Merge commit '7ed6fb9b5a5510e4ef78ab27419184741169978a' into x86/espfix

Merge in Linus' tree with:

fa81511bb0bb x86-64, modify_ldt: Make support for 16-bit segments a runtime option

... reverted, to avoid a conflict.  This commit is no longer necessary
with the proper fix in place.

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

16 files changed, 97 insertions, 58 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 7c2893602d06..47845c57eb19 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 9fcdaa705b6c..11a03d67635a 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 6cb20d2e7ee0..019d45008448 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 d55092ceee29..e0501fe7140d 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -234,6 +234,11 @@ again:
                         goto again;
                 }
                 timer->base = new_base;
+        } else {
+                if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+                        cpu = this_cpu;
+                        goto again;
+                }
         }
         return new_base;
 }
@@ -569,6 +574,23 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 
         cpu_base->expires_next.tv64 = expires_next.tv64;
 
+        /*
+         * If a hang was detected in the last timer interrupt then we
+         * leave the hang delay active in the hardware. We want the
+         * system to make progress. That also prevents the following
+         * scenario:
+         * T1 expires 50ms from now
+         * T2 expires 5s from now
+         *
+         * T1 is removed, so this code is called and would reprogram
+         * the hardware to 5s from now. Any hrtimer_start after that
+         * will not reprogram the hardware due to hang_detected being
+         * set. So we'd effectivly block all timers until the T2 event
+         * fires.
+         */
+        if (cpu_base->hang_detected)
+                return;
+
         if (cpu_base->expires_next.tv64 != KTIME_MAX)
                 tick_program_event(cpu_base->expires_next, 1);
 }
@@ -968,11 +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
@@ -987,6 +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/irq/irqdesc.c b/kernel/irq/irqdesc.c
index a7174617616b..bb07f2928f4b 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -363,6 +363,13 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
                 if (from > irq)
                         return -EINVAL;
                 from = irq;
+        } else {
+                /*
+                 * For interrupts which are freely allocated the
+                 * architecture can force a lower bound to the @from
+                 * argument. x86 uses this to exclude the GSI space.
+                 */
+                from = arch_dynirq_lower_bound(from);
         }
 
         mutex_lock(&sparse_irq_lock);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index b0e9467922e1..d24e4339b46d 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/module.c b/kernel/module.c
index 11869408f79b..079c4615607d 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -815,9 +815,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
                 return -EFAULT;
         name[MODULE_NAME_LEN-1] = '\0';
 
-        if (!(flags & O_NONBLOCK))
-                pr_warn("waiting module removal not supported: please upgrade\n");
-
         if (mutex_lock_interruptible(&module_mutex) != 0)
                 return -EINTR;
 
@@ -3271,6 +3268,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
 
         dynamic_debug_setup(info->debug, info->num_debug);
 
+        /* Ftrace init must be called in the MODULE_STATE_UNFORMED state */
+        ftrace_module_init(mod);
+
         /* Finally it's fully formed, ready to start executing. */
         err = complete_formation(mod, info);
         if (err)
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 18fb7a2fb14b..1ea328aafdc9 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 a45b50962295..7228258b85ec 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 268a45ea238c..d9d8ece46a15 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 b50990a5bea0..92f24f5e8d52 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;
@@ -779,3 +779,8 @@ int __init __weak arch_early_irq_init(void)
 {
         return 0;
 }
+
+unsigned int __weak arch_dynirq_lower_bound(unsigned int from)
+{
+        return from;
+}
diff --git a/kernel/timer.c b/kernel/timer.c
index 87bd529879c2..3bb01a323b2a 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -838,7 +838,7 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
 
         bit = find_last_bit(&mask, BITS_PER_LONG);
 
-        mask = (1 << bit) - 1;
+        mask = (1UL << bit) - 1;
 
         expires_limit = expires_limit & ~(mask);
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1fd4b9479210..4a54a25afa2f 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4330,16 +4330,11 @@ static void ftrace_init_module(struct module *mod,
         ftrace_process_locs(mod, start, end);
 }
 
-static int ftrace_module_notify_enter(struct notifier_block *self,
-                                      unsigned long val, void *data)
+void ftrace_module_init(struct module *mod)
 {
-        struct module *mod = data;
-
-        if (val == MODULE_STATE_COMING)
-                ftrace_init_module(mod, mod->ftrace_callsites,
-                                   mod->ftrace_callsites +
-                                   mod->num_ftrace_callsites);
-        return 0;
+        ftrace_init_module(mod, mod->ftrace_callsites,
+                           mod->ftrace_callsites +
+                           mod->num_ftrace_callsites);
 }
 
 static int ftrace_module_notify_exit(struct notifier_block *self,
@@ -4353,11 +4348,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self,
         return 0;
 }
 #else
-static int ftrace_module_notify_enter(struct notifier_block *self,
-                                      unsigned long val, void *data)
-{
-        return 0;
-}
 static int ftrace_module_notify_exit(struct notifier_block *self,
                                      unsigned long val, void *data)
 {
@@ -4365,11 +4355,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self,
 }
 #endif /* CONFIG_MODULES */
 
-struct notifier_block ftrace_module_enter_nb = {
-        .notifier_call = ftrace_module_notify_enter,
-        .priority = INT_MAX,    /* Run before anything that can use kprobes */
-};
-
 struct notifier_block ftrace_module_exit_nb = {
         .notifier_call = ftrace_module_notify_exit,
         .priority = INT_MIN,    /* Run after anything that can remove kprobes */
@@ -4403,10 +4388,6 @@ void __init ftrace_init(void)
                                   __start_mcount_loc,
                                   __stop_mcount_loc);
 
-        ret = register_module_notifier(&ftrace_module_enter_nb);
-        if (ret)
-                pr_warning("Failed to register trace ftrace module enter notifier\n");
-
         ret = register_module_notifier(&ftrace_module_exit_nb);
         if (ret)
                 pr_warning("Failed to register trace ftrace module exit notifier\n");
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 925f537f07d1..4747b476a030 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -77,7 +77,7 @@ event_triggers_call(struct ftrace_event_file *file, void *rec)
                         data->ops->func(data);
                         continue;
                 }
-                filter = rcu_dereference(data->filter);
+                filter = rcu_dereference_sched(data->filter);
                 if (filter && !filter_match_preds(filter, rec))
                         continue;
                 if (data->cmd_ops->post_trigger) {
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index ac5b23cf7212..6620e5837ce2 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 0ee63af30bd1..8edc87185427 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;
         }
 
         /*