perf tools: Intel PT preparation continued

index 06f1758..84df2de 100644
@@ -409,6 +409,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.tracing_data	= perf_event__repipe_op2_synth,
 			.finished_round	= perf_event__repipe_op2_synth,
 			.build_id	= perf_event__repipe_op2_synth,
+			.id_index	= perf_event__repipe_op2_synth,
 		},
 		.input_name  = "-",
 		.samples = LIST_HEAD_INIT(inject.samples),

index e00a29f..6c6d044 100644
@@ -28,6 +28,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
 	[PERF_RECORD_HEADER_BUILD_ID]		= "BUILD_ID",
 	[PERF_RECORD_FINISHED_ROUND]		= "FINISHED_ROUND",
+	[PERF_RECORD_ID_INDEX]			= "ID_INDEX",
 };
 
 const char *perf_event__name(unsigned int id)

index 5f0e0b8..8c7fe9d 100644
@@ -187,6 +187,7 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_HEADER_TRACING_DATA		= 66,
 	PERF_RECORD_HEADER_BUILD_ID		= 67,
 	PERF_RECORD_FINISHED_ROUND		= 68,
+	PERF_RECORD_ID_INDEX			= 69,
 	PERF_RECORD_HEADER_MAX
 };
 

@@ -239,6 +240,19 @@ struct tracing_data_event {
 	u32 size;
 };
 
+struct id_index_entry {
+	u64 id;
+	u64 idx;
+	u64 cpu;
+	u64 tid;
+};
+
+struct id_index_event {
+	struct perf_event_header header;
+	u64 nr;
+	struct id_index_entry entries[0];
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;

@@ -253,6 +267,7 @@ union perf_event {
 	struct event_type_event		event_type;
 	struct tracing_data_event	tracing_data;
 	struct build_id_event		build_id;
+	struct id_index_event		id_index;
 };
 
 void perf_event__print_totals(void);

index 3c9e77d..0babd39 100644
@@ -527,6 +527,22 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 	return 0;
 }
 
+static void perf_evlist__set_sid_idx(struct perf_evlist *evlist,
+				     struct perf_evsel *evsel, int idx, int cpu,
+				     int thread)
+{
+	struct perf_sample_id *sid = SID(evsel, cpu, thread);
+	sid->idx = idx;
+	if (evlist->cpus && cpu >= 0)
+		sid->cpu = evlist->cpus->map[cpu];
+	else
+		sid->cpu = -1;
+	if (!evsel->system_wide && evlist->threads && thread >= 0)
+		sid->tid = evlist->threads->map[thread];
+	else
+		sid->tid = -1;
+}
+
 struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id)
 {
 	struct hlist_head *head;

@@ -805,9 +821,13 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 			return -1;
 		}
 
-		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
-		    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
-			return -1;
+		if (evsel->attr.read_format & PERF_FORMAT_ID) {
+			if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread,
+						   fd) < 0)
+				return -1;
+			perf_evlist__set_sid_idx(evlist, evsel, idx, cpu,
+						 thread);
+		}
 	}
 
 	return 0;

index d3854c4..9797909 100644
@@ -36,6 +36,9 @@ struct perf_sample_id {
 	struct hlist_node 	node;
 	u64		 	id;
 	struct perf_evsel	*evsel;
+	int			idx;
+	int			cpu;
+	pid_t			tid;
 
 	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
 	u64			period;

149 lines not on this page · raw message

index a4be851..d8521ac 100644
@@ -126,4 +126,14 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 extern volatile int session_done;
 
 #define session_done()	ACCESS_ONCE(session_done)
+
+int perf_event__process_id_index(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session);
+
+int perf_event__synthesize_id_index(struct perf_tool *tool,
+				    perf_event__handler_t process,
+				    struct perf_evlist *evlist,
+				    struct machine *machine);
+
 #endif /* __PERF_SESSION_H */

index f116369..bb2708b 100644
@@ -39,7 +39,8 @@ struct perf_tool {
 	event_attr_op	attr;
 	event_op2	tracing_data;
 	event_op2	finished_round,
-			build_id;
+			build_id,
+			id_index;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
 };

index 27a0049..2670d98 100644
@@ -907,6 +907,20 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	}
 }
 
+int perf_session__deliver_synth_event(struct perf_session *session,
+				      union perf_event *event,
+				      struct perf_sample *sample,
+				      struct perf_tool *tool)
+{
+	events_stats__inc(&session->stats, event->header.type);
+
+	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
+		return perf_session__process_user_event(session, event, tool,
+							0);
+
+	return perf_session__deliver_event(session, event, sample, tool, 0);
+}
+
 static void event_swap(union perf_event *event, bool sample_id_all)
 {
 	perf_event__swap_op swap;

index d8521ac..dc26ebf 100644
@@ -127,6 +127,11 @@ extern volatile int session_done;
 
