1 files changed, 336 insertions, 160 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e71a8be4a6ee..496f94d57698 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -115,6 +115,9 @@ cpumask_var_t __read_mostly	tracing_buffer_mask;
 
 enum ftrace_dump_mode ftrace_dump_on_oops;
 
+/* When set, tracing will stop when a WARN*() is hit */
+int __disable_trace_on_warning;
+
 static int tracing_set_tracer(const char *buf);
 
 #define MAX_TRACER_SIZE         100
@@ -149,6 +152,13 @@ static int __init set_ftrace_dump_on_oops(char *str)
 }
 __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
 
+static int __init stop_trace_on_warning(char *str)
+{
+        __disable_trace_on_warning = 1;
+        return 1;
+}
+__setup("traceoff_on_warning=", stop_trace_on_warning);
+
 static int __init boot_alloc_snapshot(char *str)
 {
         allocate_snapshot = true;
@@ -170,6 +180,7 @@ static int __init set_trace_boot_options(char *str)
 }
 __setup("trace_options=", set_trace_boot_options);
 
+
 unsigned long long ns2usecs(cycle_t nsec)
 {
         nsec += 500;
@@ -193,6 +204,37 @@ static struct trace_array	global_trace;
 
 LIST_HEAD(ftrace_trace_arrays);
 
+int trace_array_get(struct trace_array *this_tr)
+{
+        struct trace_array *tr;
+        int ret = -ENODEV;
+
+        mutex_lock(&trace_types_lock);
+        list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+                if (tr == this_tr) {
+                        tr->ref++;
+                        ret = 0;
+                        break;
+                }
+        }
+        mutex_unlock(&trace_types_lock);
+
+        return ret;
+}
+
+static void __trace_array_put(struct trace_array *this_tr)
+{
+        WARN_ON(!this_tr->ref);
+        this_tr->ref--;
+}
+
+void trace_array_put(struct trace_array *this_tr)
+{
+        mutex_lock(&trace_types_lock);
+        __trace_array_put(this_tr);
+        mutex_unlock(&trace_types_lock);
+}
+
 int filter_current_check_discard(struct ring_buffer *buffer,
                                  struct ftrace_event_call *call, void *rec,
                                  struct ring_buffer_event *event)
@@ -201,23 +243,43 @@ int filter_current_check_discard(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(filter_current_check_discard);
 
-cycle_t ftrace_now(int cpu)
+cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
 {
         u64 ts;
 
         /* Early boot up does not have a buffer yet */
-        if (!global_trace.trace_buffer.buffer)
+        if (!buf->buffer)
                 return trace_clock_local();
 
-        ts = ring_buffer_time_stamp(global_trace.trace_buffer.buffer, cpu);
-        ring_buffer_normalize_time_stamp(global_trace.trace_buffer.buffer, cpu, &ts);
+        ts = ring_buffer_time_stamp(buf->buffer, cpu);
+        ring_buffer_normalize_time_stamp(buf->buffer, cpu, &ts);
 
         return ts;
 }
 
+cycle_t ftrace_now(int cpu)
+{
+        return buffer_ftrace_now(&global_trace.trace_buffer, cpu);
+}
+
+/**
+ * tracing_is_enabled - Show if global_trace has been disabled
+ *
+ * Shows if the global trace has been enabled or not. It uses the
+ * mirror flag "buffer_disabled" to be used in fast paths such as for
+ * the irqsoff tracer. But it may be inaccurate due to races. If you
+ * need to know the accurate state, use tracing_is_on() which is a little
+ * slower, but accurate.
+ */
 int tracing_is_enabled(void)
 {
-        return tracing_is_on();
+        /*
+         * For quick access (irqsoff uses this in fast path), just
+         * return the mirror variable of the state of the ring buffer.
+         * It's a little racy, but we don't really care.
+         */
+        smp_rmb();
+        return !global_trace.buffer_disabled;
 }
 
 /*
@@ -240,7 +302,7 @@ static struct tracer		*trace_types __read_mostly;
 /*
  * trace_types_lock is used to protect the trace_types list.
  */
-static DEFINE_MUTEX(trace_types_lock);
+DEFINE_MUTEX(trace_types_lock);
 
 /*
  * serialize the access of the ring buffer
@@ -330,6 +392,23 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
         TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |
         TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS | TRACE_ITER_FUNCTION;
 
