[PATCH 00/31] perf tools: Yet more preparation for call graph from Intel BTS

[PATCH 00/31] perf tools: Yet more preparation for call graph from Intel BTS

[Adrian Hunter]

Hi

Here is the next selection of patches based on tip/perf/core.

They can also be found here:

	http://git.infradead.org/users/ahunter/linux-perf.git/shortlog/refs/heads/for-acme


Adrian Hunter (31):
      perf tools: Identify which comms are from exec
      perf tools: Add machine__thread_exec_comm()
      perf tools: Fix missing label symbols
      perf tools: Add machine__kernel_ip()
      perf tools: Let a user specify a PMU event without any config terms
      perf tools: Let default config be defined for a PMU
      perf tools: Add perf_pmu__scan_file()
      perf evlist: Add 'system_wide' option
      perf evlist: Add perf_evlist__set_tracking_event()
      perf tools: Add id index
      perf pmu: Let pmu's with no events show up on perf list
      perf session: Add perf_session__deliver_synth_event()
      perf evlist: Add perf_evlist__enable_event_idx()
      perf session: Add perf_session__peek_event()
      perf tools: Add a thread stack for synthesizing call chains
      perf script: Allow callchains if any event samples them
      perf tools: Add facility to export data in database-friendly way
      perf tools: Add helpers for calling Python objects
      perf tools: Extend Python script interface to export data in a database-friendly way
      perf tools: Add Python script to export to postgresql
      perf tools: Add flags and insn_len to struct sample
      perf tools: Add branch type to db export
      perf tools: Add branch_type and in_tx to Python export
      perf tools: Enhance the thread stack to output call/return data
      perf tools: Add call information to the database export API
      perf tools: Add call information to Python export
      perf tools: Add 'flush' callback to scripting API
      perf tools: Defer export of comms that were not 'set'
      perf tools: Add perf-with-kcore script
      perf tools: Build programs to copy 32-bit compatibility VDSOs
      perf tools: Add support for 32-bit compatibility VDSOs

 tools/perf/.gitignore                              |   1 +
 tools/perf/Makefile.perf                           |  46 +-
 tools/perf/builtin-inject.c                        |   1 +
 tools/perf/builtin-script.c                        |  29 +-
 tools/perf/config/Makefile                         |  21 +
 tools/perf/config/Makefile.arch                    |   8 +
 tools/perf/perf-read-vdso.c                        |  59 ++
 tools/perf/perf-with-kcore.sh                      | 259 ++++++++
 .../scripts/python/bin/export-to-postgresql-record |   8 +
 .../scripts/python/bin/export-to-postgresql-report |  29 +
 tools/perf/scripts/python/export-to-postgresql.py  | 444 +++++++++++++
 tools/perf/tests/pmu.c                             |   2 +-
 tools/perf/util/comm.c                             |   7 +-
 tools/perf/util/comm.h                             |   7 +-
 tools/perf/util/db-export.c                        | 426 +++++++++++++
 tools/perf/util/db-export.h                        | 107 ++++
 tools/perf/util/dso.h                              |   1 +
 tools/perf/util/event.c                            |   7 +-
 tools/perf/util/event.h                            |  43 ++
 tools/perf/util/evlist.c                           | 135 +++-
 tools/perf/util/evlist.h                           |   5 +
 tools/perf/util/evsel.c                            |  34 +-
 tools/perf/util/evsel.h                            |   6 +
 tools/perf/util/machine.c                          |  53 +-
 tools/perf/util/machine.h                          |  22 +
 tools/perf/util/parse-events.c                     |  13 +-
 tools/perf/util/parse-events.y                     |  10 +
 tools/perf/util/pmu.c                              |  92 ++-
 tools/perf/util/pmu.h                              |  13 +-
 tools/perf/util/record.c                           |   2 +-
 .../perf/util/scripting-engines/trace-event-perl.c |   6 +
 .../util/scripting-engines/trace-event-python.c    | 511 +++++++++++++--
 tools/perf/util/session.c                          | 215 ++++++-
 tools/perf/util/session.h                          |  20 +
 tools/perf/util/symbol-elf.c                       |   2 +-
 tools/perf/util/symbol.h                           |   1 +
 tools/perf/util/thread-stack.c                     | 690 +++++++++++++++++++++
 tools/perf/util/thread-stack.h                     |  79 +++
 tools/perf/util/thread.c                           |  27 +-
 tools/perf/util/thread.h                           |  14 +-
 tools/perf/util/tool.h                             |   3 +-
 tools/perf/util/trace-event-scripting.c            |   7 +
 tools/perf/util/trace-event.h                      |   1 +
 tools/perf/util/vdso.c                             | 170 ++++-
 tools/perf/util/vdso.h                             |   4 +-
 45 files changed, 3505 insertions(+), 135 deletions(-)
 create mode 100644 tools/perf/perf-read-vdso.c
 create mode 100644 tools/perf/perf-with-kcore.sh
 create mode 100644 tools/perf/scripts/python/bin/export-to-postgresql-record
 create mode 100644 tools/perf/scripts/python/bin/export-to-postgresql-report
 create mode 100644 tools/perf/scripts/python/export-to-postgresql.py
 create mode 100644 tools/perf/util/db-export.c
 create mode 100644 tools/perf/util/db-export.h
 create mode 100644 tools/perf/util/thread-stack.c
 create mode 100644 tools/perf/util/thread-stack.h

 
 Regards
 Adrian

[PATCH 01/31] perf tools: Identify which comms are from exec

[Adrian Hunter]

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/comm.c    |  7 +++++--
 tools/perf/util/comm.h    |  6 ++++--
 tools/perf/util/machine.c |  4 +++-
 tools/perf/util/thread.c  | 24 +++++++++++++++++++-----
 tools/perf/util/thread.h  | 10 +++++++++-
 5 files changed, 40 insertions(+), 11 deletions(-)

diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index f9e7776..5e1e80e 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -74,7 +74,7 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
 	return new;
 }
 
-struct comm *comm__new(const char *str, u64 timestamp)
+struct comm *comm__new(const char *str, u64 timestamp, bool exec)
 {
 	struct comm *comm = zalloc(sizeof(*comm));
 
@@ -82,6 +82,7 @@ struct comm *comm__new(const char *str, u64 timestamp)
 		return NULL;
 
 	comm->start = timestamp;
+	comm->exec = exec;
 
 	comm->comm_str = comm_str__findnew(str, &comm_str_root);
 	if (!comm->comm_str) {
@@ -94,7 +95,7 @@ struct comm *comm__new(const char *str, u64 timestamp)
 	return comm;
 }
 
-int comm__override(struct comm *comm, const char *str, u64 timestamp)
+int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec)
 {
 	struct comm_str *new, *old = comm->comm_str;
 
@@ -106,6 +107,8 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp)
 	comm_str__put(old);
 	comm->comm_str = new;
 	comm->start = timestamp;
+	if (exec && !comm->exec)
+		comm->exec = true;
 
 	return 0;
 }
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index fac5bd5..51c10ab 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -11,11 +11,13 @@ struct comm {
 	struct comm_str *comm_str;
 	u64 start;
 	struct list_head list;
+	bool exec;
 };
 
 void comm__free(struct comm *comm);
-struct comm *comm__new(const char *str, u64 timestamp);
+struct comm *comm__new(const char *str, u64 timestamp, bool exec);
 const char *comm__str(const struct comm *comm);
-int comm__override(struct comm *comm, const char *str, u64 timestamp);
+int comm__override(struct comm *comm, const char *str, u64 timestamp,
+		   bool exec);
 
 #endif  /* __PERF_COMM_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 16bba9f..ea3e09f 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -404,11 +404,13 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 	struct thread *thread = machine__findnew_thread(machine,
 							event->comm.pid,
 							event->comm.tid);
+	bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC;
 
 	if (dump_trace)
 		perf_event__fprintf_comm(event, stdout);
 
-	if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) {
+	if (thread == NULL ||
+	    __thread__set_comm(thread, event->comm.comm, sample->time, exec)) {
 		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
 		return -1;
 	}
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 12c7a25..a9df7f2 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -42,7 +42,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 			goto err_thread;
 
 		snprintf(comm_str, 32, ":%d", tid);
-		comm = comm__new(comm_str, 0);
+		comm = comm__new(comm_str, 0, false);
 		free(comm_str);
 		if (!comm)
 			goto err_thread;
@@ -81,19 +81,33 @@ struct comm *thread__comm(const struct thread *thread)
 	return list_first_entry(&thread->comm_list, struct comm, list);
 }
 
+struct comm *thread__exec_comm(const struct thread *thread)
+{
+	struct comm *comm, *last = NULL;
+
+	list_for_each_entry(comm, &thread->comm_list, list) {
+		if (comm->exec)
+			return comm;
+		last = comm;
+	}
+
+	return last;
+}
+
 /* CHECKME: time should always be 0 if event aren't ordered */
-int thread__set_comm(struct thread *thread, const char *str, u64 timestamp)
+int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
+		       bool exec)
 {
 	struct comm *new, *curr = thread__comm(thread);
 	int err;
 
 	/* Override latest entry if it had no specific time coverage */
-	if (!curr->start) {
-		err = comm__override(curr, str, timestamp);
+	if (!curr->start && !curr->exec) {
+		err = comm__override(curr, str, timestamp, exec);
 		if (err)
 			return err;
 	} else {
-		new = comm__new(str, timestamp);
+		new = comm__new(str, timestamp, exec);
 		if (!new)
 			return -ENOMEM;
 		list_add(&new->list, &thread->comm_list);
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 716b772..8c75fa7 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -38,9 +38,17 @@ static inline void thread__exited(struct thread *thread)
 	thread->dead = true;
 }
 
-int thread__set_comm(struct thread *thread, const char *comm, u64 timestamp);
+int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
+		       bool exec);
+static inline int thread__set_comm(struct thread *thread, const char *comm,
+				   u64 timestamp)
+{
+	return __thread__set_comm(thread, comm, timestamp, false);
+}
+
 int thread__comm_len(struct thread *thread);
 struct comm *thread__comm(const struct thread *thread);
+struct comm *thread__exec_comm(const struct thread *thread);
 const char *thread__comm_str(const struct thread *thread);
 void thread__insert_map(struct thread *thread, struct map *map);
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
-- 
1.8.3.2

[PATCH 02/31] perf tools: Add machine__thread_exec_comm()

[Adrian Hunter]

Add machine__thread_exec_comm() to return the comm
that matches the last exec, if the comm_exec flag
is present, or the last comm otherwise.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/machine.c | 26 ++++++++++++++++++++++++++
 tools/perf/util/machine.h |  4 ++++
 tools/perf/util/session.c | 24 +++++++++++++++++++++++-
 3 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index ea3e09f..b093b93 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -31,6 +31,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->symbol_filter = NULL;
 	machine->id_hdr_size = 0;
+	machine->comm_exec = false;
 
 	machine->root_dir = strdup(root_dir);
 	if (machine->root_dir == NULL)
@@ -179,6 +180,19 @@ void machines__set_symbol_filter(struct machines *machines,
 	}
 }
 
+void machines__set_comm_exec(struct machines *machines, bool comm_exec)
+{
+	struct rb_node *nd;
+
+	machines->host.comm_exec = comm_exec;
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+		machine->comm_exec = comm_exec;
+	}
+}
+
 struct machine *machines__find(struct machines *machines, pid_t pid)
 {
 	struct rb_node **p = &machines->guests.rb_node;
@@ -398,6 +412,15 @@ struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 	return __machine__findnew_thread(machine, pid, tid, false);
 }
 
+struct comm *machine__thread_exec_comm(struct machine *machine,
+				       struct thread *thread)
+{
+	if (machine->comm_exec)
+		return thread__exec_comm(thread);
+	else
+		return thread__comm(thread);
+}
+
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample)
 {
@@ -406,6 +429,9 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 							event->comm.tid);
 	bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC;
 
+	if (exec)
+		machine->comm_exec = true;
+
 	if (dump_trace)
 		perf_event__fprintf_comm(event, stdout);
 
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index b972824..61216e0 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -26,6 +26,7 @@ struct machine {
 	struct rb_node	  rb_node;
 	pid_t		  pid;
 	u16		  id_hdr_size;
+	bool		  comm_exec;
 	char		  *root_dir;
 	struct rb_root	  threads;
 	struct list_head  dead_threads;
@@ -47,6 +48,8 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type)
 
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 				    pid_t tid);
+struct comm *machine__thread_exec_comm(struct machine *machine,
+				       struct thread *thread);
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
@@ -88,6 +91,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 
 void machines__set_symbol_filter(struct machines *machines,
 				 symbol_filter_t symbol_filter);
+void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 
 struct machine *machine__new_host(void);
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 88dfef7..bf24696 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -66,6 +66,25 @@ static void perf_session__destroy_kernel_maps(struct perf_session *session)
 	machines__destroy_kernel_maps(&session->machines);
 }
 
+static bool perf_session__has_comm_exec(struct perf_session *session)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(session->evlist, evsel) {
+		if (evsel->attr.comm_exec)
+			return true;
+	}
+
+	return false;
+}
+
+static void perf_session__set_comm_exec(struct perf_session *session)
+{
+	bool comm_exec = perf_session__has_comm_exec(session);
+
+	machines__set_comm_exec(&session->machines, comm_exec);
+}
+
 struct perf_session *perf_session__new(struct perf_data_file *file,
 				       bool repipe, struct perf_tool *tool)
 {
@@ -91,6 +110,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 				goto out_close;
 
 			perf_session__set_id_hdr_size(session);
+			perf_session__set_comm_exec(session);
 		}
 	}
 
@@ -1005,8 +1025,10 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	switch (event->header.type) {
 	case PERF_RECORD_HEADER_ATTR:
 		err = tool->attr(tool, event, &session->evlist);
-		if (err == 0)
+		if (err == 0) {
 			perf_session__set_id_hdr_size(session);
+			perf_session__set_comm_exec(session);
+		}
 		return err;
 	case PERF_RECORD_HEADER_EVENT_TYPE:
 		/*
-- 
1.8.3.2

[PATCH 03/31] perf tools: Fix missing label symbols

[Adrian Hunter]

label symbols are missing because elf_sec__is_a() fails
to find the section because the section strings do not
match the section headers because the sections headers
are from the 'runtime' object and the sections strings
are from the 'symbol source' object.

Fix by getting the section strings from the 'runtime'
object so that they match the section headers.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/symbol-elf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index d753499..ec0b8ea 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -736,7 +736,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	if (symstrs == NULL)
 		goto out_elf_end;
 
-	sec_strndx = elf_getscn(elf, ehdr.e_shstrndx);
+	sec_strndx = elf_getscn(runtime_ss->elf, runtime_ss->ehdr.e_shstrndx);
 	if (sec_strndx == NULL)
 		goto out_elf_end;
 
-- 
1.8.3.2

[PATCH 04/31] perf tools: Add machine__kernel_ip()

[Adrian Hunter]

Add a function to determine if an address is in
the kernel.  This is based on the kernel function
kernel_ip().

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/event.c   |  6 +++---
 tools/perf/util/machine.c | 23 +++++++++++++++++++++++
 tools/perf/util/machine.h | 17 +++++++++++++++++
 3 files changed, 43 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1398c83..ed55819 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -784,9 +784,9 @@ try_again:
 		 * "[vdso]" dso, but for now lets use the old trick of looking
 		 * in the whole kernel symbol list.
 		 */
-		if ((long long)al->addr < 0 &&
-		    cpumode == PERF_RECORD_MISC_USER &&
-		    machine && mg != &machine->kmaps) {
+		if (cpumode == PERF_RECORD_MISC_USER && machine &&
+		    mg != &machine->kmaps &&
+		    machine__kernel_ip(machine, al->addr)) {
 			mg = &machine->kmaps;
 			load_map = true;
 			goto try_again;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b093b93..b25f640 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -32,6 +32,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	machine->symbol_filter = NULL;
 	machine->id_hdr_size = 0;
 	machine->comm_exec = false;
+	machine->kernel_start = 0;
 
 	machine->root_dir = strdup(root_dir);
 	if (machine->root_dir == NULL)
@@ -1559,3 +1560,25 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 
 	return 0;
 }
+
+int machine__get_kernel_start(struct machine *machine)
+{
+	struct map *map = machine__kernel_map(machine, MAP__FUNCTION);
+	int err = 0;
+
+	/*
+	 * The only addresses above 2^63 are kernel addresses of a 64-bit
+	 * kernel.  Note that addresses are unsigned so that on a 32-bit system
+	 * all addresses including kernel addresses are less than 2^32.  In
+	 * that case (32-bit system), if the kernel mapping is unknown, all
+	 * addresses will be assumed to be in user space - see
+	 * machine__kernel_ip().
+	 */
+	machine->kernel_start = 1ULL << 63;
+	if (map) {
+		err = map__load(map, machine->symbol_filter);
+		if (map->start)
+			machine->kernel_start = map->start;
+	}
+	return err;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 61216e0..6a6bcc1 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -36,6 +36,7 @@ struct machine {
 	struct list_head  kernel_dsos;
 	struct map_groups kmaps;
 	struct map	  *vmlinux_maps[MAP__NR_TYPES];
+	u64		  kernel_start;
 	symbol_filter_t	  symbol_filter;
 	pid_t		  *current_tid;
 };
@@ -46,6 +47,22 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type)
 	return machine->vmlinux_maps[type];
 }
 
+int machine__get_kernel_start(struct machine *machine);
+
+static inline u64 machine__kernel_start(struct machine *machine)
+{
+	if (!machine->kernel_start)
+		machine__get_kernel_start(machine);
+	return machine->kernel_start;
+}
+
+static inline bool machine__kernel_ip(struct machine *machine, u64 ip)
+{
+	u64 kernel_start = machine__kernel_start(machine);
+
+	return ip >= kernel_start;
+}
+
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 				    pid_t tid);
 struct comm *machine__thread_exec_comm(struct machine *machine,
-- 
1.8.3.2

[PATCH 05/31] perf tools: Let a user specify a PMU event without any config terms

[Adrian Hunter]

This enables a PMU event to be specified in the form:

	pmu//

which is effectively the same as:

	pmu/config=0/

This patch is a precursor to defining
default config for a PMU.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/parse-events.c |  6 ++++++
 tools/perf/util/parse-events.y | 10 ++++++++++
 2 files changed, 16 insertions(+)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 1e15df1..76fd04b 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -644,6 +644,12 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 
 	memset(&attr, 0, sizeof(attr));
 
+	if (!head_config) {
+		attr.type = pmu->type;
+		evsel = __add_event(list, idx, &attr, NULL, pmu->cpus);
+		return evsel ? 0 : -ENOMEM;
+	}
+
 	if (perf_pmu__check_alias(pmu, head_config, &unit, &scale))
 		return -EINVAL;
 
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 0bc87ba..55fab6a 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -210,6 +210,16 @@ PE_NAME '/' event_config '/'
 	parse_events__free_terms($3);
 	$$ = list;
 }
+|
+PE_NAME '/' '/'
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL));
+	$$ = list;
+}
 
 value_sym:
 PE_VALUE_SYM_HW
-- 
1.8.3.2

[PATCH 06/31] perf tools: Let default config be defined for a PMU

[Adrian Hunter]

This allows default config terms to be provided
for a PMU. So, for example, when the Intel PT
PMU is added, it will be possible to specify:

	intel_pt//

which will be the same as:

	intel_pt/tsc=1,noretcomp=0/

meaning that the trace should contain
TSC timestamps and perform 'return
compression'.

An important consideration of this
patch is that it must be possible
to overwrite the default values.
That has meant changing the logic
so that a zero value can replace
a non-zero value.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/tests/pmu.c         |  2 +-
 tools/perf/util/parse-events.c |  7 ++++++-
 tools/perf/util/pmu.c          | 42 ++++++++++++++++++++++++++----------------
 tools/perf/util/pmu.h          |  9 ++++++++-
 4 files changed, 41 insertions(+), 19 deletions(-)

diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 12b322f..eeb68bb1 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -152,7 +152,7 @@ int test__pmu(void)
 		if (ret)
 			break;
 
-		ret = perf_pmu__config_terms(&formats, &attr, terms);
+		ret = perf_pmu__config_terms(&formats, &attr, terms, false);
 		if (ret)
 			break;
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 76fd04b..20d2c1e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -642,7 +642,12 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 	if (!pmu)
 		return -EINVAL;
 
-	memset(&attr, 0, sizeof(attr));
+	if (pmu->default_config) {
+		memcpy(&attr, pmu->default_config,
+		       sizeof(struct perf_event_attr));
+	} else {
+		memset(&attr, 0, sizeof(attr));
+	}
 
 	if (!head_config) {
 		attr.type = pmu->type;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 7a811eb..11ec977 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -2,6 +2,7 @@
 #include <sys/types.h>
 #include <unistd.h>
 #include <stdio.h>
+#include <stdbool.h>
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
@@ -387,6 +388,12 @@ static struct cpu_map *pmu_cpumask(const char *name)
 	return cpus;
 }
 
+struct perf_event_attr *__attribute__((weak))
+perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+{
+	return NULL;
+}
+
 static struct perf_pmu *pmu_lookup(const char *name)
 {
 	struct perf_pmu *pmu;
@@ -421,6 +428,9 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	pmu->name = strdup(name);
 	pmu->type = type;
 	list_add_tail(&pmu->list, &pmus);
+
+	pmu->default_config = perf_pmu__get_default_config(pmu);
+
 	return pmu;
 }
 
@@ -479,28 +489,24 @@ pmu_find_format(struct list_head *formats, char *name)
 }
 
 /*
- * Returns value based on the format definition (format parameter)
+ * Sets value based on the format definition (format parameter)
  * and unformated value (value parameter).
- *
- * TODO maybe optimize a little ;)
  */
-static __u64 pmu_format_value(unsigned long *format, __u64 value)
+static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
+			     bool zero)
 {
 	unsigned long fbit, vbit;
-	__u64 v = 0;
 
 	for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) {
 
 		if (!test_bit(fbit, format))
 			continue;
 
-		if (!(value & (1llu << vbit++)))
-			continue;
-
-		v |= (1llu << fbit);
+		if (value & (1llu << vbit++))
+			*v |= (1llu << fbit);
+		else if (zero)
+			*v &= ~(1llu << fbit);
 	}
-
-	return v;
 }
 
 /*
@@ -509,7 +515,8 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value)
  */
 static int pmu_config_term(struct list_head *formats,
 			   struct perf_event_attr *attr,
-			   struct parse_events_term *term)
+			   struct parse_events_term *term,
+			   bool zero)
 {
 	struct perf_pmu_format *format;
 	__u64 *vp;
@@ -548,18 +555,19 @@ static int pmu_config_term(struct list_head *formats,
 	 * non-hardcoded terms, here's the place to translate
 	 * them into value.
 	 */
-	*vp |= pmu_format_value(format->bits, term->val.num);
+	pmu_format_value(format->bits, term->val.num, vp, zero);
 	return 0;
 }
 
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
-			   struct list_head *head_terms)
+			   struct list_head *head_terms,
+			   bool zero)
 {
 	struct parse_events_term *term;
 
 	list_for_each_entry(term, head_terms, list)
-		if (pmu_config_term(formats, attr, term))
+		if (pmu_config_term(formats, attr, term, zero))
 			return -EINVAL;
 
 	return 0;
@@ -573,8 +581,10 @@ int perf_pmu__config_terms(struct list_head *formats,
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms)
 {
+	bool zero = !!pmu->default_config;
+
 	attr->type = pmu->type;
-	return perf_pmu__config_terms(&pmu->format, attr, head_terms);
+	return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero);
 }
 
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index c14a543..281d5b1 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -13,9 +13,12 @@ enum {
 
 #define PERF_PMU_FORMAT_BITS 64
 
+struct perf_event_attr;
+
 struct perf_pmu {
 	char *name;
 	__u32 type;
+	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
 	struct list_head format;
 	struct list_head aliases;
@@ -27,7 +30,8 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms);
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
-			   struct list_head *head_terms);
+			   struct list_head *head_terms,
+			   bool zero);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 			  const char **unit, double *scale);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
@@ -46,4 +50,7 @@ void print_pmu_events(const char *event_glob, bool name_only);
 bool pmu_have_event(const char *pname, const char *name);
 
 int perf_pmu__test(void);
+
+struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
+
 #endif /* __PMU_H */
-- 
1.8.3.2

[PATCH 07/31] perf tools: Add perf_pmu__scan_file()

[Adrian Hunter]

Add a function to scan a sysfs file within the pmu device
directory.

This will be used to read capability values from the PMU
'caps' subdirectory.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/pmu.c | 37 +++++++++++++++++++++++++++++++++++++
 tools/perf/util/pmu.h |  3 +++
 2 files changed, 40 insertions(+)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 11ec977..348d1d2 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -3,6 +3,7 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <stdbool.h>
+#include <stdarg.h>
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
@@ -804,3 +805,39 @@ bool pmu_have_event(const char *pname, const char *name)
 	}
 	return false;
 }
+
+static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs;
+
+	sysfs = sysfs__mountpoint();
+	if (!sysfs)
+		return NULL;
+
+	snprintf(path, PATH_MAX,
+		 "%s" EVENT_SOURCE_DEVICE_PATH "%s/%s", sysfs, pmu->name, name);
+
+	if (stat(path, &st) < 0)
+		return NULL;
+
+	return fopen(path, "r");
+}
+
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+			...)
+{
+	va_list args;
+	FILE *file;
+	int ret = EOF;
+
+	va_start(args, fmt);
+	file = perf_pmu__open_file(pmu, name);
+	if (file) {
+		ret = vfscanf(file, fmt, args);
+		fclose(file);
+	}
+	va_end(args);
+	return ret;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 281d5b1..c35f578 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -49,6 +49,9 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 void print_pmu_events(const char *event_glob, bool name_only);
 bool pmu_have_event(const char *pname, const char *name);
 
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+			...) __attribute__((format(scanf, 3, 4)));
+
 int perf_pmu__test(void);
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
-- 
1.8.3.2

[PATCH 08/31] perf evlist: Add 'system_wide' option

[Adrian Hunter]

Add an option to cause a selected event
to be opened always without a pid when
configured by perf_evsel__config().