 #define session_done()	ACCESS_ONCE(session_done)
 
+int perf_session__deliver_synth_event(struct perf_session *session,
+				      union perf_event *event,
+				      struct perf_sample *sample,
+				      struct perf_tool *tool);
+
 int perf_event__process_id_index(struct perf_tool *tool,
 				 union perf_event *event,
 				 struct perf_session *session);

index 8c7fe9d..1bbe9fe 100644
@@ -143,6 +143,32 @@ struct branch_stack {
 	struct branch_entry	entries[0];
 };
 
+enum {
+	PERF_FLAG_BRANCH		= 1ULL << 0,
+	PERF_FLAG_CALL			= 1ULL << 1,
+	PERF_FLAG_RETURN		= 1ULL << 2,
+	PERF_FLAG_CONDITIONAL		= 1ULL << 3,
+	PERF_FLAG_SYSCALLRET		= 1ULL << 4,
+	PERF_FLAG_ASYNC			= 1ULL << 5,
+	PERF_FLAG_INTERRUPT		= 1ULL << 6,
+	PERF_FLAG_TX_ABORT		= 1ULL << 7,
+	PERF_FLAG_TRACE_BEGIN		= 1ULL << 8,
+	PERF_FLAG_TRACE_END		= 1ULL << 9,
+	PERF_FLAG_IN_TX			= 1ULL << 10,
+};
+
+#define PERF_BRANCH_MASK	(\
+	PERF_FLAG_BRANCH	|\
+	PERF_FLAG_CALL		|\
+	PERF_FLAG_RETURN	|\
+	PERF_FLAG_CONDITIONAL	|\
+	PERF_FLAG_SYSCALLRET	|\
+	PERF_FLAG_ASYNC		|\
+	PERF_FLAG_INTERRUPT	|\
+	PERF_FLAG_TX_ABORT	|\
+	PERF_FLAG_TRACE_BEGIN	|\
+	PERF_FLAG_TRACE_END)
+
 struct perf_sample {
 	u64 ip;
 	u32 pid, tid;

158 lines not on this page · raw message

new file mode 100644
index 0000000..c0ba4cf
@@ -0,0 +1,32 @@
+/*
+ * thread-stack.h: Synthesize a thread's stack using call / return events
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_THREAD_STACK_H
+#define __PERF_THREAD_STACK_H
+
+#include <sys/types.h>
+
+#include <linux/types.h>
+
+struct thread;
+struct ip_callchain;
+
+void thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+			 u64 to_ip, u16 insn_len, 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);
+
+#endif

index bf5bf85..a2157f0 100644
@@ -4,6 +4,7 @@
 #include <string.h>
 #include "session.h"
 #include "thread.h"
+#include "thread-stack.h"
 #include "util.h"
 #include "debug.h"
 #include "comm.h"

@@ -66,6 +67,8 @@ void thread__delete(struct thread *thread)
 {
 	struct comm *comm, *tmp;
 
+	thread_stack__free(thread);
+
 	if (thread->mg) {
 		map_groups__put(thread->mg);
 		thread->mg = NULL;

index d34cf5c..160fd06 100644
@@ -8,6 +8,8 @@
 #include "symbol.h"
 #include <strlist.h>
 
+struct thread_stack;
+
 struct thread {
 	union {
 		struct rb_node	 rb_node;

@@ -26,6 +28,7 @@ struct thread {
 	u64			db_id;
 
 	void			*priv;
+	struct thread_stack	*ts;
 };
 
 struct machine;

index be128b0..8353e2f 100644
@@ -208,6 +208,15 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
 	return 0;
 }
 
+int db_export__branch_type(struct db_export *dbe, u32 branch_type,
+			   const char *name)
+{
+	if (dbe->export_branch_type)
+		return dbe->export_branch_type(dbe, branch_type, name);
+
+	return 0;
+}
+
 int db_export__sample(struct db_export *dbe, union perf_event *event,
 		      struct perf_sample *sample, struct perf_evsel *evsel,
 		      struct thread *thread, struct addr_location *al)

