[PATCH v6 00/16] perf tools: BPF related update and other improvements

[PATCH v6 00/16] perf tools: BPF related update and other improvements

[Wang Nan]

 - Use WARN_ONCE in patch 06/16 'perf tools: Prevent calling machine__delete() on
   non-allocated machine' and add machine__exit() back.

 - Introduce perf_evsel__is_bpf_output() in 15/16 and use it in 16/16.

 - Resend PowerPC building breakage fix.

He Kuang (1):
  perf tools: Support perf event alias name

Naveen N. Rao (1):
  perf: bpf: Fix build breakage due to libbpf

Wang Nan (14):
  perf tools: Fix PowerPC native building
  tools: Move Makefile.arch from perf/config to tools/scripts
  perf test: Fix false TEST_OK result for 'perf test hist'
  perf test: Reset err after using it hold errcode in hist testcases
  perf tools: Prevent calling machine__delete() on non-allocated machine
  perf test: Check environment before start real BPF test
  perf tools: Add API to config maps in bpf object
  perf tools: Enable BPF object configure syntax
  perf record: Apply config to BPF objects before recording
  perf tools: Enable passing event to BPF object
  perf tools: Support setting different slots in a BPF map separately
  perf tools: Enable indices setting syntax for BPF maps
  perf tools: Introduce bpf-output event
  perf data: Support converting data from bpf_perf_event_output()

 tools/build/feature/test-bpf.c               |  20 +-
 tools/lib/bpf/Makefile                       |   9 +-
 tools/lib/bpf/bpf.c                          |   4 +-
 tools/perf/builtin-record.c                  |  11 +
 tools/perf/config/Makefile                   |   2 +-
 tools/perf/tests/bpf.c                       |  37 ++
 tools/perf/tests/hists_common.c              |   5 -
 tools/perf/tests/hists_cumulate.c            |   1 +
 tools/perf/tests/hists_filter.c              |   1 +
 tools/perf/tests/hists_link.c                |   1 +
 tools/perf/tests/hists_output.c              |   1 +
 tools/perf/tests/make                        |   2 +-
 tools/perf/tests/vmlinux-kallsyms.c          |   4 +-
 tools/perf/util/bpf-loader.c                 | 699 +++++++++++++++++++++++++++
 tools/perf/util/bpf-loader.h                 |  59 +++
 tools/perf/util/data-convert-bt.c            | 112 ++++-
 tools/perf/util/evlist.c                     |  16 +
 tools/perf/util/evlist.h                     |   3 +
 tools/perf/util/evsel.c                      |   6 +
 tools/perf/util/evsel.h                      |   9 +
 tools/perf/util/machine.c                    |  13 +-
 tools/perf/util/machine.h                    |   3 +-
 tools/perf/util/parse-events.c               | 125 ++++-
 tools/perf/util/parse-events.h               |  20 +-
 tools/perf/util/parse-events.l               |  16 +-
 tools/perf/util/parse-events.y               | 123 ++++-
 tools/{perf/config => scripts}/Makefile.arch |   0
 27 files changed, 1267 insertions(+), 35 deletions(-)
 rename tools/{perf/config => scripts}/Makefile.arch (100%)

-- 
1.8.3.4

[PATCH v6 01/16] perf tools: Fix PowerPC native building

[Wang Nan]

Checks BPF syscall number, turn off libbpf building on platform doesn't
correctly support sys_bpf instead of blocking compiling.

Reported-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 tools/build/feature/test-bpf.c | 20 +++++++++++++++++++-
 tools/lib/bpf/bpf.c            |  4 ++--
 2 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c
index 062bac8..b389026 100644
--- a/tools/build/feature/test-bpf.c
+++ b/tools/build/feature/test-bpf.c
@@ -1,9 +1,23 @@
+#include <asm/unistd.h>
 #include <linux/bpf.h>
+#include <unistd.h>
+
+#ifndef __NR_bpf
+# if defined(__i386__)
+#  define __NR_bpf 357
+# elif defined(__x86_64__)
+#  define __NR_bpf 321
+# elif defined(__aarch64__)
+#  define __NR_bpf 280
+#  error __NR_bpf not defined. libbpf does not support your arch.
+# endif
+#endif
 
 int main(void)
 {
 	union bpf_attr attr;
 
+	/* Check fields in attr */
 	attr.prog_type = BPF_PROG_TYPE_KPROBE;
 	attr.insn_cnt = 0;
 	attr.insns = 0;
@@ -14,5 +28,9 @@ int main(void)
 	attr.kern_version = 0;
 
 	attr = attr;
-	return 0;
+	/*
+	 * Test existence of __NR_bpf and BPF_PROG_LOAD.
+	 * This call should fail if we run the testcase.
+	 */
+	return syscall(__NR_bpf, BPF_PROG_LOAD, attr, sizeof(attr));
 }
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 5bdc6ea..1f91cc9 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -14,8 +14,8 @@
 #include "bpf.h"
 
 /*
- * When building perf, unistd.h is override. Define __NR_bpf is
- * required to be defined.
+ * When building perf, unistd.h is overrided. __NR_bpf is
+ * required to be defined explicitly.
  */
 #ifndef __NR_bpf
 # if defined(__i386__)
-- 
1.8.3.4

[PATCH v6 02/16] tools: Move Makefile.arch from perf/config to tools/scripts

[Wang Nan]

After this patch other directories can use this architecture detector
without directly including it from perf's directory. Libbpf would
utilize it to get proper $(ARCH) so it can receive correct uapi include
directory.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 tools/perf/config/Makefile                   | 2 +-
 tools/perf/tests/make                        | 2 +-
 tools/{perf/config => scripts}/Makefile.arch | 0
 3 files changed, 2 insertions(+), 2 deletions(-)
 rename tools/{perf/config => scripts}/Makefile.arch (100%)

diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index a552417..34717e4 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -17,7 +17,7 @@ detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected)
 
 CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
 
-include $(src-perf)/config/Makefile.arch
+include $(srctree)/tools/scripts/Makefile.arch
 
 $(call detected_var,ARCH)
 
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index c1fbb8e..a8ede37 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -12,7 +12,7 @@ endif
 else
 PERF := .
 
-include config/Makefile.arch
+include $(srctree)/scripts/Makefile.arch
 
 # FIXME looks like x86 is the only arch running tests ;-)
 # we need some IS_(32/64) flag to make this generic
diff --git a/tools/perf/config/Makefile.arch b/tools/scripts/Makefile.arch
similarity index 100%
rename from tools/perf/config/Makefile.arch
rename to tools/scripts/Makefile.arch
-- 
1.8.3.4

[PATCH v6 03/16] perf: bpf: Fix build breakage due to libbpf

[Wang Nan]

From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>

perf build is currently (v4.4-rc5) broken on powerpc:

bpf.c:28:4: error: #error __NR_bpf not defined. libbpf does not support
your arch.
 #  error __NR_bpf not defined. libbpf does not support your arch.
    ^

Fix this by including tools/scripts/Makefile.arch for the proper
$ARCH macro. While at it, remove redundant LP64 macro definition.

Also, since libbpf require $(srctree) now, detect the path of
srctree like perf.

Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Wang Nan <wangnan0@huawei.com>
[Use tools/scripts/Makefile.arch]
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 tools/lib/bpf/Makefile | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 636e3dd..0b6e013 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -6,6 +6,12 @@ BPF_EXTRAVERSION = 1
 
 MAKEFLAGS += --no-print-directory
 
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
 
 # Makefiles suck: This macro sets a default value of $(2) for the
 # variable named by $(1), unless the variable has been set by
@@ -31,7 +37,8 @@ INSTALL = install
 DESTDIR ?=
 DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
 
-LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+include $(srctree)/tools/scripts/Makefile.arch
+
 ifeq ($(LP64), 1)
   libdir_relative = lib64
 else
-- 
1.8.3.4

[PATCH v6 04/16] perf test: Fix false TEST_OK result for 'perf test hist'

[Wang Nan]

Commit 71d6de64feddd4b455555326fba2111b3006d9e0 ('perf test: Fix hist
testcases when kptr_restrict is on') solves a double free problem when
'perf test hist' calling setup_fake_machine(). However, the result is
still incorrect. For example:

 $ ./perf test -v 'filtering hist entries'
 25: Test filtering hist entries                              :
 --- start ---
 test child forked, pid 4186
 Cannot create kernel maps
 test child finished with 0
 ---- end ----
 Test filtering hist entries: Ok

In this case the body of this test is not get executed at all, but the
result is 'Ok'.

Actually, in setup_fake_machine() there's no need to create real kernel
maps. What we want is the fake maps. This patch removes the
machine__create_kernel_maps() in setup_fake_machine(), so it won't be
affected by kptr_restrict setting.

Test result:

 $ cat /proc/sys/kernel/kptr_restrict
 1
 $ ~/perf test -v hist
 15: Test matching and linking multiple hists                 :
 --- start ---
 test child forked, pid 24031
 test child finished with 0
 ---- end ----
 Test matching and linking multiple hists: Ok
 [SNIP]

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Suggested-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
---
 tools/perf/tests/hists_common.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index bcfd081..071a8b5 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -87,11 +87,6 @@ struct machine *setup_fake_machine(struct machines *machines)
 		return NULL;
 	}
 
-	if (machine__create_kernel_maps(machine)) {
-		pr_debug("Cannot create kernel maps\n");
-		return NULL;
-	}
-
 	for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
 		struct thread *thread;
 
-- 
1.8.3.4

[PATCH v6 05/16] perf test: Reset err after using it hold errcode in hist testcases

[Wang Nan]

All hists test cases forget to reset err after using it to hold an
error code. If error occure in setup_fake_machine() it incorrectly
return TEST_OK.