+static void tracer_tracing_on(struct trace_array *tr)
+{
+        if (tr->trace_buffer.buffer)
+                ring_buffer_record_on(tr->trace_buffer.buffer);
+        /*
+         * This flag is looked at when buffers haven't been allocated
+         * yet, or by some tracers (like irqsoff), that just want to
+         * know if the ring buffer has been disabled, but it can handle
+         * races of where it gets disabled but we still do a record.
+         * As the check is in the fast path of the tracers, it is more
+         * important to be fast than accurate.
+         */
+        tr->buffer_disabled = 0;
+        /* Make the flag seen by readers */
+        smp_wmb();
+}
+
 /**
  * tracing_on - enable tracing buffers
  *
@@ -338,15 +417,7 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
  */
 void tracing_on(void)
 {
-        if (global_trace.trace_buffer.buffer)
-                ring_buffer_record_on(global_trace.trace_buffer.buffer);
-        /*
-         * This flag is only looked at when buffers haven't been
-         * allocated yet. We don't really care about the race
-         * between setting this flag and actually turning
-         * on the buffer.
-         */
-        global_trace.buffer_disabled = 0;
+        tracer_tracing_on(&global_trace);
 }
 EXPORT_SYMBOL_GPL(tracing_on);
 
@@ -540,6 +611,23 @@ void tracing_snapshot_alloc(void)
 EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);
 #endif /* CONFIG_TRACER_SNAPSHOT */
 
+static void tracer_tracing_off(struct trace_array *tr)
+{
+        if (tr->trace_buffer.buffer)
+                ring_buffer_record_off(tr->trace_buffer.buffer);
+        /*
+         * This flag is looked at when buffers haven't been allocated
+         * yet, or by some tracers (like irqsoff), that just want to
+         * know if the ring buffer has been disabled, but it can handle
+         * races of where it gets disabled but we still do a record.
+         * As the check is in the fast path of the tracers, it is more
+         * important to be fast than accurate.
+         */
+        tr->buffer_disabled = 1;
+        /* Make the flag seen by readers */
+        smp_wmb();
+}
+
 /**
  * tracing_off - turn off tracing buffers
  *
@@ -550,26 +638,35 @@ EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);
  */
 void tracing_off(void)
 {
-        if (global_trace.trace_buffer.buffer)
-                ring_buffer_record_off(global_trace.trace_buffer.buffer);
-        /*
-         * This flag is only looked at when buffers haven't been
-         * allocated yet. We don't really care about the race
-         * between setting this flag and actually turning
-         * on the buffer.
-         */
-        global_trace.buffer_disabled = 1;
+        tracer_tracing_off(&global_trace);
 }
 EXPORT_SYMBOL_GPL(tracing_off);
 
+void disable_trace_on_warning(void)
+{
+        if (__disable_trace_on_warning)
+                tracing_off();
+}
+
+/**
+ * tracer_tracing_is_on - show real state of ring buffer enabled
+ * @tr : the trace array to know if ring buffer is enabled
+ *
+ * Shows real state of the ring buffer if it is enabled or not.
+ */
+static int tracer_tracing_is_on(struct trace_array *tr)
+{
+        if (tr->trace_buffer.buffer)
+                return ring_buffer_record_is_on(tr->trace_buffer.buffer);
+        return !tr->buffer_disabled;
+}
+
 /**
  * tracing_is_on - show state of ring buffers enabled
  */
 int tracing_is_on(void)
 {
-        if (global_trace.trace_buffer.buffer)
-                return ring_buffer_record_is_on(global_trace.trace_buffer.buffer);
-        return !global_trace.buffer_disabled;
+        return tracer_tracing_is_on(&global_trace);
 }
 EXPORT_SYMBOL_GPL(tracing_is_on);
 
@@ -1119,7 +1216,7 @@ void tracing_reset_online_cpus(struct trace_buffer *buf)
         /* Make sure all commits have finished */
         synchronize_sched();
 
-        buf->time_start = ftrace_now(buf->cpu);
+        buf->time_start = buffer_ftrace_now(buf, buf->cpu);
 
         for_each_online_cpu(cpu)
                 ring_buffer_reset_cpu(buffer, cpu);
@@ -1127,23 +1224,17 @@ void tracing_reset_online_cpus(struct trace_buffer *buf)
         ring_buffer_record_enable(buffer);
 }
 
-void tracing_reset_current(int cpu)
-{
-        tracing_reset(&global_trace.trace_buffer, cpu);
-}
-
+/* Must have trace_types_lock held */
 void tracing_reset_all_online_cpus(void)
 {
         struct trace_array *tr;
 
-        mutex_lock(&trace_types_lock);
         list_for_each_entry(tr, &ftrace_trace_arrays, list) {
                 tracing_reset_online_cpus(&tr->trace_buffer);
 #ifdef CONFIG_TRACER_MAX_TRACE
                 tracing_reset_online_cpus(&tr->max_buffer);
 #endif
         }
-        mutex_unlock(&trace_types_lock);
 }
 
 #define SAVED_CMDLINES 128
@@ -1543,15 +1634,6 @@ trace_function(struct trace_array *tr,
                 __buffer_unlock_commit(buffer, event);
 }
 