@@ -268,3 +277,42 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 
 	return 0;
 }
+
+static struct {
+	u32 branch_type;
+	const char *name;
+} branch_types[] = {
+	{0, "no branch"},
+	{PERF_FLAG_BRANCH | PERF_FLAG_CALL, "call"},
+	{PERF_FLAG_BRANCH | PERF_FLAG_RETURN, "return"},
+	{PERF_FLAG_BRANCH | PERF_FLAG_CONDITIONAL, "conditional jump"},
+	{PERF_FLAG_BRANCH, "unconditional jump"},
+	{PERF_FLAG_BRANCH | PERF_FLAG_CALL | PERF_FLAG_INTERRUPT,
+	 "software interrupt"},
+	{PERF_FLAG_BRANCH | PERF_FLAG_RETURN | PERF_FLAG_INTERRUPT,
+	 "return from interrupt"},
+	{PERF_FLAG_BRANCH | PERF_FLAG_CALL | PERF_FLAG_SYSCALLRET,
+	 "system call"},
+	{PERF_FLAG_BRANCH | PERF_FLAG_RETURN | PERF_FLAG_SYSCALLRET,
+	 "return from system call"},
+	{PERF_FLAG_BRANCH | PERF_FLAG_ASYNC, "asynchronous branch"},
+	{PERF_FLAG_BRANCH | PERF_FLAG_CALL | PERF_FLAG_ASYNC |
+	 PERF_FLAG_INTERRUPT, "hardware interrupt"},
+	{PERF_FLAG_BRANCH | PERF_FLAG_TX_ABORT, "transaction abort"},
+	{PERF_FLAG_BRANCH | PERF_FLAG_TRACE_BEGIN, "trace begin"},
+	{PERF_FLAG_BRANCH | PERF_FLAG_TRACE_END, "trace end"},
+	{0, NULL}
+};
+
+int db_export__branch_types(struct db_export *dbe)
+{
+	int i, err = 0;
+
+	for (i = 0; branch_types[i].name ; i++) {
+		err = db_export__branch_type(dbe, branch_types[i].branch_type,
+					     branch_types[i].name);
+		if (err)
+			break;
+	}
+	return err;
+}

index b3643e8..e4baa45 100644
@@ -54,6 +54,8 @@ struct db_export {
 			  struct machine *machine);
 	int (*export_symbol)(struct db_export *dbe, struct symbol *sym,
 			     struct dso *dso);
+	int (*export_branch_type)(struct db_export *dbe, u32 branch_type,
+				  const char *name);
 	int (*export_sample)(struct db_export *dbe, struct export_sample *es);
 	u64 evsel_last_db_id;
 	u64 machine_last_db_id;

@@ -79,8 +81,12 @@ int db_export__dso(struct db_export *dbe, struct dso *dso,
 		   struct machine *machine);
 int db_export__symbol(struct db_export *dbe, struct symbol *sym,
 		      struct dso *dso);
+int db_export__branch_type(struct db_export *dbe, u32 branch_type,
+			   const char *name);
 int db_export__sample(struct db_export *dbe, union perf_event *event,
 		      struct perf_sample *sample, struct perf_evsel *evsel,
 		      struct thread *thread, struct addr_location *al);
 
+int db_export__branch_types(struct db_export *dbe);
+
 #endif

index 2fd7ee8..0874d79 100644
@@ -66,6 +66,7 @@ struct tables {
 	PyObject		*comm_thread_handler;
 	PyObject		*dso_handler;
 	PyObject		*symbol_handler;
+	PyObject		*branch_type_handler;
 	PyObject		*sample_handler;
 	bool			db_export_mode;
 };

@@ -664,13 +665,31 @@ static int python_export_symbol(struct db_export *dbe, struct symbol *sym,
 	return 0;
 }
 
+static int python_export_branch_type(struct db_export *dbe, u32 branch_type,
+				     const char *name)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(2);
+
+	tuple_set_s32(t, 0, branch_type);
+	tuple_set_string(t, 1, name);
+
+	call_object(tables->branch_type_handler, t, "branch_type_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
 static int python_export_sample(struct db_export *dbe,
 				struct export_sample *es)
 {
 	struct tables *tables = container_of(dbe, struct tables, dbe);
 	PyObject *t;
 
-	t = tuple_new(19);
+	t = tuple_new(21);
 
 	tuple_set_u64(t, 0, es->db_id);
 	tuple_set_u64(t, 1, es->evsel->db_id);

@@ -691,6 +710,8 @@ static int python_export_sample(struct db_export *dbe,
 	tuple_set_u64(t, 16, es->sample->weight);
 	tuple_set_u64(t, 17, es->sample->transaction);
 	tuple_set_u64(t, 18, es->sample->data_src);
+	tuple_set_s32(t, 19, es->sample->flags & PERF_BRANCH_MASK);
+	tuple_set_s32(t, 20, !!(es->sample->flags & PERF_FLAG_IN_TX));
 
 	call_object(tables->sample_handler, t, "sample_table");
 

@@ -861,6 +882,7 @@ static void set_table_handlers(struct tables *tables)
 	SET_TABLE_HANDLER(comm_thread);
 	SET_TABLE_HANDLER(dso);
 	SET_TABLE_HANDLER(symbol);
+	SET_TABLE_HANDLER(branch_type);
 	SET_TABLE_HANDLER(sample);
 }
 

@@ -910,6 +932,12 @@ static int python_start_script(const char *script, int argc, const char **argv)
 
 	set_table_handlers(tables);
 