This patch fixes it.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Suggested-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
---
 tools/perf/tests/hists_cumulate.c | 1 +
 tools/perf/tests/hists_filter.c   | 1 +
 tools/perf/tests/hists_link.c     | 1 +
 tools/perf/tests/hists_output.c   | 1 +
 4 files changed, 4 insertions(+)

diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 8292948..76f8922 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -706,6 +706,7 @@ int test__hists_cumulate(int subtest __maybe_unused)
 	err = parse_events(evlist, "cpu-clock", NULL);
 	if (err)
 		goto out;
+	err = TEST_FAIL;
 
 	machines__init(&machines);
 
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index ccb5b49..2cd91df 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -120,6 +120,7 @@ int test__hists_filter(int subtest __maybe_unused)
 	err = parse_events(evlist, "task-clock", NULL);
 	if (err)
 		goto out;
+	err = TEST_FAIL;
 
 	/* default sort order (comm,dso,sym) will be used */
 	if (setup_sorting() < 0)
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 6243e2b..4dd8f4e 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -293,6 +293,7 @@ int test__hists_link(int subtest __maybe_unused)
 	if (err)
 		goto out;
 
+	err = TEST_FAIL;
 	/* default sort order (comm,dso,sym) will be used */
 	if (setup_sorting() < 0)
 		goto out;
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index 248beec..dc7bf56 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -597,6 +597,7 @@ int test__hists_output(int subtest __maybe_unused)
 	err = parse_events(evlist, "cpu-clock", NULL);
 	if (err)
 		goto out;
+	err = TEST_FAIL;
 
 	machines__init(&machines);
 
-- 
1.8.3.4

[PATCH v6 06/16] perf tools: Prevent calling machine__delete() on non-allocated machine

[Wang Nan]

To prevent futher commits calling machine__delete() on non-allocated
'struct machine' (which would cause memory corruption), this patch
enforces machine__init(), record whether a machine structure is
dynamically allocated or not, and warn if machine__delete() is called
on incorrect object.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/vmlinux-kallsyms.c |  4 ++--
 tools/perf/util/machine.c           | 13 ++++++++-----
 tools/perf/util/machine.h           |  3 ++-
 3 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index f0bfc9e..441e93d 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -35,8 +35,8 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 	 * Init the machines that will hold kernel, modules obtained from
 	 * both vmlinux + .ko files and from /proc/kallsyms split by modules.
 	 */
-	machine__init(&kallsyms, "", HOST_KERNEL_ID);
-	machine__init(&vmlinux, "", HOST_KERNEL_ID);
+	machine__init(&kallsyms, "", HOST_KERNEL_ID, false);
+	machine__init(&vmlinux, "", HOST_KERNEL_ID, false);
 
 	/*
 	 * Step 2:
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index ad79297..59a3c01 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1,3 +1,4 @@
+#include <asm/bug.h>
 #include "callchain.h"
 #include "debug.h"
 #include "event.h"
@@ -23,7 +24,7 @@ static void dsos__init(struct dsos *dsos)
 	pthread_rwlock_init(&dsos->lock, NULL);
 }
 
-int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
+int machine__init(struct machine *machine, const char *root_dir, pid_t pid, bool allocated)
 {
 	memset(machine, 0, sizeof(*machine));
 	map_groups__init(&machine->kmaps, machine);
@@ -65,6 +66,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	}
 
 	machine->current_tid = NULL;
+	machine->allocated = allocated;
 
 	return 0;
 }
@@ -74,7 +76,7 @@ struct machine *machine__new_host(void)
 	struct machine *machine = malloc(sizeof(*machine));
 
 	if (machine != NULL) {
-		machine__init(machine, "", HOST_KERNEL_ID);
+		machine__init(machine, "", HOST_KERNEL_ID, true);
 
 		if (machine__create_kernel_maps(machine) < 0)
 			goto out_delete;
@@ -137,12 +139,13 @@ void machine__exit(struct machine *machine)
 void machine__delete(struct machine *machine)
 {
 	machine__exit(machine);
-	free(machine);
+	WARN_ONCE((machine->allocated ? free(machine), 0 : -1),
+		  "WARNING: deleting a non-allocated machine. Skip.\n");
 }
 
 void machines__init(struct machines *machines)
 {
-	machine__init(&machines->host, "", HOST_KERNEL_ID);
+	machine__init(&machines->host, "", HOST_KERNEL_ID, false);
 	machines->guests = RB_ROOT;
 	machines->symbol_filter = NULL;
 }
@@ -163,7 +166,7 @@ struct machine *machines__add(struct machines *machines, pid_t pid,
 	if (machine == NULL)
 		return NULL;
 
-	if (machine__init(machine, root_dir, pid) != 0) {
+	if (machine__init(machine, root_dir, pid, true) != 0) {
 		free(machine);
 		return NULL;
 	}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 2c2b443..24dfd46 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -28,6 +28,7 @@ struct machine {
 	pid_t		  pid;
 	u16		  id_hdr_size;
 	bool		  comm_exec;
+	bool		  allocated;
 	char		  *root_dir;
 	struct rb_root	  threads;
 	pthread_rwlock_t  threads_lock;
@@ -131,7 +132,7 @@ void machines__set_symbol_filter(struct machines *machines,
 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);
+int machine__init(struct machine *machine, const char *root_dir, pid_t pid, bool allocated);
 void machine__exit(struct machine *machine);
 void machine__delete_threads(struct machine *machine);
 void machine__delete(struct machine *machine);
-- 
1.8.3.4

[PATCH v6 07/16] perf test: Check environment before start real BPF test

[Wang Nan]

Copying perf to old kernel system results:

 # perf test bpf
 37: Test BPF filter                                          :
 37.1: Test basic BPF filtering                               : FAILED!
 37.2: Test BPF prologue generation                           : Skip

However, in case when kernel doesn't support a test case it should
return 'Skip', 'FAILED!' should be reserved for kernel tests for when
the kernel supports a feature that then fails to work as advertised.

This patch checks environment before real testcase.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/bpf.c | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 33689a0..826b4b3 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -1,7 +1,11 @@
 #include <stdio.h>
 #include <sys/epoll.h>
+#include <util/util.h>
 #include <util/bpf-loader.h>
 #include <util/evlist.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <bpf/bpf.h>
 #include "tests.h"
 #include "llvm.h"
 #include "debug.h"
@@ -227,6 +231,36 @@ const char *test__bpf_subtest_get_desc(int i)
 	return bpf_testcase_table[i].desc;
 }
 
+static int check_env(void)
+{
+	int err;
+	unsigned int kver_int;
+	char license[] = "GPL";
+
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	};
+
+	err = fetch_kernel_version(&kver_int, NULL, 0);
+	if (err) {
+		pr_debug("Unable to get kernel version\n");
+		return err;
+	}
+
+	err = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
+			       sizeof(insns) / sizeof(insns[0]),
+			       license, kver_int, NULL, 0);
+	if (err < 0) {
+		pr_err("Missing basic BPF support, skip this test: %s\n",
+		       strerror(errno));
+		return err;
+	}
+	close(err);
+
+	return 0;
+}
+
 int test__bpf(int i)
 {
 	int err;
@@ -239,6 +273,9 @@ int test__bpf(int i)
 		return TEST_SKIP;
 	}
 
+	if (check_env())
+		return TEST_SKIP;
+
 	err = __test__bpf(i);
 	return err;
 }
-- 
1.8.3.4

[PATCH v6 08/16] perf tools: Add API to config maps in bpf object

[Wang Nan]

bpf__config_obj() is introduced as a core API to config BPF object
after loading. One configuration option of maps is introduced. After
this patch BPF object can accept configuration like:

 maps:my_map.value=1234

(maps.my_map.value looks pretty. However, there's a small but hard
to fixed problem related to flex's greedy matching. Please see [1].
Choose ':' to avoid it in a simpler way.)

This patch is more complex than the work it really does because the
consideration of extension. In designing of BPF map configuration,
following things should be considered:

 1. Array indices selection: perf should allow user setting different
    value to different slots in an array, with syntax like:
    maps:my_map.value[0,3...6]=1234;

 2. A map can be config by different config terms, each for a part
    of it. For example, set each slot to pid of a thread;

 3. Type of value: integer is not the only valid value type. Perf
    event can also be put into a map after commit 35578d7984003097af2b1e3
    (bpf: Implement function bpf_perf_event_read() that get the selected
    hardware PMU conuter);

 4. For hash table, it is possible to use string or other as key;

 5. It is possible that map configuration is unable to be setup
    during parsing. Perf event is an example.

Therefore, this patch does following:

 1. Instead of updating map element during parsing, this patch stores
    map config options in 'struct bpf_map_priv'. Following patches
    would apply those configs at proper time;

 2. Link map operations to a list so a map can have multiple config
    terms attached, so different parts can be configured separately;

 3. Make 'struct bpf_map_priv' extensible so following patches can
    add new types of keys and operations;

 4. Use bpf_config_map_funcs array to support more maps config options.

Since the patch changing event parser to parse BPF object config is
relative large, I put in another commit. Code in this patch
could be tested after applying next patch.

[1] http://lkml.kernel.org/g/564ED621.4050500@huawei.com

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Signed-off-by: He Kuang <hekuang@huawei.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
---
 tools/perf/util/bpf-loader.c | 266 +++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/bpf-loader.h |  38 +++++++
 2 files changed, 304 insertions(+)

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 540a7ef..7d361aa 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -739,6 +739,251 @@ int bpf__foreach_tev(struct bpf_object *obj,
 	return 0;
 }
 
