * Nuke all other threads in the group.
  */
@@ -1486,15 +1584,15 @@ int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr,
 	unsigned long flags;
 	int ret = -EINVAL;
 
+	if (!valid_signal(sig))
+		return ret;
+
 	clear_siginfo(&info);
 	info.si_signo = sig;
 	info.si_errno = errno;
 	info.si_code = SI_ASYNCIO;
 	*((sigval_t *)&info.si_pid) = addr;
 
-	if (!valid_signal(sig))
-		return ret;
-
 	rcu_read_lock();
 	p = pid_task(pid, PIDTYPE_PID);
 	if (!p) {
@@ -1767,7 +1865,8 @@ EXPORT_SYMBOL(kill_pid);
  */
 struct sigqueue *sigqueue_alloc(void)
 {
-	struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0);
+	/* Preallocated sigqueue objects always from the slabcache ! */
+	struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1);
 
 	if (q)
 		q->flags |= SIGQUEUE_PREALLOC;
@@ -1876,7 +1975,7 @@ 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;
 	}
 
@@ -1938,8 +2037,12 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 		if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
 			sig = 0;
 	}
+	/*
+	 * Send with __send_signal as si_pid and si_uid are in the
+	 * parent's namespaces.
+	 */
 	if (valid_signal(sig) && sig)
-		__group_send_sig_info(sig, &info, tsk->parent);
+		__send_signal(sig, &info, tsk->parent, PIDTYPE_TGID, false);
 	__wake_up_parent(tsk, tsk->parent);
 	spin_unlock_irqrestore(&psig->siglock, flags);
 
@@ -2147,16 +2250,8 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t
 		if (gstop_done && ptrace_reparented(current))
 			do_notify_parent_cldstop(current, false, why);
 
-		/*
-		 * Don't want to allow preemption here, because
-		 * sys_ptrace() needs this task to be inactive.
-		 *
-		 * XXX: implement read_unlock_no_resched().
-		 */
-		preempt_disable();
 		read_unlock(&tasklist_lock);
 		cgroup_enter_frozen();
-		preempt_enable_no_resched();
 		freezable_schedule();
 		cgroup_leave_frozen(true);
 	} else {
@@ -2907,80 +3002,49 @@ EXPORT_SYMBOL(sigprocmask);
  *
  * This is useful for syscalls such as ppoll, pselect, io_pgetevents and
  * epoll_pwait where a new sigmask is passed from userland for the syscalls.
+ *
+ * Note that it does set_restore_sigmask() in advance, so it must be always
+ * paired with restore_saved_sigmask_unless() before return from syscall.
  */
-int set_user_sigmask(const sigset_t __user *usigmask, sigset_t *set,
-		     sigset_t *oldset, size_t sigsetsize)
+int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize)
 {
-	if (!usigmask)
-		return 0;
+	sigset_t kmask;
 
+	if (!umask)
+		return 0;
 	if (sigsetsize != sizeof(sigset_t))
 		return -EINVAL;
-	if (copy_from_user(set, usigmask, sizeof(sigset_t)))
+	if (copy_from_user(&kmask, umask, sizeof(sigset_t)))
 		return -EFAULT;
 
-	*oldset = current->blocked;
-	set_current_blocked(set);
+	set_restore_sigmask();
+	current->saved_sigmask = current->blocked;
+	set_current_blocked(&kmask);
 
 	return 0;
 }
-EXPORT_SYMBOL(set_user_sigmask);
 
 #ifdef CONFIG_COMPAT
-int set_compat_user_sigmask(const compat_sigset_t __user *usigmask,
-			    sigset_t *set, sigset_t *oldset,
+int set_compat_user_sigmask(const compat_sigset_t __user *umask,
 			    size_t sigsetsize)
 {
-	if (!usigmask)
-		return 0;
+	sigset_t kmask;
 
+	if (!umask)
+		return 0;
 	if (sigsetsize != sizeof(compat_sigset_t))
 		return -EINVAL;
-	if (get_compat_sigset(set, usigmask))
+	if (get_compat_sigset(&kmask, umask))
 		return -EFAULT;
 
-	*oldset = current->blocked;
-	set_current_blocked(set);
+	set_restore_sigmask();
+	current->saved_sigmask = current->blocked;
+	set_current_blocked(&kmask);
 
 	return 0;
 }
-EXPORT_SYMBOL(set_compat_user_sigmask);
 #endif
 
-/*
- * restore_user_sigmask:
- * usigmask: sigmask passed in from userland.
- * sigsaved: saved sigmask when the syscall started and changed the sigmask to
- *           usigmask.
- *
- * This is useful for syscalls such as ppoll, pselect, io_pgetevents and
- * epoll_pwait where a new sigmask is passed in from userland for the syscalls.
- */
-void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved,
-				bool interrupted)
-{
-
-	if (!usigmask)
-		return;
-	/*
-	 * When signals are pending, do not restore them here.
-	 * Restoring sigmask here can lead to delivering signals that the above
-	 * syscalls are intended to block because of the sigmask passed in.
-	 */
-	if (interrupted) {
-		current->saved_sigmask = *sigsaved;
-		set_restore_sigmask();
-		return;
-	}
-
-	/*
-	 * This is needed because the fast syscall return path does not restore
-	 * saved_sigmask when signals are not pending.
-	 */
-	set_current_blocked(sigsaved);
-}
-EXPORT_SYMBOL(restore_user_sigmask);
-
 /**
  *  sys_rt_sigprocmask - change the list of currently blocked signals
  *  @how: whether to add, remove, or set signals