-void
-ftrace(struct trace_array *tr, struct trace_array_cpu *data,
-       unsigned long ip, unsigned long parent_ip, unsigned long flags,
-       int pc)
-{
-        if (likely(!atomic_read(&data->disabled)))
-                trace_function(tr, ip, parent_ip, flags, pc);
-}
-
 #ifdef CONFIG_STACKTRACE
 
 #define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long))
@@ -2760,6 +2842,17 @@ static int s_show(struct seq_file *m, void *v)
         return 0;
 }
 
+/*
+ * Should be used after trace_array_get(), trace_types_lock
+ * ensures that i_cdev was already initialized.
+ */
+static inline int tracing_get_cpu(struct inode *inode)
+{
+        if (inode->i_cdev) /* See trace_create_cpu_file() */
+                return (long)inode->i_cdev - 1;
+        return RING_BUFFER_ALL_CPUS;
+}
+
 static const struct seq_operations tracer_seq_ops = {
         .start          = s_start,
         .next           = s_next,
@@ -2770,8 +2863,7 @@ static const struct seq_operations tracer_seq_ops = {
 static struct trace_iterator *
 __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 {
-        struct trace_cpu *tc = inode->i_private;
-        struct trace_array *tr = tc->tr;
+        struct trace_array *tr = inode->i_private;
         struct trace_iterator *iter;
         int cpu;
 
@@ -2812,8 +2904,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
                 iter->trace_buffer = &tr->trace_buffer;
         iter->snapshot = snapshot;
         iter->pos = -1;
+        iter->cpu_file = tracing_get_cpu(inode);
         mutex_init(&iter->mutex);
-        iter->cpu_file = tc->cpu;
 
         /* Notify the tracer early; before we stop tracing. */
         if (iter->trace && iter->trace->open)
@@ -2850,8 +2942,6 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
                 tracing_iter_reset(iter, cpu);
         }
 
-        tr->ref++;
-
         mutex_unlock(&trace_types_lock);
 
         return iter;
@@ -2874,24 +2964,41 @@ int tracing_open_generic(struct inode *inode, struct file *filp)
         return 0;
 }
 
+/*
+ * Open and update trace_array ref count.
+ * Must have the current trace_array passed to it.
+ */
+static int tracing_open_generic_tr(struct inode *inode, struct file *filp)
+{
+        struct trace_array *tr = inode->i_private;
+
+        if (tracing_disabled)
+                return -ENODEV;
+
+        if (trace_array_get(tr) < 0)
+                return -ENODEV;
+
+        filp->private_data = inode->i_private;
+
+        return 0;
+}
+
 static int tracing_release(struct inode *inode, struct file *file)
 {
+        struct trace_array *tr = inode->i_private;
         struct seq_file *m = file->private_data;
         struct trace_iterator *iter;
-        struct trace_array *tr;
         int cpu;
 
-        if (!(file->f_mode & FMODE_READ))
+        if (!(file->f_mode & FMODE_READ)) {
+                trace_array_put(tr);
                 return 0;
+        }
 
+        /* Writes do not use seq_file */
         iter = m->private;
-        tr = iter->tr;
-
         mutex_lock(&trace_types_lock);
 
-        WARN_ON(!tr->ref);
-        tr->ref--;
-
         for_each_tracing_cpu(cpu) {
                 if (iter->buffer_iter[cpu])
                         ring_buffer_read_finish(iter->buffer_iter[cpu]);
@@ -2903,6 +3010,9 @@ static int tracing_release(struct inode *inode, struct file *file)
         if (!iter->snapshot)
                 /* reenable tracing if it was previously enabled */
                 tracing_start_tr(tr);
+
+        __trace_array_put(tr);
+
         mutex_unlock(&trace_types_lock);
 
         mutex_destroy(&iter->mutex);
@@ -2910,24 +3020,44 @@ static int tracing_release(struct inode *inode, struct file *file)
         kfree(iter->trace);
         kfree(iter->buffer_iter);
         seq_release_private(inode, file);
+
+        return 0;
+}
+
+static int tracing_release_generic_tr(struct inode *inode, struct file *file)
+{
+        struct trace_array *tr = inode->i_private;
+
+        trace_array_put(tr);
         return 0;
 }
 
+static int tracing_single_release_tr(struct inode *inode, struct file *file)
+{
+        struct trace_array *tr = inode->i_private;
+
+        trace_array_put(tr);
+
+        return single_release(inode, file);
+}
+
 static int tracing_open(struct inode *inode, struct file *file)
 {
+        struct trace_array *tr = inode->i_private;
         struct trace_iterator *iter;
         int ret = 0;
 