+enum bpf_map_op_type {
+	BPF_MAP_OP_SET_VALUE,
+};
+
+enum bpf_map_key_type {
+	BPF_MAP_KEY_ALL,
+};
+
+struct bpf_map_op {
+	struct list_head list;
+	enum bpf_map_op_type op_type;
+	enum bpf_map_key_type key_type;
+	union {
+		u64 value;
+	} v;
+};
+
+struct bpf_map_priv {
+	struct list_head ops_list;
+};
+
+static void
+bpf_map_op__free(struct bpf_map_op *op)
+{
+	struct list_head *list = &op->list;
+	/*
+	 * bpf_map_op__free() needs to consider following cases:
+	 *   1. When the op is created but not linked to any list:
+	 *      impossible. This only happen in bpf_map_op__alloc()
+	 *      and it would be freed directly;
+	 *   2. Normal case, when the op is linked to a list;
+	 *   3. After the op has already be removed.
+	 * Thanks to list.h, if it has removed by list_del() then
+	 * list->{next,prev} should have been set to LIST_POISON{1,2}.
+	 */
+	if ((list->next != LIST_POISON1) && (list->prev != LIST_POISON2))
+		list_del(list);
+	free(op);
+}
+
+static void
+bpf_map_priv__clear(struct bpf_map *map __maybe_unused,
+		    void *_priv)
+{
+	struct bpf_map_priv *priv = _priv;
+	struct bpf_map_op *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &priv->ops_list, list)
+		bpf_map_op__free(pos);
+	free(priv);
+}
+
+static struct bpf_map_op *
+bpf_map_op__alloc(struct bpf_map *map)
+{
+	struct bpf_map_op *op;
+	struct bpf_map_priv *priv;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+	err = bpf_map__get_private(map, (void **)&priv);
+	if (err) {
+		pr_debug("Failed to get private from map %s\n", map_name);
+		return ERR_PTR(err);
+	}
+
+	if (!priv) {
+		priv = zalloc(sizeof(*priv));
+		if (!priv) {
+			pr_debug("No enough memory to alloc map private\n");
+			return ERR_PTR(-ENOMEM);
+		}
+		INIT_LIST_HEAD(&priv->ops_list);
+
+		if (bpf_map__set_private(map, priv, bpf_map_priv__clear)) {
+			free(priv);
+			return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL);
+		}
+	}
+
+	op = zalloc(sizeof(*op));
+	if (!op) {
+		pr_debug("Failed to alloc bpf_map_op\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	op->key_type = BPF_MAP_KEY_ALL;
+	list_add_tail(&op->list, &priv->ops_list);
+	return op;
+}
+
+static int
+bpf__obj_config_map_array_value(struct bpf_map *map,
+				struct parse_events_term *term)
+{
+	struct bpf_map_def def;
+	struct bpf_map_op *op;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("Unable to get map definition from '%s'\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	if (def.type != BPF_MAP_TYPE_ARRAY) {
+		pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+	}
+	if (def.key_size < sizeof(unsigned int)) {
+		pr_debug("Map %s has incorrect key size\n", map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE;
+	}
+	switch (def.value_size) {
+	case 1:
+	case 2:
+	case 4:
+	case 8:
+		break;
+	default:
+		pr_debug("Map %s has incorrect value size\n", map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
+	}
+
+	op = bpf_map_op__alloc(map);
+	if (IS_ERR(op))
+		return PTR_ERR(op);
+	op->op_type = BPF_MAP_OP_SET_VALUE;
+	op->v.value = term->val.num;
+	return 0;
+}
+
+static int
+bpf__obj_config_map_value(struct bpf_map *map,
+			  struct parse_events_term *term,
+			  struct perf_evlist *evlist __maybe_unused)
+{
+	if (!term->err_val) {
+		pr_debug("Config value not set\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
+	}
+
+	if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+		return bpf__obj_config_map_array_value(map, term);
+
+	pr_debug("ERROR: wrong value type\n");
+	return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
+}
+
+struct bpf_obj_config_map_func {
+	const char *config_opt;
+	int (*config_func)(struct bpf_map *, struct parse_events_term *,
+			   struct perf_evlist *);
+};
+
+struct bpf_obj_config_map_func bpf_obj_config_map_funcs[] = {
+	{"value", bpf__obj_config_map_value},
+};
+
+static int
+bpf__obj_config_map(struct bpf_object *obj,
+		    struct parse_events_term *term,
+		    struct perf_evlist *evlist,
+		    int *key_scan_pos)
+{
+	/* key is "maps:<mapname>.<config opt>" */
+	char *map_name = strdup(term->config + sizeof("maps:") - 1);
+	struct bpf_map *map;
+	int err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
+	char *map_opt;
+	size_t i;
+
+	if (!map_name)
+		return -ENOMEM;
+
+	map_opt = strchr(map_name, '.');
+	if (!map_opt) {
+		pr_debug("ERROR: Invalid map config: %s\n", map_name);
+		goto out;
+	}
+
+	*map_opt++ = '\0';
+	if (*map_opt == '\0') {
+		pr_debug("ERROR: Invalid map option: %s\n", term->config);
+		goto out;
+	}
+
+	map = bpf_object__get_map_by_name(obj, map_name);
+	if (!map) {
+		pr_debug("ERROR: Map %s is not exist\n", map_name);
+		err = -BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST;
+		goto out;
+	}
+
+	*key_scan_pos += map_opt - map_name;
+	for (i = 0; i < ARRAY_SIZE(bpf_obj_config_map_funcs); i++) {
+		struct bpf_obj_config_map_func *func =
+				&bpf_obj_config_map_funcs[i];
+
+		if (strcmp(map_opt, func->config_opt) == 0) {
+			err = func->config_func(map, term, evlist);
+			goto out;
+		}
+	}
+
+	pr_debug("ERROR: invalid config option '%s' for maps\n",
+		 map_opt);
+	err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT;
+out:
+	free(map_name);
+	if (!err)
+		key_scan_pos += strlen(map_opt);
+	return err;
+}
+
+int bpf__config_obj(struct bpf_object *obj,
+		    struct parse_events_term *term,
+		    struct perf_evlist *evlist,
+		    int *error_pos)
+{
+	int key_scan_pos = 0;
+	int err;
+
+	if (!obj || !term || !term->config)
+		return -EINVAL;
+
+	if (!prefixcmp(term->config, "maps:")) {
+		key_scan_pos = sizeof("maps:") - 1;
+		err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos);
+		goto out;
+	}
+	err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
+out:
+	if (error_pos)
+		*error_pos = key_scan_pos;
+	return err;
+
+}
+
 #define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
 #define ERRCODE_OFFSET(c)	ERRNO_OFFSET(BPF_LOADER_ERRNO__##c)
 #define NR_ERRNO	(__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START)
@@ -753,6 +998,14 @@ static const char *bpf_loader_strerror_table[NR_ERRNO] = {
 	[ERRCODE_OFFSET(PROLOGUE)]	= "Failed to generate prologue",
 	[ERRCODE_OFFSET(PROLOGUE2BIG)]	= "Prologue too big for program",
 	[ERRCODE_OFFSET(PROLOGUEOOB)]	= "Offset out of bound for prologue",
+	[ERRCODE_OFFSET(OBJCONF_OPT)]	= "Invalid object config option",
+	[ERRCODE_OFFSET(OBJCONF_CONF)]	= "Config value not set (lost '=')",
+	[ERRCODE_OFFSET(OBJCONF_MAP_OPT)]	= "Invalid object maps config option",
+	[ERRCODE_OFFSET(OBJCONF_MAP_NOTEXIST)]	= "Target map not exist",
+	[ERRCODE_OFFSET(OBJCONF_MAP_VALUE)]	= "Incorrect value type for map",
+	[ERRCODE_OFFSET(OBJCONF_MAP_TYPE)]	= "Incorrect map type",
+	[ERRCODE_OFFSET(OBJCONF_MAP_KEYSIZE)]	= "Incorrect map key size",
+	[ERRCODE_OFFSET(OBJCONF_MAP_VALUESIZE)]	= "Incorrect map value size",
 };
 
 static int
@@ -872,3 +1125,16 @@ int bpf__strerror_load(struct bpf_object *obj,
 	bpf__strerror_end(buf, size);
 	return 0;
 }
+
+int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
+			     struct parse_events_term *term __maybe_unused,
+			     struct perf_evlist *evlist __maybe_unused,
+			     int *error_pos __maybe_unused, int err,
+			     char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,
+			    "Can't use this config term to this type of map");
+	bpf__strerror_end(buf, size);
+	return 0;
+}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 6fdc045..2464db9 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -10,6 +10,7 @@
 #include <string.h>
 #include <bpf/libbpf.h>
 #include "probe-event.h"
+#include "evlist.h"
 #include "debug.h"
 
 enum bpf_loader_errno {
@@ -24,10 +25,19 @@ enum bpf_loader_errno {
 	BPF_LOADER_ERRNO__PROLOGUE,	/* Failed to generate prologue */
 	BPF_LOADER_ERRNO__PROLOGUE2BIG,	/* Prologue too big for program */
 	BPF_LOADER_ERRNO__PROLOGUEOOB,	/* Offset out of bound for prologue */
+	BPF_LOADER_ERRNO__OBJCONF_OPT,	/* Invalid object config option */
+	BPF_LOADER_ERRNO__OBJCONF_CONF,	/* Config value not set (lost '=')) */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_OPT,	/* Invalid object maps config option */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST,	/* Target map not exist */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE,	/* Incorrect value type for map */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,	/* Incorrect map type */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE,	/* Incorrect map key size */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE,/* Incorrect map value size */
 	__BPF_LOADER_ERRNO__END,
 };
 
 struct bpf_object;
+struct parse_events_term;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
 
 typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev,
@@ -53,6 +63,14 @@ int bpf__strerror_load(struct bpf_object *obj, int err,
 		       char *buf, size_t size);
 int bpf__foreach_tev(struct bpf_object *obj,
 		     bpf_prog_iter_callback_t func, void *arg);
+
+int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term,
+		    struct perf_evlist *evlist, int *error_pos);
+int bpf__strerror_config_obj(struct bpf_object *obj,
+			     struct parse_events_term *term,
+			     struct perf_evlist *evlist,
+			     int *error_pos, int err, char *buf,
+			     size_t size);
 #else
 static inline struct bpf_object *
 bpf__prepare_load(const char *filename __maybe_unused,
@@ -84,6 +102,15 @@ bpf__foreach_tev(struct bpf_object *obj __maybe_unused,
 }
 
 static inline int
+bpf__config_obj(struct bpf_object *obj __maybe_unused,
+		struct parse_events_term *term __maybe_unused,
+		struct perf_evlist *evlist __maybe_unused,
+		int *error_pos __maybe_unused)
+{
+	return 0;
+}
+
+static inline int
 __bpf_strerror(char *buf, size_t size)
 {
 	if (!size)
@@ -118,5 +145,16 @@ static inline int bpf__strerror_load(struct bpf_object *obj __maybe_unused,
 {
 	return __bpf_strerror(buf, size);
 }
+
+static inline int
+bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
+			 struct parse_events_term *term __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused,
+			 int *error_pos __maybe_unused,
+			 int err __maybe_unused,
+			 char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
 #endif
 #endif
-- 
1.8.3.4

[PATCH v6 09/16] perf tools: Enable BPF object configure syntax

[Wang Nan]

This patch adds the final step for BPF map configuration. A new syntax
is appended into parser so user can config BPF objects through '/' '/'
enclosed config terms.

After this patch, following syntax is available:

 # perf record -e ./test_bpf_map_1.c/maps:channel.value=10/ ...

It would takes effect after appling following commits.

