18 files changed, 147 insertions, 84 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index ce1e48c2d93d..cce59cb5ee6a 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -87,7 +87,7 @@ static void __exit_signal(struct task_struct *tsk)
 
         sighand = rcu_dereference_check(tsk->sighand,
                                         rcu_read_lock_held() ||
-                                        lockdep_is_held(&tasklist_lock));
+                                        lockdep_tasklist_lock_is_held());
         spin_lock(&sighand->siglock);
 
         posix_cpu_timers_exit(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index 1beb6c303c41..4799c5f0e6d0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -86,7 +86,14 @@ int max_threads;		/* tunable limit on nr_threads */
 DEFINE_PER_CPU(unsigned long, process_counts) = 0;
 
 __cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */
-EXPORT_SYMBOL_GPL(tasklist_lock);
+
+#ifdef CONFIG_PROVE_RCU
+int lockdep_tasklist_lock_is_held(void)
+{
+        return lockdep_is_held(&tasklist_lock);
+}
+EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held);
+#endif /* #ifdef CONFIG_PROVE_RCU */
 
 int nr_processes(void)
 {
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index 967e66143e11..03808ed342a6 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -413,17 +413,17 @@ EXPORT_SYMBOL_GPL(unregister_hw_breakpoint);
  *
  * @return a set of per_cpu pointers to perf events
  */
-struct perf_event **
+struct perf_event * __percpu *
 register_wide_hw_breakpoint(struct perf_event_attr *attr,
                             perf_overflow_handler_t triggered)
 {
-        struct perf_event **cpu_events, **pevent, *bp;
+        struct perf_event * __percpu *cpu_events, **pevent, *bp;
         long err;
         int cpu;
 
         cpu_events = alloc_percpu(typeof(*cpu_events));
         if (!cpu_events)
-                return ERR_PTR(-ENOMEM);
+                return (void __percpu __force *)ERR_PTR(-ENOMEM);
 
         get_online_cpus();
         for_each_online_cpu(cpu) {
@@ -451,7 +451,7 @@ fail:
         put_online_cpus();
 
         free_percpu(cpu_events);
-        return ERR_PTR(err);
+        return (void __percpu __force *)ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint);
 
@@ -459,7 +459,7 @@ EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint);
  * unregister_wide_hw_breakpoint - unregister a wide breakpoint in the kernel
  * @cpu_events: the per cpu set of events to unregister
  */
-void unregister_wide_hw_breakpoint(struct perf_event **cpu_events)
+void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events)
 {
         int cpu;
         struct perf_event **pevent;
@@ -489,5 +489,4 @@ struct pmu perf_ops_bp = {
         .enable         = arch_install_hw_breakpoint,
         .disable        = arch_uninstall_hw_breakpoint,
         .read           = hw_breakpoint_pmu_read,
-        .unthrottle     = hw_breakpoint_pmu_unthrottle
 };
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 0c30d0455de1..681bc2e1e187 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -3822,6 +3822,7 @@ void lockdep_rcu_dereference(const char *file, const int line)
         printk("%s:%d invoked rcu_dereference_check() without protection!\n",
                         file, line);
         printk("\nother info that might help us debug this:\n\n");
+        printk("\nrcu_scheduler_active = %d, debug_locks = %d\n", rcu_scheduler_active, debug_locks);
         lockdep_print_held_locks(curr);
         printk("\nstack backtrace:\n");
         dump_stack();
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index f40560b86544..4393b9e73740 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -56,21 +56,6 @@ static atomic_t nr_task_events __read_mostly;
  */
 int sysctl_perf_event_paranoid __read_mostly = 1;
 
-static inline bool perf_paranoid_tracepoint_raw(void)
-{
-        return sysctl_perf_event_paranoid > -1;
-}
-
-static inline bool perf_paranoid_cpu(void)
-{
-        return sysctl_perf_event_paranoid > 0;
-}
-
-static inline bool perf_paranoid_kernel(void)
-{
-        return sysctl_perf_event_paranoid > 1;
-}
-
 int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */
 
 /*
@@ -4123,8 +4108,7 @@ void __perf_sw_event(u32 event_id, u64 nr, int nmi,
         if (rctx < 0)
                 return;
 
-        data.addr = addr;
-        data.raw  = NULL;
+        perf_sample_data_init(&data, addr);
 
         do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs);
 