+	if (tables->db_export_mode) {
+		err = db_export__branch_types(&tables->dbe);
+		if (err)
+			goto error;
+	}
+
 	return err;
 error:
 	Py_Finalize();

index a959032..a6a4a53 100644
@@ -13,16 +13,48 @@
  *
  */
 
+#include <linux/rbtree.h>
+#include <linux/list.h>
 #include "thread.h"
 #include "event.h"
+#include "machine.h"
 #include "util.h"
 #include "debug.h"
+#include "symbol.h"
+#include "comm.h"
 #include "thread-stack.h"
 
-#define STACK_GROWTH 4096
+#define CALL_PATH_BLOCK_SHIFT 8
+#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT)
+#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1)
+
+struct call_path_block {
+	struct call_path cp[CALL_PATH_BLOCK_SIZE];
+	struct list_head node;
+};
+
+struct call_path_root {
+	struct call_path call_path;
+	struct list_head blocks;
+	size_t next;
+	size_t sz;
+};
+
+struct call_return_processor {
+	struct call_path_root *cpr;
+	int (*process)(struct call_return *cr, void *data);
+	void *data;
+};
+
+#define STACK_GROWTH 2048
 
 struct thread_stack_entry {
 	u64 ret_addr;
+	u64 timestamp;
+	u64 ref;
+	u64 branch_count;
+	struct call_path *cp;
+	bool no_call;
 };
 
 struct thread_stack {

@@ -30,6 +62,11 @@ struct thread_stack {
 	size_t cnt;
 	size_t sz;
 	u64 trace_nr;
+	u64 branch_count;
+	u64 kernel_start;
+	u64 last_time;
+	struct call_return_processor *crp;
+	struct comm *comm;
 };
 
 static void thread_stack__grow(struct thread_stack *ts)

@@ -46,7 +83,8 @@ static void thread_stack__grow(struct thread_stack *ts)
 	}
 }
 
-static struct thread_stack *thread_stack__new(void)
+static struct thread_stack *thread_stack__new(struct thread *thread,
+					      struct call_return_processor *crp)
 {
 	struct thread_stack *ts;
 

@@ -60,6 +98,12 @@ static struct thread_stack *thread_stack__new(void)
 		return NULL;
 	}
 
+	if (thread->mg && thread->mg->machine)
+		ts->kernel_start = machine__kernel_start(thread->mg->machine);
+	else
+		ts->kernel_start = 1ULL << 63;
+	ts->crp = crp;
+
 	return ts;
 }
 

@@ -97,6 +141,64 @@ static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
 	}
 }
 
+static bool thread_stack__in_kernel(struct thread_stack *ts)
+{
+	if (!ts->cnt)
+		return false;
+
+	return ts->stack[ts->cnt - 1].cp->in_kernel;
+}
+
+static int thread_stack__call_return(struct thread *thread,
+				     struct thread_stack *ts, size_t idx,
+				     u64 timestamp, u64 ref, bool no_return)
+{
+	struct call_return_processor *crp = ts->crp;
+	struct thread_stack_entry *tse;
+	struct call_return cr = {
+		.thread = thread,
+		.comm = ts->comm,
+		.db_id = 0,
+	};
+
+	tse = &ts->stack[idx];
+	cr.cp = tse->cp;
+	cr.call_time = tse->timestamp;
+	cr.return_time = timestamp;
+	cr.branch_count = ts->branch_count - tse->branch_count;
+	cr.call_ref = tse->ref;
+	cr.return_ref = ref;
+	if (tse->no_call)
+		cr.flags |= CALL_RETURN_NO_CALL;
+	if (no_return)
+		cr.flags |= CALL_RETURN_NO_RETURN;
+
+	return crp->process(&cr, crp->data);
+}
+
+static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
+{
+	struct call_return_processor *crp = ts->crp;
+	int err;
+
+	if (!crp) {
+		ts->cnt = 0;
+		return 0;
+	}
+
+	while (ts->cnt) {
+		err = thread_stack__call_return(thread, ts, --ts->cnt,
+						ts->last_time, 0, true);
+		if (err) {
+			pr_err("Error flushing thread stack!\n");
+			ts->cnt = 0;
+			return err;
+		}
+	}
+
+	return 0;
+}
+
 void thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 			 u64 to_ip, u16 insn_len, u64 trace_nr)
 {

@@ -104,7 +206,7 @@ void thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 		return;
 
 	if (!thread->ts) {
-		thread->ts = thread_stack__new();
+		thread->ts = thread_stack__new(thread, NULL);
 		if (!thread->ts) {
 			pr_warning("Out of memory: no thread stack\n");
 			return;

@@ -113,10 +215,15 @@ void thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 	}
 
 	if (trace_nr != thread->ts->trace_nr) {
+		if (thread->ts->trace_nr)
+			thread_stack__flush(thread, thread->ts);
 		thread->ts->trace_nr = trace_nr;
-		thread->ts->cnt = 0;
 	}
 
