Merge tag 'trace-v3.20' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "The updates included in this pull request for ftrace are:

   o Several clean ups to the code

     One such clean up was to convert to 64 bit time keeping, in the
     ring buffer benchmark code.

   o Adding of __print_array() helper macro for TRACE_EVENT()

   o Updating the sample/trace_events/ to add samples of different ways
     to make trace events.  Lots of features have been added since the
     sample code was made, and these features are mostly unknown.
     Developers have been making their own hacks to do things that are
     already available.

   o Performance improvements.  Most notably, I found a performance bug
     where a waiter that is waiting for a full page from the ring buffer
     will see that a full page is not available, and go to sleep.  The
     sched event caused by it going to sleep would cause it to wake up
     again.  It would see that there was still not a full page, and go
     back to sleep again, and that would wake it up again, until finally
     it would see a full page.  This change has been marked for stable.

  Other improvements include removing global locks from fast paths"

* tag 'trace-v3.20' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
  ring-buffer: Do not wake up a splice waiter when page is not full
  tracing: Fix unmapping loop in tracing_mark_write
  tracing: Add samples of DECLARE_EVENT_CLASS() and DEFINE_EVENT()
  tracing: Add TRACE_EVENT_FN example
  tracing: Add TRACE_EVENT_CONDITION sample
  tracing: Update the TRACE_EVENT fields available in the sample code
  tracing: Separate out initializing top level dir from instances
  tracing: Make tracing_init_dentry_tr() static
  trace: Use 64-bit timekeeping
  tracing: Add array printing helper
  tracing: Remove newline from trace_printk warning banner
  tracing: Use IS_ERR() check for return value of tracing_init_dentry()
  tracing: Remove unneeded includes of debugfs.h and fs.h
  tracing: Remove taking of trace_types_lock in pipe files
  tracing: Add ref count to tracer for when they are being read by pipe

1 files changed, 79 insertions, 109 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4a9079b..77b8dc5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2036,7 +2036,8 @@ void trace_printk_init_buffers(void)
 
 	/* trace_printk() is for debug use only. Don't use it in production. */
 
-	pr_warning("\n**********************************************************\n");
+	pr_warning("\n");
+	pr_warning("**********************************************************\n");
 	pr_warning("**   NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE   **\n");
 	pr_warning("**                                                      **\n");
 	pr_warning("** trace_printk() being used. Allocating extra memory.  **\n");
@@ -4140,6 +4141,12 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf)
 		goto out;
 	}
 
+	/* If trace pipe files are being read, we can't change the tracer */
+	if (tr->current_trace->ref) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	trace_branch_disable();
 
 	tr->current_trace->enabled--;
@@ -4326,17 +4333,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	}
 
 	trace_seq_init(&iter->seq);
-
-	/*
-	 * We make a copy of the current tracer to avoid concurrent
-	 * changes on it while we are reading.
-	 */
-	iter->trace = kmalloc(sizeof(*iter->trace), GFP_KERNEL);
-	if (!iter->trace) {
-		ret = -ENOMEM;
-		goto fail;
-	}
-	*iter->trace = *tr->current_trace;
+	iter->trace = tr->current_trace;
 
 	if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) {
 		ret = -ENOMEM;
@@ -4363,6 +4360,8 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 		iter->trace->pipe_open(iter);
 
 	nonseekable_open(inode, filp);
+
+	tr->current_trace->ref++;
 out:
 	mutex_unlock(&trace_types_lock);
 	return ret;
@@ -4382,6 +4381,8 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 
 	mutex_lock(&trace_types_lock);
 
+	tr->current_trace->ref--;
+
 	if (iter->trace->pipe_close)
 		iter->trace->pipe_close(iter);
 
@@ -4389,7 +4390,6 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 
 	free_cpumask_var(iter->started);
 	mutex_destroy(&iter->mutex);
-	kfree(iter->trace);
 	kfree(iter);
 
 	trace_array_put(tr);
@@ -4422,7 +4422,7 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table)
 	return trace_poll(iter, filp, poll_table);
 }
 
-/* Must be called with trace_types_lock mutex held. */
+/* Must be called with iter->mutex held. */
 static int tracing_wait_pipe(struct file *filp)
 {
 	struct trace_iterator *iter = filp->private_data;
@@ -4467,7 +4467,6 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 		  size_t cnt, loff_t *ppos)
 {
 	struct trace_iterator *iter = filp->private_data;
-	struct trace_array *tr = iter->tr;
 	ssize_t sret;
 
 	/* return any leftover data */
@@ -4477,12 +4476,6 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 
 	trace_seq_init(&iter->seq);
 