@@ -4169,11 +4153,10 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
         struct perf_event *event;
         u64 period;
 
-        event   = container_of(hrtimer, struct perf_event, hw.hrtimer);
+        event = container_of(hrtimer, struct perf_event, hw.hrtimer);
         event->pmu->read(event);
 
-        data.addr = 0;
-        data.raw = NULL;
+        perf_sample_data_init(&data, 0);
         data.period = event->hw.last_period;
         regs = get_irq_regs();
         /*
@@ -4337,17 +4320,15 @@ static const struct pmu perf_ops_task_clock = {
 void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
                           int entry_size)
 {
+        struct pt_regs *regs = get_irq_regs();
+        struct perf_sample_data data;
         struct perf_raw_record raw = {
                 .size = entry_size,
                 .data = record,
         };
 
-        struct perf_sample_data data = {
-                .addr = addr,
-                .raw = &raw,
-        };
-
-        struct pt_regs *regs = get_irq_regs();
+        perf_sample_data_init(&data, addr);
+        data.raw = &raw;
 
         if (!regs)
                 regs = task_pt_regs(current);
@@ -4463,8 +4444,7 @@ void perf_bp_event(struct perf_event *bp, void *data)
         struct perf_sample_data sample;
         struct pt_regs *regs = data;
 
-        sample.raw = NULL;
-        sample.addr = bp->attr.bp_addr;
+        perf_sample_data_init(&sample, bp->attr.bp_addr);
 
         if (!perf_exclude_event(bp, regs))
                 perf_swevent_add(bp, 1, 1, &sample, regs);
diff --git a/kernel/pid.c b/kernel/pid.c
index 86b296943e5f..aebb30d9c233 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -367,7 +367,9 @@ struct task_struct *pid_task(struct pid *pid, enum pid_type type)
         struct task_struct *result = NULL;
         if (pid) {
                 struct hlist_node *first;
-                first = rcu_dereference_check(pid->tasks[type].first, rcu_read_lock_held() || lockdep_is_held(&tasklist_lock));
+                first = rcu_dereference_check(pid->tasks[type].first,
+                                              rcu_read_lock_held() ||
+                                              lockdep_tasklist_lock_is_held());
                 if (first)
                         result = hlist_entry(first, struct task_struct, pids[(type)].node);
         }
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 1439eb504c22..4a525a30e08e 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -246,12 +246,21 @@ struct rcu_data {
 
 #define RCU_JIFFIES_TILL_FORCE_QS        3      /* for rsp->jiffies_force_qs */
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-#define RCU_SECONDS_TILL_STALL_CHECK   (10 * HZ)  /* for rsp->jiffies_stall */
-#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ)  /* for rsp->jiffies_stall */
-#define RCU_STALL_RAT_DELAY             2         /* Allow other CPUs time */
-                                                  /*  to take at least one */
-                                                  /*  scheduling clock irq */
-                                                  /*  before ratting on them. */
+
+#ifdef CONFIG_PROVE_RCU
+#define RCU_STALL_DELAY_DELTA          (5 * HZ)
+#else
+#define RCU_STALL_DELAY_DELTA          0
+#endif
+
+#define RCU_SECONDS_TILL_STALL_CHECK   (10 * HZ + RCU_STALL_DELAY_DELTA)
+                                                /* for rsp->jiffies_stall */
+#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ + RCU_STALL_DELAY_DELTA)
+                                                /* for rsp->jiffies_stall */
+#define RCU_STALL_RAT_DELAY             2       /* Allow other CPUs time */
+                                                /*  to take at least one */
+                                                /*  scheduling clock irq */
+                                                /*  before ratting on them. */
 
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 464ad2cdee00..79b53bda8943 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1010,6 +1010,10 @@ int rcu_needs_cpu(int cpu)
         int c = 0;
         int thatcpu;
 
+        /* Check for being in the holdoff period. */
+        if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies)
+                return rcu_needs_cpu_quick_check(cpu);
+
         /* Don't bother unless we are the last non-dyntick-idle CPU. */
         for_each_cpu_not(thatcpu, nohz_cpu_mask)
                 if (thatcpu != cpu) {
@@ -1041,10 +1045,8 @@ int rcu_needs_cpu(int cpu)
         }
 