+	/* Stop here if thread_stack__process() is in use */
+	if (thread->ts->crp)
+		return;
+
 	if (flags & PERF_FLAG_CALL) {
 		u64 ret_addr;
 

@@ -133,9 +240,22 @@ void thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 	}
 }
 
+void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
+{
+	if (!thread || !thread->ts)
+		return;
+
+	if (trace_nr != thread->ts->trace_nr) {
+		if (thread->ts->trace_nr)
+			thread_stack__flush(thread, thread->ts);
+		thread->ts->trace_nr = trace_nr;
+	}
+}
+
 void thread_stack__free(struct thread *thread)
 {
 	if (thread->ts) {
+		thread_stack__flush(thread, thread->ts);
 		zfree(&thread->ts->stack);
 		zfree(&thread->ts);
 	}

@@ -156,3 +276,421 @@ void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
 	for (i = 1; i < chain->nr; i++)
 		chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
 }
+
+static void call_path__init(struct call_path *cp, struct call_path *parent,
+			    struct symbol *sym, u64 ip, bool in_kernel)
+{
+	cp->parent = parent;
+	cp->sym = sym;
+	cp->ip = sym ? 0 : ip;
+	cp->db_id = 0;
+	cp->in_kernel = in_kernel;
+	RB_CLEAR_NODE(&cp->rb_node);
+	cp->children = RB_ROOT;
+}
+
+static struct call_path_root *call_path_root__new(void)
+{
+	struct call_path_root *cpr;
+
+	cpr = zalloc(sizeof(struct call_path_root));
+	if (!cpr)
+		return NULL;
+	call_path__init(&cpr->call_path, NULL, NULL, 0, false);
+	INIT_LIST_HEAD(&cpr->blocks);
+	return cpr;
+}
+
+static void call_path_root__free(struct call_path_root *cpr)
+{
+	struct call_path_block *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &cpr->blocks, node) {
+		list_del(&pos->node);
+		free(pos);
+	}
+	free(cpr);
+}
+
+static struct call_path *call_path__new(struct call_path_root *cpr,
+					struct call_path *parent,
+					struct symbol *sym, u64 ip,
+					bool in_kernel)
+{
+	struct call_path_block *cpb;
+	struct call_path *cp;
+	size_t n;
+
+	if (cpr->next < cpr->sz) {
+		cpb = list_last_entry(&cpr->blocks, struct call_path_block,
+				      node);
+	} else {
+		cpb = zalloc(sizeof(struct call_path_block));
+		if (!cpb)
+			return NULL;
+		list_add_tail(&cpb->node, &cpr->blocks);
+		cpr->sz += CALL_PATH_BLOCK_SIZE;
+	}
+
+	n = cpr->next++ & CALL_PATH_BLOCK_MASK;
+	cp = &cpb->cp[n];
+
+	call_path__init(cp, parent, sym, ip, in_kernel);
+
+	return cp;
+}
+
+static struct call_path *call_path__findnew(struct call_path_root *cpr,
+					    struct call_path *parent,
+					    struct symbol *sym, u64 ip, u64 ks)
+{
+	struct rb_node **p;
+	struct rb_node *node_parent = NULL;
+	struct call_path *cp;
+	bool in_kernel = ip >= ks;
+
+	if (sym)
+		ip = 0;
+
+	if (!parent)
+		return call_path__new(cpr, parent, sym, ip, in_kernel);
+
+	p = &parent->children.rb_node;
+	while (*p != NULL) {
+		node_parent = *p;
+		cp = rb_entry(node_parent, struct call_path, rb_node);
+
+		if (cp->sym == sym && cp->ip == ip)
+			return cp;
+
+		if (sym < cp->sym || (sym == cp->sym && ip < cp->ip))
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	cp = call_path__new(cpr, parent, sym, ip, in_kernel);
+	if (!cp)
+		return NULL;
+
+	rb_link_node(&cp->rb_node, node_parent, p);
+	rb_insert_color(&cp->rb_node, &parent->children);
+
+	return cp;
+}
+
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+			   void *data)
+{
+	struct call_return_processor *crp;
+
+	crp = zalloc(sizeof(struct call_return_processor));
+	if (!crp)
+		return NULL;
+	crp->cpr = call_path_root__new();
+	if (!crp->cpr)
+		goto out_free;
+	crp->process = process;
+	crp->data = data;
+	return crp;
+
+out_free:
+	free(crp);
+	return NULL;
+}
+
+void call_return_processor__free(struct call_return_processor *crp)
+{
+	if (crp) {
+		call_path_root__free(crp->cpr);
+		free(crp);
+	}
+}
+
+static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
+				 u64 timestamp, u64 ref, struct call_path *cp,
+				 bool no_call)
+{
+	struct thread_stack_entry *tse;
+
+	if (ts->cnt == ts->sz) {
+		thread_stack__grow(ts);
+		if (ts->cnt == ts->sz)
+			return -ENOMEM;
+	}
+
+	tse = &ts->stack[ts->cnt++];
+	tse->ret_addr = ret_addr;
+	tse->timestamp = timestamp;
+	tse->ref = ref;
+	tse->branch_count = ts->branch_count;
+	tse->cp = cp;
+	tse->no_call = no_call;
+
+	return 0;
+}
+
+static int thread_stack__pop_cp(struct thread *thread, struct thread_stack *ts,
+				u64 ret_addr, u64 timestamp, u64 ref,
+				struct symbol *sym)
+{
+	int err;
+
+	if (!ts->cnt)
+		return 1;
+
+	if (ts->cnt == 1) {
+		struct thread_stack_entry *tse = &ts->stack[0];
+
+		if (tse->cp->sym == sym)
+			return thread_stack__call_return(thread, ts, --ts->cnt,
+							 timestamp, ref, false);
+	}
+
+	if (ts->stack[ts->cnt - 1].ret_addr == ret_addr) {
+		return thread_stack__call_return(thread, ts, --ts->cnt,
+						 timestamp, ref, false);
+	} else {
+		size_t i = ts->cnt - 1;
+
+		while (i--) {
+			if (ts->stack[i].ret_addr != ret_addr)
+				continue;
+			i += 1;
+			while (ts->cnt > i) {
+				err = thread_stack__call_return(thread, ts,
+								--ts->cnt,
+								timestamp, ref,
+								true);
+				if (err)
+					return err;
+			}
+			return thread_stack__call_return(thread, ts, --ts->cnt,
+							 timestamp, ref, false);
+		}
+	}
+
+	return 1;
+}
+
+static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts,
+				struct perf_sample *sample,