-	/* copy the tracer to avoid using a global lock all around */
-	mutex_lock(&trace_types_lock);
-	if (unlikely(iter->trace->name != tr->current_trace->name))
-		*iter->trace = *tr->current_trace;
-	mutex_unlock(&trace_types_lock);
-
 	/*
 	 * Avoid more than one consumer on a single file descriptor
 	 * This is just a matter of traces coherency, the ring buffer itself
@@ -4642,7 +4635,6 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		.ops		= &tracing_pipe_buf_ops,
 		.spd_release	= tracing_spd_release_pipe,
 	};
-	struct trace_array *tr = iter->tr;
 	ssize_t ret;
 	size_t rem;
 	unsigned int i;
@@ -4650,12 +4642,6 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 	if (splice_grow_spd(pipe, &spd))
 		return -ENOMEM;
 
-	/* copy the tracer to avoid using a global lock all around */
-	mutex_lock(&trace_types_lock);
-	if (unlikely(iter->trace->name != tr->current_trace->name))
-		*iter->trace = *tr->current_trace;
-	mutex_unlock(&trace_types_lock);
-
 	mutex_lock(&iter->mutex);
 
 	if (iter->trace->splice_read) {
@@ -4942,7 +4928,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	*fpos += written;
 
  out_unlock:
-	for (i = 0; i < nr_pages; i++){
+	for (i = nr_pages - 1; i >= 0; i--) {
 		kunmap_atomic(map_page[i]);
 		put_page(pages[i]);
 	}
@@ -5331,6 +5317,8 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 
 	filp->private_data = info;
 
+	tr->current_trace->ref++;
+
 	mutex_unlock(&trace_types_lock);
 
 	ret = nonseekable_open(inode, filp);
@@ -5361,21 +5349,16 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	if (!count)
 		return 0;
 
-	mutex_lock(&trace_types_lock);
-
 #ifdef CONFIG_TRACER_MAX_TRACE
-	if (iter->snapshot && iter->tr->current_trace->use_max_tr) {
-		size = -EBUSY;
-		goto out_unlock;
-	}
+	if (iter->snapshot && iter->tr->current_trace->use_max_tr)
+		return -EBUSY;
 #endif
 
 	if (!info->spare)
 		info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer,
 							  iter->cpu_file);
-	size = -ENOMEM;
 	if (!info->spare)
-		goto out_unlock;
+		return -ENOMEM;
 
 	/* Do we have previous read data to read? */
 	if (info->read < PAGE_SIZE)
@@ -5391,21 +5374,16 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 
 	if (ret < 0) {
 		if (trace_empty(iter)) {
-			if ((filp->f_flags & O_NONBLOCK)) {
-				size = -EAGAIN;
-				goto out_unlock;
-			}
-			mutex_unlock(&trace_types_lock);
+			if ((filp->f_flags & O_NONBLOCK))
+				return -EAGAIN;
+
 			ret = wait_on_pipe(iter, false);
-			mutex_lock(&trace_types_lock);
-			if (ret) {
-				size = ret;
-				goto out_unlock;
-			}
+			if (ret)
+				return ret;
+
 			goto again;
 		}
-		size = 0;
-		goto out_unlock;
+		return 0;
 	}
 
 	info->read = 0;
@@ -5415,18 +5393,14 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 		size = count;
 
 	ret = copy_to_user(ubuf, info->spare + info->read, size);
-	if (ret == size) {
-		size = -EFAULT;
-		goto out_unlock;
-	}
+	if (ret == size)
+		return -EFAULT;
+
 	size -= ret;
 
 	*ppos += size;
 	info->read += size;
 
- out_unlock:
-	mutex_unlock(&trace_types_lock);
-
 	return size;
 }
 
@@ -5437,6 +5411,8 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 
 	mutex_lock(&trace_types_lock);
 
+	iter->tr->current_trace->ref--;
+
 	__trace_array_put(iter->tr);
 
 	if (info->spare)
@@ -5522,30 +5498,20 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	int entries, size, i;
 	ssize_t ret = 0;
 
-	mutex_lock(&trace_types_lock);
-
 #ifdef CONFIG_TRACER_MAX_TRACE
-	if (iter->snapshot && iter->tr->current_trace->use_max_tr) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (iter->snapshot && iter->tr->current_trace->use_max_tr)
+		return -EBUSY;
 #endif
 
-	if (splice_grow_spd(pipe, &spd)) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (splice_grow_spd(pipe, &spd))
+		return -ENOMEM;
 