Test result:

 # cat ./test_bpf_map_1.c
 /************************ BEGIN **************************/
 #include <uapi/linux/bpf.h>
 #define SEC(NAME) __attribute__((section(NAME), used))
 struct bpf_map_def {
     unsigned int type;
     unsigned int key_size;
     unsigned int value_size;
     unsigned int max_entries;
 };
 static void *(*map_lookup_elem)(struct bpf_map_def *, void *) =
     (void *)BPF_FUNC_map_lookup_elem;
 static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
     (void *)BPF_FUNC_trace_printk;
 struct bpf_map_def SEC("maps") channel = {
     .type = BPF_MAP_TYPE_ARRAY,
     .key_size = sizeof(int),
     .value_size = sizeof(int),
     .max_entries = 1,
 };
 SEC("func=sys_nanosleep")
 int func(void *ctx)
 {
     int key = 0;
     char fmt[] = "%d\n";
     int *pval = map_lookup_elem(&channel, &key);
     if (!pval)
         return 0;
     trace_printk(fmt, sizeof(fmt), *pval);
     return 0;
 }
 char _license[] SEC("license") = "GPL";
 int _version SEC("version") = LINUX_VERSION_CODE;
 /************************* END ***************************/

 - Normal case:
 # ./perf record -e './test_bpf_map_1.c/maps:channel.value=10/' usleep 10
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.012 MB perf.data ]

 - Error case:

 # ./perf record -e './test_bpf_map_1.c/maps:channel.value/' usleep 10
 event syntax error: '..ps:channel:value/'
                                   \___ Config value not set (lost '=')
 Hint:	Valid config term:
      	maps:[<arraymap>]:value=[value]
	     	(add -v to see detail)
	Run 'perf list' for a list of valid events

 Usage: perf record [<options>] [<command>]
    or: perf record [<options>] -- <command> [<options>]

    -e, --event <event>   event selector. use 'perf list' to list available events

 # ./perf record -e './test_bpf_map_1.c/xmaps:channel.value=10/' usleep 10
 event syntax error: '..pf_map_1.c/xmaps:channel.value=10/'
                                   \___ Invalid object config option
 [SNIP]

 # ./perf record -e './test_bpf_map_1.c/maps:xchannel.value=10/' usleep 10
 event syntax error: '..p_1.c/maps:xchannel.value=10/'
                                   \___ Target map not exist
 [SNIP]

 # ./perf record -e './test_bpf_map_1.c/maps:channel.xvalue=10/' usleep 10
 event syntax error: '..ps:channel.xvalue=10/'
                                   \___ Invalid object maps config option
 [SNIP]

 # ./perf record -e './test_bpf_map_1.c/maps:channel.value=x10/' usleep 10
 event syntax error: '..nnel.value=x10/'
                                   \___ Incorrect value type for map
 [SNIP]

 Change BPF_MAP_TYPE_ARRAY to '1':

 # ./perf record -e './test_bpf_map_1.c/maps:channel.value=10/' usleep 10
 event syntax error: '..ps:channel.value=10/'
                                   \___ Can't use this config term to this type of map

 Hint:	Valid config term:
     	maps:[<arraymap>].value=[value]
     	(add -v to see detail)

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Signed-off-by: He Kuang <hekuang@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
---
 tools/perf/util/parse-events.c | 56 +++++++++++++++++++++++++++++++++++++++---
 tools/perf/util/parse-events.h |  3 ++-
 tools/perf/util/parse-events.l |  2 +-
 tools/perf/util/parse-events.y | 23 ++++++++++++++---
 4 files changed, 75 insertions(+), 9 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4f7b0ef..1c2dc5d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -628,17 +628,64 @@ errout:
 	return err;
 }
 
+static int
+parse_events_config_bpf(struct parse_events_evlist *data,
+		       struct bpf_object *obj,
+		       struct list_head *head_config)
+{
+	struct parse_events_term *term;
+	int error_pos;
+
+	if (!head_config || list_empty(head_config))
+		return 0;
+
+	list_for_each_entry(term, head_config, list) {
+		char errbuf[BUFSIZ];
+		int err;
+
+		if (term->type_term != PARSE_EVENTS__TERM_TYPE_USER) {
+			snprintf(errbuf, sizeof(errbuf),
+				 "Invalid config term for BPF object");
+			errbuf[BUFSIZ - 1] = '\0';
+
+			data->error->idx = term->err_term;
+			data->error->str = strdup(errbuf);
+			return -EINVAL;
+		}
+
+		err = bpf__config_obj(obj, term, NULL, &error_pos);
+		if (err) {
+			bpf__strerror_config_obj(obj, term, NULL,
+						 &error_pos, err, errbuf,
+						 sizeof(errbuf));
+			data->error->help = strdup(
+"Hint:\tValid config term:\n"
+"     \tmaps:[<arraymap>].value=[value]\n"
+"     \t(add -v to see detail)");
+			data->error->str = strdup(errbuf);
+			if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE)
+				data->error->idx = term->err_val;
+			else
+				data->error->idx = term->err_term + error_pos;
+			return err;
+		}
+	}
+	return 0;
+
+}
+
 int parse_events_load_bpf(struct parse_events_evlist *data,
 			  struct list_head *list,
 			  char *bpf_file_name,
-			  bool source)
+			  bool source,
+			  struct list_head *head_config)
 {
 	struct bpf_object *obj;
+	int err;
 
 	obj = bpf__prepare_load(bpf_file_name, source);
 	if (IS_ERR(obj)) {
 		char errbuf[BUFSIZ];
-		int err;
 
 		err = PTR_ERR(obj);
 
@@ -656,7 +703,10 @@ int parse_events_load_bpf(struct parse_events_evlist *data,
 		return err;
 	}
 
-	return parse_events_load_bpf_obj(data, list, obj);
+	err = parse_events_load_bpf_obj(data, list, obj);
+	if (err)
+		return err;
+	return parse_events_config_bpf(data, obj, head_config);
 }
 
 static int
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index f1a6db1..84694f3 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -126,7 +126,8 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 int parse_events_load_bpf(struct parse_events_evlist *data,
 			  struct list_head *list,
 			  char *bpf_file_name,
-			  bool source);
+			  bool source,
+			  struct list_head *head_config);
 /* Provide this function for perf test */
 struct bpf_object;
 int parse_events_load_bpf_obj(struct parse_events_evlist *data,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 58c5831..4387728 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -122,7 +122,7 @@ num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
 name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
-name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.]*
+name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 /* If you add a modifier you need to update check_modifier() */
 modifier_event	[ukhpPGHSDI]+
 modifier_bp	[rwx]{1,3}
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index ad37996..8992d16 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -64,6 +64,7 @@ static inc_group_count(struct list_head *list,
 %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> value_sym
 %type <head> event_config
+%type <head> event_bpf_config
 %type <term> event_term
 %type <head> event_pmu
 %type <head> event_legacy_symbol
@@ -455,27 +456,41 @@ PE_RAW
 }
 
 event_bpf_file:
-PE_BPF_OBJECT
+PE_BPF_OBJECT event_bpf_config
 {
 	struct parse_events_evlist *data = _data;
 	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_load_bpf(data, list, $1, false));
+	ABORT_ON(parse_events_load_bpf(data, list, $1, false, $2));
+	if ($2)
+		parse_events__free_terms($2);
 	$$ = list;
 }
 |
-PE_BPF_SOURCE
+PE_BPF_SOURCE event_bpf_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_load_bpf(data, list, $1, true));
+	ABORT_ON(parse_events_load_bpf(data, list, $1, true, $2));
+	if ($2)
+		parse_events__free_terms($2);
 	$$ = list;
 }
 
+event_bpf_config:
+'/' event_config '/'
+{
+	$$ = $2;
+}
+|
+{
+	$$ = NULL;
+}
+
 start_terms: event_config
 {
 	struct parse_events_terms *data = _data;
-- 
1.8.3.4

[PATCH v6 10/16] perf record: Apply config to BPF objects before recording

[Wang Nan]

bpf__apply_obj_config() is introduced as the core API to apply object
config options to all BPF objects. This patch also does the real work
for setting values for BPF_MAP_TYPE_PERF_ARRAY maps by inserting value
stored in map's private field into the BPF map.

This patch is required because we are not always able to set all
BPF config during parsing. Further patch will set events created
by perf to BPF_MAP_TYPE_PERF_EVENT_ARRAY maps, which is not exist
until perf_evsel__open().

bpf_map_foreach_key() is introduced to iterate over each key
needs to be configured. This function would be extended to support
more map types and different key settings.

In perf record, before start recording, call bpf__apply_config() to
turn on all BPF config options.

Test result:

 # cat ./test_bpf_map_1.c
 /************************ BEGIN **************************/
 #include <uapi/linux/bpf.h>
 #define SEC(NAME) __attribute__((section(NAME), used))
 struct bpf_map_def {
     unsigned int type;
     unsigned int key_size;
     unsigned int value_size;
     unsigned int max_entries;
 };
 static void *(*map_lookup_elem)(struct bpf_map_def *, void *) =
     (void *)BPF_FUNC_map_lookup_elem;
 static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
     (void *)BPF_FUNC_trace_printk;
 struct bpf_map_def SEC("maps") channel = {
     .type = BPF_MAP_TYPE_ARRAY,
     .key_size = sizeof(int),
     .value_size = sizeof(int),
     .max_entries = 1,
 };
 SEC("func=sys_nanosleep")
 int func(void *ctx)
 {
     int key = 0;
     char fmt[] = "%d\n";
     int *pval = map_lookup_elem(&channel, &key);
     if (!pval)
         return 0;
     trace_printk(fmt, sizeof(fmt), *pval);
     return 0;
 }
 char _license[] SEC("license") = "GPL";
 int _version SEC("version") = LINUX_VERSION_CODE;
 /************************* END ***************************/

 # echo "" > /sys/kernel/debug/tracing/trace
 # ./perf record -e './test_bpf_map_1.c/maps:channel.value=11/' usleep 10
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.012 MB perf.data ]
 # cat /sys/kernel/debug/tracing/trace
 # tracer: nop
 #
 # entries-in-buffer/entries-written: 1/1   #P:8
 [SNIP]
 #           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
 #              | |       |   ||||       |         |
            usleep-18593 [007] d... 2394714.395539: : 11
 # ./perf record -e './test_bpf_map.c/maps:channel.value=101/' usleep 10
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.012 MB perf.data ]
 # cat /sys/kernel/debug/tracing/trace
 # tracer: nop
 #
 # entries-in-buffer/entries-written: 1/1   #P:8
 [SNIP]
 #           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
 #              | |       |   ||||       |         |
            usleep-18593 [007] d... 2394714.395539: : 11
            usleep-19000 [006] d... 2394831.057840: : 101