+        if (trace_array_get(tr) < 0)
+                return -ENODEV;
+
         /* If this file was open for write, then erase contents */
-        if ((file->f_mode & FMODE_WRITE) &&
-            (file->f_flags & O_TRUNC)) {
-                struct trace_cpu *tc = inode->i_private;
-                struct trace_array *tr = tc->tr;
+        if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
+                int cpu = tracing_get_cpu(inode);
 
-                if (tc->cpu == RING_BUFFER_ALL_CPUS)
+                if (cpu == RING_BUFFER_ALL_CPUS)
                         tracing_reset_online_cpus(&tr->trace_buffer);
                 else
-                        tracing_reset(&tr->trace_buffer, tc->cpu);
+                        tracing_reset(&tr->trace_buffer, cpu);
         }
 
         if (file->f_mode & FMODE_READ) {
@@ -2937,6 +3067,10 @@ static int tracing_open(struct inode *inode, struct file *file)
                 else if (trace_flags & TRACE_ITER_LATENCY_FMT)
                         iter->iter_flags |= TRACE_FILE_LAT_FMT;
         }
+
+        if (ret < 0)
+                trace_array_put(tr);
+
         return ret;
 }
 
@@ -3293,17 +3427,27 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 
 static int tracing_trace_options_open(struct inode *inode, struct file *file)
 {
+        struct trace_array *tr = inode->i_private;
+        int ret;
+
         if (tracing_disabled)
                 return -ENODEV;
 
-        return single_open(file, tracing_trace_options_show, inode->i_private);
+        if (trace_array_get(tr) < 0)
+                return -ENODEV;
+
+        ret = single_open(file, tracing_trace_options_show, inode->i_private);
+        if (ret < 0)
+                trace_array_put(tr);
+
+        return ret;
 }
 
 static const struct file_operations tracing_iter_fops = {
         .open           = tracing_trace_options_open,
         .read           = seq_read,
         .llseek         = seq_lseek,
-        .release        = single_release,
+        .release        = tracing_single_release_tr,
         .write          = tracing_trace_options_write,
 };
 
@@ -3379,14 +3523,14 @@ static const char readme_msg[] =
         "\n  snapshot\t\t- Like 'trace' but shows the content of the static snapshot buffer\n"
         "\t\t\t  Read the contents for more information\n"
 #endif
-#ifdef CONFIG_STACKTRACE
+#ifdef CONFIG_STACK_TRACER
         "  stack_trace\t\t- Shows the max stack trace when active\n"
         "  stack_max_size\t- Shows current max stack size that was traced\n"
         "\t\t\t  Write into this file to reset the max size (trigger a new trace)\n"
 #ifdef CONFIG_DYNAMIC_FTRACE
         "  stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace traces\n"
 #endif
-#endif /* CONFIG_STACKTRACE */
+#endif /* CONFIG_STACK_TRACER */
 ;
 
 static ssize_t
@@ -3783,20 +3927,23 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
 
 static int tracing_open_pipe(struct inode *inode, struct file *filp)
 {
-        struct trace_cpu *tc = inode->i_private;
-        struct trace_array *tr = tc->tr;
+        struct trace_array *tr = inode->i_private;
         struct trace_iterator *iter;
         int ret = 0;
 
         if (tracing_disabled)
                 return -ENODEV;
 
+        if (trace_array_get(tr) < 0)
+                return -ENODEV;
+
         mutex_lock(&trace_types_lock);
 
         /* create a buffer to store the information to pass to userspace */
         iter = kzalloc(sizeof(*iter), GFP_KERNEL);
         if (!iter) {
                 ret = -ENOMEM;
+                __trace_array_put(tr);
                 goto out;
         }
 
@@ -3826,9 +3973,9 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
         if (trace_clocks[tr->clock_id].in_ns)
                 iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
 
-        iter->cpu_file = tc->cpu;
-        iter->tr = tc->tr;
-        iter->trace_buffer = &tc->tr->trace_buffer;
+        iter->tr = tr;
+        iter->trace_buffer = &tr->trace_buffer;
+        iter->cpu_file = tracing_get_cpu(inode);
         mutex_init(&iter->mutex);
         filp->private_data = iter;
 
@@ -3843,6 +3990,7 @@ out:
 fail:
         kfree(iter->trace);
         kfree(iter);
+        __trace_array_put(tr);
         mutex_unlock(&trace_types_lock);
         return ret;
 }
@@ -3850,6 +3998,7 @@ fail:
 static int tracing_release_pipe(struct inode *inode, struct file *file)
 {
         struct trace_iterator *iter = file->private_data;
+        struct trace_array *tr = inode->i_private;
 
         mutex_lock(&trace_types_lock);
 
@@ -3863,6 +4012,8 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
         kfree(iter->trace);
         kfree(iter);
 