This is needed when using the sched_switch
tracepoint to follow object code execution.
sched_switch occurs before the task
switch and so it cannot record it in a
context limited to that task.  Note
that also means that sched_switch is
useless when capturing data per-thread,
as is the 'context-switches' software
event for the same reason.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/evlist.c | 45 +++++++++++++++++++++++++++++++++++++--------
 tools/perf/util/evsel.c  | 31 ++++++++++++++++++++++++++-----
 tools/perf/util/evsel.h  |  1 +
 3 files changed, 64 insertions(+), 13 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 814e954..7cfc371 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -265,17 +265,27 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist,
 	return 0;
 }
 
+static int perf_evlist__nr_threads(struct perf_evlist *evlist,
+				   struct perf_evsel *evsel)
+{
+	if (evsel->system_wide)
+		return 1;
+	else
+		return thread_map__nr(evlist->threads);
+}
+
 void perf_evlist__disable(struct perf_evlist *evlist)
 {
 	int cpu, thread;
 	struct perf_evsel *pos;
 	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = thread_map__nr(evlist->threads);
+	int nr_threads;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		evlist__for_each(evlist, pos) {
 			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 				continue;
+			nr_threads = perf_evlist__nr_threads(evlist, pos);
 			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_DISABLE, 0);
@@ -288,12 +298,13 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 	int cpu, thread;
 	struct perf_evsel *pos;
 	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = thread_map__nr(evlist->threads);
+	int nr_threads;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		evlist__for_each(evlist, pos) {
 			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 				continue;
+			nr_threads = perf_evlist__nr_threads(evlist, pos);
 			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_ENABLE, 0);
@@ -305,12 +316,14 @@ int perf_evlist__disable_event(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel)
 {
 	int cpu, thread, err;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
 
 	if (!evsel->fd)
 		return 0;
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-		for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		for (thread = 0; thread < nr_threads; thread++) {
 			err = ioctl(FD(evsel, cpu, thread),
 				    PERF_EVENT_IOC_DISABLE, 0);
 			if (err)
@@ -324,12 +337,14 @@ int perf_evlist__enable_event(struct perf_evlist *evlist,
 			      struct perf_evsel *evsel)
 {
 	int cpu, thread, err;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
 
 	if (!evsel->fd)
 		return -EINVAL;
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-		for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		for (thread = 0; thread < nr_threads; thread++) {
 			err = ioctl(FD(evsel, cpu, thread),
 				    PERF_EVENT_IOC_ENABLE, 0);
 			if (err)
@@ -343,7 +358,16 @@ static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
 	int nr_cpus = cpu_map__nr(evlist->cpus);
 	int nr_threads = thread_map__nr(evlist->threads);
-	int nfds = nr_cpus * nr_threads * evlist->nr_entries;
+	int nfds = 0;
+	struct perf_evsel *evsel;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		if (evsel->system_wide)
+			nfds += nr_cpus;
+		else
+			nfds += nr_cpus * nr_threads;
+	}
+
 	evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
 	return evlist->pollfd != NULL ? 0 : -ENOMEM;
 }
@@ -636,7 +660,12 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 	struct perf_evsel *evsel;
 
 	evlist__for_each(evlist, evsel) {
-		int fd = FD(evsel, cpu, thread);
+		int fd;
+
+		if (evsel->system_wide && thread)
+			continue;
+
+		fd = FD(evsel, cpu, thread);
 
 		if (*output == -1) {
 			*output = fd;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 21a373e..7baa06f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -692,6 +692,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	int cpu, thread;
+
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
 
 	if (evsel->fd) {
@@ -710,6 +714,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea
 {
 	int cpu, thread;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	for (cpu = 0; cpu < ncpus; cpu++) {
 		for (thread = 0; thread < nthreads; thread++) {
 			int fd = FD(evsel, cpu, thread),
@@ -740,6 +747,9 @@ int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
 	if (evsel->sample_id == NULL)
 		return -ENOMEM;
@@ -784,6 +794,9 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	int cpu, thread;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	for (cpu = 0; cpu < ncpus; cpu++)
 		for (thread = 0; thread < nthreads; ++thread) {
 			close(FD(evsel, cpu, thread));
@@ -872,6 +885,9 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 	int cpu, thread;
 	struct perf_counts_values *aggr = &evsel->counts->aggr, count;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	aggr->val = aggr->ena = aggr->run = 0;
 
 	for (cpu = 0; cpu < ncpus; cpu++) {
@@ -994,13 +1010,18 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 			      struct thread_map *threads)
 {
-	int cpu, thread;
+	int cpu, thread, nthreads;
 	unsigned long flags = PERF_FLAG_FD_CLOEXEC;
 	int pid = -1, err;
 	enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+	else
+		nthreads = threads->nr;
+
 	if (evsel->fd == NULL &&
-	    perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
+	    perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0)
 		return -ENOMEM;
 
 	if (evsel->cgrp) {
@@ -1024,10 +1045,10 @@ retry_sample_id:
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
-		for (thread = 0; thread < threads->nr; thread++) {
+		for (thread = 0; thread < nthreads; thread++) {
 			int group_fd;
 
-			if (!evsel->cgrp)
+			if (!evsel->cgrp && !evsel->system_wide)
 				pid = threads->map[thread];
 
 			group_fd = get_group_fd(evsel, cpu, thread);
@@ -1100,7 +1121,7 @@ out_close:
 			close(FD(evsel, cpu, thread));
 			FD(evsel, cpu, thread) = -1;
 		}
-		thread = threads->nr;
+		thread = nthreads;
 	} while (--cpu >= 0);
 	return err;
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d7f93ce..dbb2a0d 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -85,6 +85,7 @@ struct perf_evsel {
 	bool 			needs_swap;
 	bool			no_aux_samples;
 	bool			immediate;
+	bool			system_wide;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
-- 
1.8.3.2

[PATCH 09/31] perf evlist: Add perf_evlist__set_tracking_event()

[Adrian Hunter]

Add a function to change which event is used
to track mmap, comm and task events.

This is needed with Instruction Tracing
because the Instruction Tracing event
must come first but cannot be used for
tracking because it will be disabled
under some circumstances.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/evlist.c | 17 +++++++++++++++++
 tools/perf/util/evlist.h |  3 +++
 tools/perf/util/evsel.c  |  3 ++-
 tools/perf/util/evsel.h  |  1 +
 tools/perf/util/record.c |  2 +-
 5 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 7cfc371..e47d724 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -122,6 +122,7 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 {
 	list_add_tail(&entry->node, &evlist->entries);
 	entry->idx = evlist->nr_entries;
+	entry->tracking = !entry->idx;
 
 	if (!evlist->nr_entries++)
 		perf_evlist__set_id_pos(evlist);
@@ -1279,3 +1280,19 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 
 	list_splice(&move, &evlist->entries);
 }
+
+void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
+				     struct perf_evsel *tracking_evsel)
+{
+	struct perf_evsel *evsel;
+
+	if (tracking_evsel->tracking)
+		return;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel != tracking_evsel)
+			evsel->tracking = false;
+	}
+
+	tracking_evsel->tracking = true;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index f5173cd..e0084f9 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -262,4 +262,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 #define evlist__for_each_safe(evlist, tmp, evsel) \
 	__evlist__for_each_safe(&(evlist)->entries, tmp, evsel)
 
+void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
+				     struct perf_evsel *tracking_evsel);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7baa06f..fbe0ce4 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -162,6 +162,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
 	evsel->idx	   = idx;
+	evsel->tracking	   = !idx;
 	evsel->attr	   = *attr;
 	evsel->leader	   = evsel;
 	evsel->unit	   = "";
@@ -561,7 +562,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 {
 	struct perf_evsel *leader = evsel->leader;
 	struct perf_event_attr *attr = &evsel->attr;
-	int track = !evsel->idx; /* only the first counter needs these */
+	int track = evsel->tracking;
 	bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
 
 	attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index dbb2a0d..7bc314b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -86,6 +86,7 @@ struct perf_evsel {
 	bool			no_aux_samples;
 	bool			immediate;
 	bool			system_wide;
+	bool			tracking;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index fe8079e..787b882 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -106,7 +106,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 
 	evlist__for_each(evlist, evsel) {
 		perf_evsel__config(evsel, opts);
-		if (!evsel->idx && use_comm_exec)
+		if (evsel->tracking && use_comm_exec)
 			evsel->attr.comm_exec = 1;
 	}
 
-- 
1.8.3.2

[PATCH 10/31] perf tools: Add id index

[Adrian Hunter]

Add an index of the event identifiers.

This is needed to queue Instruction
Trace samples according to the mmap
buffer from which they were recorded.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/builtin-inject.c |   1 +
 tools/perf/util/event.c     |   1 +
 tools/perf/util/event.h     |  15 ++++++
 tools/perf/util/evlist.c    |  26 ++++++++--
 tools/perf/util/evsel.h     |   3 ++
 tools/perf/util/session.c   | 122 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/session.h   |  10 ++++
 tools/perf/util/tool.h      |   3 +-
 8 files changed, 177 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 9a02807..af17800 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -419,6 +419,7 @@ 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),
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index ed55819..1727574 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -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)
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 94d6976..08c6ae0 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -185,6 +185,7 @@ 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
 };
 
@@ -211,6 +212,19 @@ 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;
@@ -225,6 +239,7 @@ 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);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e47d724..b08ad11 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -442,6 +442,22 @@ 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;
@@ -677,9 +693,13 @@ 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;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 7bc314b..d46d28e 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -38,6 +38,9 @@ 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;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index bf24696..724e749 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -229,6 +229,15 @@ static int process_finished_round(struct perf_tool *tool,
 				  union perf_event *event,
 				  struct perf_session *session);
 
+static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
+				 union perf_event *event __maybe_unused,
+				 struct perf_session *perf_session
+				 __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 void perf_tool__fill_defaults(struct perf_tool *tool)
 {
 	if (tool->sample == NULL)
@@ -263,6 +272,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		else
 			tool->finished_round = process_finished_round_stub;
 	}
+	if (tool->id_index == NULL)
+		tool->id_index = process_id_index_stub;
 }
  
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -461,6 +472,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
 	[PERF_RECORD_HEADER_BUILD_ID]	  = NULL,
+	[PERF_RECORD_ID_INDEX]		  = perf_event__all64_swap,
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
@@ -1044,6 +1056,8 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		return tool->build_id(tool, event, session);
 	case PERF_RECORD_FINISHED_ROUND:
 		return tool->finished_round(tool, event, session);
+	case PERF_RECORD_ID_INDEX:
+		return tool->id_index(tool, event, session);
 	default:
 		return -EINVAL;
 	}
@@ -1704,3 +1718,111 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 out:
 	return err;
 }
+
+int perf_event__process_id_index(struct perf_tool *tool __maybe_unused,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	struct perf_evlist *evlist = session->evlist;
+	struct id_index_event *ie = &event->id_index;
+	size_t i, nr, max_nr;
+
+	max_nr = (ie->header.size - sizeof(struct id_index_event)) /
+		 sizeof(struct id_index_entry);
+	nr = ie->nr;
+	if (nr > max_nr)
+		return -EINVAL;
+
+	if (dump_trace)
+		fprintf(stdout, " nr: %zu\n", nr);
+
+	for (i = 0; i < nr; i++) {
+		struct id_index_entry *e = &ie->entries[i];
+		struct perf_sample_id *sid;
+
+		if (dump_trace) {
+			fprintf(stdout,	" ... id: %"PRIu64, e->id);
+			fprintf(stdout,	"  idx: %"PRIu64, e->idx);
+			fprintf(stdout,	"  cpu: %"PRId64, e->cpu);
+			fprintf(stdout,	"  tid: %"PRId64"\n", e->tid);
+		}
+
+		sid = perf_evlist__id2sid(evlist, e->id);
+		if (!sid)
+			return -ENOENT;
+		sid->idx = e->idx;
+		sid->cpu = e->cpu;
+		sid->tid = e->tid;
+	}
+	return 0;
+}
+
+int perf_event__synthesize_id_index(struct perf_tool *tool,
+				    perf_event__handler_t process,
+				    struct perf_evlist *evlist,
+				    struct machine *machine)
+{
+	union perf_event *ev;
+	struct perf_evsel *evsel;
+	size_t nr = 0, i = 0, sz, max_nr, n;
+	int err;
+
+	pr_debug2("Synthesizing id index\n");
+
+	max_nr = (UINT16_MAX - sizeof(struct id_index_event)) /
+		 sizeof(struct id_index_entry);
+
+	list_for_each_entry(evsel, &evlist->entries, node)
+		nr += evsel->ids;
+
+	n = nr > max_nr ? max_nr : nr;
+	sz = sizeof(struct id_index_event) + n * sizeof(struct id_index_entry);
+	ev = zalloc(sz);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->id_index.header.type = PERF_RECORD_ID_INDEX;
+	ev->id_index.header.size = sz;
+	ev->id_index.nr = n;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		u32 j;
+
+		for (j = 0; j < evsel->ids; j++) {
+			struct id_index_entry *e;
+			struct perf_sample_id *sid;
+
+			if (i >= n) {
+				err = process(tool, ev, NULL, machine);
+				if (err)
+					goto out_err;
+				nr -= n;
+				i = 0;
+			}
+
+			e = &ev->id_index.entries[i++];
+
+			e->id = evsel->id[j];
+
+			sid = perf_evlist__id2sid(evlist, e->id);
+			if (!sid) {
+				free(ev);
+				return -ENOENT;
+			}
+
+			e->idx = sid->idx;
+			e->cpu = sid->cpu;
+			e->tid = sid->tid;
+		}
+	}
+
+	sz = sizeof(struct id_index_event) + nr * sizeof(struct id_index_entry);
+	ev->id_index.header.size = sz;
+	ev->id_index.nr = nr;
+
+	err = process(tool, ev, NULL, machine);
+out_err:
+	free(ev);
+
+	return err;
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 0321013..39327ca 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -129,4 +129,14 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 extern volatile int session_done;
 
 #define session_done()	(*(volatile int *)(&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 */
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 4385816..f07d6fe 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -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_samples;
 	bool		ordering_requires_timestamps;
 };
-- 
1.8.3.2

[PATCH 11/31] perf pmu: Let pmu's with no events show up on perf list

[Adrian Hunter]

perf list only lists PMUs with events.  Add a
flag to cause a PMU to be also listed separately.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/pmu.c | 13 +++++++++++--
 tools/perf/util/pmu.h |  1 +
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 348d1d2..ba300d9 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -749,15 +749,18 @@ void print_pmu_events(const char *event_glob, bool name_only)
 
 	pmu = NULL;
 	len = 0;
-	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 		list_for_each_entry(alias, &pmu->aliases, list)
 			len++;
+		if (pmu->selectable)
+			len++;
+	}
 	aliases = malloc(sizeof(char *) * len);
 	if (!aliases)
 		return;
 	pmu = NULL;
 	j = 0;
-	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 		list_for_each_entry(alias, &pmu->aliases, list) {
 			char *name = format_alias(buf, sizeof(buf), pmu, alias);
 			bool is_cpu = !strcmp(pmu->name, "cpu");
@@ -774,6 +777,12 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			aliases[j] = strdup(aliases[j]);
 			j++;
 		}
+		if (pmu->selectable) {
+			scnprintf(buf, sizeof(buf), "%s//", pmu->name);
+			aliases[j] = strdup(buf);
+			j++;
+		}
+	}
 	len = j;
 	qsort(aliases, len, sizeof(char *), cmp_string);
 	for (j = 0; j < len; j++) {
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index c35f578..8c999b3 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -18,6 +18,7 @@ struct perf_event_attr;
 struct perf_pmu {
 	char *name;
 	__u32 type;
+	bool selectable;
 	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
 	struct list_head format;
-- 
1.8.3.2

[PATCH 12/31] perf session: Add perf_session__deliver_synth_event()

[Adrian Hunter]

Add a function to deliver synthesized events from
within a session.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/session.c | 14 ++++++++++++++
 tools/perf/util/session.h |  5 +++++
 2 files changed, 19 insertions(+)

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 724e749..c831c04 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1063,6 +1063,20 @@ 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;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 39327ca..86f1bb4 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -130,6 +130,11 @@ extern volatile int session_done;
 
 #define session_done()	(*(volatile int *)(&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);
-- 
1.8.3.2

[PATCH 13/31] perf evlist: Add perf_evlist__enable_event_idx()

[Adrian Hunter]

Add a function to enable a specific event
within a specific perf event buffer.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/evlist.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/evlist.h |  2 ++
 2 files changed, 49 insertions(+)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b08ad11..5a632bc 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -355,6 +355,53 @@ int perf_evlist__enable_event(struct perf_evlist *evlist,
 	return 0;
 }
 
+static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist,
+					 struct perf_evsel *evsel, int cpu)
+{
+	int thread, err;
+	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
+
+	if (!evsel->fd)
+		return -EINVAL;
+
+	for (thread = 0; thread < nr_threads; thread++) {
+		err = ioctl(FD(evsel, cpu, thread),
+			    PERF_EVENT_IOC_ENABLE, 0);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int perf_evlist__enable_event_thread(struct perf_evlist *evlist,
+					    struct perf_evsel *evsel,
+					    int thread)
+{
+	int cpu, err;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+
+	if (!evsel->fd)
+		return -EINVAL;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
+				  struct perf_evsel *evsel, int idx)
+{
+	bool per_cpu_mmaps = !cpu_map__empty(evlist->cpus);
+
+	if (per_cpu_mmaps)
+		return perf_evlist__enable_event_cpu(evlist, evsel, idx);
+	else
+		return perf_evlist__enable_event_thread(evlist, evsel, idx);
+}
+
 static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
 	int nr_cpus = cpu_map__nr(evlist->cpus);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index e0084f9..106de53 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -122,6 +122,8 @@ int perf_evlist__disable_event(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
 int perf_evlist__enable_event(struct perf_evlist *evlist,
 			      struct perf_evsel *evsel);
+int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
+				  struct perf_evsel *evsel, int idx);
 
 void perf_evlist__set_selected(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
-- 
1.8.3.2

[PATCH 14/31] perf session: Add perf_session__peek_event()

[Adrian Hunter]

Add a function to peek at other events in the
event stream.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/session.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/session.h |  5 +++++
 2 files changed, 60 insertions(+)

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c831c04..da440dc 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1086,6 +1086,61 @@ static void event_swap(union perf_event *event, bool sample_id_all)
 		swap(event, sample_id_all);
 }
 
+int perf_session__peek_event(struct perf_session *session, off_t file_offset,
+			     void *buf, size_t buf_sz,
+			     union perf_event **event_ptr,
+			     struct perf_sample *sample)
+{
+	union perf_event *event;
+	size_t hdr_sz, rest;
+	int fd;
+
+	if (session->one_mmap && !session->header.needs_swap) {
+		event = file_offset - session->one_mmap_offset +
+			session->one_mmap_addr;
+		goto out_parse_sample;
+	}
+
+	if (perf_data_file__is_pipe(session->file))
+		return -1;
+
+	fd = perf_data_file__fd(session->file);
+	hdr_sz = sizeof(struct perf_event_header);
+
+	if (buf_sz < hdr_sz)
+		return -1;
+
+	if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 ||
+	    readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz)
+		return -1;
+
+	event = (union perf_event *)buf;
+
+	if (session->header.needs_swap)
+		perf_event_header__bswap(&event->header);
+
+	if (event->header.size < hdr_sz)
+		return -1;
+
+	rest = event->header.size - hdr_sz;
+
+	if (readn(fd, &buf, rest) != (ssize_t)rest)
+		return -1;
+
+	if (session->header.needs_swap)
+		event_swap(event, perf_evlist__sample_id_all(session->evlist));
+
+out_parse_sample:
+
+	if (sample && event->header.type < PERF_RECORD_USER_TYPE_START &&
+	    perf_evlist__parse_sample(session->evlist, event, sample))
+		return -1;
+
+	*event_ptr = event;
+
+	return 0;
+}
+
 static s64 perf_session__process_event(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_tool *tool,
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 86f1bb4..e4ea0cf5 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -58,6 +58,11 @@ void perf_session__delete(struct perf_session *session);
 
 void perf_event_header__bswap(struct perf_event_header *hdr);
 
+int perf_session__peek_event(struct perf_session *session, off_t file_offset,
+			     void *buf, size_t buf_sz,
+			     union perf_event **event_ptr,
+			     struct perf_sample *sample);
+
 int __perf_session__process_events(struct perf_session *session,
 				   u64 data_offset, u64 data_size, u64 size,
 				   struct perf_tool *tool);
-- 
1.8.3.2

[PATCH 15/31] perf tools: Add a thread stack for synthesizing call chains

[Adrian Hunter]

Add a thread stack for synthesizing call chains from call
and return events.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/Makefile.perf       |   2 +
 tools/perf/util/event.h        |  26 +++++++
 tools/perf/util/thread-stack.c | 151 +++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/thread-stack.h |  32 +++++++++
 tools/perf/util/thread.c       |   3 +
 tools/perf/util/thread.h       |   3 +
 6 files changed, 217 insertions(+)
 create mode 100644 tools/perf/util/thread-stack.c
 create mode 100644 tools/perf/util/thread-stack.h

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 2240974..f4333b5 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -302,6 +302,7 @@ LIB_H += ui/util.h
 LIB_H += ui/ui.h
 LIB_H += util/data.h
 LIB_H += util/kvm-stat.h
+LIB_H += util/thread-stack.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -377,6 +378,7 @@ LIB_OBJS += $(OUTPUT)util/srcline.o
 LIB_OBJS += $(OUTPUT)util/data.o
 LIB_OBJS += $(OUTPUT)util/tsc.o
 LIB_OBJS += $(OUTPUT)util/cloexec.o
+LIB_OBJS += $(OUTPUT)util/thread-stack.o
 
 LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 08c6ae0..b8e5d1a 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -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;
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
new file mode 100644
index 0000000..c1ca2a9
--- /dev/null
+++ b/tools/perf/util/thread-stack.c
@@ -0,0 +1,151 @@
+/*
+ * thread-stack.c: 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.
+ *
+ */
+
+#include "thread.h"
+#include "event.h"
+#include "util.h"
+#include "thread-stack.h"
+
+#define STACK_GROWTH 4096
+
+struct thread_stack_entry {
+	u64 ret_addr;
+};
+
+struct thread_stack {
+	struct thread_stack_entry *stack;
+	size_t cnt;
+	size_t sz;
+	u64 trace_nr;
+};
+
+static void thread_stack__grow(struct thread_stack *ts)
+{
+	struct thread_stack_entry *new_stack;
+	size_t sz, new_sz;
+
+	new_sz = ts->sz + STACK_GROWTH;
+	sz = new_sz * sizeof(struct thread_stack_entry);
+	new_stack = realloc(ts->stack, sz);
+	if (new_stack) {
+		ts->stack = new_stack;
+		ts->sz = new_sz;
+	}
+}
+
+static struct thread_stack *thread_stack__new(void)
+{
+	struct thread_stack *ts;
+
+	ts = zalloc(sizeof(struct thread_stack));
+	if (!ts)
+		return NULL;
+
+	thread_stack__grow(ts);
+	if (!ts->stack) {
+		free(ts);
+		return NULL;
+	}
+
+	return ts;
+}
+
+static void thread_stack__push(struct thread_stack *ts, u64 ret_addr)
+{
+	if (ts->cnt == ts->sz) {
+		thread_stack__grow(ts);
+		if (ts->cnt == ts->sz)
+			ts->cnt = 0;
+	}
+
+	ts->stack[ts->cnt++].ret_addr = ret_addr;
+}
+
+static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
+{
+	if (!ts->cnt)
+		return;
+
+	if (ts->stack[ts->cnt - 1].ret_addr == ret_addr) {
+		ts->cnt -= 1;
+	} else {
+		size_t i = ts->cnt - 1;
+
+		while (i--) {
+			if (ts->stack[i].ret_addr == ret_addr) {
+				ts->cnt = i;
+				return;
+			}
+		}
+	}
+}
+
+void thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+			 u64 to_ip, u16 insn_len, u64 trace_nr)
+{
+	if (!thread)
+		return;
+
+	if (!thread->ts) {
+		thread->ts = thread_stack__new();
+		if (!thread->ts)
+			return;
+		thread->ts->trace_nr = trace_nr;
+	}
+
+	if (trace_nr != thread->ts->trace_nr) {
+		thread->ts->trace_nr = trace_nr;
+		thread->ts->cnt = 0;
+	}
+
+	if (flags & PERF_FLAG_CALL) {
+		u64 ret_addr;
+
+		if (!to_ip)
+			return;
+		ret_addr = from_ip + insn_len;
+		if (ret_addr == to_ip)
+			return; /* Zero-length calls are excluded */
+		thread_stack__push(thread->ts, ret_addr);
+	} else if (flags & PERF_FLAG_RETURN) {
+		if (!from_ip)
+			return;
+		thread_stack__pop(thread->ts, to_ip);
+	}
+}
+
+void thread_stack__free(struct thread *thread)
+{
+	if (thread->ts) {
+		zfree(&thread->ts->stack);
+		zfree(&thread->ts);
+	}
+}
+
+void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+			  size_t sz, u64 ip)
+{
+	size_t i;
+
+	if (!thread || !thread->ts)
+		chain->nr = 1;
+	else
+		chain->nr = min(sz, thread->ts->cnt + 1);
+
+	chain->ips[0] = ip;
+
+	for (i = 1; i < chain->nr; i++)
+		chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+}
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
new file mode 100644
index 0000000..c0ba4cf
--- /dev/null
+++ b/tools/perf/util/thread-stack.h
@@ -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
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index a9df7f2..088c036 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -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"
@@ -61,6 +62,8 @@ 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;
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 8c75fa7..a057820 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -8,6 +8,8 @@
 #include "symbol.h"
 #include <strlist.h>
 
+struct thread_stack;
+
 struct thread {
 	union {
 		struct rb_node	 rb_node;
@@ -25,6 +27,7 @@ struct thread {
 	int			comm_len;
 
 	void			*priv;
+	struct thread_stack	*ts;
 };
 
 struct machine;
-- 
1.8.3.2

[PATCH 16/31] perf script: Allow callchains if any event samples them

[Adrian Hunter]

perf script was not displaying callchains if any selected
event did not have PERF_SAMPLE_CALLCHAIN.  Change this to
disable callchains only if all selected events do not have
PERF_SAMPLE_CALLCHAIN.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/builtin-script.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index f57035b..163d12b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -184,10 +184,6 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP",
 					    PERF_OUTPUT_IP))
 			return -EINVAL;
-
-		if (!no_callchain &&
-		    !(attr->sample_type & PERF_SAMPLE_CALLCHAIN))
-			symbol_conf.use_callchain = false;
 	}
 
 	if (PRINT_FIELD(ADDR) &&
@@ -290,6 +286,19 @@ static int perf_session__check_output_opt(struct perf_session *session)
 		set_print_ip_opts(&evsel->attr);
 	}
 
+	if (!no_callchain) {
+		bool use_callchain = false;
+
+		evlist__for_each(session->evlist, evsel) {
+			if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
+				use_callchain = true;
+				break;
+			}
+		}
+		if (!use_callchain)
+			symbol_conf.use_callchain = false;
+	}
+
 	/*
 	 * set default for tracepoints to print symbols only
 	 * if callchains are present
-- 
1.8.3.2

[PATCH 17/31] perf tools: Add facility to export data in database-friendly way

[Adrian Hunter]

This patch introduces an abstraction for exporting sample
data in a database-friendly way.  The abstraction does not
implement the actual output.  A subsequent patch takes this
facility into use for extending the script interface.