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Signed-off-by: He Kuang <hekuang@huawei.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
---
 tools/perf/builtin-record.c  |  11 +++
 tools/perf/util/bpf-loader.c | 180 +++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/bpf-loader.h |  15 ++++
 3 files changed, 206 insertions(+)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 1435ef6..d49046f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -32,6 +32,7 @@
 #include "util/parse-branch-options.h"
 #include "util/parse-regs-options.h"
 #include "util/llvm-utils.h"
+#include "util/bpf-loader.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -524,6 +525,16 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		goto out_child;
 	}
 
+	err = bpf__apply_obj_config();
+	if (err) {
+		char errbuf[BUFSIZ];
+
+		bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
+		pr_err("ERROR: Apply config to BPF failed: %s\n",
+			 errbuf);
+		goto out_child;
+	}
+
 	/*
 	 * Normally perf_session__new would do this, but it doesn't have the
 	 * evlist.
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 7d361aa..96fd18b 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -7,6 +7,7 @@
 
 #include <linux/bpf.h>
 #include <bpf/libbpf.h>
+#include <bpf/bpf.h>
 #include <linux/err.h>
 #include <linux/string.h>
 #include "perf.h"
@@ -984,6 +985,178 @@ out:
 
 }
 
+typedef int (*map_config_func_t)(const char *name, int map_fd,
+				 struct bpf_map_def *pdef,
+				 struct bpf_map_op *op,
+				 void *pkey, void *arg);
+
+static int
+foreach_key_array_all(map_config_func_t func,
+		      void *arg, const char *name,
+		      int map_fd, struct bpf_map_def *pdef,
+		      struct bpf_map_op *op)
+{
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < pdef->max_entries; i++) {
+		err = func(name, map_fd, pdef, op, &i, arg);
+		if (err) {
+			pr_debug("ERROR: failed to insert value to %s[%u]\n",
+				 name, i);
+			return err;
+		}
+	}
+	return 0;
+}
+
+static int
+bpf_map_config_foreach_key(struct bpf_map *map,
+			   map_config_func_t func,
+			   void *arg)
+{
+	int err, map_fd;
+	const char *name;
+	struct bpf_map_op *op;
+	struct bpf_map_def def;
+	struct bpf_map_priv *priv;
+
+	name = bpf_map__get_name(map);
+
+	err = bpf_map__get_private(map, (void **)&priv);
+	if (err) {
+		pr_debug("ERROR: failed to get private from map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	if (!priv || list_empty(&priv->ops_list)) {
+		pr_debug("INFO: nothing to config for map %s\n", name);
+		return 0;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("ERROR: failed to get definition from map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	map_fd = bpf_map__get_fd(map);
+	if (map_fd < 0) {
+		pr_debug("ERROR: failed to get fd from map %s\n", name);
+		return map_fd;
+	}
+
+	list_for_each_entry(op, &priv->ops_list, list) {
+		switch (def.type) {
+		case BPF_MAP_TYPE_ARRAY:
+			switch (op->key_type) {
+			case BPF_MAP_KEY_ALL:
+				return foreach_key_array_all(func, arg, name,
+							     map_fd, &def, op);
+			default:
+				pr_debug("ERROR: keytype for map '%s' invalid\n",
+					 name);
+				return -BPF_LOADER_ERRNO__INTERNAL;
+		}
+		default:
+			pr_debug("ERROR: type of '%s' incorrect\n", name);
+			return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+		}
+	}
+
+	return 0;
+}
+
+static int
+apply_config_value_for_key(int map_fd, void *pkey,
+			   size_t val_size, u64 val)
+{
+	int err = 0;
+
+	switch (val_size) {
+	case 1: {
+		u8 _val = (u8)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 2: {
+		u16 _val = (u16)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 4: {
+		u32 _val = (u32)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 8: {
+		err = bpf_map_update_elem(map_fd, pkey, &val, BPF_ANY);
+		break;
+	}
+	default:
+		pr_debug("ERROR: invalid value size\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
+	}
+	if (err && errno)
+		err = -errno;
+	return err;
+}
+
+static int
+apply_obj_config_map_for_key(const char *name, int map_fd,
+			     struct bpf_map_def *pdef __maybe_unused,
+			     struct bpf_map_op *op,
+			     void *pkey, void *arg __maybe_unused)
+{
+	int err;
+
+	switch (op->op_type) {
+	case BPF_MAP_OP_SET_VALUE:
+		err = apply_config_value_for_key(map_fd, pkey,
+						 pdef->value_size,
+						 op->v.value);
+		break;
+	default:
+		pr_debug("ERROR: unknown value type for '%s'\n", name);
+		err = -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	return err;
+}
+
+static int
+apply_obj_config_map(struct bpf_map *map)
+{
+	return bpf_map_config_foreach_key(map,
+					  apply_obj_config_map_for_key,
+					  NULL);
+}
+
+static int
+apply_obj_config_object(struct bpf_object *obj)
+{
+	struct bpf_map *map;
+	int err;
+
+	bpf_map__for_each(map, obj) {
+		err = apply_obj_config_map(map);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+int bpf__apply_obj_config(void)
+{
+	struct bpf_object *obj, *tmp;
+	int err;
+
+	bpf_object__for_each_safe(obj, tmp) {
+		err = apply_obj_config_object(obj);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 #define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
 #define ERRCODE_OFFSET(c)	ERRNO_OFFSET(BPF_LOADER_ERRNO__##c)
 #define NR_ERRNO	(__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START)
@@ -1138,3 +1311,10 @@ int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
 	bpf__strerror_end(buf, size);
 	return 0;
 }
+
+int bpf__strerror_apply_obj_config(int err, char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_end(buf, size);
+	return 0;
+}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 2464db9..db3c34c 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -71,6 +71,8 @@ int bpf__strerror_config_obj(struct bpf_object *obj,
 			     struct perf_evlist *evlist,
 			     int *error_pos, int err, char *buf,
 			     size_t size);
+int bpf__apply_obj_config(void);
+int bpf__strerror_apply_obj_config(int err, char *buf, size_t size);
 #else
 static inline struct bpf_object *
 bpf__prepare_load(const char *filename __maybe_unused,
@@ -111,6 +113,12 @@ bpf__config_obj(struct bpf_object *obj __maybe_unused,
 }
 
 static inline int
+bpf__apply_obj_config(void)
+{
+	return 0;
+}
+
+static inline int
 __bpf_strerror(char *buf, size_t size)
 {
 	if (!size)
@@ -156,5 +164,12 @@ bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
 {
 	return __bpf_strerror(buf, size);
 }
+
+static inline int
+bpf__strerror_apply_obj_config(int err __maybe_unused,
+			       char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
 #endif
 #endif
-- 
1.8.3.4

[PATCH v6 11/16] perf tools: Enable passing event to BPF object

[Wang Nan]

A new syntax is appended into parser so user can pass predefined perf
events into BPF objects.

After this patch, BPF programs for perf are finally able to utilize
bpf_perf_event_read() introduced in commit 35578d7984003097af2b1e3
(bpf: Implement function bpf_perf_event_read() that get the selected
hardware PMU conuter).

Test result:

 # cat ./test_bpf_map_2.c
 /************************ BEGIN **************************/
 #include <uapi/linux/bpf.h>
 #define SEC(NAME) __attribute__((section(NAME), used))
 struct bpf_map_def {
     unsigned int type;
     unsigned int key_size;
     unsigned int value_size;
     unsigned int max_entries;
 };
 static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
     (void *)BPF_FUNC_trace_printk;
 static int (*get_smp_processor_id)(void) =
     (void *)BPF_FUNC_get_smp_processor_id;
 static int (*perf_event_read)(struct bpf_map_def *, int) =
     (void *)BPF_FUNC_perf_event_read;

 struct bpf_map_def SEC("maps") pmu_map = {
     .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
     .key_size = sizeof(int),
     .value_size = sizeof(int),
     .max_entries = __NR_CPUS__,
 };
 SEC("func_write=sys_write")
 int func_write(void *ctx)
 {
     unsigned long long val;
     char fmt[] = "sys_write:        pmu=%llu\n";
     val = perf_event_read(&pmu_map, get_smp_processor_id());
     trace_printk(fmt, sizeof(fmt), val);
     return 0;
 }

 SEC("func_write_return=sys_write%return")
 int func_write_return(void *ctx)
 {
     unsigned long long val = 0;
     char fmt[] = "sys_write_return: pmu=%llu\n";
     val = perf_event_read(&pmu_map, get_smp_processor_id());
     trace_printk(fmt, sizeof(fmt), val);
     return 0;
 }
 char _license[] SEC("license") = "GPL";
 int _version SEC("version") = LINUX_VERSION_CODE;
 /************************* END ***************************/

Normal case:
 # echo "" > /sys/kernel/debug/tracing/trace
 # ./perf record -i -e cycles -e './test_bpf_map_2.c/maps:pmu_map.event=cycles/' ls /
 [SNIP]
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.013 MB perf.data (7 samples) ]
 # cat /sys/kernel/debug/tracing/trace | grep ls
               ls-17066 [000] d... 938449.863301: : sys_write:        pmu=1157327
               ls-17066 [000] dN.. 938449.863342: : sys_write_return: pmu=1225218
               ls-17066 [000] d... 938449.863349: : sys_write:        pmu=1241922
               ls-17066 [000] dN.. 938449.863369: : sys_write_return: pmu=1267445

Normal case (system wide):
 # echo "" > /sys/kernel/debug/tracing/trace
 # ./perf record -i -e cycles -e './test_bpf_map_2.c/maps:pmu_map.event=cycles/' -a
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.811 MB perf.data (120 samples) ]

 # cat /sys/kernel/debug/tracing/trace | grep -v '18446744073709551594' | grep -v perf | head -n 20
 [SNIP]
 #           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
 #              | |       |   ||||       |         |
            gmain-30828 [002] d... 2740551.068992: : sys_write:        pmu=84373
            gmain-30828 [002] d... 2740551.068992: : sys_write_return: pmu=87696
            gmain-30828 [002] d... 2740551.068996: : sys_write:        pmu=100658
            gmain-30828 [002] d... 2740551.068997: : sys_write_return: pmu=102572

Error case 1:

 # ./perf record -e './test_bpf_map_2.c' ls /
 [SNIP]
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.014 MB perf.data ]
 # cat /sys/kernel/debug/tracing/trace | grep ls
               ls-17115 [007] d... 2724279.665625: : sys_write:        pmu=18446744073709551614
               ls-17115 [007] dN.. 2724279.665651: : sys_write_return: pmu=18446744073709551614
               ls-17115 [007] d... 2724279.665658: : sys_write:        pmu=18446744073709551614
               ls-17115 [007] dN.. 2724279.665677: : sys_write_return: pmu=18446744073709551614

 (18446744073709551614 is 0xfffffffffffffffe (-2))

Error case 2:
 # ./perf record -e cycles -e './test_bpf_map_2.c/maps:pmu_map.event=evt/' -a
 event syntax error: '..ps:pmu_map.event=evt/'
                                   \___ Event not found for map setting

 Hint:	Valid config terms:
      	maps:[<arraymap>].value=[value]
      	maps:[<eventmap>].event=[event]
 [SNIP]

Error case 3:
 # ls /proc/2348/task/
 2348  2505  2506  2507  2508
 # ./perf record -i -e cycles -e './test_bpf_map_2.c/maps:pmu_map.event=cycles/' -p 2348
 ERROR: Apply config to BPF failed: Cannot set event to BPF maps in multi-thread tracing

Error case 4:
 # ./perf record -e cycles -e './test_bpf_map_2.c/maps:pmu_map.event=cycles/' ls /
 ERROR: Apply config to BPF failed: Doesn't support inherit event (Hint: use -i to turn off inherit)

Error case 5:
 # ./perf record -i -e raw_syscalls:sys_enter -e './test_bpf_map_2.c/maps:pmu_map.event=raw_syscalls:sys_enter/' ls
 ERROR: Apply config to BPF failed: Can only put raw, hardware and BPF output event into a BPF map

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Signed-off-by: He Kuang <hekuang@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
---
 tools/perf/util/bpf-loader.c   | 138 ++++++++++++++++++++++++++++++++++++++++-
 tools/perf/util/bpf-loader.h   |   5 ++
 tools/perf/util/evlist.c       |  16 +++++
 tools/perf/util/evlist.h       |   3 +
 tools/perf/util/parse-events.c |  15 +++--
 tools/perf/util/parse-events.h |   1 +
 6 files changed, 171 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 96fd18b..84b4581 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -742,6 +742,7 @@ int bpf__foreach_tev(struct bpf_object *obj,
 
 enum bpf_map_op_type {
 	BPF_MAP_OP_SET_VALUE,
+	BPF_MAP_OP_SET_EVSEL,
 };
 
 enum bpf_map_key_type {
@@ -754,6 +755,7 @@ struct bpf_map_op {
 	enum bpf_map_key_type key_type;
 	union {
 		u64 value;
+		struct perf_evsel *evsel;
 	} v;
 };
 
@@ -891,10 +893,73 @@ bpf__obj_config_map_value(struct bpf_map *map,
 	if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
 		return bpf__obj_config_map_array_value(map, term);
 
-	pr_debug("ERROR: wrong value type\n");
+	pr_debug("ERROR: wrong value type for 'value'\n");
 	return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
 }
 
+static int
+bpf__obj_config_map_array_event(struct bpf_map *map,
+				struct parse_events_term *term,
+				struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	struct bpf_map_def def;
+	struct bpf_map_op *op;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+	evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str);
+	if (!evsel) {
+		pr_debug("Event (for '%s') '%s' doesn't exist\n",
+			 map_name, term->val.str);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("Unable to get map definition from '%s'\n",
+			 map_name);
+		return err;
+	}
+
+	/*
+	 * No need to check key_size and value_size:
+	 * kernel has already checked them.
+	 */
+	if (def.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+		pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+	}
+
+	op = bpf_map_op__alloc(map);
+	if (IS_ERR(op))
+		return PTR_ERR(op);
+
+	op->v.evsel = evsel;
+	op->op_type = BPF_MAP_OP_SET_EVSEL;
+	return 0;
+}
+
+static int
+bpf__obj_config_map_event(struct bpf_map *map,
+			  struct parse_events_term *term,
+			  struct perf_evlist *evlist)
+{
+	if (!term->err_val) {
+		pr_debug("Config value not set\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
+	}
+
+	if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+		return bpf__obj_config_map_array_event(map, term, evlist);
+
+	pr_debug("ERROR: wrong value type for 'event'\n");
+	return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
+}
+
+
 struct bpf_obj_config_map_func {
 	const char *config_opt;
 	int (*config_func)(struct bpf_map *, struct parse_events_term *,
@@ -903,6 +968,7 @@ struct bpf_obj_config_map_func {
 
 struct bpf_obj_config_map_func bpf_obj_config_map_funcs[] = {
 	{"value", bpf__obj_config_map_value},
+	{"event", bpf__obj_config_map_event},
 };
 
 static int
@@ -1047,6 +1113,7 @@ bpf_map_config_foreach_key(struct bpf_map *map,
 	list_for_each_entry(op, &priv->ops_list, list) {
 		switch (def.type) {
 		case BPF_MAP_TYPE_ARRAY:
+		case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
 			switch (op->key_type) {
 			case BPF_MAP_KEY_ALL:
 				return foreach_key_array_all(func, arg, name,
@@ -1101,6 +1168,60 @@ apply_config_value_for_key(int map_fd, void *pkey,
 }
 
 static int
+apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
+			   struct perf_evsel *evsel)
+{
+	struct xyarray *xy = evsel->fd;
+	struct perf_event_attr *attr;
+	unsigned int key, events;
+	bool check_pass = false;
+	int *evt_fd;
+	int err;
+
+	if (!xy) {
+		pr_debug("ERROR: evsel not ready for map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	if (xy->row_size / xy->entry_size != 1) {
+		pr_debug("ERROR: Dimension of target event is incorrect for map %s\n",
+			 name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM;
+	}
+
+	attr = &evsel->attr;
+	if (attr->inherit) {
+		pr_debug("ERROR: Can't put inherit event into map %s\n", name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH;
+	}
+
+	if (attr->type == PERF_TYPE_RAW)
+		check_pass = true;
+	if (attr->type == PERF_TYPE_HARDWARE)
+		check_pass = true;
+	if (attr->type == PERF_TYPE_SOFTWARE &&
+			attr->config == PERF_COUNT_SW_BPF_OUTPUT)
+		check_pass = true;
+	if (!check_pass) {
+		pr_debug("ERROR: Event type is wrong for map %s\n", name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE;
+	}
+
+	events = xy->entries / (xy->row_size / xy->entry_size);
+	key = *((unsigned int *)pkey);
+	if (key >= events) {
+		pr_debug("ERROR: there is no event %d for map %s\n",
+			 key, name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE;
+	}
+	evt_fd = xyarray__entry(xy, key, 0);
+	err = bpf_map_update_elem(map_fd, pkey, evt_fd, BPF_ANY);
+	if (err && errno)
+		err = -errno;
+	return err;
+}
+
+static int
 apply_obj_config_map_for_key(const char *name, int map_fd,
 			     struct bpf_map_def *pdef __maybe_unused,
 			     struct bpf_map_op *op,
@@ -1114,6 +1235,10 @@ apply_obj_config_map_for_key(const char *name, int map_fd,
 						 pdef->value_size,
 						 op->v.value);
 		break;
+	case BPF_MAP_OP_SET_EVSEL:
+		err = apply_config_evsel_for_key(name, map_fd, pkey,
+						 op->v.evsel);
+		break;
 	default:
 		pr_debug("ERROR: unknown value type for '%s'\n", name);
 		err = -BPF_LOADER_ERRNO__INTERNAL;
@@ -1179,6 +1304,11 @@ static const char *bpf_loader_strerror_table[NR_ERRNO] = {
 	[ERRCODE_OFFSET(OBJCONF_MAP_TYPE)]	= "Incorrect map type",
 	[ERRCODE_OFFSET(OBJCONF_MAP_KEYSIZE)]	= "Incorrect map key size",
 	[ERRCODE_OFFSET(OBJCONF_MAP_VALUESIZE)]	= "Incorrect map value size",
+	[ERRCODE_OFFSET(OBJCONF_MAP_NOEVT)]	= "Event not found for map setting",
+	[ERRCODE_OFFSET(OBJCONF_MAP_MAPSIZE)]	= "Invalid map size for event setting",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTDIM)]	= "Event dimension too large",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTINH)]	= "Doesn't support inherit event",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTTYPE)]	= "Wrong event type for map",
 };
 
 static int
@@ -1315,6 +1445,12 @@ int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
 int bpf__strerror_apply_obj_config(int err, char *buf, size_t size)
 {
 	bpf__strerror_head(err, buf, size);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,
+			    "Cannot set event to BPF maps in multi-thread tracing");
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,
+			    "%s (Hint: use -i to turn off inherit)", emsg);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,
+			    "Can only put raw, hardware and BPF output event into a BPF map");
 	bpf__strerror_end(buf, size);
 	return 0;
 }
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index db3c34c..c9ce792 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -33,6 +33,11 @@ enum bpf_loader_errno {
 	BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,	/* Incorrect map type */
 	BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE,	/* Incorrect map key size */
 	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE,/* Incorrect map value size */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT,	/* Event not found for map setting */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE,	/* Invalid map size for event setting */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,	/* Event dimension too large */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,	/* Doesn't support inherit event */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,	/* Wrong event type for map */
 	__BPF_LOADER_ERRNO__END,
 };
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 8c44aad..4bbf8aa 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1737,3 +1737,19 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 
 	tracking_evsel->tracking = true;
 }
+
+struct perf_evsel *
+perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
+			       const char *str)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (!evsel->name)
+			continue;
+		if (strcmp(str, evsel->name) == 0)
+			return evsel;
+	}
+
+	return NULL;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index a459fe7..9450656 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -292,4 +292,7 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
 
 void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
+
+struct perf_evsel *
+perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 1c2dc5d..6e2543c 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -653,14 +653,16 @@ parse_events_config_bpf(struct parse_events_evlist *data,
 			return -EINVAL;
 		}
 