-	if (*ppos & (PAGE_SIZE - 1)) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (*ppos & (PAGE_SIZE - 1))
+		return -EINVAL;
 
 	if (len & (PAGE_SIZE - 1)) {
-		if (len < PAGE_SIZE) {
-			ret = -EINVAL;
-			goto out;
-		}
+		if (len < PAGE_SIZE)
+			return -EINVAL;
 		len &= PAGE_MASK;
 	}
 
@@ -5606,25 +5572,20 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	/* did we read anything? */
 	if (!spd.nr_pages) {
 		if (ret)
-			goto out;
+			return ret;
+
+		if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK))
+			return -EAGAIN;
 
-		if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) {
-			ret = -EAGAIN;
-			goto out;
-		}
-		mutex_unlock(&trace_types_lock);
 		ret = wait_on_pipe(iter, true);
-		mutex_lock(&trace_types_lock);
 		if (ret)
-			goto out;
+			return ret;
 
 		goto again;
 	}
 
 	ret = splice_to_pipe(pipe, &spd);
 	splice_shrink_spd(&spd);
-out:
-	mutex_unlock(&trace_types_lock);
 
 	return ret;
 }
@@ -5854,28 +5815,11 @@ static __init int register_snapshot_cmd(void)
 static inline __init int register_snapshot_cmd(void) { return 0; }
 #endif /* defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) */
 
-struct dentry *tracing_init_dentry_tr(struct trace_array *tr)
+static struct dentry *tracing_get_dentry(struct trace_array *tr)
 {
-	if (tr->dir)
-		return tr->dir;
-
-	if (!debugfs_initialized())
-		return NULL;
-
-	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
-		tr->dir = debugfs_create_dir("tracing", NULL);
-
-	if (!tr->dir)
-		pr_warn_once("Could not create debugfs directory 'tracing'\n");
-
 	return tr->dir;
 }
 
-struct dentry *tracing_init_dentry(void)
-{
-	return tracing_init_dentry_tr(&global_trace);
-}
-
 static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu)
 {
 	struct dentry *d_tracer;
@@ -5883,8 +5827,8 @@ static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu)
 	if (tr->percpu_dir)
 		return tr->percpu_dir;
 
-	d_tracer = tracing_init_dentry_tr(tr);
-	if (!d_tracer)
+	d_tracer = tracing_get_dentry(tr);
+	if (IS_ERR(d_tracer))
 		return NULL;
 
 	tr->percpu_dir = debugfs_create_dir("per_cpu", d_tracer);
@@ -6086,8 +6030,8 @@ static struct dentry *trace_options_init_dentry(struct trace_array *tr)
 	if (tr->options)
 		return tr->options;
 
-	d_tracer = tracing_init_dentry_tr(tr);
-	if (!d_tracer)
+	d_tracer = tracing_get_dentry(tr);
+	if (IS_ERR(d_tracer))
 		return NULL;
 
 	tr->options = debugfs_create_dir("options", d_tracer);
@@ -6416,7 +6360,7 @@ static int instance_delete(const char *name)
 		goto out_unlock;
 
 	ret = -EBUSY;
-	if (tr->ref)
+	if (tr->ref || (tr->current_trace && tr->current_trace->ref))
 		goto out_unlock;
 
 	list_del(&tr->list);
@@ -6571,6 +6515,33 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 
 }
 
+/**
+ * tracing_init_dentry - initialize top level trace array
+ *
+ * This is called when creating files or directories in the tracing
+ * directory. It is called via fs_initcall() by any of the boot up code
+ * and expects to return the dentry of the top level tracing directory.
+ */
+struct dentry *tracing_init_dentry(void)
+{
+	struct trace_array *tr = &global_trace;
+
+	if (tr->dir)
+		return tr->dir;
+
+	if (WARN_ON(!debugfs_initialized()))
+		return ERR_PTR(-ENODEV);
+
+	tr->dir = debugfs_create_dir("tracing", NULL);
+
+	if (!tr->dir) {
+		pr_warn_once("Could not create debugfs directory 'tracing'\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return tr->dir;
+}
+
 static __init int tracer_init_debugfs(void)
 {
 	struct dentry *d_tracer;
@@ -6578,7 +6549,7 @@ static __init int tracer_init_debugfs(void)
 	trace_access_lock_init();
 
 	d_tracer = tracing_init_dentry();
-	if (!d_tracer)
+	if (IS_ERR(d_tracer))
 		return 0;
 
 	init_tracer_debugfs(&global_trace, d_tracer);
@@ -6811,7 +6782,6 @@ __init static int tracer_alloc_buffers(void)
 	int ring_buf_size;
 	int ret = -ENOMEM;
 
-
 	if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
 		goto out;