7 files changed, 95 insertions, 37 deletions

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 0287f9f52f5a..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))
@@ -2542,7 +2542,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable);
  * @buffer: The ring buffer to enable writes
  *
  * Note, multiple disables will need the same number of enables
- * to truely enable the writing (much like preempt_disable).
+ * to truly enable the writing (much like preempt_disable).
  */
 void ring_buffer_record_enable(struct ring_buffer *buffer)
 {
@@ -2578,7 +2578,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu);
  * @cpu: The CPU to enable.
  *
  * Note, multiple disables will need the same number of enables
- * to truely enable the writing (much like preempt_disable).
+ * to truly enable the writing (much like preempt_disable).
  */
 void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
 {
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 fd05bcaf91b0..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,
@@ -550,7 +551,7 @@ static inline int ftrace_trace_task(struct task_struct *task)
  * struct trace_parser - servers for reading the user input separated by spaces
  * @cont: set if the input is not complete - no final space char was found
  * @buffer: holds the parsed user input
- * @idx: user input lenght
+ * @idx: user input length
  * @size: buffer size
  */
 struct trace_parser {
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;
         }