The abstraction is needed because static data like symbols,
dsos, comms etc need to be exported only once.  That means
allocating them a unique identifier and recording it on each
structure.  The member 'db_id' is used for that.  'db_id'
is just a 64-bit sequence number.

Exporting centres around the db_export__sample() function
which exports the associated data structures if they have
not yet been allocated a db_id.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/Makefile.perf    |   2 +
 tools/perf/util/comm.h      |   1 +
 tools/perf/util/db-export.c | 268 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/db-export.h |  86 ++++++++++++++
 tools/perf/util/dso.h       |   1 +
 tools/perf/util/evsel.h     |   1 +
 tools/perf/util/machine.h   |   1 +
 tools/perf/util/symbol.h    |   1 +
 tools/perf/util/thread.h    |   1 +
 9 files changed, 362 insertions(+)
 create mode 100644 tools/perf/util/db-export.c
 create mode 100644 tools/perf/util/db-export.h

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index f4333b5..f7bb2b4 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -303,6 +303,7 @@ LIB_H += ui/ui.h
 LIB_H += util/data.h
 LIB_H += util/kvm-stat.h
 LIB_H += util/thread-stack.h
+LIB_H += util/db-export.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -379,6 +380,7 @@ LIB_OBJS += $(OUTPUT)util/data.o
 LIB_OBJS += $(OUTPUT)util/tsc.o
 LIB_OBJS += $(OUTPUT)util/cloexec.o
 LIB_OBJS += $(OUTPUT)util/thread-stack.o
+LIB_OBJS += $(OUTPUT)util/db-export.o
 
 LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index 51c10ab..99e7021 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -10,6 +10,7 @@ struct comm_str;
 struct comm {
 	struct comm_str *comm_str;
 	u64 start;
+	u64 db_id;
 	struct list_head list;
 	bool exec;
 };
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
new file mode 100644
index 0000000..53d0e75
--- /dev/null
+++ b/tools/perf/util/db-export.c
@@ -0,0 +1,268 @@
+/*
+ * db-export.c: Support for exporting data suitable for import to a database
+ * 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.
+ *
+ */
+
+#include <errno.h>
+
+#include "evsel.h"
+#include "machine.h"
+#include "thread.h"
+#include "comm.h"
+#include "symbol.h"
+#include "event.h"
+#include "db-export.h"
+
+int db_export__init(struct db_export *dbe)
+{
+	memset(dbe, 0, sizeof(struct db_export));
+	return 0;
+}
+
+void db_export__exit(struct db_export *dbe __maybe_unused)
+{
+}
+
+int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel)
+{
+	if (evsel->db_id)
+		return 0;
+
+	evsel->db_id = ++dbe->evsel_last_db_id;
+
+	if (dbe->export_evsel)
+		return dbe->export_evsel(dbe, evsel);
+
+	return 0;
+}
+
+int db_export__machine(struct db_export *dbe, struct machine *machine)
+{
+	if (machine->db_id)
+		return 0;
+
+	machine->db_id = ++dbe->machine_last_db_id;
+
+	if (dbe->export_machine)
+		return dbe->export_machine(dbe, machine);
+
+	return 0;
+}
+
+int db_export__thread(struct db_export *dbe, struct thread *thread,
+		      struct machine *machine, struct comm *comm)
+{
+	u64 main_thread_db_id = 0;
+	int err;
+
+	if (thread->db_id)
+		return 0;
+
+	thread->db_id = ++dbe->thread_last_db_id;
+
+	if (thread->pid_ != -1) {
+		struct thread *main_thread;
+
+		if (thread->pid_ == thread->tid) {
+			main_thread = thread;
+		} else {
+			main_thread = machine__findnew_thread(machine,
+							      thread->pid_,
+							      thread->pid_);
+			if (!main_thread)
+				return -ENOMEM;
+			err = db_export__thread(dbe, main_thread, machine,
+						comm);
+			if (err)
+				return err;
+			if (comm) {
+				err = db_export__comm_thread(dbe, comm, thread);
+				if (err)
+					return err;
+			}
+		}
+		main_thread_db_id = main_thread->db_id;
+	}
+
+	if (dbe->export_thread)
+		return dbe->export_thread(dbe, thread, main_thread_db_id,
+					  machine);
+
+	return 0;
+}
+
+int db_export__comm(struct db_export *dbe, struct comm *comm,
+		    struct thread *main_thread)
+{
+	int err;
+
+	if (comm->db_id)
+		return 0;
+
+	comm->db_id = ++dbe->comm_last_db_id;
+
+	if (dbe->export_comm) {
+		err = dbe->export_comm(dbe, comm);
+		if (err)
+			return err;
+	}
+
+	return db_export__comm_thread(dbe, comm, main_thread);
+}
+
+int db_export__comm_thread(struct db_export *dbe, struct comm *comm,
+			   struct thread *thread)
+{
+	u64 db_id;
+
+	db_id = ++dbe->comm_thread_last_db_id;
+
+	if (dbe->export_comm_thread)
+		return dbe->export_comm_thread(dbe, db_id, comm, thread);
+
+	return 0;
+}
+
+int db_export__dso(struct db_export *dbe, struct dso *dso,
+		   struct machine *machine)
+{
+	if (dso->db_id)
+		return 0;
+
+	dso->db_id = ++dbe->dso_last_db_id;
+
+	if (dbe->export_dso)
+		return dbe->export_dso(dbe, dso, machine);
+
+	return 0;
+}
+
+int db_export__symbol(struct db_export *dbe, struct symbol *sym,
+		      struct dso *dso)
+{
+	if (sym->db_id)
+		return 0;
+
+	sym->db_id = ++dbe->symbol_last_db_id;
+
+	if (dbe->export_symbol)
+		return dbe->export_symbol(dbe, sym, dso);
+
+	return 0;
+}
+
+static struct thread *get_main_thread(struct machine *machine,
+				      struct thread *thread)
+{
+	if (thread->pid_ == thread->tid)
+		return thread;
+
+	if (thread->pid_ == -1)
+		return NULL;
+
+	return machine__find_thread(machine, thread->pid_, thread->pid_);
+}
+
+static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
+			  u64 *dso_db_id, u64 *sym_db_id, u64 *offset)
+{
+	int err;
+
+	if (al->map) {
+		struct dso *dso = al->map->dso;
+
+		err = db_export__dso(dbe, dso, al->machine);
+		if (err)
+			return err;
+		*dso_db_id = dso->db_id;
+
+		if (!al->sym) {
+			al->sym = symbol__new(al->addr, 0, 0, "unknown");
+			if (al->sym)
+				symbols__insert(&dso->symbols[al->map->type],
+						al->sym);
+		}
+
+		if (al->sym) {
+			err = db_export__symbol(dbe, al->sym, dso);
+			if (err)
+				return err;
+			*sym_db_id = al->sym->db_id;
+			*offset = al->addr - al->sym->start;
+		}
+	}
+
+	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)
+{
+	struct export_sample es = {
+		.event = event,
+		.sample = sample,
+		.evsel = evsel,
+		.thread = thread,
+		.al = al,
+	};
+	struct thread *main_thread;
+	struct comm *comm = NULL;
+	int err;
+
+	err = db_export__evsel(dbe, evsel);
+	if (err)
+		return err;
+
+	err = db_export__machine(dbe, al->machine);
+	if (err)
+		return err;
+
+	main_thread = get_main_thread(al->machine, thread);
+	if (main_thread)
+		comm = machine__thread_exec_comm(al->machine, main_thread);
+
+	err = db_export__thread(dbe, thread, al->machine, comm);
+	if (err)
+		return err;
+
+	if (comm) {
+		err = db_export__comm(dbe, comm, main_thread);
+		if (err)
+			return err;
+		es.comm_db_id = comm->db_id;
+	}
+
+	es.db_id = ++dbe->sample_last_db_id;
+
+	err = db_ids_from_al(dbe, al, &es.dso_db_id, &es.sym_db_id, &es.offset);
+	if (err)
+		return err;
+
+	if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
+	    sample_addr_correlates_sym(&evsel->attr)) {
+		struct addr_location addr_al;
+
+		perf_event__preprocess_sample_addr(event, sample, al->machine,
+						   thread, &addr_al);
+		err = db_ids_from_al(dbe, &addr_al, &es.addr_dso_db_id,
+				     &es.addr_sym_db_id, &es.addr_offset);
+		if (err)
+			return err;
+	}
+
+	if (dbe->export_sample)
+		return dbe->export_sample(dbe, &es);
+
+	return 0;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
new file mode 100644
index 0000000..b3643e8
--- /dev/null
+++ b/tools/perf/util/db-export.h
@@ -0,0 +1,86 @@
+/*
+ * db-export.h: Support for exporting data suitable for import to a database
+ * 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_DB_EXPORT_H
+#define __PERF_DB_EXPORT_H
+
+#include <linux/types.h>
+
+struct perf_evsel;
+struct machine;
+struct thread;
+struct comm;
+struct dso;
+struct perf_sample;
+struct addr_location;
+
+struct export_sample {
+	union perf_event	*event;
+	struct perf_sample	*sample;
+	struct perf_evsel	*evsel;
+	struct thread		*thread;
+	struct addr_location	*al;
+	u64			db_id;
+	u64			comm_db_id;
+	u64			dso_db_id;
+	u64			sym_db_id;
+	u64			offset; /* ip offset from symbol start */
+	u64			addr_dso_db_id;
+	u64			addr_sym_db_id;
+	u64			addr_offset; /* addr offset from symbol start */
+};
+
+struct db_export {
+	int (*export_evsel)(struct db_export *dbe, struct perf_evsel *evsel);
+	int (*export_machine)(struct db_export *dbe, struct machine *machine);
+	int (*export_thread)(struct db_export *dbe, struct thread *thread,
+			     u64 main_thread_db_id, struct machine *machine);
+	int (*export_comm)(struct db_export *dbe, struct comm *comm);
+	int (*export_comm_thread)(struct db_export *dbe, u64 db_id,
+				  struct comm *comm, struct thread *thread);
+	int (*export_dso)(struct db_export *dbe, struct dso *dso,
+			  struct machine *machine);
+	int (*export_symbol)(struct db_export *dbe, struct symbol *sym,
+			     struct dso *dso);
+	int (*export_sample)(struct db_export *dbe, struct export_sample *es);
+	u64 evsel_last_db_id;
+	u64 machine_last_db_id;
+	u64 thread_last_db_id;
+	u64 comm_last_db_id;
+	u64 comm_thread_last_db_id;
+	u64 dso_last_db_id;
+	u64 symbol_last_db_id;
+	u64 sample_last_db_id;
+};
+
+int db_export__init(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);
+int db_export__thread(struct db_export *dbe, struct thread *thread,
+		      struct machine *machine, struct comm *comm);
+int db_export__comm(struct db_export *dbe, struct comm *comm,
+		    struct thread *main_thread);
+int db_export__comm_thread(struct db_export *dbe, struct comm *comm,
+			   struct thread *thread);
+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__sample(struct db_export *dbe, union perf_event *event,
+		      struct perf_sample *sample, struct perf_evsel *evsel,
+		      struct thread *thread, struct addr_location *al);
+
+#endif
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 5e463c0..1c72a33 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -101,6 +101,7 @@ struct dso {
 	enum dso_swap_type	needs_swap;
 	enum dso_binary_type	symtab_type;
 	enum dso_binary_type	binary_type;
+	u64		 db_id;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
 	u8		 has_srcline:1;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d46d28e..378e670 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -96,6 +96,7 @@ struct perf_evsel {
 	int			sample_read;
 	struct perf_evsel	*leader;
 	char			*group_name;
+	u64			db_id;
 };
 
 union u64_swap {
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 6a6bcc1..f385f23 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -39,6 +39,7 @@ struct machine {
 	u64		  kernel_start;
 	symbol_filter_t	  symbol_filter;
 	pid_t		  *current_tid;
+	u64		  db_id;
 };
 
 static inline
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index e7295e9..51fb26b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -71,6 +71,7 @@ struct symbol {
 	struct rb_node	rb_node;
 	u64		start;
 	u64		end;
+	u64		db_id;
 	u16		namelen;
 	u8		binding;
 	bool		ignore;
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index a057820..a3ebb21 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -25,6 +25,7 @@ struct thread {
 	bool			dead; /* if set thread has exited */
 	struct list_head	comm_list;
 	int			comm_len;
+	u64			db_id;
 
 	void			*priv;
 	struct thread_stack	*ts;
-- 
1.8.3.2

[PATCH 18/31] perf tools: Add helpers for calling Python objects

[Adrian Hunter]

The Python script API repeatedly uses the same
lines of code to get and call objects.  Make that
into helper functions instead.  A side-effect is
that some reference counting bugs disappear because
the new call_object() function always decrements
the reference count of 'retval'.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 .../util/scripting-engines/trace-event-python.c    | 114 +++++++++------------
 1 file changed, 47 insertions(+), 67 deletions(-)

diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cbce254..26e5f14 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -73,6 +73,35 @@ static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObj
 	Py_DECREF(val);
 }
 
+static PyObject *get_handler(const char *handler_name)
+{
+	PyObject *handler;
+
+	handler = PyDict_GetItemString(main_dict, handler_name);
+	if (handler && !PyCallable_Check(handler))
+		return NULL;
+	return handler;
+}
+
+static void call_object(PyObject *handler, PyObject *args, const char *die_msg)
+{
+	PyObject *retval;
+
+	retval = PyObject_CallObject(handler, args);
+	if (retval == NULL)
+		handler_call_die(die_msg);
+	Py_DECREF(retval);
+}
+
+static void try_call_object(const char *handler_name, PyObject *args)
+{
+	PyObject *handler;
+
+	handler = get_handler(handler_name);
+	if (handler)
+		call_object(handler, args, handler_name);
+}
+
 static void define_value(enum print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
@@ -80,7 +109,7 @@ static void define_value(enum print_arg_type field_type,
 			 const char *field_str)
 {
 	const char *handler_name = "define_flag_value";
-	PyObject *handler, *t, *retval;
+	PyObject *t;
 	unsigned long long value;
 	unsigned n = 0;
 
@@ -98,13 +127,7 @@ static void define_value(enum print_arg_type field_type,
 	PyTuple_SetItem(t, n++, PyInt_FromLong(value));
 	PyTuple_SetItem(t, n++, PyString_FromString(field_str));
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && PyCallable_Check(handler)) {
-		retval = PyObject_CallObject(handler, t);
-		if (retval == NULL)
-			handler_call_die(handler_name);
-		Py_DECREF(retval);
-	}
+	try_call_object(handler_name, t);
 
 	Py_DECREF(t);
 }
@@ -127,7 +150,7 @@ static void define_field(enum print_arg_type field_type,
 			 const char *delim)
 {
 	const char *handler_name = "define_flag_field";
-	PyObject *handler, *t, *retval;
+	PyObject *t;
 	unsigned n = 0;
 
 	if (field_type == PRINT_SYMBOL)
@@ -145,13 +168,7 @@ static void define_field(enum print_arg_type field_type,
 	if (field_type == PRINT_FLAGS)
 		PyTuple_SetItem(t, n++, PyString_FromString(delim));
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && PyCallable_Check(handler)) {
-		retval = PyObject_CallObject(handler, t);
-		if (retval == NULL)
-			handler_call_die(handler_name);
-		Py_DECREF(retval);
-	}
+	try_call_object(handler_name, t);
 
 	Py_DECREF(t);
 }
@@ -362,7 +379,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				      struct thread *thread,
 				      struct addr_location *al)
 {
-	PyObject *handler, *retval, *context, *t, *obj, *callchain;
+	PyObject *handler, *context, *t, *obj, *callchain;
 	PyObject *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
@@ -387,9 +404,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 
 	sprintf(handler_name, "%s__%s", event->system, event->name);
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && !PyCallable_Check(handler))
-		handler = NULL;
+	handler = get_handler(handler_name);
 	if (!handler) {
 		dict = PyDict_New();
 		if (!dict)
@@ -450,19 +465,9 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		Py_FatalError("error resizing Python tuple");
 
 	if (handler) {
-		retval = PyObject_CallObject(handler, t);
-		if (retval == NULL)
-			handler_call_die(handler_name);
-		Py_DECREF(retval);
+		call_object(handler, t, handler_name);
 	} else {
-		handler = PyDict_GetItemString(main_dict, "trace_unhandled");
-		if (handler && PyCallable_Check(handler)) {
-
-			retval = PyObject_CallObject(handler, t);
-			if (retval == NULL)
-				handler_call_die("trace_unhandled");
-			Py_DECREF(retval);
-		}
+		try_call_object("trace_unhandled", t);
 		Py_DECREF(dict);
 	}
 
@@ -474,7 +479,7 @@ static void python_process_general_event(struct perf_sample *sample,
 					 struct thread *thread,
 					 struct addr_location *al)
 {
-	PyObject *handler, *retval, *t, *dict, *callchain, *dict_sample;
+	PyObject *handler, *t, *dict, *callchain, *dict_sample;
 	static char handler_name[64];
 	unsigned n = 0;
 
@@ -496,8 +501,8 @@ static void python_process_general_event(struct perf_sample *sample,
 
 	snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (!handler || !PyCallable_Check(handler))
+	handler = get_handler(handler_name);
+	if (!handler)
 		goto exit;
 
 	pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
@@ -539,10 +544,7 @@ static void python_process_general_event(struct perf_sample *sample,
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
 
-	retval = PyObject_CallObject(handler, t);
-	if (retval == NULL)
-		handler_call_die(handler_name);
-	Py_DECREF(retval);
+	call_object(handler, t, handler_name);
 exit:
 	Py_DECREF(dict);
 	Py_DECREF(t);
@@ -566,36 +568,24 @@ static void python_process_event(union perf_event *event __maybe_unused,
 
 static int run_start_sub(void)
 {
-	PyObject *handler, *retval;
-	int err = 0;
-
 	main_module = PyImport_AddModule("__main__");
 	if (main_module == NULL)
 		return -1;
 	Py_INCREF(main_module);
 
 	main_dict = PyModule_GetDict(main_module);
-	if (main_dict == NULL) {
-		err = -1;
+	if (main_dict == NULL)
 		goto error;
-	}
 	Py_INCREF(main_dict);
 
-	handler = PyDict_GetItemString(main_dict, "trace_begin");
-	if (handler == NULL || !PyCallable_Check(handler))
-		goto out;
+	try_call_object("trace_begin", NULL);
 
-	retval = PyObject_CallObject(handler, NULL);
-	if (retval == NULL)
-		handler_call_die("trace_begin");
+	return 0;
 
-	Py_DECREF(retval);
-	return err;
 error:
 	Py_XDECREF(main_dict);
 	Py_XDECREF(main_module);
-out:
-	return err;
+	return -1;
 }
 
 /*
@@ -654,23 +644,13 @@ error:
  */
 static int python_stop_script(void)
 {
-	PyObject *handler, *retval;
-	int err = 0;
+	try_call_object("trace_end", NULL);
 
-	handler = PyDict_GetItemString(main_dict, "trace_end");
-	if (handler == NULL || !PyCallable_Check(handler))
-		goto out;
-
-	retval = PyObject_CallObject(handler, NULL);
-	if (retval == NULL)
-		handler_call_die("trace_end");
-	Py_DECREF(retval);
-out:
 	Py_XDECREF(main_dict);
 	Py_XDECREF(main_module);
 	Py_Finalize();
 
-	return err;
+	return 0;
 }
 
 static int python_generate_script(struct pevent *pevent, const char *outfile)
-- 
1.8.3.2

[PATCH 19/31] perf tools: Extend Python script interface to export data in a database-friendly way

[Adrian Hunter]

Use the new db_export facility to export data in a
database-friendly way.

A Python script selects the db_export mode by setting
a global variable 'perf_db_export_mode' to True.  The
script then optionally implements functions to receive
table rows.  The functions are:

	evsel_table
	machine_table
	thread_table
	comm_table
	dso_table
	symbol_table
	sample_table

An example script is provided in a subsequent patch.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 .../util/scripting-engines/trace-event-python.c    | 281 ++++++++++++++++++++-
 1 file changed, 279 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 26e5f14..3062eb8 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -24,6 +24,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <stdbool.h>
 #include <errno.h>
 
 #include "../../perf.h"
@@ -32,6 +33,9 @@
 #include "../util.h"
 #include "../event.h"
 #include "../thread.h"
+#include "../comm.h"
+#include "../machine.h"
+#include "../db-export.h"
 #include "../trace-event.h"
 #include "../machine.h"
 
@@ -52,6 +56,21 @@ static int zero_flag_atom;
 
 static PyObject *main_module, *main_dict;
 
+struct tables {
+	struct db_export	dbe;
+	PyObject		*evsel_handler;
+	PyObject		*machine_handler;
+	PyObject		*thread_handler;
+	PyObject		*comm_handler;
+	PyObject		*comm_thread_handler;
+	PyObject		*dso_handler;
+	PyObject		*symbol_handler;
+	PyObject		*sample_handler;
+	bool			db_export_mode;
+};
+
+static struct tables tables_global;
+
 static void handler_call_die(const char *handler_name) NORETURN;
 static void handler_call_die(const char *handler_name)
 {
@@ -474,6 +493,210 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	Py_DECREF(t);
 }
 
+static PyObject *tuple_new(unsigned int sz)
+{
+	PyObject *t;
+
+	t = PyTuple_New(sz);
+	if (!t)
+		Py_FatalError("couldn't create Python tuple");
+	return t;
+}
+
+static int tuple_set_u64(PyObject *t, unsigned int pos, u64 val)
+{
+#if BITS_PER_LONG == 64
+	return PyTuple_SetItem(t, pos, PyInt_FromLong(val));
+#endif
+#if BITS_PER_LONG == 32
+	return PyTuple_SetItem(t, pos, PyLong_FromLongLong(val));
+#endif
+}
+
+static int tuple_set_s32(PyObject *t, unsigned int pos, s32 val)
+{
+	return PyTuple_SetItem(t, pos, PyInt_FromLong(val));
+}
+
+static int tuple_set_string(PyObject *t, unsigned int pos, const char *s)
+{
+	return PyTuple_SetItem(t, pos, PyString_FromString(s));
+}
+
+static int python_export_evsel(struct db_export *dbe, struct perf_evsel *evsel)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(2);
+
+	tuple_set_u64(t, 0, evsel->db_id);
+	tuple_set_string(t, 1, perf_evsel__name(evsel));
+
+	call_object(tables->evsel_handler, t, "evsel_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_machine(struct db_export *dbe,
+				 struct machine *machine)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(3);
+
+	tuple_set_u64(t, 0, machine->db_id);
+	tuple_set_s32(t, 1, machine->pid);
+	tuple_set_string(t, 2, machine->root_dir ? machine->root_dir : "");
+
+	call_object(tables->machine_handler, t, "machine_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_thread(struct db_export *dbe, struct thread *thread,
+				u64 main_thread_db_id, struct machine *machine)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(5);
+
+	tuple_set_u64(t, 0, thread->db_id);
+	tuple_set_u64(t, 1, machine->db_id);
+	tuple_set_u64(t, 2, main_thread_db_id);
+	tuple_set_s32(t, 3, thread->pid_);
+	tuple_set_s32(t, 4, thread->tid);
+
+	call_object(tables->thread_handler, t, "thread_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_comm(struct db_export *dbe, struct comm *comm)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(2);
+
+	tuple_set_u64(t, 0, comm->db_id);
+	tuple_set_string(t, 1, comm__str(comm));
+
+	call_object(tables->comm_handler, t, "comm_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_comm_thread(struct db_export *dbe, u64 db_id,
+				     struct comm *comm, struct thread *thread)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(3);
+
+	tuple_set_u64(t, 0, db_id);
+	tuple_set_u64(t, 1, comm->db_id);
+	tuple_set_u64(t, 2, thread->db_id);
+
+	call_object(tables->comm_thread_handler, t, "comm_thread_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_dso(struct db_export *dbe, struct dso *dso,
+			     struct machine *machine)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	PyObject *t;
+
+	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+
+	t = tuple_new(5);
+
+	tuple_set_u64(t, 0, dso->db_id);
+	tuple_set_u64(t, 1, machine->db_id);
+	tuple_set_string(t, 2, dso->short_name);
+	tuple_set_string(t, 3, dso->long_name);
+	tuple_set_string(t, 4, sbuild_id);
+
+	call_object(tables->dso_handler, t, "dso_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_symbol(struct db_export *dbe, struct symbol *sym,
+				struct dso *dso)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(6);
+
+	tuple_set_u64(t, 0, sym->db_id);
+	tuple_set_u64(t, 1, dso->db_id);
+	tuple_set_u64(t, 2, sym->start);
+	tuple_set_u64(t, 3, sym->end);
+	tuple_set_s32(t, 4, sym->binding);
+	tuple_set_string(t, 5, sym->name);
+
+	call_object(tables->symbol_handler, t, "symbol_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);
+
+	tuple_set_u64(t, 0, es->db_id);
+	tuple_set_u64(t, 1, es->evsel->db_id);
+	tuple_set_u64(t, 2, es->al->machine->db_id);
+	tuple_set_u64(t, 3, es->thread->db_id);
+	tuple_set_u64(t, 4, es->comm_db_id);
+	tuple_set_u64(t, 5, es->dso_db_id);
+	tuple_set_u64(t, 6, es->sym_db_id);
+	tuple_set_u64(t, 7, es->offset);
+	tuple_set_u64(t, 8, es->sample->ip);
+	tuple_set_u64(t, 9, es->sample->time);
+	tuple_set_s32(t, 10, es->sample->cpu);
+	tuple_set_u64(t, 11, es->addr_dso_db_id);
+	tuple_set_u64(t, 12, es->addr_sym_db_id);
+	tuple_set_u64(t, 13, es->addr_offset);
+	tuple_set_u64(t, 14, es->sample->addr);
+	tuple_set_u64(t, 15, es->sample->period);
+	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);
+
+	call_object(tables->sample_handler, t, "sample_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
 static void python_process_general_event(struct perf_sample *sample,
 					 struct perf_evsel *evsel,
 					 struct thread *thread,
@@ -550,19 +773,25 @@ exit:
 	Py_DECREF(t);
 }
 
-static void python_process_event(union perf_event *event __maybe_unused,
+static void python_process_event(union perf_event *event,
 				 struct perf_sample *sample,
 				 struct perf_evsel *evsel,
 				 struct thread *thread,
 				 struct addr_location *al)
 {
+	struct tables *tables = &tables_global;
+
 	switch (evsel->attr.type) {
 	case PERF_TYPE_TRACEPOINT:
 		python_process_tracepoint(sample, evsel, thread, al);
 		break;
 	/* Reserve for future process_hw/sw/raw APIs */
 	default:
-		python_process_general_event(sample, evsel, thread, al);
+		if (tables->db_export_mode)
+			db_export__sample(&tables->dbe, event, sample, evsel,
+					  thread, al);
+		else
+			python_process_general_event(sample, evsel, thread, al);
 	}
 }
 
@@ -588,11 +817,53 @@ error:
 	return -1;
 }
 
+#define SET_TABLE_HANDLER_(name, handler_name, table_name) do {		\
+	tables->handler_name = get_handler(#table_name);		\
+	if (tables->handler_name)					\
+		tables->dbe.export_ ## name = python_export_ ## name;	\
+} while (0)
+
+#define SET_TABLE_HANDLER(name) \
+	SET_TABLE_HANDLER_(name, name ## _handler, name ## _table)
+
+static void set_table_handlers(struct tables *tables)
+{
+	const char *perf_db_export_mode = "perf_db_export_mode";
+	PyObject *db_export_mode;
+	int ret;
+
+	memset(tables, 0, sizeof(struct tables));
+	if (db_export__init(&tables->dbe))
+		Py_FatalError("failed to initialize export");
+
+	db_export_mode = PyDict_GetItemString(main_dict, perf_db_export_mode);
+	if (!db_export_mode)
+		return;
+
+	ret = PyObject_IsTrue(db_export_mode);
+	if (ret == -1)
+		handler_call_die(perf_db_export_mode);
+	if (!ret)
+		return;
+
+	tables->db_export_mode = true;
+
+	SET_TABLE_HANDLER(evsel);
+	SET_TABLE_HANDLER(machine);
+	SET_TABLE_HANDLER(thread);
+	SET_TABLE_HANDLER(comm);
+	SET_TABLE_HANDLER(comm_thread);
+	SET_TABLE_HANDLER(dso);
+	SET_TABLE_HANDLER(symbol);
+	SET_TABLE_HANDLER(sample);
+}
+
 /*
  * Start trace script
  */
 static int python_start_script(const char *script, int argc, const char **argv)
 {
+	struct tables *tables = &tables_global;
 	const char **command_line;
 	char buf[PATH_MAX];
 	int i, err = 0;
@@ -631,6 +902,8 @@ static int python_start_script(const char *script, int argc, const char **argv)
 
 	free(command_line);
 
+	set_table_handlers(tables);
+
 	return err;
 error:
 	Py_Finalize();
@@ -644,8 +917,12 @@ error:
  */
 static int python_stop_script(void)
 {
+	struct tables *tables = &tables_global;
+
 	try_call_object("trace_end", NULL);
 
+	db_export__exit(&tables->dbe);
+
 	Py_XDECREF(main_dict);
 	Py_XDECREF(main_module);
 	Py_Finalize();
-- 
1.8.3.2

[PATCH 20/31] perf tools: Add Python script to export to postgresql

[Adrian Hunter]

Add a Python script to export to a postgresql database.
The script requires the Python psycopg2 module.  The
caller of the script must be able to create postgresql
databases.

