perf tools: Enhance the thread stack to output call/return data
Enhance the thread stack to output detailed information about paired
calls and returns.
The enhanced processing consumes sample information via
thread_stack__process() and outputs information about paired calls /
returns via a call-back.
While the call-back makes it possible for the facility to be used by
arbitrary tools, a subsequent patch will provide the information to
Python scripting via the db-export interface.
An important part of the call/return information is the
call path which provides a structure that defines a context
sensitive call graph.
Note that there are now two ways to use the thread stack.
For simply providing a call stack (like you would get from the perf
record -g option) the interface consists of thread_stack__event() and
thread_stack__sample().
Whereas the enhanced interface consists of call_return_processor__new()
and thread_stack__process().
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1414678188-14946-5-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index 7c41579..b843bbe 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -19,14 +19,93 @@
#include <sys/types.h>
#include <linux/types.h>
+#include <linux/rbtree.h>
struct thread;
+struct comm;
struct ip_callchain;
+struct symbol;
+struct dso;
+struct call_return_processor;
+struct comm;
+struct perf_sample;
+struct addr_location;
+
+/*
+ * Call/Return flags.
+ *
+ * CALL_RETURN_NO_CALL: 'return' but no matching 'call'
+ * CALL_RETURN_NO_RETURN: 'call' but no matching 'return'
+ */
+enum {
+ CALL_RETURN_NO_CALL = 1 << 0,
+ CALL_RETURN_NO_RETURN = 1 << 1,
+};
+
+/**
+ * struct call_return - paired call/return information.
+ * @thread: thread in which call/return occurred
+ * @comm: comm in which call/return occurred
+ * @cp: call path
+ * @call_time: timestamp of call (if known)
+ * @return_time: timestamp of return (if known)
+ * @branch_count: number of branches seen between call and return
+ * @call_ref: external reference to 'call' sample (e.g. db_id)
+ * @return_ref: external reference to 'return' sample (e.g. db_id)
+ * @db_id: id used for db-export
+ * @flags: Call/Return flags
+ */
+struct call_return {
+ struct thread *thread;
+ struct comm *comm;
+ struct call_path *cp;
+ u64 call_time;
+ u64 return_time;
+ u64 branch_count;
+ u64 call_ref;
+ u64 return_ref;
+ u64 db_id;
+ u32 flags;
+};
+
+/**
+ * struct call_path - node in list of calls leading to a function call.
+ * @parent: call path to the parent function call
+ * @sym: symbol of function called
+ * @ip: only if sym is null, the ip of the function
+ * @db_id: id used for db-export
+ * @in_kernel: whether function is a in the kernel
+ * @rb_node: node in parent's tree of called functions
+ * @children: tree of call paths of functions called
+ *
+ * In combination with the call_return structure, the call_path structure
+ * defines a context-sensitve call-graph.
+ */
+struct call_path {
+ struct call_path *parent;
+ struct symbol *sym;
+ u64 ip;
+ u64 db_id;
+ bool in_kernel;
+ struct rb_node rb_node;
+ struct rb_root children;
+};
int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
u64 to_ip, u16 insn_len, u64 trace_nr);
+void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
size_t sz, u64 ip);
void thread_stack__free(struct thread *thread);
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+ void *data);
+void call_return_processor__free(struct call_return_processor *crp);
+int thread_stack__process(struct thread *thread, struct comm *comm,
+ struct perf_sample *sample,
+ struct addr_location *from_al,
+ struct addr_location *to_al, u64 ref,
+ struct call_return_processor *crp);
+
#endif