-		err = bpf__config_obj(obj, term, NULL, &error_pos);
+		err = bpf__config_obj(obj, term, data->evlist, &error_pos);
 		if (err) {
-			bpf__strerror_config_obj(obj, term, NULL,
+			bpf__strerror_config_obj(obj, term, data->evlist,
 						 &error_pos, err, errbuf,
 						 sizeof(errbuf));
 			data->error->help = strdup(
-"Hint:\tValid config term:\n"
+"Hint:\tValid config terms:\n"
 "     \tmaps:[<arraymap>].value=[value]\n"
+"     \tmaps:[<eventmap>].event=[event]\n"
+"\n"
 "     \t(add -v to see detail)");
 			data->error->str = strdup(errbuf);
 			if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE)
@@ -1442,9 +1444,10 @@ int parse_events(struct perf_evlist *evlist, const char *str,
 		 struct parse_events_error *err)
 {
 	struct parse_events_evlist data = {
-		.list  = LIST_HEAD_INIT(data.list),
-		.idx   = evlist->nr_entries,
-		.error = err,
+		.list   = LIST_HEAD_INIT(data.list),
+		.idx    = evlist->nr_entries,
+		.error  = err,
+		.evlist = evlist,
 	};
 	int ret;
 
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 84694f3..2a2b172 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -98,6 +98,7 @@ struct parse_events_evlist {
 	int			   idx;
 	int			   nr_groups;
 	struct parse_events_error *error;
+	struct perf_evlist	  *evlist;
 };
 
 struct parse_events_terms {
-- 
1.8.3.4

[PATCH v6 12/16] perf tools: Support perf event alias name

[Wang Nan]

From: He Kuang <hekuang@huawei.com>

This patch is useful when trying to pass a perf event to BPF map.
Before this patch we are unable to pass an event with config term to
BPF maps. For example:

 # perf record -a -e cycles/no-inherit,period=0x7fffffffffffffff/ \
                  -e './test_bpf_map_2.c/maps:pmu_map.event=cycles/no-inherit,period=0x7fffffffffffffff//' ls /
 event syntax error: '..ps:pmu_map.event=cycles/'
                                   \___ Event not found for map setting

Because those '/' and ',' embarrass parser.

This patch adds new bison rules for specifying an alias name to a perf
event, which allows cmdline refer to previous defined perf event through
its name. With this patch user can give alias name to a perf event using
following cmdline. The above goal can be achieved using:

 # perf record -a -e cyc=cycles/no-inherit,period=0x7fffffffffffffff/ \
                  -e './test_bpf_map_2.c/maps:pmu_map.event=cyc/' ls /

If alias is not provided (normal case):

 # perf record -e cycles ...

It will be set to event's name automatically ('cycles' in the above
example).

To allow parser refer to existing event selector, pass event list to
'struct parse_events_evlist'. perf_evlist__find_evsel_by_alias() is
introduced to get evsel through its alias.

Test result:
 # cat ./test_bpf_map_2.c
 /************************ BEGIN **************************/
 #include <uapi/linux/bpf.h>
 #define SEC(NAME) __attribute__((section(NAME), used))
 struct bpf_map_def {
     unsigned int type;
     unsigned int key_size;
     unsigned int value_size;
     unsigned int max_entries;
 };
 static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
     (void *)BPF_FUNC_trace_printk;
 static int (*get_smp_processor_id)(void) =
     (void *)BPF_FUNC_get_smp_processor_id;
 static int (*perf_event_read)(struct bpf_map_def *, int) =
     (void *)BPF_FUNC_perf_event_read;

 struct bpf_map_def SEC("maps") pmu_map = {
     .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
     .key_size = sizeof(int),
     .value_size = sizeof(int),
     .max_entries = __NR_CPUS__,
 };
 SEC("func_write=sys_write")
 int func_write(void *ctx)
 {
     unsigned long long val;
     char fmt[] = "sys_write:        pmu=%llu\n";
     val = perf_event_read(&pmu_map, get_smp_processor_id());
     trace_printk(fmt, sizeof(fmt), val);
     return 0;
 }

 SEC("func_write_return=sys_write%return")
 int func_write_return(void *ctx)
 {
     unsigned long long val = 0;
     char fmt[] = "sys_write_return: pmu=%llu\n";
     val = perf_event_read(&pmu_map, get_smp_processor_id());
     trace_printk(fmt, sizeof(fmt), val);
     return 0;
 }
 char _license[] SEC("license") = "GPL";
 int _version SEC("version") = LINUX_VERSION_CODE;
 /************************* END ***************************/
 # echo "" > /sys/kernel/debug/tracing/trace
 # ./perf record -a -e cyc=cycles/no-inherit,period=0x7fffffffffffffff/ \
                    -e './test_bpf_map_2.c/maps:pmu_map.event=cyc/' ls /
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.755 MB perf.data ]
 # cat /sys/kernel/debug/tracing/trace | grep ls
               ls-25328 [002] d... 940138.313178: : sys_write:        pmu=4503165
               ls-25328 [002] dN.. 940138.313207: : sys_write_return: pmu=4582975
               ls-25328 [002] d... 940138.313211: : sys_write:        pmu=4599840
               ls-25328 [002] dN.. 940138.313220: : sys_write_return: pmu=4633352
 # ./perf report --stdio
 Error:
 The perf.data file has no samples!
 ...
 (This is expected because we set period of cycles to a very large
 value to period of cycles event because we want to use this event
 as a counter only, don't need sampling)

 # ./perf record -e cycles -e './test_bpf_map_2.c/maps:pmu_map.event=cycles/' ls /
 ERROR: Apply config to BPF failed: Doesn't support inherit event (Hint: use -i or use /no-inherit/ to turn off inherit)

Signed-off-by: He Kuang <hekuang@huawei.com>
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
---
 tools/perf/util/bpf-loader.c   |  2 +-
 tools/perf/util/evlist.c       |  4 ++--
 tools/perf/util/evsel.c        |  1 +
 tools/perf/util/evsel.h        |  1 +
 tools/perf/util/parse-events.c | 26 ++++++++++++++++++++++++++
 tools/perf/util/parse-events.h |  4 ++++
 tools/perf/util/parse-events.y | 15 ++++++++++++++-
 7 files changed, 49 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 84b4581..2893b4e 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1448,7 +1448,7 @@ int bpf__strerror_apply_obj_config(int err, char *buf, size_t size)
 	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,
 			    "Cannot set event to BPF maps in multi-thread tracing");
 	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,
-			    "%s (Hint: use -i to turn off inherit)", emsg);
+			    "%s (Hint: use -i or use /no-inherit/ to turn off inherit)", emsg);
 	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,
 			    "Can only put raw, hardware and BPF output event into a BPF map");
 	bpf__strerror_end(buf, size);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 4bbf8aa..4fe20192 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1745,9 +1745,9 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
 	struct perf_evsel *evsel;
 
 	evlist__for_each(evlist, evsel) {
-		if (!evsel->name)
+		if (!evsel->alias)
 			continue;
-		if (strcmp(str, evsel->name) == 0)
+		if (strcmp(str, evsel->alias) == 0)
 			return evsel;
 	}
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 544e440..1911dc8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1076,6 +1076,7 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 	thread_map__put(evsel->threads);
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
+	zfree(&evsel->alias);
 	perf_evsel__object.fini(evsel);
 }
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 5ded1fc..5f6dd57 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -89,6 +89,7 @@ struct perf_evsel {
 	int			idx;
 	u32			ids;
 	char			*name;
+	char			*alias;
 	double			scale;
 	const char		*unit;
 	struct event_format	*tp_format;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 6e2543c..1e0ac77 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1091,6 +1091,30 @@ int parse_events__modifier_group(struct list_head *list,
 	return parse_events__modifier_event(list, event_mod, true);
 }
 
+int parse_events__set_event_alias(struct parse_events_evlist *data,
+				  struct list_head *list,
+				  const char *str,
+				  void *loc_alias_)
+{
+	struct perf_evsel *evsel;
+	YYLTYPE *loc_alias = loc_alias_;
+
+	if (!str)
+		return 0;
+
+	if (!list_is_singular(list)) {
+		struct parse_events_error *err = data->error;
+
+		err->idx = loc_alias->first_column;
+		err->str = strdup("One alias can be applied to one event only");
+		return -EINVAL;
+	}
+
+	evsel = list_first_entry(list, struct perf_evsel, node);
+	evsel->alias = strdup(str);
+	return evsel->alias ? 0 : -ENOMEM;
+}
+
 void parse_events__set_leader(char *name, struct list_head *list)
 {
 	struct perf_evsel *leader;
@@ -1283,6 +1307,8 @@ int parse_events_name(struct list_head *list, char *name)
 	__evlist__for_each(list, evsel) {
 		if (!evsel->name)
 			evsel->name = strdup(name);
+		if (!evsel->alias)
+			evsel->alias = strdup(name);
 	}
 
 	return 0;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 2a2b172..20ad3c2 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -172,4 +172,8 @@ extern int is_valid_tracepoint(const char *event_string);
 int valid_event_mount(const char *eventfs);
 char *parse_events_formats_error_string(char *additional_terms);
 
+int parse_events__set_event_alias(struct parse_events_evlist *data,
+				  struct list_head *list,
+				  const char *str,
+				  void *loc_alias_);
 #endif /* __PERF_PARSE_EVENTS_H */
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 8992d16..c3cbd7a 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -77,6 +77,7 @@ static inc_group_count(struct list_head *list,
 %type <head> event_bpf_file
 %type <head> event_def
 %type <head> event_mod
+%type <head> event_alias
 %type <head> event_name
 %type <head> event
 %type <head> events
@@ -193,13 +194,25 @@ event_name PE_MODIFIER_EVENT
 event_name
 
 event_name:
-PE_EVENT_NAME event_def
+PE_EVENT_NAME event_alias
 {
 	ABORT_ON(parse_events_name($2, $1));
 	free($1);
 	$$ = $2;
 }
 |
+event_alias
+
+event_alias:
+PE_NAME '=' event_def
+{
+	struct list_head *list = $3;
+	struct parse_events_evlist *data = _data;
+
+	ABORT_ON(parse_events__set_event_alias(data, list, $1, &@1));
+	$$ = list;
+}
+|
 event_def
 
 event_def: event_pmu |
-- 
1.8.3.4

[PATCH v6 13/16] perf tools: Support setting different slots in a BPF map separately

[Wang Nan]

This patch introduces basic facilities to support config different
slots in a BPF map one by one.

array.nr_ranges and array.ranges are introduced into 'struct
parse_events_term', where ranges is an array of indices range (start,
length) which will be configured by this config term. nr_ranges
is the size of the array. The array is passed to 'struct bpf_map_priv'.
To indicate the new type of configuration, BPF_MAP_KEY_RANGES is
added as a new key type. bpf_map_config_foreach_key() is extended to
iterate over those indices instead of all possible keys.

