10 files changed, 72 insertions, 35 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2a9926275f80..a7c9e6ddb979 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1686,11 +1686,14 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
                  */
                 cgroup_drop_root(opts.new_root);
 
-                if (((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) &&
-                    root->flags != opts.flags) {
-                        pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n");
-                        ret = -EINVAL;
-                        goto drop_new_super;
+                if (root->flags != opts.flags) {
+                        if ((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) {
+                                pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n");
+                                ret = -EINVAL;
+                                goto drop_new_super;
+                        } else {
+                                pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n");
+                        }
                 }
 
                 /* no subsys rebinding, so refcounts don't change */
@@ -2699,13 +2702,14 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
                 goto out;
         }
 
+        cfe->type = (void *)cft;
+        cfe->dentry = dentry;
+        dentry->d_fsdata = cfe;
+        simple_xattrs_init(&cfe->xattrs);
+
         mode = cgroup_file_mode(cft);
         error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb);
         if (!error) {
-                cfe->type = (void *)cft;
-                cfe->dentry = dentry;
-                dentry->d_fsdata = cfe;
-                simple_xattrs_init(&cfe->xattrs);
                 list_add_tail(&cfe->node, &parent->files);
                 cfe = NULL;
         }
@@ -2953,11 +2957,8 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos,
         WARN_ON_ONCE(!rcu_read_lock_held());
 
         /* if first iteration, pretend we just visited @cgroup */
-        if (!pos) {
-                if (list_empty(&cgroup->children))
-                        return NULL;
+        if (!pos)
                 pos = cgroup;
-        }
 
         /* visit the first child if exists */
         next = list_first_or_null_rcu(&pos->children, struct cgroup, sibling);
@@ -2965,14 +2966,14 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos,
                 return next;
 
         /* no child, visit my or the closest ancestor's next sibling */
-        do {
+        while (pos != cgroup) {
                 next = list_entry_rcu(pos->sibling.next, struct cgroup,
                                       sibling);
                 if (&next->sibling != &pos->parent->children)
                         return next;
 
                 pos = pos->parent;
-        } while (pos != cgroup);
+        }
 
         return NULL;
 }
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 5a83dde8ca0c..54a4d5223238 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -143,7 +143,10 @@ static unsigned int irq_domain_legacy_revmap(struct irq_domain *domain,
  * irq_domain_add_simple() - Allocate and register a simple irq_domain.
  * @of_node: pointer to interrupt controller's device tree node.
  * @size: total number of irqs in mapping
- * @first_irq: first number of irq block assigned to the domain
+ * @first_irq: first number of irq block assigned to the domain,
+ *      pass zero to assign irqs on-the-fly. This will result in a
+ *      linear IRQ domain so it is important to use irq_create_mapping()
+ *      for each used IRQ, especially when SPARSE_IRQ is enabled.
  * @ops: map/unmap domain callbacks
  * @host_data: Controller private data pointer
  *
@@ -191,6 +194,7 @@ struct irq_domain *irq_domain_add_simple(struct device_node *of_node,
         /* A linear domain is the default */
         return irq_domain_add_linear(of_node, size, ops, host_data);
 }
+EXPORT_SYMBOL_GPL(irq_domain_add_simple);
 
 /**
  * irq_domain_add_legacy() - Allocate and register a legacy revmap irq_domain.
@@ -397,11 +401,12 @@ static void irq_domain_disassociate_many(struct irq_domain *domain,
         while (count--) {
                 int irq = irq_base + count;
                 struct irq_data *irq_data = irq_get_irq_data(irq);
-                irq_hw_number_t hwirq = irq_data->hwirq;
+                irq_hw_number_t hwirq;
 
                 if (WARN_ON(!irq_data || irq_data->domain != domain))
                         continue;
 
+                hwirq = irq_data->hwirq;
                 irq_set_status_flags(irq, IRQ_NOREQUEST);
 
                 /* remove chip and handler */
diff --git a/kernel/range.c b/kernel/range.c
index 071b0ab455cb..eb911dbce267 100644
--- a/kernel/range.c
+++ b/kernel/range.c
@@ -48,9 +48,11 @@ int add_range_with_merge(struct range *range, int az, int nr_range,
                 final_start = min(range[i].start, start);
                 final_end = max(range[i].end, end);
 
-                range[i].start = final_start;
-                range[i].end =  final_end;
-                return nr_range;
+                /* clear it and add it back for further merge */
+                range[i].start = 0;
+                range[i].end =  0;
+                return add_range_with_merge(range, az, nr_range,
+                        final_start, final_end);
         }
 
         /* Need to add it: */
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 12ff13a838c6..8f5b3b98577b 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -874,7 +874,6 @@ static void hardpps_update_phase(long error)
 void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
 {
         struct pps_normtime pts_norm, freq_norm;
-        unsigned long flags;
 
         pts_norm = pps_normalize_ts(*phase_ts);
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 24938d577669..0c739423b0f9 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -511,6 +511,12 @@ again:
                 }
         }
 
+        /*
+         * Remove the current cpu from the pending mask. The event is
+         * delivered immediately in tick_do_broadcast() !
+         */
+        cpumask_clear_cpu(smp_processor_id(), tick_broadcast_pending_mask);
+
         /* Take care of enforced broadcast requests */
         cpumask_or(tmpmask, tmpmask, tick_broadcast_force_mask);
         cpumask_clear(tick_broadcast_force_mask);
@@ -575,8 +581,8 @@ void tick_broadcast_oneshot_control(unsigned long reason)
 
         raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
         if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
-                WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
                 if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
+                        WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
                         clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
                         /*
                          * We only reprogram the broadcast timer if we
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 98cd470bbe49..baeeb5c87cf1 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -975,6 +975,14 @@ static int timekeeping_suspend(void)
 
         read_persistent_clock(&timekeeping_suspend_time);
 