+				struct addr_location *from_al,
+				struct addr_location *to_al, u64 ref)
+{
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *cp;
+	struct symbol *sym;
+	u64 ip;
+
+	if (sample->ip) {
+		ip = sample->ip;
+		sym = from_al->sym;
+	} else if (sample->addr) {
+		ip = sample->addr;
+		sym = to_al->sym;
+	} else {
+		return 0;
+	}
+
+	cp = call_path__findnew(cpr, &cpr->call_path, sym, ip,
+				ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp,
+				     true);
+}
+
+static int thread_stack__no_call_return(struct thread *thread,
+					struct thread_stack *ts,
+					struct perf_sample *sample,
+					struct addr_location *from_al,
+					struct addr_location *to_al, u64 ref)
+{
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *cp, *parent;
+	u64 ks = ts->kernel_start;
+	int err;
+
+	if (sample->ip >= ks && sample->addr < ks) {
+		/* Return to userspace, so pop all kernel addresses */
+		while (thread_stack__in_kernel(ts)) {
+			err = thread_stack__call_return(thread, ts, --ts->cnt,
+							sample->time, ref,
+							true);
+			if (err)
+				return err;
+		}
+
+		/* If the stack is empty, push the userspace address */
+		if (!ts->cnt) {
+			cp = call_path__findnew(cpr, &cpr->call_path,
+						to_al->sym, sample->addr,
+						ts->kernel_start);
+			if (!cp)
+				return -ENOMEM;
+			return thread_stack__push_cp(ts, 0, sample->time, ref,
+						     cp, true);
+		}
+	} else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
+		/* Return to userspace, so pop all kernel addresses */
+		while (thread_stack__in_kernel(ts)) {
+			err = thread_stack__call_return(thread, ts, --ts->cnt,
+							sample->time, ref,
+							true);
+			if (err)
+				return err;
+		}
+	}
+
+	if (ts->cnt)
+		parent = ts->stack[ts->cnt - 1].cp;
+	else
+		parent = &cpr->call_path;
+
+	/* This 'return' had no 'call', so push and pop top of stack */
+	cp = call_path__findnew(cpr, parent, from_al->sym, sample->ip,
+				ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
+				    true);
+	if (err)
+		return err;
+
+	return thread_stack__pop_cp(thread, ts, sample->addr, sample->time, ref,
+				    to_al->sym);
+}
+
+static int thread_stack__trace_begin(struct thread *thread,
+				     struct thread_stack *ts, u64 timestamp,
+				     u64 ref)
+{
+	struct thread_stack_entry *tse;
+	int err;
+
+	if (!ts->cnt)
+		return 0;
+
+	/* Pop trace end */
+	tse = &ts->stack[ts->cnt - 1];
+	if (tse->cp->sym == NULL && tse->cp->ip == 0) {
+		err = thread_stack__call_return(thread, ts, --ts->cnt,
+						timestamp, ref, false);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int thread_stack__trace_end(struct thread_stack *ts,
+				   struct perf_sample *sample, u64 ref)
+{
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *cp;
+	u64 ret_addr;
+
+	/* No point having 'trace end' on the bottom of the stack */
+	if (!ts->cnt || (ts->cnt == 1 && ts->stack[0].ref == ref))
+		return 0;
+
+	cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp, NULL, 0,
+				ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	ret_addr = sample->ip + sample->insn_len;
+
+	return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp,
+				     false);
+}
+
+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)
+{
+	struct thread_stack *ts = thread->ts;
+	int err = 0;
+
+	if (ts) {
+		if (!ts->crp) {
+			/* Supersede thread_stack__event() */
+			thread_stack__free(thread);
+			thread->ts = thread_stack__new(thread, crp);
+			if (!thread->ts)
+				return -ENOMEM;
+			ts = thread->ts;
+			ts->comm = comm;
+		}
+	} else {
+		thread->ts = thread_stack__new(thread, crp);
+		if (!thread->ts)
+			return -ENOMEM;
+		ts = thread->ts;
+		ts->comm = comm;
+	}
+
+	/* Flush stack on exec */
+	if (ts->comm != comm && thread->pid_ == thread->tid) {
+		err = thread_stack__flush(thread, ts);
+		if (err)
+			return err;
+		ts->comm = comm;
+	}
+
+	/* If the stack is empty, put the current symbol on the stack */
+	if (!ts->cnt) {
+		err = thread_stack__bottom(thread, ts, sample, from_al, to_al,
+					   ref);
+		if (err)
+			return err;
+	}
+
+	ts->branch_count += 1;
+	ts->last_time = sample->time;
+
+	if (sample->flags & PERF_FLAG_CALL) {
+		struct call_path_root *cpr = ts->crp->cpr;
+		struct call_path *cp;
+		u64 ret_addr;
+
+		if (!sample->ip || !sample->addr)
+			return 0;
+
+		ret_addr = sample->ip + sample->insn_len;
+		if (ret_addr == sample->addr)
+			return 0; /* Zero-length calls are excluded */
+
+		cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp,
+					to_al->sym, sample->addr,
+					ts->kernel_start);
+		if (!cp)
+			return -ENOMEM;
+		err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
+					    cp, false);
+	} else if (sample->flags & PERF_FLAG_RETURN) {
+		if (!sample->ip || !sample->addr)
+			return 0;
+
+		err = thread_stack__pop_cp(thread, ts, sample->addr,
+					   sample->time, ref, from_al->sym);
+		if (err) {
+			if (err < 0)
+				return err;
+			err = thread_stack__no_call_return(thread, ts, sample,
+							   from_al, to_al, ref);
+		}
+	} else if (sample->flags & PERF_FLAG_TRACE_BEGIN) {
+		err = thread_stack__trace_begin(thread, ts, sample->time, ref);
+	} else if (sample->flags & PERF_FLAG_TRACE_END) {
+		err = thread_stack__trace_end(ts, sample, ref);
+	}
+
+	return err;
+}

