Merge remote-tracking branch 'origin/x86/espfix' into x86/vdso

Merge x86/espfix into x86/vdso, due to changes in the vdso setup code
that otherwise cause conflicts.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

11 files changed, 54 insertions, 30 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 7c28936..47845c5 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -643,13 +643,13 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
 		if ((task_active_pid_ns(current) != &init_pid_ns))
 			return -EPERM;
 
-		if (!capable(CAP_AUDIT_CONTROL))
+		if (!netlink_capable(skb, CAP_AUDIT_CONTROL))
 			err = -EPERM;
 		break;
 	case AUDIT_USER:
 	case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG:
 	case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
-		if (!capable(CAP_AUDIT_WRITE))
+		if (!netlink_capable(skb, CAP_AUDIT_WRITE))
 			err = -EPERM;
 		break;
 	default:  /* bad msg */
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 9fcdaa7..11a03d6 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1495,7 +1495,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 	 */
 	if (!use_task_css_set_links)
 		cgroup_enable_task_cg_lists();
-retry:
+
 	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
@@ -1503,7 +1503,7 @@ retry:
 	ret = parse_cgroupfs_options(data, &opts);
 	if (ret)
 		goto out_unlock;
-
+retry:
 	/* look for a matching existing root */
 	if (!opts.subsys_mask && !opts.none && !opts.name) {
 		cgrp_dfl_root_visible = true;
@@ -1562,9 +1562,9 @@ retry:
 		if (!atomic_inc_not_zero(&root->cgrp.refcnt)) {
 			mutex_unlock(&cgroup_mutex);
 			mutex_unlock(&cgroup_tree_mutex);
-			kfree(opts.release_agent);
-			kfree(opts.name);
 			msleep(10);
+			mutex_lock(&cgroup_tree_mutex);
+			mutex_lock(&cgroup_mutex);
 			goto retry;
 		}
 
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 6cb20d2..019d450 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -120,7 +120,7 @@ void context_tracking_user_enter(void)
  * instead of preempt_schedule() to exit user context if needed before
  * calling the scheduler.
  */
-asmlinkage void __sched notrace preempt_schedule_context(void)
+asmlinkage __visible void __sched notrace preempt_schedule_context(void)
 {
 	enum ctx_state prev_ctx;
 
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 6b715c0..e0501fe 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -990,11 +990,8 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	/* Remove an active timer from the queue: */
 	ret = remove_hrtimer(timer, base);
 
-	/* Switch the timer base, if necessary: */
-	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
-
 	if (mode & HRTIMER_MODE_REL) {
-		tim = ktime_add_safe(tim, new_base->get_time());
+		tim = ktime_add_safe(tim, base->get_time());
 		/*
 		 * CONFIG_TIME_LOW_RES is a temporary way for architectures
 		 * to signal that they simply return xtime in
@@ -1009,6 +1006,9 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 
 	hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
+	/* Switch the timer base, if necessary: */
+	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
+
 	timer_stats_hrtimer_set_start_info(timer);
 
 	leftmost = enqueue_hrtimer(timer, new_base);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index b0e9467..d24e433 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4188,7 +4188,7 @@ void debug_show_held_locks(struct task_struct *task)
 }
 EXPORT_SYMBOL_GPL(debug_show_held_locks);
 
-asmlinkage void lockdep_sys_exit(void)
+asmlinkage __visible void lockdep_sys_exit(void)
 {
 	struct task_struct *curr = current;
 
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 18fb7a2..1ea328a 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1586,7 +1586,7 @@ swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
 	return -ENOMEM;
 }
 
-asmlinkage int swsusp_save(void)
+asmlinkage __visible int swsusp_save(void)
 {
 	unsigned int nr_pages, nr_highmem;
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index a45b509..7228258 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1674,7 +1674,7 @@ EXPORT_SYMBOL(printk_emit);
  *
  * See the vsnprintf() documentation for format string extensions over C99.
  */
-asmlinkage int printk(const char *fmt, ...)
+asmlinkage __visible int printk(const char *fmt, ...)
 {
 	va_list args;
 	int r;
@@ -1737,7 +1737,7 @@ void early_vprintk(const char *fmt, va_list ap)
 	}
 }
 
-asmlinkage void early_printk(const char *fmt, ...)
+asmlinkage __visible void early_printk(const char *fmt, ...)
 {
 	va_list ap;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 268a45e..d9d8ece 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2192,7 +2192,7 @@ static inline void post_schedule(struct rq *rq)
  * schedule_tail - first thing a freshly forked thread must call.
  * @prev: the thread we just switched away from.
  */
-asmlinkage void schedule_tail(struct task_struct *prev)
+asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	__releases(rq->lock)
 {
 	struct rq *rq = this_rq();
@@ -2741,7 +2741,7 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		blk_schedule_flush_plug(tsk);
 }
 
-asmlinkage void __sched schedule(void)
+asmlinkage __visible void __sched schedule(void)
 {
 	struct task_struct *tsk = current;
 
@@ -2751,7 +2751,7 @@ asmlinkage void __sched schedule(void)
 EXPORT_SYMBOL(schedule);
 