         /* If RCU callbacks are still pending, RCU still needs this CPU. */
-        if (c) {
+        if (c)
                 raise_softirq(RCU_SOFTIRQ);
-                per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
-        }
         return c;
 }
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 150b6988de49..9ab3cd7858d3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2359,7 +2359,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 {
         int cpu, orig_cpu, this_cpu, success = 0;
         unsigned long flags;
-        struct rq *rq, *orig_rq;
+        struct rq *rq;
 
         if (!sched_feat(SYNC_WAKEUPS))
                 wake_flags &= ~WF_SYNC;
@@ -2367,7 +2367,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
         this_cpu = get_cpu();
 
         smp_wmb();
-        rq = orig_rq = task_rq_lock(p, &flags);
+        rq = task_rq_lock(p, &flags);
         update_rq_clock(rq);
         if (!(p->state & state))
                 goto out;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 3e1fd96c6cf9..5a5ea2cd924f 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -3476,7 +3476,7 @@ static void run_rebalance_domains(struct softirq_action *h)
 
 static inline int on_null_domain(int cpu)
 {
-        return !rcu_dereference(cpu_rq(cpu)->sd);
+        return !rcu_dereference_sched(cpu_rq(cpu)->sd);
 }
 
 /*
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 5a6ed1f0990a..b5b920ae2ea7 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1146,7 +1146,12 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
                 if (next && next->prio < idx)
                         continue;
                 list_for_each_entry(rt_se, array->queue + idx, run_list) {
-                        struct task_struct *p = rt_task_of(rt_se);
+                        struct task_struct *p;
+
+                        if (!rt_entity_is_task(rt_se))
+                                continue;
+
+                        p = rt_task_of(rt_se);
                         if (pick_rt_task(rq, p, cpu)) {
                                 next = p;
                                 break;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 83783579378f..d9062f5cc0c0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -27,6 +27,7 @@
 #include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/hash.h>
+#include <linux/rcupdate.h>
 
 #include <trace/events/sched.h>
 
@@ -84,22 +85,22 @@ ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
-#endif
-
+/*
+ * Traverse the ftrace_list, invoking all entries.  The reason that we
+ * can use rcu_dereference_raw() 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
+ * concurrent insertions into the ftrace_list.
+ *
+ * Silly Alpha and silly pointer-speculation compiler optimizations!
+ */
 static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
 {
-        struct ftrace_ops *op = ftrace_list;
-
-        /* in case someone actually ports this to alpha! */
-        read_barrier_depends();
+        struct ftrace_ops *op = rcu_dereference_raw(ftrace_list); /*see above*/
 
         while (op != &ftrace_list_end) {
-                /* silly alpha */
-                read_barrier_depends();
                 op->func(ip, parent_ip);
-                op = op->next;
+                op = rcu_dereference_raw(op->next); /*see above*/
         };
 }
 
@@ -154,8 +155,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
          * the ops->next pointer is valid before another CPU sees
          * the ops pointer included into the ftrace_list.
          */
-        smp_wmb();
-        ftrace_list = ops;
+        rcu_assign_pointer(ftrace_list, ops);
 
         if (ftrace_enabled) {
                 ftrace_func_t func;
@@ -2276,6 +2276,8 @@ __setup("ftrace_filter=", set_ftrace_filter);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
+static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
+
 static int __init set_graph_function(char *str)
 {
         strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
@@ -3351,6 +3353,7 @@ void ftrace_graph_init_task(struct task_struct *t)
 {
         /* Make sure we do not use the parent ret_stack */
         t->ret_stack = NULL;
+        t->curr_ret_stack = -1;
 
         if (ftrace_graph_active) {
                 struct ftrace_ret_stack *ret_stack;
@@ -3360,7 +3363,6 @@ void ftrace_graph_init_task(struct task_struct *t)
                                 GFP_KERNEL);
                 if (!ret_stack)
                         return;
-                t->curr_ret_stack = -1;
                 atomic_set(&t->tracing_graph_pause, 0);
                 atomic_set(&t->trace_overrun, 0);
                 t->ftrace_timestamp = 0;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a2f0fe951831..05a9f83b8819 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2233,12 +2233,12 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
         if (ring_buffer_flags != RB_BUFFERS_ON)
                 return NULL;
 
-        if (atomic_read(&buffer->record_disabled))
-                return NULL;
-
         /* If we are tracing schedule, we don't want to recurse */
         resched = ftrace_preempt_disable();
 
