tracing: Add hook to function tracing for other subsystems to use

Currently Function traces can be only exported to the ring buffer. This
adds a trace_export concept which can process traces and export
them to a registered destination as an addition to the current
one that outputs to Ftrace - i.e. ring buffer.

In this way, if we want function traces to be sent to other destinations
rather than only to the ring buffer, we just need to register a new
trace_export and implement its own .write() function for writing traces to
storage.

With this patch, only function tracing (trace type is TRACE_FN)
is supported.

Link: http://lkml.kernel.org/r/1479715043-6534-2-git-send-email-zhang.chunyan@linaro.org
Signed-off-by: Chunyan Zhang <zhang.chunyan@linaro.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/include/linux/trace.h b/include/linux/trace.h
new file mode 100644 (file)
index 0000000..9330a58
--- /dev/null
+++ b/include/linux/trace.h
@@ -0,0 +1,28 @@
+#ifndef _LINUX_TRACE_H
+#define _LINUX_TRACE_H
+
+#ifdef CONFIG_TRACING
+/*
+ * The trace export - an export of Ftrace output. The trace_export
+ * can process traces and export them to a registered destination as
+ * an addition to the current only output of Ftrace - i.e. ring buffer.
+ *
+ * If you want traces to be sent to some other place rather than ring
+ * buffer only, just need to register a new trace_export and implement
+ * its own .write() function for writing traces to the storage.
+ *
+ * next                - pointer to the next trace_export
+ * write       - copy traces which have been delt with ->commit() to
+ *               the destination
+ */
+struct trace_export {
+       struct trace_export __rcu       *next;
+       void (*write)(const void *, unsigned int);
+};
+
+int register_ftrace_export(struct trace_export *export);
+int unregister_ftrace_export(struct trace_export *export);
+
+#endif /* CONFIG_TRACING */
+
+#endif /* _LINUX_TRACE_H */

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 57069e7..edccdff 100644 (file)
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -40,6 +40,7 @@
 #include <linux/poll.h>
 #include <linux/nmi.h>
 #include <linux/fs.h>
+#include <linux/trace.h>
 #include <linux/sched/rt.h>
 
 #include "trace.h"
@@ -2128,6 +2129,129 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr,
        ftrace_trace_userstack(buffer, flags, pc);
 }
 
+static void
+trace_process_export(struct trace_export *export,
+              struct ring_buffer_event *event)
+{
+       struct trace_entry *entry;
+       unsigned int size = 0;
+
+       entry = ring_buffer_event_data(event);
+       size = ring_buffer_event_length(event);
+       export->write(entry, size);
+}
+
+static DEFINE_MUTEX(ftrace_export_lock);
+
+static struct trace_export __rcu *ftrace_exports_list __read_mostly;
+
+static DEFINE_STATIC_KEY_FALSE(ftrace_exports_enabled);
+
+static inline void ftrace_exports_enable(void)
+{
+       static_branch_enable(&ftrace_exports_enabled);
+}
+
+static inline void ftrace_exports_disable(void)
+{
+       static_branch_disable(&ftrace_exports_enabled);
+}
+
+void ftrace_exports(struct ring_buffer_event *event)
+{
+       struct trace_export *export;
+
+       preempt_disable_notrace();
+
+       export = rcu_dereference_raw_notrace(ftrace_exports_list);
+       while (export) {
+               trace_process_export(export, event);
+               export = rcu_dereference_raw_notrace(export->next);
+       }
+
+       preempt_enable_notrace();
+}
+
+static inline void
+add_trace_export(struct trace_export **list, struct trace_export *export)
+{
+       rcu_assign_pointer(export->next, *list);
+       /*
+        * We are entering export into the list but another
+        * CPU might be walking that list. We need to make sure
+        * the export->next pointer is valid before another CPU sees
+        * the export pointer included into the list.
+        */
+       rcu_assign_pointer(*list, export);
+}
+
+static inline int
+rm_trace_export(struct trace_export **list, struct trace_export *export)
+{
+       struct trace_export **p;
+
+       for (p = list; *p != NULL; p = &(*p)->next)
+               if (*p == export)
+                       break;
+
+       if (*p != export)
+               return -1;
+
+       rcu_assign_pointer(*p, (*p)->next);
+
+       return 0;
+}
+
+static inline void
+add_ftrace_export(struct trace_export **list, struct trace_export *export)
+{
+       if (*list == NULL)
+               ftrace_exports_enable();
+
+       add_trace_export(list, export);
+}
+
+static inline int
+rm_ftrace_export(struct trace_export **list, struct trace_export *export)
+{
+       int ret;
+
+       ret = rm_trace_export(list, export);
+       if (*list == NULL)
+               ftrace_exports_disable();
+
+       return ret;
+}
+
+int register_ftrace_export(struct trace_export *export)
+{
+       if (WARN_ON_ONCE(!export->write))
+               return -1;
+
+       mutex_lock(&ftrace_export_lock);
+
+       add_ftrace_export(&ftrace_exports_list, export);
+
+       mutex_unlock(&ftrace_export_lock);
+
+       return 0;
+}
+EXPORT_SYMBOL_GPL(register_ftrace_export);
+
+int unregister_ftrace_export(struct trace_export *export)
+{
+       int ret;
+
+       mutex_lock(&ftrace_export_lock);
+
+       ret = rm_ftrace_export(&ftrace_exports_list, export);
+
+       mutex_unlock(&ftrace_export_lock);
+
+       return ret;
+}
+EXPORT_SYMBOL_GPL(unregister_ftrace_export);
+
 void
 trace_function(struct trace_array *tr,
               unsigned long ip, unsigned long parent_ip, unsigned long flags,
@@ -2146,8 +2270,11 @@ trace_function(struct trace_array *tr,
        entry->ip                       = ip;
        entry->parent_ip                = parent_ip;
 
-       if (!call_filter_check_discard(call, entry, buffer, event))
+       if (!call_filter_check_discard(call, entry, buffer, event)) {
+               if (static_branch_unlikely(&ftrace_exports_enabled))
+                       ftrace_exports(event);
                __buffer_unlock_commit(buffer, event);
+       }
 }
 
 #ifdef CONFIG_STACKTRACE