The script takes the database name as a parameter.  The
database and database tables are created.  Data is written
to flat files which are then imported using SQL COPY FROM.

Example:

$ perf record ls
...
$ perf script report export-to-postgresql lsdb
2014-02-14 10:55:38.631431 Creating database...
2014-02-14 10:55:39.291958 Writing to intermediate files...
2014-02-14 10:55:39.350280 Copying to database...
2014-02-14 10:55:39.358536 Removing intermediate files...
2014-02-14 10:55:39.358665 Adding primary keys
2014-02-14 10:55:39.658697 Adding foreign keys
2014-02-14 10:55:39.667412 Done
$ psql lsdb
lsdb=# select * from samples_view;

id |      time       | cpu |  pid  |  tid  | command | event  |      ip_hex      |            symbol            | sym_offset |  dso_short_name   | to_ip_hex | to_symbol | to_sym_offset | to_dso_short_name
----+-----------------+-----+-------+-------+---------+--------+------------------+------------------------------+------------+-------------------+-----------+-----------+---------------+-------------------
  1 | 592112202825015 |  -1 | 17339 | 17339 | :17339  | cycles | ffffffff8104d24a | native_write_msr_safe        |         10 | [kernel.kallsyms] | 0         | unknown   |             0 | unknown
  2 | 592112203258804 |  -1 | 17339 | 17339 | :17339  | cycles | ffffffff8104d24a | native_write_msr_safe        |         10 | [kernel.kallsyms] | 0         | unknown   |             0 | unknown
  3 | 592112203988119 |  -1 | 17339 | 17339 | :17339  | cycles | ffffffff8104d24a | native_write_msr_safe        |         10 | [kernel.kallsyms] | 0         | unknown   |             0 | unknown

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 .../scripts/python/bin/export-to-postgresql-record |   8 +
 .../scripts/python/bin/export-to-postgresql-report |  24 ++
 tools/perf/scripts/python/export-to-postgresql.py  | 360 +++++++++++++++++++++
 3 files changed, 392 insertions(+)
 create mode 100644 tools/perf/scripts/python/bin/export-to-postgresql-record
 create mode 100644 tools/perf/scripts/python/bin/export-to-postgresql-report
 create mode 100644 tools/perf/scripts/python/export-to-postgresql.py

diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-record b/tools/perf/scripts/python/bin/export-to-postgresql-record
new file mode 100644
index 0000000..221d66e
--- /dev/null
+++ b/tools/perf/scripts/python/bin/export-to-postgresql-record
@@ -0,0 +1,8 @@
+#!/bin/bash
+
+#
+# export perf data to a postgresql database. Can cover
+# perf ip samples (excluding the tracepoints). No special
+# record requirements, just record what you want to export.
+#
+perf record $@
diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-report b/tools/perf/scripts/python/bin/export-to-postgresql-report
new file mode 100644
index 0000000..a8fdd15
--- /dev/null
+++ b/tools/perf/scripts/python/bin/export-to-postgresql-report
@@ -0,0 +1,24 @@
+#!/bin/bash
+# description: export perf data to a postgresql database
+# args: [database name] [columns]
+n_args=0
+for i in "$@"
+do
+    if expr match "$i" "-" > /dev/null ; then
+	break
+    fi
+    n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 2 ] ; then
+    echo "usage: export-to-postgresql-report [database name] [columns]"
+    exit
+fi
+if [ "$n_args" -gt 1 ] ; then
+    dbname=$1
+    columns=$2
+    shift 2
+elif [ "$n_args" -gt 0 ] ; then
+    dbname=$1
+    shift
+fi
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
new file mode 100644
index 0000000..d8f6df0
--- /dev/null
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -0,0 +1,360 @@
+# export-to-postgresql.py: export perf data to a postgresql database
+# 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.
+
+import os
+import sys
+import struct
+import datetime
+
+from PySide.QtSql import *
+
+# Need to access PostgreSQL C library directly to use COPY FROM STDIN
+from ctypes import *
+libpq = CDLL("libpq.so.5")
+PQconnectdb = libpq.PQconnectdb
+PQconnectdb.restype = c_void_p
+PQfinish = libpq.PQfinish
+PQstatus = libpq.PQstatus
+PQexec = libpq.PQexec
+PQexec.restype = c_void_p
+PQresultStatus = libpq.PQresultStatus
+PQputCopyData = libpq.PQputCopyData
+PQputCopyData.argtypes = [ c_void_p, c_void_p, c_int ]
+PQputCopyEnd = libpq.PQputCopyEnd
+PQputCopyEnd.argtypes = [ c_void_p, c_void_p ]
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+# These perf imports are not used at present
+#from perf_trace_context import *
+#from Core import *
+
+perf_db_export_mode = True
+
+def usage():
+	print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>]"
+	print >> sys.stderr, "where:	columns		'all' or 'branches'"
+	raise Exception("Too few arguments")
+
+if (len(sys.argv) < 2):
+	usage()
+
+dbname = sys.argv[1]
+
+if (len(sys.argv) >= 3):
+	columns = sys.argv[2]
+else:
+	columns = "all"
+
+if columns not in ("all", "branches"):
+	usage()
+
+branches = (columns == "branches")
+
+output_dir_name = os.getcwd() + "/" + dbname + "-perf-data"
+os.mkdir(output_dir_name)
+
+def do_query(q, s):
+	if (q.exec_(s)):
+		return
+	raise Exception("Query failed: " + q.lastError().text())
+
+print datetime.datetime.today(), "Creating database..."
+
+db = QSqlDatabase.addDatabase('QPSQL')
+query = QSqlQuery(db)
+db.setDatabaseName('postgres')
+db.open()
+try:
+	do_query(query, 'CREATE DATABASE ' + dbname)
+except:
+	os.rmdir(output_dir_name)
+	raise
+query.finish()
+query.clear()
+db.close()
+
+db.setDatabaseName(dbname)
+db.open()
+
+query = QSqlQuery(db)
+do_query(query, 'SET client_min_messages TO WARNING')
+
+do_query(query, 'CREATE TABLE selected_events ('
+		'id		bigint		NOT NULL,'
+		'name		varchar(80))')
+do_query(query, 'CREATE TABLE machines ('
+		'id		bigint		NOT NULL,'
+		'pid		integer,'
+		'root_dir 	varchar(4096))')
+do_query(query, 'CREATE TABLE threads ('
+		'id		bigint		NOT NULL,'
+		'machine_id	bigint,'
+		'process_id	bigint,'
+		'pid		integer,'
+		'tid		integer)')
+do_query(query, 'CREATE TABLE comms ('
+		'id		bigint		NOT NULL,'
+		'comm		varchar(16))')
+do_query(query, 'CREATE TABLE comm_threads ('
+		'id		bigint		NOT NULL,'
+		'comm_id	bigint,'
+		'thread_id	bigint)')
+do_query(query, 'CREATE TABLE dsos ('
+		'id		bigint		NOT NULL,'
+		'machine_id	bigint,'
+		'short_name	varchar(256),'
+		'long_name	varchar(4096),'
+		'build_id	varchar(64))')
+do_query(query, 'CREATE TABLE symbols ('
+		'id		bigint		NOT NULL,'
+		'dso_id		bigint,'
+		'sym_start	bigint,'
+		'sym_end	bigint,'
+		'binding	integer,'
+		'name		varchar(2048))')
+if branches:
+	do_query(query, 'CREATE TABLE samples ('
+		'id		bigint		NOT NULL,'
+		'evsel_id	bigint,'
+		'machine_id	bigint,'
+		'thread_id	bigint,'
+		'comm_id	bigint,'
+		'dso_id		bigint,'
+		'symbol_id	bigint,'
+		'sym_offset	bigint,'
+		'ip		bigint,'
+		'time		bigint,'
+		'cpu		integer,'
+		'to_dso_id	bigint,'
+		'to_symbol_id	bigint,'
+		'to_sym_offset	bigint,'
+		'to_ip		bigint)')
+else:
+	do_query(query, 'CREATE TABLE samples ('
+		'id		bigint		NOT NULL,'
+		'evsel_id	bigint,'
+		'machine_id	bigint,'
+		'thread_id	bigint,'
+		'comm_id	bigint,'
+		'dso_id		bigint,'
+		'symbol_id	bigint,'
+		'sym_offset	bigint,'
+		'ip		bigint,'
+		'time		bigint,'
+		'cpu		integer,'
+		'to_dso_id	bigint,'
+		'to_symbol_id	bigint,'
+		'to_sym_offset	bigint,'
+		'to_ip		bigint,'
+		'period		bigint,'
+		'weight		bigint,'
+		'transaction	bigint,'
+		'data_src	bigint)')
+
+do_query(query, 'CREATE VIEW samples_view AS '
+	'SELECT '
+		'id,'
+		'time,'
+		'cpu,'
+		'(SELECT pid FROM threads WHERE id = thread_id) AS pid,'
+		'(SELECT tid FROM threads WHERE id = thread_id) AS tid,'
+		'(SELECT comm FROM comms WHERE id = comm_id) AS command,'
+		'(SELECT name FROM selected_events WHERE id = evsel_id) AS event,'
+		'to_hex(ip) AS ip_hex,'
+		'(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,'
+		'sym_offset,'
+		'(SELECT short_name FROM dsos WHERE id = dso_id) AS dso_short_name,'
+		'to_hex(to_ip) AS to_ip_hex,'
+		'(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,'
+		'to_sym_offset,'
+		'(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name'
+	' FROM samples')
+
+
+file_header = struct.pack("!11sii", "PGCOPY\n\377\r\n\0", 0, 0)
+file_trailer = "\377\377"
+
+def open_output_file(file_name):
+	path_name = output_dir_name + "/" + file_name
+	file = open(path_name, "w+")
+	file.write(file_header)
+	return file
+
+def close_output_file(file):
+	file.write(file_trailer)
+	file.close()
+
+def copy_output_file_direct(file, table_name):
+	close_output_file(file)
+	sql = "COPY " + table_name + " FROM '" + file.name + "' (FORMAT 'binary')"
+	do_query(query, sql)
+
+# Use COPY FROM STDIN because security may prevent postgres from accessing the files directly
+def copy_output_file(file, table_name):
+	conn = PQconnectdb("dbname = " + dbname)
+	if (PQstatus(conn)):
+		raise Exception("COPY FROM STDIN PQconnectdb failed")
+	file.write(file_trailer)
+	file.seek(0)
+	sql = "COPY " + table_name + " FROM STDIN (FORMAT 'binary')"
+	res = PQexec(conn, sql)
+	if (PQresultStatus(res) != 4):
+		raise Exception("COPY FROM STDIN PQexec failed")
+	data = file.read(65536)
+	while (len(data)):
+		ret = PQputCopyData(conn, data, len(data))
+		if (ret != 1):
+			raise Exception("COPY FROM STDIN PQputCopyData failed, error " + str(ret))
+		data = file.read(65536)
+	ret = PQputCopyEnd(conn, None)
+	if (ret != 1):
+		raise Exception("COPY FROM STDIN PQputCopyEnd failed, error " + str(ret))
+	PQfinish(conn)
+
+def remove_output_file(file):
+	name = file.name
+	file.close()
+	os.unlink(name)
+
+evsel_file		= open_output_file("evsel_table.bin")
+machine_file		= open_output_file("machine_table.bin")
+thread_file		= open_output_file("thread_table.bin")
+comm_file		= open_output_file("comm_table.bin")
+comm_thread_file	= open_output_file("comm_thread_table.bin")
+dso_file		= open_output_file("dso_table.bin")
+symbol_file		= open_output_file("symbol_table.bin")
+sample_file		= open_output_file("sample_table.bin")
+
+def trace_begin():
+	print datetime.datetime.today(), "Writing to intermediate files..."
+	# id == 0 means unknown.  It is easier to create records for them than replace the zeroes with NULLs
+	evsel_table(0, "unknown")
+	machine_table(0, 0, "unknown")
+	thread_table(0, 0, 0, -1, -1)
+	comm_table(0, "unknown")
+	dso_table(0, 0, "unknown", "unknown", "")
+	symbol_table(0, 0, 0, 0, 0, "unknown")
+
+unhandled_count = 0
+
+def trace_end():
+	print datetime.datetime.today(), "Copying to database..."
+	copy_output_file(evsel_file,		"selected_events")
+	copy_output_file(machine_file,		"machines")
+	copy_output_file(thread_file,		"threads")
+	copy_output_file(comm_file,		"comms")
+	copy_output_file(comm_thread_file,	"comm_threads")
+	copy_output_file(dso_file,		"dsos")
+	copy_output_file(symbol_file,		"symbols")
+	copy_output_file(sample_file,		"samples")
+
+	print datetime.datetime.today(), "Removing intermediate files..."
+	remove_output_file(evsel_file)
+	remove_output_file(machine_file)
+	remove_output_file(thread_file)
+	remove_output_file(comm_file)
+	remove_output_file(comm_thread_file)
+	remove_output_file(dso_file)
+	remove_output_file(symbol_file)
+	remove_output_file(sample_file)
+	os.rmdir(output_dir_name)
+	print datetime.datetime.today(), "Adding primary keys"
+	do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE machines        ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE threads         ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE comms           ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE comm_threads    ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE dsos            ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE symbols         ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE samples         ADD PRIMARY KEY (id)')
+
+	print datetime.datetime.today(), "Adding foreign keys"
+	do_query(query, 'ALTER TABLE threads '
+					'ADD CONSTRAINT machinefk  FOREIGN KEY (machine_id)   REFERENCES machines   (id),'
+					'ADD CONSTRAINT processfk  FOREIGN KEY (process_id)   REFERENCES threads    (id)')
+	do_query(query, 'ALTER TABLE comm_threads '
+					'ADD CONSTRAINT commfk     FOREIGN KEY (comm_id)      REFERENCES comms      (id),'
+					'ADD CONSTRAINT threadfk   FOREIGN KEY (thread_id)    REFERENCES threads    (id)')
+	do_query(query, 'ALTER TABLE dsos '
+					'ADD CONSTRAINT machinefk  FOREIGN KEY (machine_id)   REFERENCES machines   (id)')
+	do_query(query, 'ALTER TABLE symbols '
+					'ADD CONSTRAINT dsofk      FOREIGN KEY (dso_id)       REFERENCES dsos       (id)')
+	do_query(query, 'ALTER TABLE samples '
+					'ADD CONSTRAINT evselfk    FOREIGN KEY (evsel_id)     REFERENCES selected_events (id),'
+					'ADD CONSTRAINT machinefk  FOREIGN KEY (machine_id)   REFERENCES machines   (id),'
+					'ADD CONSTRAINT threadfk   FOREIGN KEY (thread_id)    REFERENCES threads    (id),'
+					'ADD CONSTRAINT commfk     FOREIGN KEY (comm_id)      REFERENCES comms      (id),'
+					'ADD CONSTRAINT dsofk      FOREIGN KEY (dso_id)       REFERENCES dsos       (id),'
+					'ADD CONSTRAINT symbolfk   FOREIGN KEY (symbol_id)    REFERENCES symbols    (id),'
+					'ADD CONSTRAINT todsofk    FOREIGN KEY (to_dso_id)    REFERENCES dsos       (id),'
+					'ADD CONSTRAINT tosymbolfk FOREIGN KEY (to_symbol_id) REFERENCES symbols    (id)')
+
+	if (unhandled_count):
+		print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events"
+	print datetime.datetime.today(), "Done"
+
+def trace_unhandled(event_name, context, event_fields_dict):
+	global unhandled_count
+	unhandled_count += 1
+
+def sched__sched_switch(*x):
+	pass
+
+def evsel_table(evsel_id, evsel_name, *x):
+	n = len(evsel_name)
+	fmt = "!hiqi" + str(n) + "s"
+	value = struct.pack(fmt, 2, 8, evsel_id, n, evsel_name)
+	evsel_file.write(value)
+
+def machine_table(machine_id, pid, root_dir, *x):
+	n = len(root_dir)
+	fmt = "!hiqiii" + str(n) + "s"
+	value = struct.pack(fmt, 3, 8, machine_id, 4, pid, n, root_dir)
+	machine_file.write(value)
+
+def thread_table(thread_id, machine_id, process_id, pid, tid, *x):
+	value = struct.pack("!hiqiqiqiiii", 5, 8, thread_id, 8, machine_id, 8, process_id, 4, pid, 4, tid)
+	thread_file.write(value)
+
+def comm_table(comm_id, comm_str, *x):
+	n = len(comm_str)
+	fmt = "!hiqi" + str(n) + "s"
+	value = struct.pack(fmt, 2, 8, comm_id, n, comm_str)
+	comm_file.write(value)
+
+def comm_thread_table(comm_thread_id, comm_id, thread_id, *x):
+	fmt = "!hiqiqiq"
+	value = struct.pack(fmt, 3, 8, comm_thread_id, 8, comm_id, 8, thread_id)
+	comm_thread_file.write(value)
+
+def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x):
+	n1 = len(short_name)
+	n2 = len(long_name)
+	n3 = len(build_id)
+	fmt = "!hiqiqi" + str(n1) + "si"  + str(n2) + "si" + str(n3) + "s"
+	value = struct.pack(fmt, 5, 8, dso_id, 8, machine_id, n1, short_name, n2, long_name, n3, build_id)
+	dso_file.write(value)
+
+def symbol_table(symbol_id, dso_id, sym_start, sym_end, binding, symbol_name, *x):
+	n = len(symbol_name)
+	fmt = "!hiqiqiqiqiii" + str(n) + "s"
+	value = struct.pack(fmt, 6, 8, symbol_id, 8, dso_id, 8, sym_start, 8, sym_end, 4, binding, n, symbol_name)
+	symbol_file.write(value)
+
+def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, *x):
+	if branches:
+		value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiq", 15, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip)
+	else:
+		value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiq", 19, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src)
+	sample_file.write(value)
-- 
1.8.3.2

[PATCH 21/31] perf tools: Add flags and insn_len to struct sample

[Adrian Hunter]

Add flags and insn_len to struct sample.  The flags
will be used to export branch type and transaction
status.  insn_len is preparation for pairing calls
and returns because the return address equals the
call address plus the instruction length (insn_len).

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/event.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index b8e5d1a..17048f7 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -182,6 +182,8 @@ struct perf_sample {
 	u32 cpu;
 	u32 raw_size;
 	u64 data_src;
+	u32 flags;
+	u16 insn_len;
 	void *raw_data;
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
-- 
1.8.3.2

[PATCH 22/31] perf tools: Add branch type to db export

[Adrian Hunter]

Add the ability to export branch types through the
database export facility.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/db-export.c | 48 +++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/db-export.h |  6 ++++++
 2 files changed, 54 insertions(+)

diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 53d0e75..c5b6e02 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -205,6 +205,15 @@ 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)
@@ -266,3 +275,42 @@ 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;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index b3643e8..e4baa45 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -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
-- 
1.8.3.2

[PATCH 23/31] perf tools: Add branch_type and in_tx to Python export

[Adrian Hunter]

Add branch_type and in_tx to Python db export and
the export-to-postgresql.py script.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/scripts/python/export-to-postgresql.py  | 32 ++++++++++++++++++----
 .../util/scripting-engines/trace-event-python.c    | 30 +++++++++++++++++++-
 2 files changed, 55 insertions(+), 7 deletions(-)

diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index d8f6df0..bb79aec 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -123,6 +123,10 @@ do_query(query, 'CREATE TABLE symbols ('
 		'sym_end	bigint,'
 		'binding	integer,'
 		'name		varchar(2048))')
+do_query(query, 'CREATE TABLE branch_types ('
+		'id		integer		NOT NULL,'
+		'name		varchar(80))')
+
 if branches:
 	do_query(query, 'CREATE TABLE samples ('
 		'id		bigint		NOT NULL,'
@@ -139,7 +143,9 @@ if branches:
 		'to_dso_id	bigint,'
 		'to_symbol_id	bigint,'
 		'to_sym_offset	bigint,'
-		'to_ip		bigint)')
+		'to_ip		bigint,'
+		'branch_type	integer,'
+		'in_tx		boolean)')
 else:
 	do_query(query, 'CREATE TABLE samples ('
 		'id		bigint		NOT NULL,'
@@ -160,7 +166,9 @@ else:
 		'period		bigint,'
 		'weight		bigint,'
 		'transaction	bigint,'
-		'data_src	bigint)')
+		'data_src	bigint,'
+		'branch_type	integer,'
+		'in_tx		boolean)')
 
 do_query(query, 'CREATE VIEW samples_view AS '
 	'SELECT '
@@ -178,7 +186,9 @@ do_query(query, 'CREATE VIEW samples_view AS '
 		'to_hex(to_ip) AS to_ip_hex,'
 		'(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,'
 		'to_sym_offset,'
-		'(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name'
+		'(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,'
+		'(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,'
+		'in_tx'
 	' FROM samples')
 
 
@@ -234,6 +244,7 @@ comm_file		= open_output_file("comm_table.bin")
 comm_thread_file	= open_output_file("comm_thread_table.bin")
 dso_file		= open_output_file("dso_table.bin")
 symbol_file		= open_output_file("symbol_table.bin")
+branch_type_file	= open_output_file("branch_type_table.bin")
 sample_file		= open_output_file("sample_table.bin")
 
 def trace_begin():
@@ -257,6 +268,7 @@ def trace_end():
 	copy_output_file(comm_thread_file,	"comm_threads")
 	copy_output_file(dso_file,		"dsos")
 	copy_output_file(symbol_file,		"symbols")
+	copy_output_file(branch_type_file,	"branch_types")
 	copy_output_file(sample_file,		"samples")
 
 	print datetime.datetime.today(), "Removing intermediate files..."
@@ -267,6 +279,7 @@ def trace_end():
 	remove_output_file(comm_thread_file)
 	remove_output_file(dso_file)
 	remove_output_file(symbol_file)
+	remove_output_file(branch_type_file)
 	remove_output_file(sample_file)
 	os.rmdir(output_dir_name)
 	print datetime.datetime.today(), "Adding primary keys"
@@ -277,6 +290,7 @@ def trace_end():
 	do_query(query, 'ALTER TABLE comm_threads    ADD PRIMARY KEY (id)')
 	do_query(query, 'ALTER TABLE dsos            ADD PRIMARY KEY (id)')
 	do_query(query, 'ALTER TABLE symbols         ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE branch_types    ADD PRIMARY KEY (id)')
 	do_query(query, 'ALTER TABLE samples         ADD PRIMARY KEY (id)')
 
 	print datetime.datetime.today(), "Adding foreign keys"
@@ -352,9 +366,15 @@ def symbol_table(symbol_id, dso_id, sym_start, sym_end, binding, symbol_name, *x
 	value = struct.pack(fmt, 6, 8, symbol_id, 8, dso_id, 8, sym_start, 8, sym_end, 4, binding, n, symbol_name)
 	symbol_file.write(value)
 