 #ifdef CONFIG_CONTEXT_TRACKING
-asmlinkage void __sched schedule_user(void)
+asmlinkage __visible void __sched schedule_user(void)
 {
 	/*
 	 * If we come here after a random call to set_need_resched(),
@@ -2783,7 +2783,7 @@ void __sched schedule_preempt_disabled(void)
  * off of preempt_enable. Kernel preemptions off return from interrupt
  * occur there and call schedule directly.
  */
-asmlinkage void __sched notrace preempt_schedule(void)
+asmlinkage __visible void __sched notrace preempt_schedule(void)
 {
 	/*
 	 * If there is a non-zero preempt_count or interrupts are disabled,
@@ -2813,7 +2813,7 @@ EXPORT_SYMBOL(preempt_schedule);
  * Note, that this is called and return with irqs disabled. This will
  * protect us against recursive calling from irq.
  */
-asmlinkage void __sched preempt_schedule_irq(void)
+asmlinkage __visible void __sched preempt_schedule_irq(void)
 {
 	enum ctx_state prev_state;
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 33e4648..92f24f5 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -223,7 +223,7 @@ static inline bool lockdep_softirq_start(void) { return false; }
 static inline void lockdep_softirq_end(bool in_hardirq) { }
 #endif
 
-asmlinkage void __do_softirq(void)
+asmlinkage __visible void __do_softirq(void)
 {
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
 	unsigned long old_flags = current->flags;
@@ -299,7 +299,7 @@ restart:
 	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
 }
 
-asmlinkage void do_softirq(void)
+asmlinkage __visible void do_softirq(void)
 {
 	__u32 pending;
 	unsigned long flags;
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index ac5b23c..6620e58 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -188,7 +188,6 @@ static int tracepoint_add_func(struct tracepoint *tp,
 		WARN_ON_ONCE(1);
 		return PTR_ERR(old);
 	}
-	release_probes(old);
 
 	/*
 	 * rcu_assign_pointer has a smp_wmb() which makes sure that the new
@@ -200,6 +199,7 @@ static int tracepoint_add_func(struct tracepoint *tp,
 	rcu_assign_pointer(tp->funcs, tp_funcs);
 	if (!static_key_enabled(&tp->key))
 		static_key_slow_inc(&tp->key);
+	release_probes(old);
 	return 0;
 }
 
@@ -221,7 +221,6 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 		WARN_ON_ONCE(1);
 		return PTR_ERR(old);
 	}
-	release_probes(old);
 
 	if (!tp_funcs) {
 		/* Removed last function */
@@ -232,6 +231,7 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 			static_key_slow_dec(&tp->key);
 	}
 	rcu_assign_pointer(tp->funcs, tp_funcs);
+	release_probes(old);
 	return 0;
 }
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0ee63af..8edc871 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1916,6 +1916,12 @@ static void send_mayday(struct work_struct *work)
 
 	/* mayday mayday mayday */
 	if (list_empty(&pwq->mayday_node)) {
+		/*
+		 * If @pwq is for an unbound wq, its base ref may be put at
+		 * any time due to an attribute change.  Pin @pwq until the
+		 * rescuer is done with it.
+		 */
+		get_pwq(pwq);
 		list_add_tail(&pwq->mayday_node, &wq->maydays);
 		wake_up_process(wq->rescuer->task);
 	}
@@ -2398,6 +2404,7 @@ static int rescuer_thread(void *__rescuer)
 	struct worker *rescuer = __rescuer;
 	struct workqueue_struct *wq = rescuer->rescue_wq;
 	struct list_head *scheduled = &rescuer->scheduled;
+	bool should_stop;
 
 	set_user_nice(current, RESCUER_NICE_LEVEL);
 
@@ -2409,11 +2416,15 @@ static int rescuer_thread(void *__rescuer)
 repeat:
 	set_current_state(TASK_INTERRUPTIBLE);
 
-	if (kthread_should_stop()) {
-		__set_current_state(TASK_RUNNING);
-		rescuer->task->flags &= ~PF_WQ_WORKER;
-		return 0;
-	}
+	/*
+	 * By the time the rescuer is requested to stop, the workqueue
+	 * shouldn't have any work pending, but @wq->maydays may still have
+	 * pwq(s) queued.  This can happen by non-rescuer workers consuming
+	 * all the work items before the rescuer got to them.  Go through
+	 * @wq->maydays processing before acting on should_stop so that the
+	 * list is always empty on exit.
+	 */
+	should_stop = kthread_should_stop();
 
 	/* see whether any pwq is asking for help */
 	spin_lock_irq(&wq_mayday_lock);
@@ -2445,6 +2456,12 @@ repeat:
 		process_scheduled_works(rescuer);
 
 		/*
+		 * Put the reference grabbed by send_mayday().  @pool won't
+		 * go away while we're holding its lock.
+		 */
+		put_pwq(pwq);
+
+		/*
 		 * Leave this pool.  If keep_working() is %true, notify a
 		 * regular worker; otherwise, we end up with 0 concurrency
 		 * and stalling the execution.
@@ -2459,6 +2476,12 @@ repeat:
 
 	spin_unlock_irq(&wq_mayday_lock);
 
+	if (should_stop) {
+		__set_current_state(TASK_RUNNING);
+		rescuer->task->flags &= ~PF_WQ_WORKER;
+		return 0;
+	}
+
 	/* rescuers should never participate in concurrency management */
 	WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING));
 	schedule();
@@ -4100,7 +4123,8 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
 	if (!pwq) {
 		pr_warning("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n",
 			   wq->name);
-		goto out_unlock;
+		mutex_lock(&wq->mutex);
+		goto use_dfl_pwq;
 	}
 
 	/*