+        trace_array_put(tr);
+
         return 0;
 }
 
@@ -3939,7 +4090,7 @@ static int tracing_wait_pipe(struct file *filp)
                  *
                  * iter->pos will be 0 if we haven't read anything.
                  */
-                if (!tracing_is_enabled() && iter->pos)
+                if (!tracing_is_on() && iter->pos)
                         break;
         }
 
@@ -4000,6 +4151,7 @@ waitagain:
         memset(&iter->seq, 0,
                sizeof(struct trace_iterator) -
                offsetof(struct trace_iterator, seq));
+        cpumask_clear(iter->started);
         iter->pos = -1;
 
         trace_event_read_lock();
@@ -4200,15 +4352,16 @@ static ssize_t
 tracing_entries_read(struct file *filp, char __user *ubuf,
                      size_t cnt, loff_t *ppos)
 {
-        struct trace_cpu *tc = filp->private_data;
-        struct trace_array *tr = tc->tr;
+        struct inode *inode = file_inode(filp);
+        struct trace_array *tr = inode->i_private;
+        int cpu = tracing_get_cpu(inode);
         char buf[64];
         int r = 0;
         ssize_t ret;
 
         mutex_lock(&trace_types_lock);
 
-        if (tc->cpu == RING_BUFFER_ALL_CPUS) {
+        if (cpu == RING_BUFFER_ALL_CPUS) {
                 int cpu, buf_size_same;
                 unsigned long size;
 
@@ -4235,7 +4388,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf,
                 } else
                         r = sprintf(buf, "X\n");
         } else
-                r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, tc->cpu)->entries >> 10);
+                r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10);
 
         mutex_unlock(&trace_types_lock);
 
@@ -4247,7 +4400,8 @@ static ssize_t
 tracing_entries_write(struct file *filp, const char __user *ubuf,
                       size_t cnt, loff_t *ppos)
 {
-        struct trace_cpu *tc = filp->private_data;
+        struct inode *inode = file_inode(filp);
+        struct trace_array *tr = inode->i_private;
         unsigned long val;
         int ret;
 
@@ -4261,8 +4415,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 
         /* value is in KB */
         val <<= 10;
-
-        ret = tracing_resize_ring_buffer(tc->tr, val, tc->cpu);
+        ret = tracing_resize_ring_buffer(tr, val, tracing_get_cpu(inode));
         if (ret < 0)
                 return ret;
 
@@ -4316,10 +4469,12 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp)
 
         /* disable tracing ? */
         if (trace_flags & TRACE_ITER_STOP_ON_FREE)
-                tracing_off();
+                tracer_tracing_off(tr);
         /* resize the ring buffer to 0 */
         tracing_resize_ring_buffer(tr, 0, RING_BUFFER_ALL_CPUS);
 
+        trace_array_put(tr);
+
         return 0;
 }
 
@@ -4328,6 +4483,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
                                         size_t cnt, loff_t *fpos)
 {
         unsigned long addr = (unsigned long)ubuf;
+        struct trace_array *tr = filp->private_data;
         struct ring_buffer_event *event;
         struct ring_buffer *buffer;
         struct print_entry *entry;
@@ -4387,7 +4543,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 
         local_save_flags(irq_flags);
         size = sizeof(*entry) + cnt + 2; /* possible \n added */
-        buffer = global_trace.trace_buffer.buffer;
+        buffer = tr->trace_buffer.buffer;
         event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
                                           irq_flags, preempt_count());
         if (!event) {
@@ -4478,12 +4634,12 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
          * New clock may not be consistent with the previous clock.
          * Reset the buffer so that it doesn't have incomparable timestamps.
          */
-        tracing_reset_online_cpus(&global_trace.trace_buffer);
+        tracing_reset_online_cpus(&tr->trace_buffer);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
         if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer)
                 ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func);
-        tracing_reset_online_cpus(&global_trace.max_buffer);
+        tracing_reset_online_cpus(&tr->max_buffer);
 #endif
 
         mutex_unlock(&trace_types_lock);
@@ -4495,10 +4651,20 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
 
 static int tracing_clock_open(struct inode *inode, struct file *file)
 {
+        struct trace_array *tr = inode->i_private;
+        int ret;
+
         if (tracing_disabled)
                 return -ENODEV;
 
-        return single_open(file, tracing_clock_show, inode->i_private);
+        if (trace_array_get(tr))
+                return -ENODEV;
+
+        ret = single_open(file, tracing_clock_show, inode->i_private);
+        if (ret < 0)
+                trace_array_put(tr);
+
+        return ret;
 }
 
 struct ftrace_buffer_info {
@@ -4510,31 +4676,40 @@ struct ftrace_buffer_info {
 #ifdef CONFIG_TRACER_SNAPSHOT
 static int tracing_snapshot_open(struct inode *inode, struct file *file)
 {
-        struct trace_cpu *tc = inode->i_private;
+        struct trace_array *tr = inode->i_private;
         struct trace_iterator *iter;
         struct seq_file *m;
         int ret = 0;
 