-def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, *x):
+def branch_type_table(branch_type, name, *x):
+	n = len(name)
+	fmt = "!hiii" + str(n) + "s"
+	value = struct.pack(fmt, 2, 4, branch_type, n, name)
+	branch_type_file.write(value)
+
+def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, *x):
 	if branches:
-		value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiq", 15, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip)
+		value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiB", 17, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx)
 	else:
-		value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiq", 19, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src)
+		value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiB", 21, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx)
 	sample_file.write(value)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 3062eb8..45483a4 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -65,6 +65,7 @@ struct tables {
 	PyObject		*comm_thread_handler;
 	PyObject		*dso_handler;
 	PyObject		*symbol_handler;
+	PyObject		*branch_type_handler;
 	PyObject		*sample_handler;
 	bool			db_export_mode;
 };
@@ -662,13 +663,31 @@ 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);
@@ -689,6 +708,8 @@ 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");
 
@@ -855,6 +876,7 @@ 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);
 }
 
@@ -904,6 +926,12 @@ 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();
-- 
1.8.3.2

[PATCH 24/31] perf tools: Enhance the thread stack to output call/return data

[Adrian Hunter]

Enhance the thread stack to output detailed information
about paired calls and returns.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/thread-stack.c | 547 ++++++++++++++++++++++++++++++++++++++++-
 tools/perf/util/thread-stack.h |  47 ++++
 2 files changed, 590 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index c1ca2a9..444d132 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -13,15 +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 {
@@ -29,6 +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)
@@ -45,7 +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;
 
@@ -59,6 +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;
 }
 
@@ -92,6 +137,64 @@ 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)
 {
@@ -99,17 +202,22 @@ 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)
 			return;
 		thread->ts->trace_nr = trace_nr;
 	}
 
 	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;
 
@@ -126,9 +234,22 @@ 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);
 	}
@@ -149,3 +270,421 @@ 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;
+}
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index c0ba4cf..5bca14e 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -19,14 +19,61 @@
 #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;
+
+enum {
+	CALL_RETURN_NO_CALL	= 1 << 0,
+	CALL_RETURN_NO_RETURN	= 1 << 1,
+};
+
+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 {
+	struct call_path *parent;
+	struct symbol *sym;
+	u64 ip; /* Only if sym is null */
+	u64 db_id;
+	bool in_kernel;
+	struct rb_node rb_node;
+	struct rb_root children;
+};
 
 void 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
-- 
1.8.3.2

[PATCH 25/31] perf tools: Add call information to the database export API

[Adrian Hunter]

Make it possible for the database export API to use the
enhanced thread stack and export detailed information
about paired calls and returns.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/db-export.c | 52 ++++++++++++++++++++++++++++++++++++++++++++-
 tools/perf/util/db-export.h | 12 +++++++++++
 2 files changed, 63 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index c5b6e02..ca79616 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -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)
@@ -268,6 +271,13 @@ 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)
@@ -314,3 +324,43 @@ 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;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index e4baa45..dd5ac2a 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -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
-- 
1.8.3.2

[PATCH 26/31] perf tools: Add call information to Python export

[Adrian Hunter]

Add the ability to export detailed information about
paired calls and returns to Python db export and
the export-to-postgresql.py script.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 .../scripts/python/bin/export-to-postgresql-report | 15 ++--
 tools/perf/scripts/python/export-to-postgresql.py  | 66 ++++++++++++++++-
 .../util/scripting-engines/trace-event-python.c    | 84 +++++++++++++++++++++-
 3 files changed, 158 insertions(+), 7 deletions(-)

diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-report b/tools/perf/scripts/python/bin/export-to-postgresql-report
index a8fdd15..cd335b6 100644
--- a/tools/perf/scripts/python/bin/export-to-postgresql-report
+++ b/tools/perf/scripts/python/bin/export-to-postgresql-report
@@ -1,6 +1,6 @@
 #!/bin/bash
 # description: export perf data to a postgresql database
-# args: [database name] [columns]
+# args: [database name] [columns] [calls]
 n_args=0
 for i in "$@"
 do
@@ -9,11 +9,16 @@ do
     fi
     n_args=$(( $n_args + 1 ))
 done
-if [ "$n_args" -gt 2 ] ; then
-    echo "usage: export-to-postgresql-report [database name] [columns]"
+if [ "$n_args" -gt 3 ] ; then
+    echo "usage: export-to-postgresql-report [database name] [columns] [calls]"
     exit
 fi
-if [ "$n_args" -gt 1 ] ; then
+if [ "$n_args" -gt 2 ] ; then
+    dbname=$1
+    columns=$2
+    calls=$3
+    shift 3
+elif [ "$n_args" -gt 1 ] ; then
     dbname=$1
     columns=$2
     shift 2
@@ -21,4 +26,4 @@ elif [ "$n_args" -gt 0 ] ; then
     dbname=$1
     shift
 fi
-perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns $calls
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index bb79aec..4cdafd8 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -40,10 +40,12 @@ sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 #from Core import *
 
 perf_db_export_mode = True
+perf_db_export_calls = False
 
 def usage():
-	print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>]"
+	print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>]"
 	print >> sys.stderr, "where:	columns		'all' or 'branches'"
+	print >> sys.stderr, "		calls		'calls' => create calls table"
 	raise Exception("Too few arguments")
 
 if (len(sys.argv) < 2):
@@ -61,6 +63,12 @@ if columns not in ("all", "branches"):
 
 branches = (columns == "branches")
 
+if (len(sys.argv) >= 4):
+	if (sys.argv[3] == "calls"):
+		perf_db_export_calls = True
+	else:
+		usage()
+
 output_dir_name = os.getcwd() + "/" + dbname + "-perf-data"
 os.mkdir(output_dir_name)
 
@@ -170,6 +178,25 @@ else:
 		'branch_type	integer,'
 		'in_tx		boolean)')
 
+if perf_db_export_calls:
+	do_query(query, 'CREATE TABLE call_paths ('
+		'id		bigint		NOT NULL,'
+		'parent_id	bigint,'
+		'symbol_id	bigint,'
+		'ip		bigint)')
+	do_query(query, 'CREATE TABLE calls ('
+		'id		bigint		NOT NULL,'
+		'thread_id	bigint,'
+		'comm_id	bigint,'
+		'call_path_id	bigint,'
+		'call_time	bigint,'
+		'return_time	bigint,'
+		'branch_count	bigint,'
+		'call_id	bigint,'
+		'return_id	bigint,'
+		'parent_call_path_id	bigint,'
+		'flags		integer)')
+
 do_query(query, 'CREATE VIEW samples_view AS '
 	'SELECT '
 		'id,'
@@ -246,6 +273,9 @@ dso_file		= open_output_file("dso_table.bin")
 symbol_file		= open_output_file("symbol_table.bin")
 branch_type_file	= open_output_file("branch_type_table.bin")
 sample_file		= open_output_file("sample_table.bin")
+if perf_db_export_calls:
+	call_path_file		= open_output_file("call_path_table.bin")
+	call_file		= open_output_file("call_table.bin")
 
 def trace_begin():
 	print datetime.datetime.today(), "Writing to intermediate files..."
@@ -256,6 +286,9 @@ def trace_begin():
 	comm_table(0, "unknown")
 	dso_table(0, 0, "unknown", "unknown", "")
 	symbol_table(0, 0, 0, 0, 0, "unknown")
+	sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+	if perf_db_export_calls:
+		call_path_table(0, 0, 0, 0)
 
 unhandled_count = 0
 
@@ -270,6 +303,9 @@ def trace_end():
 	copy_output_file(symbol_file,		"symbols")
 	copy_output_file(branch_type_file,	"branch_types")
 	copy_output_file(sample_file,		"samples")
+	if perf_db_export_calls:
+		copy_output_file(call_path_file,	"call_paths")
+		copy_output_file(call_file,		"calls")
 
 	print datetime.datetime.today(), "Removing intermediate files..."
 	remove_output_file(evsel_file)
@@ -281,6 +317,9 @@ def trace_end():
 	remove_output_file(symbol_file)
 	remove_output_file(branch_type_file)
 	remove_output_file(sample_file)
+	if perf_db_export_calls:
+		remove_output_file(call_path_file)
+		remove_output_file(call_file)
 	os.rmdir(output_dir_name)
 	print datetime.datetime.today(), "Adding primary keys"
 	do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)')
@@ -292,6 +331,9 @@ def trace_end():
 	do_query(query, 'ALTER TABLE symbols         ADD PRIMARY KEY (id)')
 	do_query(query, 'ALTER TABLE branch_types    ADD PRIMARY KEY (id)')
 	do_query(query, 'ALTER TABLE samples         ADD PRIMARY KEY (id)')
+	if perf_db_export_calls:
+		do_query(query, 'ALTER TABLE call_paths      ADD PRIMARY KEY (id)')
+		do_query(query, 'ALTER TABLE calls           ADD PRIMARY KEY (id)')
 
 	print datetime.datetime.today(), "Adding foreign keys"
 	do_query(query, 'ALTER TABLE threads '
@@ -313,6 +355,18 @@ def trace_end():
 					'ADD CONSTRAINT symbolfk   FOREIGN KEY (symbol_id)    REFERENCES symbols    (id),'
 					'ADD CONSTRAINT todsofk    FOREIGN KEY (to_dso_id)    REFERENCES dsos       (id),'
 					'ADD CONSTRAINT tosymbolfk FOREIGN KEY (to_symbol_id) REFERENCES symbols    (id)')
+	if perf_db_export_calls:
+		do_query(query, 'ALTER TABLE call_paths '
+					'ADD CONSTRAINT parentfk    FOREIGN KEY (parent_id)    REFERENCES call_paths (id),'
+					'ADD CONSTRAINT symbolfk    FOREIGN KEY (symbol_id)    REFERENCES symbols    (id)')
+		do_query(query, 'ALTER TABLE calls '
+					'ADD CONSTRAINT threadfk    FOREIGN KEY (thread_id)    REFERENCES threads    (id),'
+					'ADD CONSTRAINT commfk      FOREIGN KEY (comm_id)      REFERENCES comms      (id),'
+					'ADD CONSTRAINT call_pathfk FOREIGN KEY (call_path_id) REFERENCES call_paths (id),'
+					'ADD CONSTRAINT callfk      FOREIGN KEY (call_id)      REFERENCES samples    (id),'
+					'ADD CONSTRAINT returnfk    FOREIGN KEY (return_id)    REFERENCES samples    (id),'
+					'ADD CONSTRAINT parent_call_pathfk FOREIGN KEY (parent_call_path_id) REFERENCES call_paths (id)')
+		do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
 
 	if (unhandled_count):
 		print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events"
@@ -378,3 +432,13 @@ def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, sy
 	else:
 		value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiB", 21, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx)
 	sample_file.write(value)
+
+def call_path_table(cp_id, parent_id, symbol_id, ip, *x):
+	fmt = "!hiqiqiqiq"
+	value = struct.pack(fmt, 4, 8, cp_id, 8, parent_id, 8, symbol_id, 8, ip)
+	call_path_file.write(value)
+
+def call_return_table(cr_id, thread_id, comm_id, call_path_id, call_time, return_time, branch_count, call_id, return_id, parent_call_path_id, flags, *x):
+	fmt = "!hiqiqiqiqiqiqiqiqiqiqii"
+	value = struct.pack(fmt, 11, 8, cr_id, 8, thread_id, 8, comm_id, 8, call_path_id, 8, call_time, 8, return_time, 8, branch_count, 8, call_id, 8, return_id, 8, parent_call_path_id, 4, flags)
+	call_file.write(value)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 45483a4..5f7b76b 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -36,6 +36,7 @@
 #include "../comm.h"
 #include "../machine.h"
 #include "../db-export.h"
+#include "../thread-stack.h"
 #include "../trace-event.h"
 #include "../machine.h"
 
@@ -67,6 +68,8 @@ struct tables {
 	PyObject		*symbol_handler;
 	PyObject		*branch_type_handler;
 	PyObject		*sample_handler;
+	PyObject		*call_path_handler;
+	PyObject		*call_return_handler;
 	bool			db_export_mode;
 };
 
@@ -718,6 +721,64 @@ static int python_export_sample(struct db_export *dbe,
 	return 0;
 }
 
+static int python_export_call_path(struct db_export *dbe, struct call_path *cp)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+	u64 parent_db_id, sym_db_id;
+
+	parent_db_id = cp->parent ? cp->parent->db_id : 0;
+	sym_db_id = cp->sym ? cp->sym->db_id : 0;
+
+	t = tuple_new(4);
+
+	tuple_set_u64(t, 0, cp->db_id);
+	tuple_set_u64(t, 1, parent_db_id);
+	tuple_set_u64(t, 2, sym_db_id);
+	tuple_set_u64(t, 3, cp->ip);
+
+	call_object(tables->call_path_handler, t, "call_path_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_call_return(struct db_export *dbe,
+				     struct call_return *cr)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	u64 comm_db_id = cr->comm ? cr->comm->db_id : 0;
+	PyObject *t;
+
+	t = tuple_new(11);
+
+	tuple_set_u64(t, 0, cr->db_id);
+	tuple_set_u64(t, 1, cr->thread->db_id);
+	tuple_set_u64(t, 2, comm_db_id);
+	tuple_set_u64(t, 3, cr->cp->db_id);
+	tuple_set_u64(t, 4, cr->call_time);
+	tuple_set_u64(t, 5, cr->return_time);
+	tuple_set_u64(t, 6, cr->branch_count);
+	tuple_set_u64(t, 7, cr->call_ref);
+	tuple_set_u64(t, 8, cr->return_ref);
+	tuple_set_u64(t, 9, cr->cp->parent->db_id);
+	tuple_set_s32(t, 10, cr->flags);
+
+	call_object(tables->call_return_handler, t, "call_return_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_process_call_return(struct call_return *cr, void *data)
+{
+	struct db_export *dbe = data;
+
+	return db_export__call_return(dbe, cr);
+}
+
 static void python_process_general_event(struct perf_sample *sample,
 					 struct perf_evsel *evsel,
 					 struct thread *thread,
@@ -850,7 +911,9 @@ error:
 static void set_table_handlers(struct tables *tables)
 {
 	const char *perf_db_export_mode = "perf_db_export_mode";
-	PyObject *db_export_mode;
+	const char *perf_db_export_calls = "perf_db_export_calls";
+	PyObject *db_export_mode, *db_export_calls;
+	bool export_calls = false;
 	int ret;
 
 	memset(tables, 0, sizeof(struct tables));
@@ -867,6 +930,23 @@ static void set_table_handlers(struct tables *tables)
 	if (!ret)
 		return;
 
+	tables->dbe.crp = NULL;
+	db_export_calls = PyDict_GetItemString(main_dict, perf_db_export_calls);
+	if (db_export_calls) {
+		ret = PyObject_IsTrue(db_export_calls);
+		if (ret == -1)
+			handler_call_die(perf_db_export_calls);
+		export_calls = !!ret;
+	}
+
+	if (export_calls) {
+		tables->dbe.crp =
+			call_return_processor__new(python_process_call_return,
+						   &tables->dbe);
+		if (!tables->dbe.crp)
+			Py_FatalError("failed to create calls processor");
+	}
+
 	tables->db_export_mode = true;
 
 	SET_TABLE_HANDLER(evsel);
@@ -878,6 +958,8 @@ static void set_table_handlers(struct tables *tables)
 	SET_TABLE_HANDLER(symbol);
 	SET_TABLE_HANDLER(branch_type);
 	SET_TABLE_HANDLER(sample);
+	SET_TABLE_HANDLER(call_path);
+	SET_TABLE_HANDLER(call_return);
 }
 
 /*
-- 
1.8.3.2

[PATCH 27/31] perf tools: Add 'flush' callback to scripting API

[Adrian Hunter]

In order to defer some output via the scripting API,
there needs to be a callback after session processing
but before the session is deleted.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/builtin-script.c                            | 12 ++++++++++++
 tools/perf/util/scripting-engines/trace-event-perl.c   |  6 ++++++
 tools/perf/util/scripting-engines/trace-event-python.c |  6 ++++++
 tools/perf/util/trace-event-scripting.c                |  7 +++++++
 tools/perf/util/trace-event.h                          |  1 +
 5 files changed, 32 insertions(+)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 163d12b..4d4fe4e 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -485,6 +485,11 @@ static int default_start_script(const char *script __maybe_unused,
 	return 0;
 }
 
+static int default_flush_script(void)
+{
+	return 0;
+}
+
 static int default_stop_script(void)
 {
 	return 0;
@@ -498,6 +503,7 @@ static int default_generate_script(struct pevent *pevent __maybe_unused,
 
 static struct scripting_ops default_scripting_ops = {
 	.start_script		= default_start_script,
+	.flush_script		= default_flush_script,
 	.stop_script		= default_stop_script,
 	.process_event		= process_event,
 	.generate_script	= default_generate_script,
@@ -513,6 +519,11 @@ static void setup_scripting(void)
 	scripting_ops = &default_scripting_ops;
 }
 
+static int flush_scripting(void)
+{
+	return scripting_ops->flush_script();
+}
+
 static int cleanup_scripting(void)
 {
 	pr_debug("\nperf script stopped\n");
@@ -1806,6 +1817,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	err = __cmd_script(&script);
 
+	flush_scripting();
 	perf_session__delete(session);
 	cleanup_scripting();
 out:
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b2dba9c..0a01bac 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -432,6 +432,11 @@ error:
 	return err;
 }
 
+static int perl_flush_script(void)
+{
+	return 0;
+}
+
 /*
  * Stop trace script
  */
@@ -633,6 +638,7 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile)
 struct scripting_ops perl_scripting_ops = {
 	.name = "Perl",
 	.start_script = perl_start_script,
+	.flush_script = perl_flush_script,
 	.stop_script = perl_stop_script,
 	.process_event = perl_process_event,
 	.generate_script = perl_generate_script,
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 5f7b76b..ed754d0 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1022,6 +1022,11 @@ error:
 	return err;
 }
 
+static int python_flush_script(void)
+{
+	return 0;
+}
+
 /*
  * Stop trace script
  */
@@ -1210,6 +1215,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 struct scripting_ops python_scripting_ops = {
 	.name = "Python",
 	.start_script = python_start_script,
+	.flush_script = python_flush_script,
 	.stop_script = python_stop_script,
 	.process_event = python_process_event,
 	.generate_script = python_generate_script,
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 57aaccc..5c9bdd1 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -30,6 +30,11 @@
 
 struct scripting_context *scripting_context;
 
+static int flush_script_unsupported(void)
+{
+	return 0;
+}
+
 static int stop_script_unsupported(void)
 {
 	return 0;
@@ -74,6 +79,7 @@ static int python_generate_script_unsupported(struct pevent *pevent
 struct scripting_ops python_scripting_unsupported_ops = {
 	.name = "Python",
 	.start_script = python_start_script_unsupported,
+	.flush_script = flush_script_unsupported,
 	.stop_script = stop_script_unsupported,
 	.process_event = process_event_unsupported,
 	.generate_script = python_generate_script_unsupported,
@@ -137,6 +143,7 @@ static int perl_generate_script_unsupported(struct pevent *pevent
 struct scripting_ops perl_scripting_unsupported_ops = {
 	.name = "Perl",
 	.start_script = perl_start_script_unsupported,
+	.flush_script = flush_script_unsupported,
 	.stop_script = stop_script_unsupported,
 	.process_event = process_event_unsupported,
 	.generate_script = perl_generate_script_unsupported,
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 7b6d686..52aaa19 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -64,6 +64,7 @@ struct perf_session;
 struct scripting_ops {
 	const char *name;
 	int (*start_script) (const char *script, int argc, const char **argv);
+	int (*flush_script) (void);
 	int (*stop_script) (void);
 	void (*process_event) (union perf_event *event,
 			       struct perf_sample *sample,
-- 
1.8.3.2

[PATCH 28/31] perf tools: Defer export of comms that were not 'set'

[Adrian Hunter]

Tracing for a workload begins before the comm event
is seen, which results in the initial comm having a
string of the form ":<pid>" (e.g. ":12345").  In order
to export the correct string, defer the export until
the new script 'flush' callback.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/db-export.c                        | 62 +++++++++++++++++++++-
 tools/perf/util/db-export.h                        |  3 ++
 .../util/scripting-engines/trace-event-python.c    |  4 +-
 3 files changed, 67 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index ca79616..ef61cf7 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -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;
 	}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index dd5ac2a..adbd22d 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -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);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index ed754d0..6c0ce62 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1024,7 +1024,9 @@ error:
 
 static int python_flush_script(void)
 {
-	return 0;
+	struct tables *tables = &tables_global;
+
+	return db_export__flush(&tables->dbe);
 }
 
 /*
-- 
1.8.3.2

[PATCH 29/31] perf tools: Add perf-with-kcore script

[Adrian Hunter]

Decoding an Intel PT trace of the kernel requires
an accurate kernel object image.  This is provided
by making a copy of kcore.  However the copy needs
to be made under the same conditions as the original
recording, and then it needs to be associated with
the perf.data file. The perf-with-kcore script does
that.

The script also checks the permissions on the buildid
cache and can be used to fix them.  That is needed
for distributions where root does not have a home
directory and consequently writes to the same
buildid cache as the user, resulting in cached files
that the user does not have access to.

Example:

$ ./perf-with-kcore
Usage: perf-with-kcore <perf sub-command> <perf.data directory> [<sub-command options> [ -- <workload>]]
       <perf sub-command> can be record, script, report or inject
   or: perf-with-kcore fix_buildid_cache_permissions
$ ./perf-with-kcore record pt_uname -e intel_pt// -- uname
Recording
Using /home/ahunter/bin/perf
perf version 3.15.rc3.g4549ba
/home/ahunter/bin/perf record -o pt_uname/perf.data -e intel_pt//  -- uname
Linux
[ perf record: Woken up 3 times to write data ]
[ perf record: Captured and wrote 0.023 MB pt_uname/perf.data ]
Copying kcore
[sudo] password for ahunter:
Done
$ tools/perf/perf-with-kcore.sh script pt_uname | head
Using /home/ahunter/bin/perf
perf version 3.15.rc3.g4549ba
/home/ahunter/bin/perf script -i pt_uname/perf.data --kallsyms=pt_uname/kcore_dir/kallsyms
         swapper     0 [002] 161533.969666: sched:sched_switch: swapper/2:0 [120] R ==> perf:11316 [120]
          :11315 11315 [003] 161533.969704: sched:sched_switch: perf:11315 [120] S ==> swapper/3:0 [120]
          :11316 11316 [002] 161533.969783: sched:sched_switch: perf:11316 [120] R ==> migration/2:33 [0]
             :33    33 [002] 161533.969791: sched:sched_switch: migration/2:33 [0] S ==> swapper/2:0 [120]
         swapper     0 [003] 161533.969792: sched:sched_switch: swapper/3:0 [120] R ==> perf:11316 [120]
          :11316 11316 [003] 161533.970062: branches:                 0 [unknown] ([unknown]) => ffffffff810532fa native_write_msr_safe ([kernel.kallsyms])
          :11316 11316 [003] 161533.970062: branches:  ffffffff810532fd native_write_msr_safe ([kernel.kallsyms]) => ffffffff81035b31 pt_config_start ([kernel.kallsyms])

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/.gitignore         |   1 +
 tools/perf/Makefile.perf      |   5 +-
 tools/perf/perf-with-kcore.sh | 259 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 264 insertions(+), 1 deletion(-)
 create mode 100644 tools/perf/perf-with-kcore.sh

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 782d86e..717221e 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -15,6 +15,7 @@ perf.data
 perf.data.old
 output.svg
 perf-archive
+perf-with-kcore
 tags
 TAGS
 cscope*
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index f7bb2b4..9b1f05d 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -126,6 +126,7 @@ PYRF_OBJS =
 SCRIPT_SH =
 