61 lines not on this page · raw message

index 8353e2f..259be45 100644
@@ -21,6 +21,7 @@
 #include "comm.h"
 #include "symbol.h"
 #include "event.h"
+#include "thread-stack.h"
 #include "db-export.h"
 
 int db_export__init(struct db_export *dbe)

@@ -29,8 +30,10 @@ int db_export__init(struct db_export *dbe)
 	return 0;
 }
 
-void db_export__exit(struct db_export *dbe __maybe_unused)
+void db_export__exit(struct db_export *dbe)
 {
+	call_return_processor__free(dbe->crp);
+	dbe->crp = NULL;
 }
 
 int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel)

@@ -270,6 +273,13 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 				     &es.addr_sym_db_id, &es.addr_offset);
 		if (err)
 			return err;
+		if (dbe->crp) {
+			err = thread_stack__process(thread, comm, sample, al,
+						    &addr_al, es.db_id,
+						    dbe->crp);
+			if (err)
+				return err;
+		}
 	}
 
 	if (dbe->export_sample)

@@ -316,3 +326,43 @@ int db_export__branch_types(struct db_export *dbe)
 	}
 	return err;
 }
+
+int db_export__call_path(struct db_export *dbe, struct call_path *cp)
+{
+	int err;
+
+	if (cp->db_id)
+		return 0;
+
+	if (cp->parent) {
+		err = db_export__call_path(dbe, cp->parent);
+		if (err)
+			return err;
+	}
+
+	cp->db_id = ++dbe->call_path_last_db_id;
+
+	if (dbe->export_call_path)
+		return dbe->export_call_path(dbe, cp);
+
+	return 0;
+}
+
+int db_export__call_return(struct db_export *dbe, struct call_return *cr)
+{
+	int err;
+
+	if (cr->db_id)
+		return 0;
+
+	err = db_export__call_path(dbe, cr->cp);
+	if (err)
+		return err;
+
+	cr->db_id = ++dbe->call_return_last_db_id;
+
+	if (dbe->export_call_return)
+		return dbe->export_call_return(dbe, cr);
+
+	return 0;
+}

index e4baa45..dd5ac2a 100644
@@ -25,6 +25,9 @@ struct comm;
 struct dso;
 struct perf_sample;
 struct addr_location;
+struct call_return_processor;
+struct call_path;
+struct call_return;
 
 struct export_sample {
 	union perf_event	*event;