+        if (trace_array_get(tr) < 0)
+                return -ENODEV;
+
         if (file->f_mode & FMODE_READ) {
                 iter = __tracing_open(inode, file, true);
                 if (IS_ERR(iter))
                         ret = PTR_ERR(iter);
         } else {
                 /* Writes still need the seq_file to hold the private data */
+                ret = -ENOMEM;
                 m = kzalloc(sizeof(*m), GFP_KERNEL);
                 if (!m)
-                        return -ENOMEM;
+                        goto out;
                 iter = kzalloc(sizeof(*iter), GFP_KERNEL);
                 if (!iter) {
                         kfree(m);
-                        return -ENOMEM;
+                        goto out;
                 }
-                iter->tr = tc->tr;
-                iter->trace_buffer = &tc->tr->max_buffer;
-                iter->cpu_file = tc->cpu;
+                ret = 0;
+
+                iter->tr = tr;
+                iter->trace_buffer = &tr->max_buffer;
+                iter->cpu_file = tracing_get_cpu(inode);
                 m->private = iter;
                 file->private_data = m;
         }
+out:
+        if (ret < 0)
+                trace_array_put(tr);
 
         return ret;
 }
@@ -4616,9 +4791,12 @@ out:
 static int tracing_snapshot_release(struct inode *inode, struct file *file)
 {
         struct seq_file *m = file->private_data;
+        int ret;
+
+        ret = tracing_release(inode, file);
 
         if (file->f_mode & FMODE_READ)
-                return tracing_release(inode, file);
+                return ret;
 
         /* If write only, the seq_file is just a stub */
         if (m)
@@ -4684,34 +4862,38 @@ static const struct file_operations tracing_pipe_fops = {
 };
 
 static const struct file_operations tracing_entries_fops = {
-        .open           = tracing_open_generic,
+        .open           = tracing_open_generic_tr,
         .read           = tracing_entries_read,
         .write          = tracing_entries_write,
         .llseek         = generic_file_llseek,
+        .release        = tracing_release_generic_tr,
 };
 
 static const struct file_operations tracing_total_entries_fops = {
-        .open           = tracing_open_generic,
+        .open           = tracing_open_generic_tr,
         .read           = tracing_total_entries_read,
         .llseek         = generic_file_llseek,
+        .release        = tracing_release_generic_tr,
 };
 
 static const struct file_operations tracing_free_buffer_fops = {
+        .open           = tracing_open_generic_tr,
         .write          = tracing_free_buffer_write,
         .release        = tracing_free_buffer_release,
 };
 
 static const struct file_operations tracing_mark_fops = {
-        .open           = tracing_open_generic,
+        .open           = tracing_open_generic_tr,
         .write          = tracing_mark_write,
         .llseek         = generic_file_llseek,
+        .release        = tracing_release_generic_tr,
 };
 
 static const struct file_operations trace_clock_fops = {
         .open           = tracing_clock_open,
         .read           = seq_read,
         .llseek         = seq_lseek,
-        .release        = single_release,
+        .release        = tracing_single_release_tr,
         .write          = tracing_clock_write,
 };
 
@@ -4736,23 +4918,26 @@ static const struct file_operations snapshot_raw_fops = {
 
 static int tracing_buffers_open(struct inode *inode, struct file *filp)
 {
-        struct trace_cpu *tc = inode->i_private;
-        struct trace_array *tr = tc->tr;
+        struct trace_array *tr = inode->i_private;
         struct ftrace_buffer_info *info;
+        int ret;
 
         if (tracing_disabled)
                 return -ENODEV;
 
+        if (trace_array_get(tr) < 0)
+                return -ENODEV;
+
         info = kzalloc(sizeof(*info), GFP_KERNEL);
-        if (!info)
+        if (!info) {
+                trace_array_put(tr);
                 return -ENOMEM;
+        }
 
         mutex_lock(&trace_types_lock);
 
-        tr->ref++;
-
         info->iter.tr           = tr;
-        info->iter.cpu_file     = tc->cpu;
+        info->iter.cpu_file     = tracing_get_cpu(inode);
         info->iter.trace        = tr->current_trace;
         info->iter.trace_buffer = &tr->trace_buffer;
         info->spare             = NULL;
@@ -4763,7 +4948,11 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 
         mutex_unlock(&trace_types_lock);
 