 SCRIPT_SH += perf-archive.sh
+SCRIPT_SH += perf-with-kcore.sh
 
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
@@ -879,6 +880,8 @@ install-bin: all install-gtk
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(call QUIET_INSTALL, perf-archive) \
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+	$(call QUIET_INSTALL, perf-with-kcore) \
+		$(INSTALL) $(OUTPUT)perf-with-kcore -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifndef NO_LIBPERL
 	$(call QUIET_INSTALL, perl-scripts) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
@@ -924,7 +927,7 @@ config-clean:
 	@$(MAKE) -C config/feature-checks clean >/dev/null
 
 clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
-	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
+	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
diff --git a/tools/perf/perf-with-kcore.sh b/tools/perf/perf-with-kcore.sh
new file mode 100644
index 0000000..c7ff90a
--- /dev/null
+++ b/tools/perf/perf-with-kcore.sh
@@ -0,0 +1,259 @@
+#!/bin/bash
+# perf-with-kcore: use perf with a copy of kcore
+# Copyright (c) 2014, Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+# more details.
+
+set -e
+
+usage()
+{
+        echo "Usage: perf-with-kcore <perf sub-command> <perf.data directory> [<sub-command options> [ -- <workload>]]" >&2
+        echo "       <perf sub-command> can be record, script, report or inject" >&2
+        echo "   or: perf-with-kcore fix_buildid_cache_permissions" >&2
+        exit 1
+}
+
+find_perf()
+{
+	if [ -n "$PERF" ] ; then
+		return
+	fi
+	PERF=`which perf || true`
+	if [ -z "$PERF" ] ; then
+		echo "Failed to find perf" >&2
+	        exit 1
+	fi
+	if [ ! -x "$PERF" ] ; then
+		echo "Failed to find perf" >&2
+	        exit 1
+	fi
+	echo "Using $PERF"
+	"$PERF" version
+}
+
+copy_kcore()
+{
+	echo "Copying kcore"
+
+	if [ $EUID -eq 0 ] ; then
+		SUDO=""
+	else
+		SUDO="sudo"
+	fi
+
+	rm -f perf.data.junk
+	("$PERF" record -o perf.data.junk $PERF_OPTIONS -- sleep 60) >/dev/null 2>/dev/null &
+	PERF_PID=$!
+
+	# Need to make sure that perf has started
+	sleep 1
+
+	KCORE=$(($SUDO "$PERF" buildid-cache -v -f -k /proc/kcore >/dev/null) 2>&1)
+	case "$KCORE" in
+	"kcore added to build-id cache directory "*)
+		KCORE_DIR=${KCORE#"kcore added to build-id cache directory "}
+	;;
+	*)
+		kill $PERF_PID
+		wait >/dev/null 2>/dev/null || true
+		rm perf.data.junk
+		echo "$KCORE"
+		echo "Failed to find kcore" >&2
+		exit 1
+	;;
+	esac
+
+	kill $PERF_PID
+	wait >/dev/null 2>/dev/null || true
+	rm perf.data.junk
+
+	$SUDO cp -a "$KCORE_DIR" "$(pwd)/$PERF_DATA_DIR"
+	$SUDO rm -f "$KCORE_DIR/kcore"
+	$SUDO rm -f "$KCORE_DIR/kallsyms"
+	$SUDO rm -f "$KCORE_DIR/modules"
+	$SUDO rmdir "$KCORE_DIR"
+
+	KCORE_DIR_BASENAME=$(basename "$KCORE_DIR")
+	KCORE_DIR="$(pwd)/$PERF_DATA_DIR/$KCORE_DIR_BASENAME"
+
+	$SUDO chown $UID "$KCORE_DIR"
+	$SUDO chown $UID "$KCORE_DIR/kcore"
+	$SUDO chown $UID "$KCORE_DIR/kallsyms"
+	$SUDO chown $UID "$KCORE_DIR/modules"
+
+	$SUDO chgrp $GROUPS "$KCORE_DIR"
+	$SUDO chgrp $GROUPS "$KCORE_DIR/kcore"
+	$SUDO chgrp $GROUPS "$KCORE_DIR/kallsyms"
+	$SUDO chgrp $GROUPS "$KCORE_DIR/modules"
+
+	ln -s "$KCORE_DIR_BASENAME" "$PERF_DATA_DIR/kcore_dir"
+}
+
+fix_buildid_cache_permissions()
+{
+	if [ $EUID -ne 0 ] ; then
+		echo "This script must be run as root via sudo " >&2
+		exit 1
+	fi
+
+	if [ -z "$SUDO_USER" ] ; then
+		echo "This script must be run via sudo" >&2
+		exit 1
+	fi
+
+	USER_HOME=$(bash <<< "echo ~$SUDO_USER")
+
+	if [ "$HOME" != "$USER_HOME" ] ; then
+		echo "Fix unnecessary because root has a home: $HOME" >&2
+		exit 1
+	fi
+
+	echo "Fixing buildid cache permissions"
+
+	find "$USER_HOME/.debug" -xdev -type d          ! -user "$SUDO_USER" -ls -exec chown    "$SUDO_USER" \{\} \;
+	find "$USER_HOME/.debug" -xdev -type f -links 1 ! -user "$SUDO_USER" -ls -exec chown    "$SUDO_USER" \{\} \;
+	find "$USER_HOME/.debug" -xdev -type l          ! -user "$SUDO_USER" -ls -exec chown -h "$SUDO_USER" \{\} \;
+
+	if [ -n "$SUDO_GID" ] ; then
+		find "$USER_HOME/.debug" -xdev -type d          ! -group "$SUDO_GID" -ls -exec chgrp    "$SUDO_GID" \{\} \;
+		find "$USER_HOME/.debug" -xdev -type f -links 1 ! -group "$SUDO_GID" -ls -exec chgrp    "$SUDO_GID" \{\} \;
+		find "$USER_HOME/.debug" -xdev -type l          ! -group "$SUDO_GID" -ls -exec chgrp -h "$SUDO_GID" \{\} \;
+	fi
+
+	echo "Done"
+}
+
+check_buildid_cache_permissions()
+{
+	if [ $EUID -eq 0 ] ; then
+		return
+	fi
+
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d          ! -user "$USER" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -user "$USER" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l          ! -user "$USER" -print -quit)
+
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d          ! -group "$GROUPS" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -group "$GROUPS" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l          ! -group "$GROUPS" -print -quit)
+
+	if [ -n "$PERMISSIONS_OK" ] ; then
+		echo "*** WARNING *** buildid cache permissions may need fixing" >&2
+	fi
+}
+
+record()
+{
+	echo "Recording"
+
+	if [ $EUID -ne 0 ] ; then
+
+		if [ "$(cat /proc/sys/kernel/kptr_restrict)" -ne 0 ] ; then
+			echo "*** WARNING *** /proc/sys/kernel/kptr_restrict prevents access to kernel addresses" >&2
+		fi
+
+		if echo "$PERF_OPTIONS" | grep -q ' -a \|^-a \| -a$\|^-a$\| --all-cpus \|^--all-cpus \| --all-cpus$\|^--all-cpus$' ; then
+			echo "*** WARNING *** system-wide tracing without root access will not be able to read all necessary information from /proc" >&2
+		fi
+
+		if echo "$PERF_OPTIONS" | grep -q 'intel_pt\|intel_bts\| -I\|^-I' ; then
+			if [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt -1 ] ; then
+				echo "*** WARNING *** /proc/sys/kernel/perf_event_paranoid restricts buffer size and tracepoint (sched_switch) use" >&2
+			fi
+
+			if echo "$PERF_OPTIONS" | grep -q ' --per-thread \|^--per-thread \| --per-thread$\|^--per-thread$' ; then
+				true
+			elif echo "$PERF_OPTIONS" | grep -q ' -t \|^-t \| -t$\|^-t$' ; then
+				true
+			elif [ ! -r /sys/kernel/debug -o ! -x /sys/kernel/debug ] ; then
+				echo "*** WARNING *** /sys/kernel/debug permissions prevent tracepoint (sched_switch) use" >&2
+			fi
+		fi
+	fi
+
+	if [ -z "$1" ] ; then
+		echo "Workload is required for recording" >&2
+		usage
+	fi
+
+	if [ -e "$PERF_DATA_DIR" ] ; then
+		echo "'$PERF_DATA_DIR' exists" >&2
+		exit 1
+	fi
+
+	find_perf
+
+	mkdir "$PERF_DATA_DIR"
+
+	echo "$PERF record -o $PERF_DATA_DIR/perf.data $PERF_OPTIONS -- $*"
+	"$PERF" record -o "$PERF_DATA_DIR/perf.data" $PERF_OPTIONS -- $* || true
+
+	if rmdir "$PERF_DATA_DIR" > /dev/null 2>/dev/null ; then
+		exit 1
+	fi
+
+	copy_kcore
+
+	echo "Done"
+}
+
+subcommand()
+{
+	find_perf
+	check_buildid_cache_permissions
+	echo "$PERF $PERF_SUB_COMMAND -i $PERF_DATA_DIR/perf.data --kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms $*"
+	"$PERF" $PERF_SUB_COMMAND -i "$PERF_DATA_DIR/perf.data" "--kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms" $*
+}
+
+if [ "$1" = "fix_buildid_cache_permissions" ] ; then
+	fix_buildid_cache_permissions
+	exit 0
+fi
+
+PERF_SUB_COMMAND=$1
+PERF_DATA_DIR=$2
+shift || true
+shift || true
+
+if [ -z "$PERF_SUB_COMMAND" ] ; then
+	usage
+fi
+
+if [ -z "$PERF_DATA_DIR" ] ; then
+	usage
+fi
+
+case "$PERF_SUB_COMMAND" in
+"record")
+	while [ "$1" != "--" ] ; do
+		PERF_OPTIONS+="$1 "
+		shift || break
+	done
+	if [ "$1" != "--" ] ; then
+		echo "Options and workload are required for recording" >&2
+		usage
+	fi
+	shift
+	record $*
+;;
+"script")
+	subcommand $*
+;;
+"report")
+	subcommand $*
+;;
+"inject")
+	subcommand $*
+;;
+*)
+	usage
+;;
+esac
-- 
1.8.3.2

[PATCH 30/31] perf tools: Build programs to copy 32-bit compatibility VDSOs

[Adrian Hunter]

perf tools copy VDSO out of memory.  However, on 64-bit
machines there may be 32-bit compatibility VDOs also.  To
copy those requires separate 32-bit executables.  This
patch adds to the build additional programs perf-read-vdso32
and perf-read-vdsox32 for 32-bit and x32 respectively.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/Makefile.perf        | 37 +++++++++++++++++++++++---
 tools/perf/config/Makefile      | 21 +++++++++++++++
 tools/perf/config/Makefile.arch |  8 ++++++
 tools/perf/perf-read-vdso.c     | 59 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 121 insertions(+), 4 deletions(-)
 create mode 100644 tools/perf/perf-read-vdso.c

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 9b1f05d..2cd3316 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -60,6 +60,12 @@ include config/utilities.mak
 #
 # Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support
 # for dwarf backtrace post unwind.
+#
+# Define NO_PERF_READ_VDSO32 if you do not want to build perf-read-vdso32
+# for reading the 32-bit compatibility VDSO in 64-bit mode
+#
+# Define NO_PERF_READ_VDSOX32 if you do not want to build perf-read-vdsox32
+# for reading the x32 mode 32-bit compatibility VDSO in 64-bit mode
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))
@@ -171,11 +177,16 @@ $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 
 SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
 
-#
-# Single 'perf' binary right now:
-#
 PROGRAMS += $(OUTPUT)perf
 
+ifndef NO_PERF_READ_VDSO32
+PROGRAMS += $(OUTPUT)perf-read-vdso32
+endif
+
+ifndef NO_PERF_READ_VDSOX32
+PROGRAMS += $(OUTPUT)perf-read-vdsox32
+endif
+
 # what 'all' will build and 'install' will install, in perfexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
 
@@ -732,6 +743,16 @@ $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Uti
 $(OUTPUT)perf-%: %.o $(PERFLIBS)
 	$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS)
 
+ifndef NO_PERF_READ_VDSO32
+$(OUTPUT)perf-read-vdso32: perf-read-vdso.c
+	$(QUIET_CC)$(CC) -m32 -Wall -Werror -o $@ perf-read-vdso.c
+endif
+
+ifndef NO_PERF_READ_VDSOX32
+$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c
+	$(QUIET_CC)$(CC) -mx32 -Wall -Werror -o $@ perf-read-vdso.c
+endif
+
 $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
 $(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
 
@@ -876,6 +897,14 @@ install-bin: all install-gtk
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \
 		$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \
 		$(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(bindir_SQ)/trace'
+ifndef NO_PERF_READ_VDSO32
+	$(call QUIET_INSTALL, perf-read-vdso32) \
+		$(INSTALL) $(OUTPUT)perf-read-vdso32 '$(DESTDIR_SQ)$(bindir_SQ)';
+endif
+ifndef NO_PERF_READ_VDSOX32
+	$(call QUIET_INSTALL, perf-read-vdsox32) \
+		$(INSTALL) $(OUTPUT)perf-read-vdsox32 '$(DESTDIR_SQ)$(bindir_SQ)';
+endif
 	$(call QUIET_INSTALL, libexec) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(call QUIET_INSTALL, perf-archive) \
@@ -928,7 +957,7 @@ config-clean:
 
 clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
-	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
+	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 1f67aa0..45ab040 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -604,6 +604,27 @@ ifdef HAVE_KVM_STAT_SUPPORT
     CFLAGS += -DHAVE_KVM_STAT_SUPPORT
 endif
 
+ifeq (${IS_64_BIT}, 1)
+  ifndef NO_PERF_READ_VDSO32
+    CAN_DO := $(shell echo "main() {}" | ${CC} -m32 -x c - >/dev/null 2>/dev/null && echo 1 || echo 0)
+    ifneq (${CAN_DO}, 1)
+      NO_PERF_READ_VDSO32 := 1
+    endif
+  endif
+  ifneq (${IS_X86_64}, 1)
+    NO_PERF_READ_VDSOX32 := 1
+  endif
+  ifndef NO_PERF_READ_VDSOX32
+    CAN_DO := $(shell echo 'main() {}' | ${CC} -mx32 -x c - >/dev/null 2>/dev/null && echo 1 || echo 0)
+    ifneq (${CAN_DO}, 1)
+      NO_PERF_READ_VDSOX32 := 1
+    endif
+  endif
+else
+  NO_PERF_READ_VDSO32 := 1
+  NO_PERF_READ_VDSOX32 := 1
+endif
+
 # Among the variables below, these:
 #   perfexecdir
 #   template_dir
diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch
index 4b06719..851cd01 100644
--- a/tools/perf/config/Makefile.arch
+++ b/tools/perf/config/Makefile.arch
@@ -21,3 +21,11 @@ ifeq ($(ARCH),x86_64)
     RAW_ARCH := x86_64
   endif
 endif
+
+ifeq (${IS_X86_64}, 1)
+  IS_64_BIT := 1
+else ifeq ($(ARCH),x86)
+  IS_64_BIT := 0
+else
+  IS_64_BIT := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+endif
diff --git a/tools/perf/perf-read-vdso.c b/tools/perf/perf-read-vdso.c
new file mode 100644
index 0000000..a6b49b5
--- /dev/null
+++ b/tools/perf/perf-read-vdso.c
@@ -0,0 +1,59 @@
+#include <stdio.h>
+#include <string.h>
+
+#define VDSO__MAP_NAME "[vdso]"
+
+static int find_vdso_map(void **start, void **end)
+{
+	FILE *maps;
+	char line[128];
+	int found = 0;
+
+	maps = fopen("/proc/self/maps", "r");
+	if (!maps) {
+		fprintf(stderr, "vdso: cannot open maps\n");
+		return -1;
+	}
+
+	while (!found && fgets(line, sizeof(line), maps)) {
+		int m = -1;
+
+		/* We care only about private r-x mappings. */
+		if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n",
+				start, end, &m))
+			continue;
+		if (m < 0)
+			continue;
+
+		if (!strncmp(&line[m], VDSO__MAP_NAME,
+			     sizeof(VDSO__MAP_NAME) - 1))
+			found = 1;
+	}
+
+	fclose(maps);
+	return !found;
+}
+
+int main(void)
+{
+	void *start, *end;
+	size_t size, written;
+
+	if (find_vdso_map(&start, &end))
+		return 1;
+
+	size = end - start;
+
+	while (size) {
+		written = fwrite(start, 1, size, stdout);
+		if (!written)
+			return 1;
+		start += written;
+		size -= written;
+	}
+
+	if (fflush(stdout))
+		return 1;
+
+	return 0;
+}
-- 
1.8.3.2

[PATCH 31/31] perf tools: Add support for 32-bit compatibility VDSOs

[Adrian Hunter]

'perf record' post-processes the event stream  to create
a list of build-ids for object files for which sample
events have been recorded.  That results in those object
files being recorded in the build-id cache.

In the case of VDSO, perf tools reads it from memory
and copies it into a temporary file, which as decribed
above, gets added to the build-id cache.

Then when the perf.data file is processed by other
tools, the build-id of VDSO is listed in the perf.data
file and the VDSO can be read from the build-id cache.
In that case the name of the map, the short name of the
DSO, and the entry in the build-id cache are all
"[vdso]".

However, in the 64-bit case, there also can be 32-bit
compatibility VDSOs.

A previous patch added programs "perf-read-vdso32" and
"perf read-vdsox32".  This patch uses those programs to
read the correct VDSO for a thread and create a
temporary file just as for the 64-bit VDSO.  The map
name and the entry in the build-id cache are still
"[vdso]" but the DSO short name becomes "[vdso32]"
and "[vdsox32]" respectively.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/vdso.c | 170 ++++++++++++++++++++++++++++++++++++++++++++++++-
 tools/perf/util/vdso.h |   4 +-
 2 files changed, 172 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index adca693..b721f4c 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -12,6 +12,7 @@
 #include "util.h"
 #include "symbol.h"
 #include "machine.h"
+#include "thread.h"
 #include "linux/string.h"
 #include "debug.h"
 
@@ -22,10 +23,15 @@ struct vdso_file {
 	bool error;
 	char temp_file_name[sizeof(VDSO__TEMP_FILE_NAME)];
 	const char *dso_name;
+	const char *read_prog;
 };
 
 struct vdso_info {
 	struct vdso_file vdso;
+#if BITS_PER_LONG == 64
+	struct vdso_file vdso32;
+	struct vdso_file vdsox32;
+#endif
 };
 
 static struct vdso_info *vdso_info__new(void)
@@ -35,6 +41,18 @@ static struct vdso_info *vdso_info__new(void)
 			.temp_file_name = VDSO__TEMP_FILE_NAME,
 			.dso_name = DSO__NAME_VDSO,
 		},
+#if BITS_PER_LONG == 64
+		.vdso32  = {
+			.temp_file_name = VDSO__TEMP_FILE_NAME,
+			.dso_name = DSO__NAME_VDSO32,
+			.read_prog = "perf-read-vdso32",
+		},
+		.vdsox32  = {
+			.temp_file_name = VDSO__TEMP_FILE_NAME,
+			.dso_name = DSO__NAME_VDSOX32,
+			.read_prog = "perf-read-vdsox32",
+		},
+#endif
 	};
 
 	return memdup(&vdso_info_init, sizeof(vdso_info_init));
@@ -117,6 +135,12 @@ void vdso__exit(struct machine *machine)
 
 	if (vdso_info->vdso.found)
 		unlink(vdso_info->vdso.temp_file_name);
+#if BITS_PER_LONG == 64
+	if (vdso_info->vdso32.found)
+		unlink(vdso_info->vdso.temp_file_name);
+	if (vdso_info->vdsox32.found)
+		unlink(vdso_info->vdso.temp_file_name);
+#endif
 
 	zfree(&machine->vdso_info);
 }
@@ -135,6 +159,143 @@ static struct dso *vdso__new(struct machine *machine, const char *short_name,
 	return dso;
 }
 
+#if BITS_PER_LONG == 64
+
+static enum dso_type machine__thread_dso_type(struct machine *machine,
+					      struct thread *thread)
+{
+	enum dso_type dso_type = DSO__TYPE_UNKNOWN;
+	struct map *map;
+	struct dso *dso;
+
+	map = map_groups__first(thread->mg, MAP__FUNCTION);
+	for (; map ; map = map_groups__next(map)) {
+		dso = map->dso;
+		if (!dso || dso->long_name[0] != '/')
+			continue;
+		dso_type = dso__type(dso, machine);
+		if (dso_type != DSO__TYPE_UNKNOWN)
+			break;
+	}
+
+	return dso_type;
+}
+
+static int vdso__do_copy_compat(FILE *f, int fd)
+{
+	char buf[4096];
+	size_t count;
+
+	while (1) {
+		count = fread(buf, 1, sizeof(buf), f);
+		if (ferror(f))
+			return -errno;
+		if (feof(f))
+			break;
+		if (count && writen(fd, buf, count) != (ssize_t)count)
+			return -errno;
+	}
+
+	return 0;
+}
+
+static int vdso__copy_compat(const char *prog, int fd)
+{
+	FILE *f;
+	int err;
+
+	f = popen(prog, "r");
+	if (!f)
+		return -errno;
+
+	err = vdso__do_copy_compat(f, fd);
+
+	if (pclose(f) == -1)
+		return -errno;
+
+	return err;
+}
+
+static int vdso__create_compat_file(const char *prog, char *temp_name)
+{
+	int fd, err;
+
+	fd = mkstemp(temp_name);
+	if (fd < 0)
+		return -errno;
+
+	err = vdso__copy_compat(prog, fd);
+
+	if (close(fd) == -1)
+		return -errno;
+
+	return err;
+}
+
+static const char *vdso__get_compat_file(struct vdso_file *vdso_file)
+{
+	int err;
+
+	if (vdso_file->found)
+		return vdso_file->temp_file_name;
+
+	if (vdso_file->error)
+		return NULL;
+
+	err = vdso__create_compat_file(vdso_file->read_prog,
+				       vdso_file->temp_file_name);
+	if (err) {
+		pr_err("%s failed, error %d\n", vdso_file->read_prog, err);
+		vdso_file->error = true;
+		return NULL;
+	}
+
+	vdso_file->found = true;
+
+	return vdso_file->temp_file_name;
+}
+
+static struct dso *vdso__findnew_compat(struct machine *machine,
+					struct vdso_file *vdso_file)
+{
+	const char *file_name;
+	struct dso *dso;
+
+	dso = dsos__find(&machine->user_dsos, vdso_file->dso_name, true);
+	if (dso)
+		return dso;
+
+	file_name = vdso__get_compat_file(vdso_file);
+	if (!file_name)
+		return NULL;
+
+	return vdso__new(machine, vdso_file->dso_name, file_name);
+}
+
+static int vdso__dso_findnew_compat(struct machine *machine,
+				    struct thread *thread,
+				    struct vdso_info *vdso_info,
+				    struct dso **dso)
+{
+	enum dso_type dso_type;
+
+	dso_type = machine__thread_dso_type(machine, thread);
+	switch (dso_type) {
+	case DSO__TYPE_32BIT:
+		*dso = vdso__findnew_compat(machine, &vdso_info->vdso32);
+		return 1;
+	case DSO__TYPE_X32BIT:
+		*dso = vdso__findnew_compat(machine, &vdso_info->vdsox32);
+		return 1;
+	case DSO__TYPE_UNKNOWN:
+	case DSO__TYPE_64BIT:
+	default:
+		return 0;
+	}
+}
+
+#endif
+
 struct dso *vdso__dso_findnew(struct machine *machine,
 			      struct thread *thread __maybe_unused)
 {
@@ -148,6 +309,11 @@ struct dso *vdso__dso_findnew(struct machine *machine,
 	if (!vdso_info)
 		return NULL;
 
+#if BITS_PER_LONG == 64
+	if (vdso__dso_findnew_compat(machine, thread, vdso_info, &dso))
+		return dso;
+#endif
+
 	dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true);
 	if (!dso) {
 		char *file;
@@ -164,5 +330,7 @@ struct dso *vdso__dso_findnew(struct machine *machine,
 
 bool dso__is_vdso(struct dso *dso)
 {
-	return !strcmp(dso->short_name, DSO__NAME_VDSO);
+	return !strcmp(dso->short_name, DSO__NAME_VDSO) ||
+	       !strcmp(dso->short_name, DSO__NAME_VDSO32) ||
+	       !strcmp(dso->short_name, DSO__NAME_VDSOX32);
 }
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
index af9d692..d97da16 100644
--- a/tools/perf/util/vdso.h
+++ b/tools/perf/util/vdso.h
@@ -7,7 +7,9 @@
 
 #define VDSO__MAP_NAME "[vdso]"
 
-#define DSO__NAME_VDSO "[vdso]"
+#define DSO__NAME_VDSO    "[vdso]"
+#define DSO__NAME_VDSO32  "[vdso32]"
+#define DSO__NAME_VDSOX32 "[vdsox32]"
 
 static inline bool is_vdso_map(const char *filename)
 {
-- 
1.8.3.2

Re: [PATCH 00/31] perf tools: Yet more preparation for call graph from Intel BTS

[Arnaldo Carvalho de Melo]

Em Thu, Jul 31, 2014 at 09:00:43AM +0300, Adrian Hunter escreveu:
> Hi
> 
> Here is the next selection of patches based on tip/perf/core.
> 
> They can also be found here:
> 
> 	http://git.infradead.org/users/ahunter/linux-perf.git/shortlog/refs/heads/for-acme

Just FYI, did some processing today, what I picked I stashed on my
tmp.perf/core branch, will continue.

But having something that actually uses all this stuff in 'perf test' is
something I'm missing...

Things like using that set_tracking new API on a evlist with the
sched_switch, using it to track, then switching it off after moving the
tracking event to another event in the list, etc. 

- Arnaldo

Re: [PATCH 00/31] perf tools: Yet more preparation for call graph from Intel BTS

[Adrian Hunter]

On 5/08/2014 12:58 a.m., Arnaldo Carvalho de Melo wrote:
> Em Thu, Jul 31, 2014 at 09:00:43AM +0300, Adrian Hunter escreveu:
>> Hi
>>
>> Here is the next selection of patches based on tip/perf/core.
>>
>> They can also be found here:
>>
>> 	http://git.infradead.org/users/ahunter/linux-perf.git/shortlog/refs/heads/for-acme
>
> Just FYI, did some processing today, what I picked I stashed on my
> tmp.perf/core branch, will continue.

Thank you!

>
> But having something that actually uses all this stuff in 'perf test' is
> something I'm missing...
>
> Things like using that set_tracking new API on a evlist with the
> sched_switch, using it to track, then switching it off after moving the
> tracking event to another event in the list, etc.

I will look at that.

[tip:perf/core] perf symbols: Fix missing label symbols

[tip-bot for Adrian Hunter]

Commit-ID:  f247fb8191aa7f10d3f6c987e8ef0853ae789a02
Gitweb:     http://git.kernel.org/tip/f247fb8191aa7f10d3f6c987e8ef0853ae789a02
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 31 Jul 2014 09:00:46 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 13 Aug 2014 19:20:39 -0300

perf symbols: Fix missing label symbols

Label symbols are missing because elf_sec__is_a() fails to find the
section because the section strings do not match the section headers
because the sections headers are from the 'runtime' object and the
sections strings are from the 'symbol source' object.

Fix by getting the section strings from the 'runtime' object so that
they match the section headers.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
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/1406786474-9306-4-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/symbol-elf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index ec5ec1c..9fb5e9e 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -736,7 +736,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	if (symstrs == NULL)
 		goto out_elf_end;
 
-	sec_strndx = elf_getscn(elf, ehdr.e_shstrndx);
+	sec_strndx = elf_getscn(runtime_ss->elf, runtime_ss->ehdr.e_shstrndx);
 	if (sec_strndx == NULL)
 		goto out_elf_end;
 

[tip:perf/core] perf evlist: Add 'system_wide' option

[tip-bot for Adrian Hunter]

Commit-ID:  bf8e8f4b832972c76d64ab2e2837a48397144887
Gitweb:     http://git.kernel.org/tip/bf8e8f4b832972c76d64ab2e2837a48397144887
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 31 Jul 2014 09:00:51 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 13 Aug 2014 19:21:18 -0300

perf evlist: Add 'system_wide' option

Add an option to cause a selected event to be opened always without a
pid when configured by perf_evsel__config().