+        /*
+         * On some systems the persistent_clock can not be detected at
+         * timekeeping_init by its return value, so if we see a valid
+         * value returned, update the persistent_clock_exists flag.
+         */
+        if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
+                persistent_clock_exist = true;
+
         raw_spin_lock_irqsave(&timekeeper_lock, flags);
         write_seqcount_begin(&timekeeper_seq);
         timekeeping_forward_now(tk);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b549b0f5b977..6c508ff33c62 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -120,22 +120,22 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
 
 /*
  * Traverse the ftrace_global_list, invoking all entries.  The reason that we
- * can use rcu_dereference_raw() is that elements removed from this list
+ * can use rcu_dereference_raw_notrace() is that elements removed from this list
  * are simply leaked, so there is no need to interact with a grace-period
- * mechanism.  The rcu_dereference_raw() calls are needed to handle
+ * mechanism.  The rcu_dereference_raw_notrace() calls are needed to handle
  * concurrent insertions into the ftrace_global_list.
  *
  * Silly Alpha and silly pointer-speculation compiler optimizations!
  */
 #define do_for_each_ftrace_op(op, list)                 \
-        op = rcu_dereference_raw(list);                 \
+        op = rcu_dereference_raw_notrace(list);                 \
         do
 
 /*
  * Optimized for just a single item in the list (as that is the normal case).
  */
 #define while_for_each_ftrace_op(op)                            \
-        while (likely(op = rcu_dereference_raw((op)->next)) &&  \
+        while (likely(op = rcu_dereference_raw_notrace((op)->next)) &&  \
                unlikely((op) != &ftrace_list_end))
 
 static inline void ftrace_ops_init(struct ftrace_ops *ops)
@@ -779,7 +779,7 @@ ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip)
         if (hlist_empty(hhd))
                 return NULL;
 
-        hlist_for_each_entry_rcu(rec, hhd, node) {
+        hlist_for_each_entry_rcu_notrace(rec, hhd, node) {
                 if (rec->ip == ip)
                         return rec;
         }
@@ -1165,7 +1165,7 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip)
 
         hhd = &hash->buckets[key];
 
-        hlist_for_each_entry_rcu(entry, hhd, hlist) {
+        hlist_for_each_entry_rcu_notrace(entry, hhd, hlist) {
                 if (entry->ip == ip)
                         return entry;
         }
@@ -1422,8 +1422,8 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
         struct ftrace_hash *notrace_hash;
         int ret;
 
-        filter_hash = rcu_dereference_raw(ops->filter_hash);
-        notrace_hash = rcu_dereference_raw(ops->notrace_hash);
+        filter_hash = rcu_dereference_raw_notrace(ops->filter_hash);
+        notrace_hash = rcu_dereference_raw_notrace(ops->notrace_hash);
 
         if ((ftrace_hash_empty(filter_hash) ||
              ftrace_lookup_ip(filter_hash, ip)) &&
@@ -2920,7 +2920,7 @@ static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip,
          * on the hash. rcu_read_lock is too dangerous here.
          */
         preempt_disable_notrace();
-        hlist_for_each_entry_rcu(entry, hhd, node) {
+        hlist_for_each_entry_rcu_notrace(entry, hhd, node) {
                 if (entry->ip == ip)
                         entry->ops->func(ip, parent_ip, &entry->data);
         }
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b59aea2c48c2..e444ff88f0a4 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -620,6 +620,9 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
         if (cpu == RING_BUFFER_ALL_CPUS)
                 work = &buffer->irq_work;
         else {
+                if (!cpumask_test_cpu(cpu, buffer->cpumask))
+                        return -EINVAL;
+
                 cpu_buffer = buffer->buffers[cpu];
                 work = &cpu_buffer->irq_work;
         }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ae6fa2d1cdf7..1a41023a1f88 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -843,7 +843,15 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
         memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
         max_data->pid = tsk->pid;
-        max_data->uid = task_uid(tsk);
+        /*
+         * If tsk == current, then use current_uid(), as that does not use
+         * RCU. The irq tracer can be called out of RCU scope.
+         */
+        if (tsk == current)
+                max_data->uid = current_uid();
+        else
+                max_data->uid = task_uid(tsk);
+
         max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
         max_data->policy = tsk->policy;
         max_data->rt_priority = tsk->rt_priority;
@@ -6216,10 +6224,15 @@ __init static int tracer_alloc_buffers(void)
 
         trace_init_cmdlines();
 
-        register_tracer(&nop_trace);
-
+        /*
+         * register_tracer() might reference current_trace, so it
+         * needs to be set before we register anything. This is
+         * just a bootstrap of current_trace anyway.
+         */
         global_trace.current_trace = &nop_trace;
 
+        register_tracer(&nop_trace);
+
         /* All seems OK, enable tracing */
         tracing_disabled = 0;
 
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 55e2cf66967b..2901e3b88590 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1159,7 +1159,7 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
         /* stop the tracing. */
         tracing_stop();
         /* check the trace buffer */
-        ret = trace_test_buffer(tr, &count);
+        ret = trace_test_buffer(&tr->trace_buffer, &count);
         trace->reset(tr);
         tracing_start();