@@ -57,6 +60,10 @@ struct db_export {
 	int (*export_branch_type)(struct db_export *dbe, u32 branch_type,
 				  const char *name);
 	int (*export_sample)(struct db_export *dbe, struct export_sample *es);
+	int (*export_call_path)(struct db_export *dbe, struct call_path *cp);
+	int (*export_call_return)(struct db_export *dbe,
+				  struct call_return *cr);
+	struct call_return_processor *crp;
 	u64 evsel_last_db_id;
 	u64 machine_last_db_id;
 	u64 thread_last_db_id;

@@ -65,6 +72,8 @@ struct db_export {
 	u64 dso_last_db_id;
 	u64 symbol_last_db_id;
 	u64 sample_last_db_id;
+	u64 call_path_last_db_id;
+	u64 call_return_last_db_id;
 };
 
 int db_export__init(struct db_export *dbe);

@@ -89,4 +98,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 
 int db_export__branch_types(struct db_export *dbe);
 
+int db_export__call_path(struct db_export *dbe, struct call_path *cp);
+int db_export__call_return(struct db_export *dbe, struct call_return *cr);
+
 #endif

120 lines not on this page · raw message

index 259be45..08339a3 100644
@@ -21,17 +21,74 @@
 #include "comm.h"
 #include "symbol.h"
 #include "event.h"
+#include "util.h"
 #include "thread-stack.h"
 #include "db-export.h"
 
+struct deferred_export {
+	struct list_head node;
+	struct comm *comm;
+};
+
+static int db_export__deferred(struct db_export *dbe)
+{
+	struct deferred_export *de;
+	int err;
+
+	while (!list_empty(&dbe->deferred)) {
+		de = list_entry(dbe->deferred.next, struct deferred_export,
+				node);
+		err = dbe->export_comm(dbe, de->comm);
+		list_del(&de->node);
+		free(de);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void db_export__free_deferred(struct db_export *dbe)
+{
+	struct deferred_export *de;
+
+	while (!list_empty(&dbe->deferred)) {
+		de = list_entry(dbe->deferred.next, struct deferred_export,
+				node);
+		list_del(&de->node);
+		free(de);
+	}
+}
+
+static int db_export__defer_comm(struct db_export *dbe, struct comm *comm)
+{
+	struct deferred_export *de;
+
+	de = zalloc(sizeof(struct deferred_export));
+	if (!de)
+		return -ENOMEM;
+
+	de->comm = comm;
+	list_add_tail(&de->node, &dbe->deferred);
+
+	return 0;
+}
+
 int db_export__init(struct db_export *dbe)
 {
 	memset(dbe, 0, sizeof(struct db_export));
+	INIT_LIST_HEAD(&dbe->deferred);
 	return 0;
 }
 
+int db_export__flush(struct db_export *dbe)
+{
+	return db_export__deferred(dbe);
+}
+
 void db_export__exit(struct db_export *dbe)
 {
+	db_export__free_deferred(dbe);
 	call_return_processor__free(dbe->crp);
 	dbe->crp = NULL;
 }

@@ -115,7 +172,10 @@ int db_export__comm(struct db_export *dbe, struct comm *comm,
 	comm->db_id = ++dbe->comm_last_db_id;
 
 	if (dbe->export_comm) {
-		err = dbe->export_comm(dbe, comm);
+		if (main_thread->comm_set)
+			err = dbe->export_comm(dbe, comm);
+		else
+			err = db_export__defer_comm(dbe, comm);
 		if (err)
 			return err;
 	}

index dd5ac2a..adbd22d 100644
@@ -17,6 +17,7 @@
 #define __PERF_DB_EXPORT_H
 
 #include <linux/types.h>
+#include <linux/list.h>
 
 struct perf_evsel;
 struct machine;

@@ -74,9 +75,11 @@ struct db_export {
 	u64 sample_last_db_id;
 	u64 call_path_last_db_id;
 	u64 call_return_last_db_id;
+	struct list_head deferred;
 };
 
 int db_export__init(struct db_export *dbe);
+int db_export__flush(struct db_export *dbe);
 void db_export__exit(struct db_export *dbe);
 int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel);
 int db_export__machine(struct db_export *dbe, struct machine *machine);

index 0e8ad55..357a927 100644
@@ -1030,7 +1030,9 @@ error:
 
 static int python_flush_script(void)
 {
-	return 0;
+	struct tables *tables = &tables_global;
+
+	return db_export__flush(&tables->dbe);
 }
 
 /*