This is needed when using the sched_switch tracepoint to follow object
code execution.

sched_switch occurs before the task switch and so it cannot record it in
a context limited to that task.  Note that also means that sched_switch
is useless when capturing data per-thread, as is the 'context-switches'
software event for the same reason.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
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/1406786474-9306-9-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c | 45 +++++++++++++++++++++++++++++++++++++--------
 tools/perf/util/evsel.c  | 31 ++++++++++++++++++++++++++-----
 tools/perf/util/evsel.h  |  1 +
 3 files changed, 64 insertions(+), 13 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 3b366c0..c74d8ec 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -265,17 +265,27 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist,
 	return 0;
 }
 
+static int perf_evlist__nr_threads(struct perf_evlist *evlist,
+				   struct perf_evsel *evsel)
+{
+	if (evsel->system_wide)
+		return 1;
+	else
+		return thread_map__nr(evlist->threads);
+}
+
 void perf_evlist__disable(struct perf_evlist *evlist)
 {
 	int cpu, thread;
 	struct perf_evsel *pos;
 	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = thread_map__nr(evlist->threads);
+	int nr_threads;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		evlist__for_each(evlist, pos) {
 			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 				continue;
+			nr_threads = perf_evlist__nr_threads(evlist, pos);
 			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_DISABLE, 0);
@@ -288,12 +298,13 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 	int cpu, thread;
 	struct perf_evsel *pos;
 	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = thread_map__nr(evlist->threads);
+	int nr_threads;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		evlist__for_each(evlist, pos) {
 			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 				continue;
+			nr_threads = perf_evlist__nr_threads(evlist, pos);
 			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_ENABLE, 0);
@@ -305,12 +316,14 @@ int perf_evlist__disable_event(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel)
 {
 	int cpu, thread, err;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
 
 	if (!evsel->fd)
 		return 0;
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-		for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		for (thread = 0; thread < nr_threads; thread++) {
 			err = ioctl(FD(evsel, cpu, thread),
 				    PERF_EVENT_IOC_DISABLE, 0);
 			if (err)
@@ -324,12 +337,14 @@ int perf_evlist__enable_event(struct perf_evlist *evlist,
 			      struct perf_evsel *evsel)
 {
 	int cpu, thread, err;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
 
 	if (!evsel->fd)
 		return -EINVAL;
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-		for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		for (thread = 0; thread < nr_threads; thread++) {
 			err = ioctl(FD(evsel, cpu, thread),
 				    PERF_EVENT_IOC_ENABLE, 0);
 			if (err)
@@ -343,7 +358,16 @@ static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
 	int nr_cpus = cpu_map__nr(evlist->cpus);
 	int nr_threads = thread_map__nr(evlist->threads);
-	int nfds = nr_cpus * nr_threads * evlist->nr_entries;
+	int nfds = 0;
+	struct perf_evsel *evsel;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		if (evsel->system_wide)
+			nfds += nr_cpus;
+		else
+			nfds += nr_cpus * nr_threads;
+	}
+
 	evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
 	return evlist->pollfd != NULL ? 0 : -ENOMEM;
 }
@@ -636,7 +660,12 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 	struct perf_evsel *evsel;
 
 	evlist__for_each(evlist, evsel) {
-		int fd = FD(evsel, cpu, thread);
+		int fd;
+
+		if (evsel->system_wide && thread)
+			continue;
+
+		fd = FD(evsel, cpu, thread);
 
 		if (*output == -1) {
 			*output = fd;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 0c8919d..66de9a7 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -695,6 +695,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	int cpu, thread;
+
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
 
 	if (evsel->fd) {
@@ -713,6 +717,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea
 {
 	int cpu, thread;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	for (cpu = 0; cpu < ncpus; cpu++) {
 		for (thread = 0; thread < nthreads; thread++) {
 			int fd = FD(evsel, cpu, thread),
@@ -743,6 +750,9 @@ int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
 	if (evsel->sample_id == NULL)
 		return -ENOMEM;
@@ -787,6 +797,9 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	int cpu, thread;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	for (cpu = 0; cpu < ncpus; cpu++)
 		for (thread = 0; thread < nthreads; ++thread) {
 			close(FD(evsel, cpu, thread));
@@ -875,6 +888,9 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 	int cpu, thread;
 	struct perf_counts_values *aggr = &evsel->counts->aggr, count;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	aggr->val = aggr->ena = aggr->run = 0;
 
 	for (cpu = 0; cpu < ncpus; cpu++) {
@@ -997,13 +1013,18 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 			      struct thread_map *threads)
 {
-	int cpu, thread;
+	int cpu, thread, nthreads;
 	unsigned long flags = PERF_FLAG_FD_CLOEXEC;
 	int pid = -1, err;
 	enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+	else
+		nthreads = threads->nr;
+
 	if (evsel->fd == NULL &&
-	    perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
+	    perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0)
 		return -ENOMEM;
 
 	if (evsel->cgrp) {
@@ -1027,10 +1048,10 @@ retry_sample_id:
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
-		for (thread = 0; thread < threads->nr; thread++) {
+		for (thread = 0; thread < nthreads; thread++) {
 			int group_fd;
 
-			if (!evsel->cgrp)
+			if (!evsel->cgrp && !evsel->system_wide)
 				pid = threads->map[thread];
 
 			group_fd = get_group_fd(evsel, cpu, thread);
@@ -1103,7 +1124,7 @@ out_close:
 			close(FD(evsel, cpu, thread));
 			FD(evsel, cpu, thread) = -1;
 		}
-		thread = threads->nr;
+		thread = nthreads;
 	} while (--cpu >= 0);
 	return err;
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d7f93ce..dbb2a0d 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -85,6 +85,7 @@ struct perf_evsel {
 	bool 			needs_swap;
 	bool			no_aux_samples;
 	bool			immediate;
+	bool			system_wide;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;

[tip:perf/core] perf evlist: Add perf_evlist__set_tracking_event( )

[tip-bot for Adrian Hunter]

Commit-ID:  60b0896cc35243f515eda2085f9897e296177e45
Gitweb:     http://git.kernel.org/tip/60b0896cc35243f515eda2085f9897e296177e45
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 31 Jul 2014 09:00:52 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 13 Aug 2014 19:21:32 -0300

perf evlist: Add perf_evlist__set_tracking_event()

Add a function to change which event is used to track mmap, comm and
task events.

This is needed with Instruction Tracing because the Instruction Tracing
event must come first but cannot be used for tracking because it will be
disabled under some circumstances.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
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/1406786474-9306-10-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c | 17 +++++++++++++++++
 tools/perf/util/evlist.h |  3 +++
 tools/perf/util/evsel.c  |  3 ++-
 tools/perf/util/evsel.h  |  1 +
 tools/perf/util/record.c |  2 +-
 5 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c74d8ec..9d863db 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -122,6 +122,7 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 {
 	list_add_tail(&entry->node, &evlist->entries);
 	entry->idx = evlist->nr_entries;
+	entry->tracking = !entry->idx;
 
 	if (!evlist->nr_entries++)
 		perf_evlist__set_id_pos(evlist);
@@ -1295,3 +1296,19 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 
 	list_splice(&move, &evlist->entries);
 }
+
+void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
+				     struct perf_evsel *tracking_evsel)
+{
+	struct perf_evsel *evsel;
+
+	if (tracking_evsel->tracking)
+		return;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel != tracking_evsel)
+			evsel->tracking = false;
+	}
+
+	tracking_evsel->tracking = true;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index f5173cd..e0084f9 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -262,4 +262,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 #define evlist__for_each_safe(evlist, tmp, evsel) \
 	__evlist__for_each_safe(&(evlist)->entries, tmp, evsel)
 
+void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
+				     struct perf_evsel *tracking_evsel);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 66de9a7..01ce14c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -162,6 +162,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
 	evsel->idx	   = idx;
+	evsel->tracking	   = !idx;
 	evsel->attr	   = *attr;
 	evsel->leader	   = evsel;
 	evsel->unit	   = "";
@@ -561,7 +562,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 {
 	struct perf_evsel *leader = evsel->leader;
 	struct perf_event_attr *attr = &evsel->attr;
-	int track = !evsel->idx; /* only the first counter needs these */
+	int track = evsel->tracking;
 	bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
 
 	attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index dbb2a0d..7bc314b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -86,6 +86,7 @@ struct perf_evsel {
 	bool			no_aux_samples;
 	bool			immediate;
 	bool			system_wide;
+	bool			tracking;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index e778afd..cf69325 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -115,7 +115,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 
 	evlist__for_each(evlist, evsel) {
 		perf_evsel__config(evsel, opts);
-		if (!evsel->idx && use_comm_exec)
+		if (evsel->tracking && use_comm_exec)
 			evsel->attr.comm_exec = 1;
 	}
 

[tip:perf/core] perf session: Add perf_session__peek_event()

[tip-bot for Adrian Hunter]

Commit-ID:  5a52f33adf02a3e5eafdc1e597a3fe172e620bec
Gitweb:     http://git.kernel.org/tip/5a52f33adf02a3e5eafdc1e597a3fe172e620bec
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 31 Jul 2014 09:00:57 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 13 Aug 2014 19:21:44 -0300

perf session: Add perf_session__peek_event()

Add a function to peek at other events in the event stream.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
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/1406786474-9306-15-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/session.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/session.h |  5 +++++
 2 files changed, 60 insertions(+)

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 7e27f1e..1b383bd 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -897,6 +897,61 @@ static void event_swap(union perf_event *event, bool sample_id_all)
 		swap(event, sample_id_all);
 }
 
+int perf_session__peek_event(struct perf_session *session, off_t file_offset,
+			     void *buf, size_t buf_sz,
+			     union perf_event **event_ptr,
+			     struct perf_sample *sample)
+{
+	union perf_event *event;
+	size_t hdr_sz, rest;
+	int fd;
+
+	if (session->one_mmap && !session->header.needs_swap) {
+		event = file_offset - session->one_mmap_offset +
+			session->one_mmap_addr;
+		goto out_parse_sample;
+	}
+
+	if (perf_data_file__is_pipe(session->file))
+		return -1;
+
+	fd = perf_data_file__fd(session->file);
+	hdr_sz = sizeof(struct perf_event_header);
+
+	if (buf_sz < hdr_sz)
+		return -1;
+
+	if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 ||
+	    readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz)
+		return -1;
+
+	event = (union perf_event *)buf;
+
+	if (session->header.needs_swap)
+		perf_event_header__bswap(&event->header);
+
+	if (event->header.size < hdr_sz)
+		return -1;
+
+	rest = event->header.size - hdr_sz;
+
+	if (readn(fd, &buf, rest) != (ssize_t)rest)
+		return -1;
+
+	if (session->header.needs_swap)
+		event_swap(event, perf_evlist__sample_id_all(session->evlist));
+
+out_parse_sample:
+
+	if (sample && event->header.type < PERF_RECORD_USER_TYPE_START &&
+	    perf_evlist__parse_sample(session->evlist, event, sample))
+		return -1;
+
+	*event_ptr = event;
+
+	return 0;
+}
+
 static s64 perf_session__process_event(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_tool *tool,
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 0630e65..8dd41ca 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -45,6 +45,11 @@ void perf_session__delete(struct perf_session *session);
 
 void perf_event_header__bswap(struct perf_event_header *hdr);
 
+int perf_session__peek_event(struct perf_session *session, off_t file_offset,
+			     void *buf, size_t buf_sz,
+			     union perf_event **event_ptr,
+			     struct perf_sample *sample);
+
 int __perf_session__process_events(struct perf_session *session,
 				   u64 data_offset, u64 data_size, u64 size,
 				   struct perf_tool *tool);

[tip:perf/core] perf script: Allow callchains if any event samples them

[tip-bot for Adrian Hunter]

Commit-ID:  98526ee7229be8537373aebe037b74cac112d84b
Gitweb:     http://git.kernel.org/tip/98526ee7229be8537373aebe037b74cac112d84b
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 31 Jul 2014 09:00:59 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 13 Aug 2014 19:21:53 -0300

perf script: Allow callchains if any event samples them

perf script was not displaying callchains if any selected event did not
have PERF_SAMPLE_CALLCHAIN.

Change this to disable callchains only if all selected events do not
have PERF_SAMPLE_CALLCHAIN.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
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/1406786474-9306-17-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 37d2b60..c1b7029 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -184,10 +184,6 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP",
 					    PERF_OUTPUT_IP))
 			return -EINVAL;
-
-		if (!no_callchain &&
-		    !(attr->sample_type & PERF_SAMPLE_CALLCHAIN))
-			symbol_conf.use_callchain = false;
 	}
 
 	if (PRINT_FIELD(ADDR) &&
@@ -290,6 +286,19 @@ static int perf_session__check_output_opt(struct perf_session *session)
 		set_print_ip_opts(&evsel->attr);
 	}
 
+	if (!no_callchain) {
+		bool use_callchain = false;
+
+		evlist__for_each(session->evlist, evsel) {
+			if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
+				use_callchain = true;
+				break;
+			}
+		}
+		if (!use_callchain)
+			symbol_conf.use_callchain = false;
+	}
+
 	/*
 	 * set default for tracepoints to print symbols only
 	 * if callchains are present

[tip:perf/core] perf script python: Add helpers for calling Python objects

[tip-bot for Adrian Hunter]

Commit-ID:  a5563edfa1bd25d052d81f5ad7fe74ba71c3d44e
Gitweb:     http://git.kernel.org/tip/a5563edfa1bd25d052d81f5ad7fe74ba71c3d44e
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 31 Jul 2014 09:01:01 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 13 Aug 2014 19:22:01 -0300

perf script python: Add helpers for calling Python objects

The Python script API repeatedly uses the same lines of code to get and
call objects.  Make that into helper functions instead.

A side-effect is that some reference counting bugs disappear because the
new call_object() function always decrements the reference count of
'retval'.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
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/1406786474-9306-19-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../util/scripting-engines/trace-event-python.c    | 114 +++++++++------------
 1 file changed, 47 insertions(+), 67 deletions(-)

diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cbce254..26e5f14 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -73,6 +73,35 @@ static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObj
 	Py_DECREF(val);
 }
 
+static PyObject *get_handler(const char *handler_name)
+{
+	PyObject *handler;
+
+	handler = PyDict_GetItemString(main_dict, handler_name);
+	if (handler && !PyCallable_Check(handler))
+		return NULL;
+	return handler;
+}
+
+static void call_object(PyObject *handler, PyObject *args, const char *die_msg)
+{
+	PyObject *retval;
+
+	retval = PyObject_CallObject(handler, args);
+	if (retval == NULL)
+		handler_call_die(die_msg);
+	Py_DECREF(retval);
+}
+
+static void try_call_object(const char *handler_name, PyObject *args)
+{
+	PyObject *handler;
+
+	handler = get_handler(handler_name);
+	if (handler)
+		call_object(handler, args, handler_name);
+}
+
 static void define_value(enum print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
@@ -80,7 +109,7 @@ static void define_value(enum print_arg_type field_type,
 			 const char *field_str)
 {
 	const char *handler_name = "define_flag_value";
-	PyObject *handler, *t, *retval;
+	PyObject *t;
 	unsigned long long value;
 	unsigned n = 0;
 
@@ -98,13 +127,7 @@ static void define_value(enum print_arg_type field_type,
 	PyTuple_SetItem(t, n++, PyInt_FromLong(value));
 	PyTuple_SetItem(t, n++, PyString_FromString(field_str));
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && PyCallable_Check(handler)) {
-		retval = PyObject_CallObject(handler, t);
-		if (retval == NULL)
-			handler_call_die(handler_name);
-		Py_DECREF(retval);
-	}
+	try_call_object(handler_name, t);
 
 	Py_DECREF(t);
 }
@@ -127,7 +150,7 @@ static void define_field(enum print_arg_type field_type,
 			 const char *delim)
 {
 	const char *handler_name = "define_flag_field";
-	PyObject *handler, *t, *retval;
+	PyObject *t;
 	unsigned n = 0;
 
 	if (field_type == PRINT_SYMBOL)
@@ -145,13 +168,7 @@ static void define_field(enum print_arg_type field_type,
 	if (field_type == PRINT_FLAGS)
 		PyTuple_SetItem(t, n++, PyString_FromString(delim));
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && PyCallable_Check(handler)) {
-		retval = PyObject_CallObject(handler, t);
-		if (retval == NULL)
-			handler_call_die(handler_name);
-		Py_DECREF(retval);
-	}
+	try_call_object(handler_name, t);
 
 	Py_DECREF(t);
 }
@@ -362,7 +379,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				      struct thread *thread,
 				      struct addr_location *al)
 {
-	PyObject *handler, *retval, *context, *t, *obj, *callchain;
+	PyObject *handler, *context, *t, *obj, *callchain;
 	PyObject *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
@@ -387,9 +404,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 
 	sprintf(handler_name, "%s__%s", event->system, event->name);
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && !PyCallable_Check(handler))
-		handler = NULL;
+	handler = get_handler(handler_name);
 	if (!handler) {
 		dict = PyDict_New();
 		if (!dict)
@@ -450,19 +465,9 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		Py_FatalError("error resizing Python tuple");
 
 	if (handler) {
-		retval = PyObject_CallObject(handler, t);
-		if (retval == NULL)
-			handler_call_die(handler_name);
-		Py_DECREF(retval);
+		call_object(handler, t, handler_name);
 	} else {
-		handler = PyDict_GetItemString(main_dict, "trace_unhandled");
-		if (handler && PyCallable_Check(handler)) {
-
-			retval = PyObject_CallObject(handler, t);
-			if (retval == NULL)
-				handler_call_die("trace_unhandled");
-			Py_DECREF(retval);
-		}
+		try_call_object("trace_unhandled", t);
 		Py_DECREF(dict);
 	}
 
@@ -474,7 +479,7 @@ static void python_process_general_event(struct perf_sample *sample,
 					 struct thread *thread,
 					 struct addr_location *al)
 {
-	PyObject *handler, *retval, *t, *dict, *callchain, *dict_sample;
+	PyObject *handler, *t, *dict, *callchain, *dict_sample;
 	static char handler_name[64];
 	unsigned n = 0;
 
@@ -496,8 +501,8 @@ static void python_process_general_event(struct perf_sample *sample,
 
 	snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (!handler || !PyCallable_Check(handler))
+	handler = get_handler(handler_name);
+	if (!handler)
 		goto exit;
 
 	pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
@@ -539,10 +544,7 @@ static void python_process_general_event(struct perf_sample *sample,
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
 
-	retval = PyObject_CallObject(handler, t);
-	if (retval == NULL)
-		handler_call_die(handler_name);
-	Py_DECREF(retval);
+	call_object(handler, t, handler_name);
 exit:
 	Py_DECREF(dict);
 	Py_DECREF(t);
@@ -566,36 +568,24 @@ static void python_process_event(union perf_event *event __maybe_unused,
 
 static int run_start_sub(void)
 {
-	PyObject *handler, *retval;
-	int err = 0;
-
 	main_module = PyImport_AddModule("__main__");
 	if (main_module == NULL)
 		return -1;
 	Py_INCREF(main_module);
 
 	main_dict = PyModule_GetDict(main_module);
-	if (main_dict == NULL) {
-		err = -1;
+	if (main_dict == NULL)
 		goto error;
-	}
 	Py_INCREF(main_dict);
 
-	handler = PyDict_GetItemString(main_dict, "trace_begin");
-	if (handler == NULL || !PyCallable_Check(handler))
-		goto out;
+	try_call_object("trace_begin", NULL);
 
-	retval = PyObject_CallObject(handler, NULL);
-	if (retval == NULL)
-		handler_call_die("trace_begin");
+	return 0;
 
-	Py_DECREF(retval);
-	return err;
 error:
 	Py_XDECREF(main_dict);
 	Py_XDECREF(main_module);
-out:
-	return err;
+	return -1;
 }
 
 /*
@@ -654,23 +644,13 @@ error:
  */
 static int python_stop_script(void)
 {
-	PyObject *handler, *retval;
-	int err = 0;
+	try_call_object("trace_end", NULL);
 
-	handler = PyDict_GetItemString(main_dict, "trace_end");
-	if (handler == NULL || !PyCallable_Check(handler))
-		goto out;
-
-	retval = PyObject_CallObject(handler, NULL);
-	if (retval == NULL)
-		handler_call_die("trace_end");
-	Py_DECREF(retval);
-out:
 	Py_XDECREF(main_dict);
 	Py_XDECREF(main_module);
 	Py_Finalize();
 
-	return err;
+	return 0;
 }
 
 static int python_generate_script(struct pevent *pevent, const char *outfile)

[tip:perf/core] perf tools: Identify which comms are from exec

[tip-bot for Adrian Hunter]

Commit-ID:  65de51f93ebf9305ec011da59c0b5fe29429d1b9
Gitweb:     http://git.kernel.org/tip/65de51f93ebf9305ec011da59c0b5fe29429d1b9
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 31 Jul 2014 09:00:44 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 13 Aug 2014 19:23:08 -0300

perf tools: Identify which comms are from exec

For grouping together all the data from a single execution, which is
needed for pairing calls and returns e.g. any outstanding calls when a
process exec's will never return.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
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/1406786474-9306-2-git-send-email-adrian.hunter@intel.com
[ Remove testing if comm->exec is false before setting it to true ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/comm.c    |  7 +++++--
 tools/perf/util/comm.h    |  6 ++++--
 tools/perf/util/machine.c |  4 +++-
 tools/perf/util/thread.c  | 24 +++++++++++++++++++-----
 tools/perf/util/thread.h  | 10 +++++++++-
 5 files changed, 40 insertions(+), 11 deletions(-)

diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index f9e7776..b2bb59d 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -74,7 +74,7 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
 	return new;
 }
 
-struct comm *comm__new(const char *str, u64 timestamp)
+struct comm *comm__new(const char *str, u64 timestamp, bool exec)
 {
 	struct comm *comm = zalloc(sizeof(*comm));
 
@@ -82,6 +82,7 @@ struct comm *comm__new(const char *str, u64 timestamp)
 		return NULL;
 
 	comm->start = timestamp;
+	comm->exec = exec;
 
 	comm->comm_str = comm_str__findnew(str, &comm_str_root);
 	if (!comm->comm_str) {
@@ -94,7 +95,7 @@ struct comm *comm__new(const char *str, u64 timestamp)
 	return comm;
 }
 
-int comm__override(struct comm *comm, const char *str, u64 timestamp)
+int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec)
 {
 	struct comm_str *new, *old = comm->comm_str;
 
@@ -106,6 +107,8 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp)
 	comm_str__put(old);
 	comm->comm_str = new;
 	comm->start = timestamp;
+	if (exec)
+		comm->exec = true;
 
 	return 0;
 }
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index fac5bd5..51c10ab 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -11,11 +11,13 @@ struct comm {
 	struct comm_str *comm_str;
 	u64 start;
 	struct list_head list;
+	bool exec;
 };
 
 void comm__free(struct comm *comm);
-struct comm *comm__new(const char *str, u64 timestamp);
+struct comm *comm__new(const char *str, u64 timestamp, bool exec);
 const char *comm__str(const struct comm *comm);
-int comm__override(struct comm *comm, const char *str, u64 timestamp);
+int comm__override(struct comm *comm, const char *str, u64 timestamp,
+		   bool exec);
 
 #endif  /* __PERF_COMM_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 16bba9f..ea3e09f 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -404,11 +404,13 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 	struct thread *thread = machine__findnew_thread(machine,
 							event->comm.pid,
 							event->comm.tid);
+	bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC;
 
 	if (dump_trace)
 		perf_event__fprintf_comm(event, stdout);
 
-	if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) {
+	if (thread == NULL ||
+	    __thread__set_comm(thread, event->comm.comm, sample->time, exec)) {
 		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
 		return -1;
 	}
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 12c7a25..a9df7f2 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -42,7 +42,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 			goto err_thread;
 
 		snprintf(comm_str, 32, ":%d", tid);
-		comm = comm__new(comm_str, 0);
+		comm = comm__new(comm_str, 0, false);
 		free(comm_str);
 		if (!comm)
 			goto err_thread;
@@ -81,19 +81,33 @@ struct comm *thread__comm(const struct thread *thread)
 	return list_first_entry(&thread->comm_list, struct comm, list);
 }
 
+struct comm *thread__exec_comm(const struct thread *thread)
+{
+	struct comm *comm, *last = NULL;
+
+	list_for_each_entry(comm, &thread->comm_list, list) {
+		if (comm->exec)
+			return comm;
+		last = comm;
+	}
+
+	return last;
+}
+
 /* CHECKME: time should always be 0 if event aren't ordered */
-int thread__set_comm(struct thread *thread, const char *str, u64 timestamp)
+int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
+		       bool exec)
 {
 	struct comm *new, *curr = thread__comm(thread);
 	int err;
 
 	/* Override latest entry if it had no specific time coverage */
-	if (!curr->start) {
-		err = comm__override(curr, str, timestamp);
+	if (!curr->start && !curr->exec) {
+		err = comm__override(curr, str, timestamp, exec);
 		if (err)
 			return err;
 	} else {
-		new = comm__new(str, timestamp);
+		new = comm__new(str, timestamp, exec);
 		if (!new)
 			return -ENOMEM;
 		list_add(&new->list, &thread->comm_list);
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 716b772..8c75fa7 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -38,9 +38,17 @@ static inline void thread__exited(struct thread *thread)
 	thread->dead = true;
 }
 
-int thread__set_comm(struct thread *thread, const char *comm, u64 timestamp);
+int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
+		       bool exec);
+static inline int thread__set_comm(struct thread *thread, const char *comm,
+				   u64 timestamp)
+{
+	return __thread__set_comm(thread, comm, timestamp, false);
+}
+
 int thread__comm_len(struct thread *thread);
 struct comm *thread__comm(const struct thread *thread);
+struct comm *thread__exec_comm(const struct thread *thread);
 const char *thread__comm_str(const struct thread *thread);
 void thread__insert_map(struct thread *thread, struct map *map);
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);

[tip:perf/core] perf machine: Add machine__thread_exec_comm()

[tip-bot for Adrian Hunter]

Commit-ID:  cfe1c41405fe9a559f8b3c24c904b2bb42d4a6e8
Gitweb:     http://git.kernel.org/tip/cfe1c41405fe9a559f8b3c24c904b2bb42d4a6e8
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 31 Jul 2014 09:00:45 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 13 Aug 2014 19:23:21 -0300

perf machine: Add machine__thread_exec_comm()

Add machine__thread_exec_comm() to return the comm that matches the last
exec, if the comm_exec flag is present, or the last comm otherwise.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
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/1406786474-9306-3-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c | 26 ++++++++++++++++++++++++++
 tools/perf/util/machine.h |  4 ++++
 tools/perf/util/session.c | 24 +++++++++++++++++++++++-
 3 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index ea3e09f..b093b93 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -31,6 +31,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->symbol_filter = NULL;
 	machine->id_hdr_size = 0;
+	machine->comm_exec = false;
 
 	machine->root_dir = strdup(root_dir);
 	if (machine->root_dir == NULL)
@@ -179,6 +180,19 @@ void machines__set_symbol_filter(struct machines *machines,
 	}
 }
 
+void machines__set_comm_exec(struct machines *machines, bool comm_exec)
+{
+	struct rb_node *nd;
+
+	machines->host.comm_exec = comm_exec;
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+		machine->comm_exec = comm_exec;
+	}
+}
+
 struct machine *machines__find(struct machines *machines, pid_t pid)
 {
 	struct rb_node **p = &machines->guests.rb_node;
@@ -398,6 +412,15 @@ struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 	return __machine__findnew_thread(machine, pid, tid, false);
 }
 
+struct comm *machine__thread_exec_comm(struct machine *machine,
+				       struct thread *thread)
+{
+	if (machine->comm_exec)
+		return thread__exec_comm(thread);
+	else
+		return thread__comm(thread);
+}
+
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample)
 {
@@ -406,6 +429,9 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 							event->comm.tid);
 	bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC;
 
+	if (exec)
+		machine->comm_exec = true;
+
 	if (dump_trace)
 		perf_event__fprintf_comm(event, stdout);
 
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index b972824..61216e0 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -26,6 +26,7 @@ struct machine {
 	struct rb_node	  rb_node;
 	pid_t		  pid;
 	u16		  id_hdr_size;
+	bool		  comm_exec;
 	char		  *root_dir;
 	struct rb_root	  threads;
 	struct list_head  dead_threads;
@@ -47,6 +48,8 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type)
 
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 				    pid_t tid);
+struct comm *machine__thread_exec_comm(struct machine *machine,
+				       struct thread *thread);
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
@@ -88,6 +91,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 
 void machines__set_symbol_filter(struct machines *machines,
 				 symbol_filter_t symbol_filter);
+void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 
 struct machine *machine__new_host(void);
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 1b383bd..6d2d50d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -67,6 +67,25 @@ static void perf_session__destroy_kernel_maps(struct perf_session *session)
 	machines__destroy_kernel_maps(&session->machines);
 }
 
+static bool perf_session__has_comm_exec(struct perf_session *session)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(session->evlist, evsel) {
+		if (evsel->attr.comm_exec)
+			return true;
+	}
+
+	return false;
+}
+
+static void perf_session__set_comm_exec(struct perf_session *session)
+{
+	bool comm_exec = perf_session__has_comm_exec(session);
+
+	machines__set_comm_exec(&session->machines, comm_exec);
+}
+
 struct perf_session *perf_session__new(struct perf_data_file *file,
 				       bool repipe, struct perf_tool *tool)
 {
@@ -90,6 +109,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 				goto out_close;
 
 			perf_session__set_id_hdr_size(session);
+			perf_session__set_comm_exec(session);
 		}
 	}
 
@@ -866,8 +886,10 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	switch (event->header.type) {
 	case PERF_RECORD_HEADER_ATTR:
 		err = tool->attr(tool, event, &session->evlist);
-		if (err == 0)
+		if (err == 0) {
 			perf_session__set_id_hdr_size(session);
+			perf_session__set_comm_exec(session);
+		}
 		return err;
 	case PERF_RECORD_HEADER_EVENT_TYPE:
 		/*

[tip:perf/core] perf tools: Add flags and insn_len to struct sample

[tip-bot for Adrian Hunter]

Commit-ID:  bf4939027decde7aaaf8b5dbeee70126d2822eb6
Gitweb:     http://git.kernel.org/tip/bf4939027decde7aaaf8b5dbeee70126d2822eb6
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 31 Jul 2014 09:01:04 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 13 Aug 2014 19:23:32 -0300

perf tools: Add flags and insn_len to struct sample

The flags will be used to export branch type and transaction status.

insn_len is preparation for pairing calls and returns because the return
address equals the call address plus the instruction length (insn_len).