-        return nonseekable_open(inode, filp);
+        ret = nonseekable_open(inode, filp);
+        if (ret < 0)
+                trace_array_put(tr);
+
+        return ret;
 }
 
 static unsigned int
@@ -4863,8 +5052,7 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 
         mutex_lock(&trace_types_lock);
 
-        WARN_ON(!iter->tr->ref);
-        iter->tr->ref--;
+        __trace_array_put(iter->tr);
 
         if (info->spare)
                 ring_buffer_free_read_page(iter->trace_buffer->buffer, info->spare);
@@ -5066,14 +5254,14 @@ static ssize_t
 tracing_stats_read(struct file *filp, char __user *ubuf,
                    size_t count, loff_t *ppos)
 {
-        struct trace_cpu *tc = filp->private_data;
-        struct trace_array *tr = tc->tr;
+        struct inode *inode = file_inode(filp);
+        struct trace_array *tr = inode->i_private;
         struct trace_buffer *trace_buf = &tr->trace_buffer;
+        int cpu = tracing_get_cpu(inode);
         struct trace_seq *s;
         unsigned long cnt;
         unsigned long long t;
         unsigned long usec_rem;
-        int cpu = tc->cpu;
 
         s = kmalloc(sizeof(*s), GFP_KERNEL);
         if (!s)
@@ -5126,9 +5314,10 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 }
 
 static const struct file_operations tracing_stats_fops = {
-        .open           = tracing_open_generic,
+        .open           = tracing_open_generic_tr,
         .read           = tracing_stats_read,
         .llseek         = generic_file_llseek,
+        .release        = tracing_release_generic_tr,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -5317,10 +5506,20 @@ static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu)
         return tr->percpu_dir;
 }
 
+static struct dentry *
+trace_create_cpu_file(const char *name, umode_t mode, struct dentry *parent,
+                      void *data, long cpu, const struct file_operations *fops)
+{
+        struct dentry *ret = trace_create_file(name, mode, parent, data, fops);
+
+        if (ret) /* See tracing_get_cpu() */
+                ret->d_inode->i_cdev = (void *)(cpu + 1);
+        return ret;
+}
+
 static void
 tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 {
-        struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, cpu);
         struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu);
         struct dentry *d_cpu;
         char cpu_dir[30]; /* 30 characters should be more than enough */
@@ -5336,28 +5535,28 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
         }
 
         /* per cpu trace_pipe */
-        trace_create_file("trace_pipe", 0444, d_cpu,
-                        (void *)&data->trace_cpu, &tracing_pipe_fops);
+        trace_create_cpu_file("trace_pipe", 0444, d_cpu,
+                                tr, cpu, &tracing_pipe_fops);
 
         /* per cpu trace */
-        trace_create_file("trace", 0644, d_cpu,
-                        (void *)&data->trace_cpu, &tracing_fops);
+        trace_create_cpu_file("trace", 0644, d_cpu,
+                                tr, cpu, &tracing_fops);
 
-        trace_create_file("trace_pipe_raw", 0444, d_cpu,
-                        (void *)&data->trace_cpu, &tracing_buffers_fops);
+        trace_create_cpu_file("trace_pipe_raw", 0444, d_cpu,
+                                tr, cpu, &tracing_buffers_fops);
 
-        trace_create_file("stats", 0444, d_cpu,
-                        (void *)&data->trace_cpu, &tracing_stats_fops);
+        trace_create_cpu_file("stats", 0444, d_cpu,
+                                tr, cpu, &tracing_stats_fops);
 
-        trace_create_file("buffer_size_kb", 0444, d_cpu,
-                        (void *)&data->trace_cpu, &tracing_entries_fops);
+        trace_create_cpu_file("buffer_size_kb", 0444, d_cpu,
+                                tr, cpu, &tracing_entries_fops);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-        trace_create_file("snapshot", 0644, d_cpu,
-                          (void *)&data->trace_cpu, &snapshot_fops);
+        trace_create_cpu_file("snapshot", 0644, d_cpu,
+                                tr, cpu, &snapshot_fops);
 
-        trace_create_file("snapshot_raw", 0444, d_cpu,
-                        (void *)&data->trace_cpu, &snapshot_raw_fops);
+        trace_create_cpu_file("snapshot_raw", 0444, d_cpu,
+                                tr, cpu, &snapshot_raw_fops);
 #endif
 }
 
@@ -5612,15 +5811,10 @@ rb_simple_read(struct file *filp, char __user *ubuf,
                size_t cnt, loff_t *ppos)
 {
         struct trace_array *tr = filp->private_data;
-        struct ring_buffer *buffer = tr->trace_buffer.buffer;
         char buf[64];
         int r;
 