+        if (atomic_read(&buffer->record_disabled))
+                goto out_nocheck;
+
         if (trace_recursive_lock())
                 goto out_nocheck;
 
@@ -2470,11 +2470,11 @@ int ring_buffer_write(struct ring_buffer *buffer,
         if (ring_buffer_flags != RB_BUFFERS_ON)
                 return -EBUSY;
 
-        if (atomic_read(&buffer->record_disabled))
-                return -EBUSY;
-
         resched = ftrace_preempt_disable();
 
+        if (atomic_read(&buffer->record_disabled))
+                goto out;
+
         cpu = raw_smp_processor_id();
 
         if (!cpumask_test_cpu(cpu, buffer->cpumask))
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ed01fdba4a55..3ec2ee6f6560 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -374,6 +374,21 @@ static int __init set_buf_size(char *str)
 }
 __setup("trace_buf_size=", set_buf_size);
 
+static int __init set_tracing_thresh(char *str)
+{
+        unsigned long threshhold;
+        int ret;
+
+        if (!str)
+                return 0;
+        ret = strict_strtoul(str, 0, &threshhold);
+        if (ret < 0)
+                return 0;
+        tracing_thresh = threshhold * 1000;
+        return 1;
+}
+__setup("tracing_thresh=", set_tracing_thresh);
+
 unsigned long nsecs_to_usecs(unsigned long nsecs)
 {
         return nsecs / 1000;
@@ -579,9 +594,10 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 static arch_spinlock_t ftrace_max_lock =
         (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
+unsigned long __read_mostly     tracing_thresh;
+
 #ifdef CONFIG_TRACER_MAX_TRACE
 unsigned long __read_mostly     tracing_max_latency;
-unsigned long __read_mostly     tracing_thresh;
 
 /*
  * Copy the new maximum trace into the separate maximum-trace
@@ -592,7 +608,7 @@ static void
 __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
         struct trace_array_cpu *data = tr->data[cpu];
-        struct trace_array_cpu *max_data = tr->data[cpu];
+        struct trace_array_cpu *max_data;
 
         max_tr.cpu = cpu;
         max_tr.time_start = data->preempt_timestamp;
@@ -602,7 +618,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
         max_data->critical_start = data->critical_start;
         max_data->critical_end = data->critical_end;
 
-        memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
+        memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
         max_data->pid = tsk->pid;
         max_data->uid = task_uid(tsk);
         max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
@@ -824,10 +840,10 @@ out:
         mutex_unlock(&trace_types_lock);
 }
 
-static void __tracing_reset(struct trace_array *tr, int cpu)
+static void __tracing_reset(struct ring_buffer *buffer, int cpu)
 {
         ftrace_disable_cpu();
-        ring_buffer_reset_cpu(tr->buffer, cpu);
+        ring_buffer_reset_cpu(buffer, cpu);
         ftrace_enable_cpu();
 }
 
@@ -839,7 +855,7 @@ void tracing_reset(struct trace_array *tr, int cpu)
 
         /* Make sure all commits have finished */
         synchronize_sched();
-        __tracing_reset(tr, cpu);
+        __tracing_reset(buffer, cpu);
 
         ring_buffer_record_enable(buffer);
 }
@@ -857,7 +873,7 @@ void tracing_reset_online_cpus(struct trace_array *tr)
         tr->time_start = ftrace_now(tr->cpu);
 
         for_each_online_cpu(cpu)
-                __tracing_reset(tr, cpu);
+                __tracing_reset(buffer, cpu);
 
         ring_buffer_record_enable(buffer);
 }
@@ -934,6 +950,8 @@ void tracing_start(void)
                 goto out;
         }
 
+        /* Prevent the buffers from switching */
+        arch_spin_lock(&ftrace_max_lock);
 
         buffer = global_trace.buffer;
         if (buffer)
@@ -943,6 +961,8 @@ void tracing_start(void)
         if (buffer)
                 ring_buffer_record_enable(buffer);
 
+        arch_spin_unlock(&ftrace_max_lock);
+
         ftrace_start();
  out:
         spin_unlock_irqrestore(&tracing_start_lock, flags);
@@ -964,6 +984,9 @@ void tracing_stop(void)
         if (trace_stop_count++)
                 goto out;
 