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
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/1406786474-9306-22-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/event.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 94d6976..7eb7107 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -156,6 +156,8 @@ struct perf_sample {
 	u32 cpu;
 	u32 raw_size;
 	u64 data_src;
+	u32 flags;
+	u16 insn_len;
 	void *raw_data;
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;

[tip:perf/core] perf evlist: Add perf_evlist__enable_event_idx()

[tip-bot for Adrian Hunter]

Commit-ID:  1c65056c547141a0cb52fb8e6056f63524d2bbf2
Gitweb:     http://git.kernel.org/tip/1c65056c547141a0cb52fb8e6056f63524d2bbf2
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 31 Jul 2014 09:00:56 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 13 Aug 2014 19:23:48 -0300

perf evlist: Add perf_evlist__enable_event_idx()

Add a function to enable a specific event within a specific perf event
buffer.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
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/1406786474-9306-14-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/evlist.h |  2 ++
 2 files changed, 49 insertions(+)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 9d863db..5dcd28c 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -355,6 +355,53 @@ int perf_evlist__enable_event(struct perf_evlist *evlist,
 	return 0;
 }
 
+static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist,
+					 struct perf_evsel *evsel, int cpu)
+{
+	int thread, err;
+	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
+
+	if (!evsel->fd)
+		return -EINVAL;
+
+	for (thread = 0; thread < nr_threads; thread++) {
+		err = ioctl(FD(evsel, cpu, thread),
+			    PERF_EVENT_IOC_ENABLE, 0);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int perf_evlist__enable_event_thread(struct perf_evlist *evlist,
+					    struct perf_evsel *evsel,
+					    int thread)
+{
+	int cpu, err;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+
+	if (!evsel->fd)
+		return -EINVAL;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
+				  struct perf_evsel *evsel, int idx)
+{
+	bool per_cpu_mmaps = !cpu_map__empty(evlist->cpus);
+
+	if (per_cpu_mmaps)
+		return perf_evlist__enable_event_cpu(evlist, evsel, idx);
+	else
+		return perf_evlist__enable_event_thread(evlist, evsel, idx);
+}
+
 static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
 	int nr_cpus = cpu_map__nr(evlist->cpus);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index e0084f9..106de53 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -122,6 +122,8 @@ int perf_evlist__disable_event(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
 int perf_evlist__enable_event(struct perf_evlist *evlist,
 			      struct perf_evsel *evsel);
+int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
+				  struct perf_evsel *evsel, int idx);
 
 void perf_evlist__set_selected(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);

[tip:perf/core] perf tools: Add perf-with-kcore script

[tip-bot for Adrian Hunter]

Commit-ID:  c501e90b4700e4f247ccdcf5ae81f9846a2ef5f9
Gitweb:     http://git.kernel.org/tip/c501e90b4700e4f247ccdcf5ae81f9846a2ef5f9
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 31 Jul 2014 09:01:12 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 17 Sep 2014 17:08:08 -0300

perf tools: Add perf-with-kcore script

Decoding an Intel PT trace of the kernel requires an accurate kernel
object image.  This is provided by making a copy of kcore.  However the
copy needs to be made under the same conditions as the original
recording, and then it needs to be associated with the perf.data file.
The perf-with-kcore script does that.

The script also checks the permissions on the buildid cache and can be
used to fix them.  That is needed for distributions where root does not
have a home directory and consequently writes to the same buildid cache
as the user, resulting in cached files that the user does not have
access to.

Example:

$ ./perf-with-kcore
Usage: perf-with-kcore <perf sub-command> <perf.data directory> [<sub-command options> [ -- <workload>]]
       <perf sub-command> can be record, script, report or inject
   or: perf-with-kcore fix_buildid_cache_permissions
$ ./perf-with-kcore record pt_uname -e intel_pt// -- uname
Recording
Using /home/ahunter/bin/perf
perf version 3.15.rc3.g4549ba
/home/ahunter/bin/perf record -o pt_uname/perf.data -e intel_pt//  -- uname
Linux
[ perf record: Woken up 3 times to write data ]
[ perf record: Captured and wrote 0.023 MB pt_uname/perf.data ]
Copying kcore
[sudo] password for ahunter:
Done
$ tools/perf/perf-with-kcore.sh script pt_uname | head
Using /home/ahunter/bin/perf
perf version 3.15.rc3.g4549ba
/home/ahunter/bin/perf script -i pt_uname/perf.data --kallsyms=pt_uname/kcore_dir/kallsyms
         swapper     0 [002] 161533.969666: sched:sched_switch: swapper/2:0 [120] R ==> perf:11316 [120]
          :11315 11315 [003] 161533.969704: sched:sched_switch: perf:11315 [120] S ==> swapper/3:0 [120]
          :11316 11316 [002] 161533.969783: sched:sched_switch: perf:11316 [120] R ==> migration/2:33 [0]
             :33    33 [002] 161533.969791: sched:sched_switch: migration/2:33 [0] S ==> swapper/2:0 [120]
         swapper     0 [003] 161533.969792: sched:sched_switch: swapper/3:0 [120] R ==> perf:11316 [120]
          :11316 11316 [003] 161533.970062: branches:                 0 [unknown] ([unknown]) => ffffffff810532fa native_write_msr_safe ([kernel.kallsyms])
          :11316 11316 [003] 161533.970062: branches:  ffffffff810532fd native_write_msr_safe ([kernel.kallsyms]) => ffffffff81035b31 pt_config_start ([kernel.kallsyms])

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
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/1406786474-9306-30-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/.gitignore         |   1 +
 tools/perf/Makefile.perf      |   5 +-
 tools/perf/perf-with-kcore.sh | 259 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 264 insertions(+), 1 deletion(-)

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 782d86e..717221e 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -15,6 +15,7 @@ perf.data
 perf.data.old
 output.svg
 perf-archive
+perf-with-kcore
 tags
 TAGS
 cscope*
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 95e832b..171f4e6 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -126,6 +126,7 @@ PYRF_OBJS =
 SCRIPT_SH =
 
 SCRIPT_SH += perf-archive.sh
+SCRIPT_SH += perf-with-kcore.sh
 
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
@@ -878,6 +879,8 @@ install-bin: all install-gtk
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(call QUIET_INSTALL, perf-archive) \
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+	$(call QUIET_INSTALL, perf-with-kcore) \
+		$(INSTALL) $(OUTPUT)perf-with-kcore -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifndef NO_LIBPERL
 	$(call QUIET_INSTALL, perl-scripts) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
@@ -923,7 +926,7 @@ config-clean:
 	@$(MAKE) -C config/feature-checks clean >/dev/null
 
 clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
-	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
+	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
diff --git a/tools/perf/perf-with-kcore.sh b/tools/perf/perf-with-kcore.sh
new file mode 100644
index 0000000..c7ff90a
--- /dev/null
+++ b/tools/perf/perf-with-kcore.sh
@@ -0,0 +1,259 @@
+#!/bin/bash
+# perf-with-kcore: use perf with a copy of kcore
+# Copyright (c) 2014, Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+# more details.
+
+set -e
+
+usage()
+{
+        echo "Usage: perf-with-kcore <perf sub-command> <perf.data directory> [<sub-command options> [ -- <workload>]]" >&2
+        echo "       <perf sub-command> can be record, script, report or inject" >&2
+        echo "   or: perf-with-kcore fix_buildid_cache_permissions" >&2
+        exit 1
+}
+
+find_perf()
+{
+	if [ -n "$PERF" ] ; then
+		return
+	fi
+	PERF=`which perf || true`
+	if [ -z "$PERF" ] ; then
+		echo "Failed to find perf" >&2
+	        exit 1
+	fi
+	if [ ! -x "$PERF" ] ; then
+		echo "Failed to find perf" >&2
+	        exit 1
+	fi
+	echo "Using $PERF"
+	"$PERF" version
+}
+
+copy_kcore()
+{
+	echo "Copying kcore"
+
+	if [ $EUID -eq 0 ] ; then
+		SUDO=""
+	else
+		SUDO="sudo"
+	fi
+
+	rm -f perf.data.junk
+	("$PERF" record -o perf.data.junk $PERF_OPTIONS -- sleep 60) >/dev/null 2>/dev/null &
+	PERF_PID=$!
+
+	# Need to make sure that perf has started
+	sleep 1
+
+	KCORE=$(($SUDO "$PERF" buildid-cache -v -f -k /proc/kcore >/dev/null) 2>&1)
+	case "$KCORE" in
+	"kcore added to build-id cache directory "*)
+		KCORE_DIR=${KCORE#"kcore added to build-id cache directory "}
+	;;
+	*)
+		kill $PERF_PID
+		wait >/dev/null 2>/dev/null || true
+		rm perf.data.junk
+		echo "$KCORE"
+		echo "Failed to find kcore" >&2
+		exit 1
+	;;
+	esac
+
+	kill $PERF_PID
+	wait >/dev/null 2>/dev/null || true
+	rm perf.data.junk
+
+	$SUDO cp -a "$KCORE_DIR" "$(pwd)/$PERF_DATA_DIR"
+	$SUDO rm -f "$KCORE_DIR/kcore"
+	$SUDO rm -f "$KCORE_DIR/kallsyms"
+	$SUDO rm -f "$KCORE_DIR/modules"
+	$SUDO rmdir "$KCORE_DIR"
+
+	KCORE_DIR_BASENAME=$(basename "$KCORE_DIR")
+	KCORE_DIR="$(pwd)/$PERF_DATA_DIR/$KCORE_DIR_BASENAME"
+
+	$SUDO chown $UID "$KCORE_DIR"
+	$SUDO chown $UID "$KCORE_DIR/kcore"
+	$SUDO chown $UID "$KCORE_DIR/kallsyms"
+	$SUDO chown $UID "$KCORE_DIR/modules"
+
+	$SUDO chgrp $GROUPS "$KCORE_DIR"
+	$SUDO chgrp $GROUPS "$KCORE_DIR/kcore"
+	$SUDO chgrp $GROUPS "$KCORE_DIR/kallsyms"
+	$SUDO chgrp $GROUPS "$KCORE_DIR/modules"
+
+	ln -s "$KCORE_DIR_BASENAME" "$PERF_DATA_DIR/kcore_dir"
+}
+
+fix_buildid_cache_permissions()
+{
+	if [ $EUID -ne 0 ] ; then
+		echo "This script must be run as root via sudo " >&2
+		exit 1
+	fi
+
+	if [ -z "$SUDO_USER" ] ; then
+		echo "This script must be run via sudo" >&2
+		exit 1
+	fi
+
+	USER_HOME=$(bash <<< "echo ~$SUDO_USER")
+
+	if [ "$HOME" != "$USER_HOME" ] ; then
+		echo "Fix unnecessary because root has a home: $HOME" >&2
+		exit 1
+	fi
+
+	echo "Fixing buildid cache permissions"
+
+	find "$USER_HOME/.debug" -xdev -type d          ! -user "$SUDO_USER" -ls -exec chown    "$SUDO_USER" \{\} \;
+	find "$USER_HOME/.debug" -xdev -type f -links 1 ! -user "$SUDO_USER" -ls -exec chown    "$SUDO_USER" \{\} \;
+	find "$USER_HOME/.debug" -xdev -type l          ! -user "$SUDO_USER" -ls -exec chown -h "$SUDO_USER" \{\} \;
+
+	if [ -n "$SUDO_GID" ] ; then
+		find "$USER_HOME/.debug" -xdev -type d          ! -group "$SUDO_GID" -ls -exec chgrp    "$SUDO_GID" \{\} \;
+		find "$USER_HOME/.debug" -xdev -type f -links 1 ! -group "$SUDO_GID" -ls -exec chgrp    "$SUDO_GID" \{\} \;
+		find "$USER_HOME/.debug" -xdev -type l          ! -group "$SUDO_GID" -ls -exec chgrp -h "$SUDO_GID" \{\} \;
+	fi
+
+	echo "Done"
+}
+
+check_buildid_cache_permissions()
+{
+	if [ $EUID -eq 0 ] ; then
+		return
+	fi
+
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d          ! -user "$USER" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -user "$USER" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l          ! -user "$USER" -print -quit)
+
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d          ! -group "$GROUPS" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -group "$GROUPS" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l          ! -group "$GROUPS" -print -quit)
+
+	if [ -n "$PERMISSIONS_OK" ] ; then
+		echo "*** WARNING *** buildid cache permissions may need fixing" >&2
+	fi
+}
+
+record()
+{
+	echo "Recording"
+
+	if [ $EUID -ne 0 ] ; then
+
+		if [ "$(cat /proc/sys/kernel/kptr_restrict)" -ne 0 ] ; then
+			echo "*** WARNING *** /proc/sys/kernel/kptr_restrict prevents access to kernel addresses" >&2
+		fi
+
+		if echo "$PERF_OPTIONS" | grep -q ' -a \|^-a \| -a$\|^-a$\| --all-cpus \|^--all-cpus \| --all-cpus$\|^--all-cpus$' ; then
+			echo "*** WARNING *** system-wide tracing without root access will not be able to read all necessary information from /proc" >&2
+		fi
+
+		if echo "$PERF_OPTIONS" | grep -q 'intel_pt\|intel_bts\| -I\|^-I' ; then
+			if [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt -1 ] ; then
+				echo "*** WARNING *** /proc/sys/kernel/perf_event_paranoid restricts buffer size and tracepoint (sched_switch) use" >&2
+			fi
+
+			if echo "$PERF_OPTIONS" | grep -q ' --per-thread \|^--per-thread \| --per-thread$\|^--per-thread$' ; then
+				true
+			elif echo "$PERF_OPTIONS" | grep -q ' -t \|^-t \| -t$\|^-t$' ; then
+				true
+			elif [ ! -r /sys/kernel/debug -o ! -x /sys/kernel/debug ] ; then
+				echo "*** WARNING *** /sys/kernel/debug permissions prevent tracepoint (sched_switch) use" >&2
+			fi
+		fi
+	fi
+
+	if [ -z "$1" ] ; then
+		echo "Workload is required for recording" >&2
+		usage
+	fi
+
+	if [ -e "$PERF_DATA_DIR" ] ; then
+		echo "'$PERF_DATA_DIR' exists" >&2
+		exit 1
+	fi
+
+	find_perf
+
+	mkdir "$PERF_DATA_DIR"
+
+	echo "$PERF record -o $PERF_DATA_DIR/perf.data $PERF_OPTIONS -- $*"
+	"$PERF" record -o "$PERF_DATA_DIR/perf.data" $PERF_OPTIONS -- $* || true
+
+	if rmdir "$PERF_DATA_DIR" > /dev/null 2>/dev/null ; then
+		exit 1
+	fi
+
+	copy_kcore
+
+	echo "Done"
+}
+
+subcommand()
+{
+	find_perf
+	check_buildid_cache_permissions
+	echo "$PERF $PERF_SUB_COMMAND -i $PERF_DATA_DIR/perf.data --kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms $*"
+	"$PERF" $PERF_SUB_COMMAND -i "$PERF_DATA_DIR/perf.data" "--kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms" $*
+}
+
+if [ "$1" = "fix_buildid_cache_permissions" ] ; then
+	fix_buildid_cache_permissions
+	exit 0
+fi
+
+PERF_SUB_COMMAND=$1
+PERF_DATA_DIR=$2
+shift || true
+shift || true
+
+if [ -z "$PERF_SUB_COMMAND" ] ; then
+	usage
+fi
+
+if [ -z "$PERF_DATA_DIR" ] ; then
+	usage
+fi
+
+case "$PERF_SUB_COMMAND" in
+"record")
+	while [ "$1" != "--" ] ; do
+		PERF_OPTIONS+="$1 "
+		shift || break
+	done
+	if [ "$1" != "--" ] ; then
+		echo "Options and workload are required for recording" >&2
+		usage
+	fi
+	shift
+	record $*
+;;
+"script")
+	subcommand $*
+;;
+"report")
+	subcommand $*
+;;
+"inject")
+	subcommand $*
+;;
+*)
+	usage
+;;
+esac

[tip:perf/core] perf tools: Let default config be defined for a PMU

[tip-bot for Adrian Hunter]

Commit-ID:  dc0a6202421170a6d8d2c6f5176575b3f60e0f85
Gitweb:     http://git.kernel.org/tip/dc0a6202421170a6d8d2c6f5176575b3f60e0f85
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 31 Jul 2014 09:00:49 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 17 Sep 2014 17:08:08 -0300

perf tools: Let default config be defined for a PMU

This allows default config terms to be provided for a PMU. So, for
example, when the Intel PT PMU is added, it will be possible to specify:

	intel_pt//

which will be the same as:

	intel_pt/tsc=1,noretcomp=0/

meaning that the trace should contain TSC timestamps and perform 'return
compression'.

An important consideration of this patch is that it must be possible to
overwrite the default values.  That has meant changing the logic so that
a zero value can replace a non-zero value.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
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/1406786474-9306-7-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/pmu.c         |  2 +-
 tools/perf/util/parse-events.c |  7 ++++++-
 tools/perf/util/pmu.c          | 42 ++++++++++++++++++++++++++----------------
 tools/perf/util/pmu.h          |  9 ++++++++-
 4 files changed, 41 insertions(+), 19 deletions(-)

diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 12b322f..eeb68bb1 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -152,7 +152,7 @@ int test__pmu(void)
 		if (ret)
 			break;
 
-		ret = perf_pmu__config_terms(&formats, &attr, terms);
+		ret = perf_pmu__config_terms(&formats, &attr, terms, false);
 		if (ret)
 			break;
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index e756288..61be3e6 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -643,7 +643,12 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 	if (!pmu)
 		return -EINVAL;
 
-	memset(&attr, 0, sizeof(attr));
+	if (pmu->default_config) {
+		memcpy(&attr, pmu->default_config,
+		       sizeof(struct perf_event_attr));
+	} else {
+		memset(&attr, 0, sizeof(attr));
+	}
 
 	if (!head_config) {
 		attr.type = pmu->type;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 9bf5827..438bb26 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -2,6 +2,7 @@
 #include <sys/types.h>
 #include <unistd.h>
 #include <stdio.h>
+#include <stdbool.h>
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
@@ -387,6 +388,12 @@ static struct cpu_map *pmu_cpumask(const char *name)
 	return cpus;
 }
 
+struct perf_event_attr *__attribute__((weak))
+perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+{
+	return NULL;
+}
+
 static struct perf_pmu *pmu_lookup(const char *name)
 {
 	struct perf_pmu *pmu;
@@ -421,6 +428,9 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	pmu->name = strdup(name);
 	pmu->type = type;
 	list_add_tail(&pmu->list, &pmus);
+
+	pmu->default_config = perf_pmu__get_default_config(pmu);
+
 	return pmu;
 }
 
@@ -479,28 +489,24 @@ pmu_find_format(struct list_head *formats, char *name)
 }
 
 /*
- * Returns value based on the format definition (format parameter)
+ * Sets value based on the format definition (format parameter)
  * and unformated value (value parameter).
- *
- * TODO maybe optimize a little ;)
  */
-static __u64 pmu_format_value(unsigned long *format, __u64 value)
+static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
+			     bool zero)
 {
 	unsigned long fbit, vbit;
-	__u64 v = 0;
 
 	for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) {
 
 		if (!test_bit(fbit, format))
 			continue;
 
-		if (!(value & (1llu << vbit++)))
-			continue;
-
-		v |= (1llu << fbit);
+		if (value & (1llu << vbit++))
+			*v |= (1llu << fbit);
+		else if (zero)
+			*v &= ~(1llu << fbit);
 	}
-
-	return v;
 }
 
 /*
@@ -509,7 +515,8 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value)
  */
 static int pmu_config_term(struct list_head *formats,
 			   struct perf_event_attr *attr,
-			   struct parse_events_term *term)
+			   struct parse_events_term *term,
+			   bool zero)
 {
 	struct perf_pmu_format *format;
 	__u64 *vp;
@@ -548,18 +555,19 @@ static int pmu_config_term(struct list_head *formats,
 	 * non-hardcoded terms, here's the place to translate
 	 * them into value.
 	 */
-	*vp |= pmu_format_value(format->bits, term->val.num);
+	pmu_format_value(format->bits, term->val.num, vp, zero);
 	return 0;
 }
 
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
-			   struct list_head *head_terms)
+			   struct list_head *head_terms,
+			   bool zero)
 {
 	struct parse_events_term *term;
 
 	list_for_each_entry(term, head_terms, list)
-		if (pmu_config_term(formats, attr, term))
+		if (pmu_config_term(formats, attr, term, zero))
 			return -EINVAL;
 
 	return 0;
@@ -573,8 +581,10 @@ int perf_pmu__config_terms(struct list_head *formats,
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms)
 {
+	bool zero = !!pmu->default_config;
+
 	attr->type = pmu->type;
-	return perf_pmu__config_terms(&pmu->format, attr, head_terms);
+	return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero);
 }
 
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 1c1e2ee..413b9a6 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -13,9 +13,12 @@ enum {
 
 #define PERF_PMU_FORMAT_BITS 64
 
+struct perf_event_attr;
+
 struct perf_pmu {
 	char *name;
 	__u32 type;
+	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
 	struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */
@@ -27,7 +30,8 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms);
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
-			   struct list_head *head_terms);
+			   struct list_head *head_terms,
+			   bool zero);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 			  const char **unit, double *scale);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
@@ -46,4 +50,7 @@ void print_pmu_events(const char *event_glob, bool name_only);
 bool pmu_have_event(const char *pname, const char *name);
 
 int perf_pmu__test(void);
+
+struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
+
 #endif /* __PMU_H */

[tip:perf/core] perf tools: Add perf_pmu__scan_file()

[tip-bot for Adrian Hunter]

Commit-ID:  7d4bdab5a441772bfc757d7f9eea9465ec5de0ec
Gitweb:     http://git.kernel.org/tip/7d4bdab5a441772bfc757d7f9eea9465ec5de0ec
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 31 Jul 2014 09:00:50 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 17 Sep 2014 17:08:09 -0300

perf tools: Add perf_pmu__scan_file()

Add a function to scan a sysfs file within the pmu device directory.

This will be used to read capability values from the PMU 'caps'
subdirectory.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
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/1406786474-9306-8-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.c | 37 +++++++++++++++++++++++++++++++++++++
 tools/perf/util/pmu.h |  3 +++
 2 files changed, 40 insertions(+)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 438bb26..22a4ad5 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -3,6 +3,7 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <stdbool.h>
+#include <stdarg.h>
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
@@ -804,3 +805,39 @@ bool pmu_have_event(const char *pname, const char *name)
 	}
 	return false;
 }
+
+static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs;
+
+	sysfs = sysfs__mountpoint();
+	if (!sysfs)
+		return NULL;
+
+	snprintf(path, PATH_MAX,
+		 "%s" EVENT_SOURCE_DEVICE_PATH "%s/%s", sysfs, pmu->name, name);
+
+	if (stat(path, &st) < 0)
+		return NULL;
+
+	return fopen(path, "r");
+}
+
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+			...)
+{
+	va_list args;
+	FILE *file;
+	int ret = EOF;
+
+	va_start(args, fmt);
+	file = perf_pmu__open_file(pmu, name);
+	if (file) {
+		ret = vfscanf(file, fmt, args);
+		fclose(file);
+	}
+	va_end(args);
+	return ret;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 413b9a6..0f5c0a8 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -49,6 +49,9 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 void print_pmu_events(const char *event_glob, bool name_only);
 bool pmu_have_event(const char *pname, const char *name);
 
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+			...) __attribute__((format(scanf, 3, 4)));
+
 int perf_pmu__test(void);
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);