-        if (buffer)
-                r = ring_buffer_record_is_on(buffer);
-        else
-                r = 0;
-
+        r = tracer_tracing_is_on(tr);
         r = sprintf(buf, "%d\n", r);
 
         return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
@@ -5642,11 +5836,11 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
         if (buffer) {
                 mutex_lock(&trace_types_lock);
                 if (val) {
-                        ring_buffer_record_on(buffer);
+                        tracer_tracing_on(tr);
                         if (tr->current_trace->start)
                                 tr->current_trace->start(tr);
                 } else {
-                        ring_buffer_record_off(buffer);
+                        tracer_tracing_off(tr);
                         if (tr->current_trace->stop)
                                 tr->current_trace->stop(tr);
                 }
@@ -5659,9 +5853,10 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
 }
 
 static const struct file_operations rb_simple_fops = {
-        .open           = tracing_open_generic,
+        .open           = tracing_open_generic_tr,
         .read           = rb_simple_read,
         .write          = rb_simple_write,
+        .release        = tracing_release_generic_tr,
         .llseek         = default_llseek,
 };
 
@@ -5670,17 +5865,6 @@ struct dentry *trace_instance_dir;
 static void
 init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer);
 
-static void init_trace_buffers(struct trace_array *tr, struct trace_buffer *buf)
-{
-        int cpu;
-
-        for_each_tracing_cpu(cpu) {
-                memset(per_cpu_ptr(buf->data, cpu), 0, sizeof(struct trace_array_cpu));
-                per_cpu_ptr(buf->data, cpu)->trace_cpu.cpu = cpu;
-                per_cpu_ptr(buf->data, cpu)->trace_cpu.tr = tr;
-        }
-}
-
 static int
 allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size)
 {
@@ -5698,8 +5882,6 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
                 return -ENOMEM;
         }
 
-        init_trace_buffers(tr, buf);
-
         /* Allocate the first page for all buffers */
         set_buffer_entries(&tr->trace_buffer,
                            ring_buffer_size(tr->trace_buffer.buffer, 0));
@@ -5766,17 +5948,15 @@ static int new_instance_create(const char *name)
         if (allocate_trace_buffers(tr, trace_buf_size) < 0)
                 goto out_free_tr;
 
-        /* Holder for file callbacks */
-        tr->trace_cpu.cpu = RING_BUFFER_ALL_CPUS;
-        tr->trace_cpu.tr = tr;
-
         tr->dir = debugfs_create_dir(name, trace_instance_dir);
         if (!tr->dir)
                 goto out_free_tr;
 
         ret = event_trace_add_tracer(tr->dir, tr);
-        if (ret)
+        if (ret) {
+                debugfs_remove_recursive(tr->dir);
                 goto out_free_tr;
+        }
 
         init_tracer_debugfs(tr, tr->dir);
 
@@ -5922,18 +6102,18 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
                           tr, &tracing_iter_fops);
 
         trace_create_file("trace", 0644, d_tracer,
-                        (void *)&tr->trace_cpu, &tracing_fops);
+                          tr, &tracing_fops);
 
         trace_create_file("trace_pipe", 0444, d_tracer,
-                        (void *)&tr->trace_cpu, &tracing_pipe_fops);
+                          tr, &tracing_pipe_fops);
 
         trace_create_file("buffer_size_kb", 0644, d_tracer,
-                        (void *)&tr->trace_cpu, &tracing_entries_fops);
+                          tr, &tracing_entries_fops);
 
         trace_create_file("buffer_total_size_kb", 0444, d_tracer,
                           tr, &tracing_total_entries_fops);
 
-        trace_create_file("free_buffer", 0644, d_tracer,
+        trace_create_file("free_buffer", 0200, d_tracer,
                           tr, &tracing_free_buffer_fops);
 
         trace_create_file("trace_marker", 0220, d_tracer,
@@ -5943,11 +6123,11 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
                           &trace_clock_fops);
 
         trace_create_file("tracing_on", 0644, d_tracer,
-                            tr, &rb_simple_fops);
+                          tr, &rb_simple_fops);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
         trace_create_file("snapshot", 0644, d_tracer,
-                          (void *)&tr->trace_cpu, &snapshot_fops);
+                          tr, &snapshot_fops);
 #endif
 
         for_each_tracing_cpu(cpu)
@@ -6241,10 +6421,6 @@ __init static int tracer_alloc_buffers(void)
 
         global_trace.flags = TRACE_ARRAY_FL_GLOBAL;
 
-        /* Holder for file callbacks */
-        global_trace.trace_cpu.cpu = RING_BUFFER_ALL_CPUS;
-        global_trace.trace_cpu.tr = &global_trace;
-
         INIT_LIST_HEAD(&global_trace.systems);
         INIT_LIST_HEAD(&global_trace.events);
         list_add(&global_trace.list, &ftrace_trace_arrays);