+        /* Prevent the buffers from switching */
+        arch_spin_lock(&ftrace_max_lock);
+
         buffer = global_trace.buffer;
         if (buffer)
                 ring_buffer_record_disable(buffer);
@@ -972,6 +995,8 @@ void tracing_stop(void)
         if (buffer)
                 ring_buffer_record_disable(buffer);
 
+        arch_spin_unlock(&ftrace_max_lock);
+
  out:
         spin_unlock_irqrestore(&tracing_start_lock, flags);
 }
@@ -1259,6 +1284,13 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
         if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
                 return;
 
+        /*
+         * NMIs can not handle page faults, even with fix ups.
+         * The save user stack can (and often does) fault.
+         */
+        if (unlikely(in_nmi()))
+                return;
+
         event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
                                           sizeof(*entry), flags, pc);
         if (!event)
@@ -1703,6 +1735,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
                 ftrace_enable_cpu();
 
+                iter->leftover = 0;
                 for (p = iter; p && l < *pos; p = s_next(m, p, &l))
                         ;
 
@@ -4248,10 +4281,10 @@ static __init int tracer_init_debugfs(void)
 #ifdef CONFIG_TRACER_MAX_TRACE
         trace_create_file("tracing_max_latency", 0644, d_tracer,
                         &tracing_max_latency, &tracing_max_lat_fops);
+#endif
 
         trace_create_file("tracing_thresh", 0644, d_tracer,
                         &tracing_thresh, &tracing_max_lat_fops);
-#endif
 
         trace_create_file("README", 0444, d_tracer,
                         NULL, &tracing_readme_fops);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 09b39112a5e2..2825ef2c0b15 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -396,9 +396,10 @@ extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr);
 
 extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 
+extern unsigned long tracing_thresh;
+
 #ifdef CONFIG_TRACER_MAX_TRACE
 extern unsigned long tracing_max_latency;
-extern unsigned long tracing_thresh;
 
 void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
 void update_max_tr_single(struct trace_array *tr,
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 84a3a7ba072a..6fbfb8f417b9 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -13,6 +13,7 @@
  * Tracer plugins will chose a default from these clocks.
  */
 #include <linux/spinlock.h>
+#include <linux/irqflags.h>
 #include <linux/hardirq.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
index f0d693005075..c1cc3ab633de 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_profile.c
@@ -138,9 +138,9 @@ __kprobes void *ftrace_perf_buf_prepare(int size, unsigned short type,
         cpu = smp_processor_id();
 
         if (in_nmi())
-                trace_buf = rcu_dereference(perf_trace_buf_nmi);
+                trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
         else
-                trace_buf = rcu_dereference(perf_trace_buf);
+                trace_buf = rcu_dereference_sched(perf_trace_buf);
 
         if (!trace_buf)
                 goto err;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 3fc2a575664f..e6989d9b44da 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -237,6 +237,14 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
         return ret;
 }
 
+int trace_graph_thresh_entry(struct ftrace_graph_ent *trace)
+{
+        if (tracing_thresh)
+                return 1;
+        else
+                return trace_graph_entry(trace);
+}
+
 static void __trace_graph_return(struct trace_array *tr,
                                 struct ftrace_graph_ret *trace,
                                 unsigned long flags,
@@ -290,13 +298,26 @@ void set_graph_array(struct trace_array *tr)
         smp_mb();
 }
 
+void trace_graph_thresh_return(struct ftrace_graph_ret *trace)
+{
+        if (tracing_thresh &&
+            (trace->rettime - trace->calltime < tracing_thresh))
+                return;
+        else
+                trace_graph_return(trace);
+}
+
 static int graph_trace_init(struct trace_array *tr)
 {
         int ret;
 
         set_graph_array(tr);
-        ret = register_ftrace_graph(&trace_graph_return,
-                                    &trace_graph_entry);
+        if (tracing_thresh)
+                ret = register_ftrace_graph(&trace_graph_thresh_return,
+                                            &trace_graph_thresh_entry);
+        else
+                ret = register_ftrace_graph(&trace_graph_return,
+                                            &trace_graph_entry);
         if (ret)
                 return ret;
         tracing_start_cmdline_record();
@@ -920,7 +941,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
         } else {
-                ret = trace_seq_printf(s, "} (%ps)\n", (void *)trace->func);
+                ret = trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func);
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
         }