Code in this commit will be enabled by following commit which enables
the indices syntax for array configuration.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
---
 tools/perf/util/bpf-loader.c   | 132 ++++++++++++++++++++++++++++++++++++++---
 tools/perf/util/bpf-loader.h   |   1 +
 tools/perf/util/parse-events.c |  33 ++++++++++-
 tools/perf/util/parse-events.h |  12 ++++
 4 files changed, 170 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 2893b4e..6c25de8 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -17,6 +17,7 @@
 #include "llvm-utils.h"
 #include "probe-event.h"
 #include "probe-finder.h" // for MAX_PROBES
+#include "parse-events.h"
 #include "llvm-utils.h"
 
 #define DEFINE_PRINT_FN(name, level) \
@@ -747,6 +748,7 @@ enum bpf_map_op_type {
 
 enum bpf_map_key_type {
 	BPF_MAP_KEY_ALL,
+	BPF_MAP_KEY_RANGES,
 };
 
 struct bpf_map_op {
@@ -754,6 +756,9 @@ struct bpf_map_op {
 	enum bpf_map_op_type op_type;
 	enum bpf_map_key_type key_type;
 	union {
+		struct parse_events_array array;
+	} k;
+	union {
 		u64 value;
 		struct perf_evsel *evsel;
 	} v;
@@ -779,6 +784,8 @@ bpf_map_op__free(struct bpf_map_op *op)
 	 */
 	if ((list->next != LIST_POISON1) && (list->prev != LIST_POISON2))
 		list_del(list);
+	if (op->key_type == BPF_MAP_KEY_RANGES)
+		parse_events__clear_array(&op->k.array);
 	free(op);
 }
 
@@ -794,8 +801,30 @@ bpf_map_priv__clear(struct bpf_map *map __maybe_unused,
 	free(priv);
 }
 
+static int
+bpf_map_op_setkey(struct bpf_map_op *op, struct parse_events_term *term,
+		  const char *map_name)
+{
+	op->key_type = BPF_MAP_KEY_ALL;
+
+	if (term->array.nr_ranges) {
+		size_t memsz = term->array.nr_ranges *
+				sizeof(op->k.array.ranges[0]);
+
+		op->k.array.ranges = memdup(term->array.ranges, memsz);
+		if (!op->k.array.ranges) {
+			pr_debug("No enough memory to alloc indices for %s\n",
+				 map_name);
+			return -ENOMEM;
+		}
+		op->key_type = BPF_MAP_KEY_RANGES;
+		op->k.array.nr_ranges = term->array.nr_ranges;
+	}
+	return 0;
+}
+
 static struct bpf_map_op *
-bpf_map_op__alloc(struct bpf_map *map)
+bpf_map_op__alloc(struct bpf_map *map, struct parse_events_term *term)
 {
 	struct bpf_map_op *op;
 	struct bpf_map_priv *priv;
@@ -829,7 +858,12 @@ bpf_map_op__alloc(struct bpf_map *map)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	op->key_type = BPF_MAP_KEY_ALL;
+	err = bpf_map_op_setkey(op, term, map_name);
+	if (err) {
+		free(op);
+		return ERR_PTR(err);
+	}
+
 	list_add_tail(&op->list, &priv->ops_list);
 	return op;
 }
@@ -872,7 +906,7 @@ bpf__obj_config_map_array_value(struct bpf_map *map,
 		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
 	}
 
-	op = bpf_map_op__alloc(map);
+	op = bpf_map_op__alloc(map, term);
 	if (IS_ERR(op))
 		return PTR_ERR(op);
 	op->op_type = BPF_MAP_OP_SET_VALUE;
@@ -933,7 +967,7 @@ bpf__obj_config_map_array_event(struct bpf_map *map,
 		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
 	}
 
-	op = bpf_map_op__alloc(map);
+	op = bpf_map_op__alloc(map, term);
 	if (IS_ERR(op))
 		return PTR_ERR(op);
 
@@ -972,6 +1006,44 @@ struct bpf_obj_config_map_func bpf_obj_config_map_funcs[] = {
 };
 
 static int
+config_map_indices_range_check(struct parse_events_term *term,
+			       struct bpf_map *map,
+			       const char *map_name)
+{
+	struct parse_events_array *array = &term->array;
+	struct bpf_map_def def;
+	unsigned int i;
+	int err;
+
+	if (!array->nr_ranges)
+		return 0;
+	if (!array->ranges) {
+		pr_debug("ERROR: map %s: array->nr_ranges is %d but range array is NULL\n",
+			 map_name, (int)array->nr_ranges);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("ERROR: Unable to get map definition from '%s'\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	for (i = 0; i < array->nr_ranges; i++) {
+		unsigned int start = array->ranges[i].start;
+		size_t length = array->ranges[i].length;
+		unsigned int idx = start + length - 1;
+
+		if (idx >= def.max_entries) {
+			pr_debug("ERROR: index %d too large\n", idx);
+			return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG;
+		}
+	}
+	return 0;
+}
+
+static int
 bpf__obj_config_map(struct bpf_object *obj,
 		    struct parse_events_term *term,
 		    struct perf_evlist *evlist,
@@ -1007,6 +1079,13 @@ bpf__obj_config_map(struct bpf_object *obj,
 	}
 
 	*key_scan_pos += map_opt - map_name;
+
+	*key_scan_pos += strlen(map_opt);
+	err = config_map_indices_range_check(term, map, map_name);
+	if (err)
+		goto out;
+	*key_scan_pos -= strlen(map_opt);
+
 	for (i = 0; i < ARRAY_SIZE(bpf_obj_config_map_funcs); i++) {
 		struct bpf_obj_config_map_func *func =
 				&bpf_obj_config_map_funcs[i];
@@ -1077,6 +1156,33 @@ foreach_key_array_all(map_config_func_t func,
 }
 
 static int
+foreach_key_array_ranges(map_config_func_t func, void *arg,
+			 const char *name, int map_fd,
+			 struct bpf_map_def *pdef,
+			 struct bpf_map_op *op)
+{
+	unsigned int i, j;
+	int err;
+
+	for (i = 0; i < op->k.array.nr_ranges; i++) {
+		unsigned int start = op->k.array.ranges[i].start;
+		size_t length = op->k.array.ranges[i].length;
+
+		for (j = 0; j < length; j++) {
+			unsigned int idx = start + j;
+
+			err = func(name, map_fd, pdef, op, &idx, arg);
+			if (err) {
+				pr_debug("ERROR: failed to insert value to %s[%u]\n",
+					 name, idx);
+				return err;
+			}
+		}
+	}
+	return 0;
+}
+
+static int
 bpf_map_config_foreach_key(struct bpf_map *map,
 			   map_config_func_t func,
 			   void *arg)
@@ -1116,13 +1222,24 @@ bpf_map_config_foreach_key(struct bpf_map *map,
 		case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
 			switch (op->key_type) {
 			case BPF_MAP_KEY_ALL:
-				return foreach_key_array_all(func, arg, name,
-							     map_fd, &def, op);
+				err = foreach_key_array_all(func, arg, name,
+							    map_fd, &def, op);
+				if (err)
+					return err;
+				break;
+			case BPF_MAP_KEY_RANGES:
+				err = foreach_key_array_ranges(func, arg, name,
+							       map_fd, &def,
+							       op);
+				if (err)
+					return err;
+				break;
 			default:
 				pr_debug("ERROR: keytype for map '%s' invalid\n",
 					 name);
 				return -BPF_LOADER_ERRNO__INTERNAL;
-		}
+			}
+			break;
 		default:
 			pr_debug("ERROR: type of '%s' incorrect\n", name);
 			return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
@@ -1309,6 +1426,7 @@ static const char *bpf_loader_strerror_table[NR_ERRNO] = {
 	[ERRCODE_OFFSET(OBJCONF_MAP_EVTDIM)]	= "Event dimension too large",
 	[ERRCODE_OFFSET(OBJCONF_MAP_EVTINH)]	= "Doesn't support inherit event",
 	[ERRCODE_OFFSET(OBJCONF_MAP_EVTTYPE)]	= "Wrong event type for map",
+	[ERRCODE_OFFSET(OBJCONF_MAP_IDX2BIG)]	= "Index too large",
 };
 
 static int
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index c9ce792..30ee519 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -38,6 +38,7 @@ enum bpf_loader_errno {
 	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,	/* Event dimension too large */
 	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,	/* Doesn't support inherit event */
 	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,	/* Wrong event type for map */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG,	/* Index too large */
 	__BPF_LOADER_ERRNO__END,
 };
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 1e0ac77..f229663 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2148,8 +2148,39 @@ void parse_events__free_terms(struct list_head *terms)
 {
 	struct parse_events_term *term, *h;
 
-	list_for_each_entry_safe(term, h, terms, list)
+	list_for_each_entry_safe(term, h, terms, list) {
+		if (term->array.nr_ranges)
+			free(term->array.ranges);
 		free(term);
+	}
+}
+
+int parse_events__merge_arrays(struct parse_events_array *dest,
+			       struct parse_events_array *another)
+{
+	struct parse_events_array new;
+
+	if (!dest || !another)
+		return -EINVAL;
+
+	new.nr_ranges = dest->nr_ranges + another->nr_ranges;
+	new.ranges = malloc(sizeof(new.ranges[0]) * new.nr_ranges);
+	if (!new.ranges)
+		return -ENOMEM;
+
+	memcpy(&new.ranges[0], dest->ranges,
+	       sizeof(new.ranges[0]) * dest->nr_ranges);
+	memcpy(&new.ranges[dest->nr_ranges], another->ranges,
+	       sizeof(new.ranges[0]) * another->nr_ranges);
+	free(dest->ranges);
+	free(another->ranges);
+	*dest = new;
+	return 0;
+}
+
+void parse_events__clear_array(struct parse_events_array *a)
+{
+	free(a->ranges);
 }
 
 void parse_events_evlist_error(struct parse_events_evlist *data,
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 20ad3c2..c34615f 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -71,8 +71,17 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_INHERIT
 };
 
+struct parse_events_array {
+	size_t nr_ranges;
+	struct {
+		unsigned int start;
+		size_t length;
+	} *ranges;
+};
+
 struct parse_events_term {
 	char *config;
+	struct parse_events_array array;
 	union {
 		char *str;
 		u64  num;
@@ -117,6 +126,9 @@ int parse_events_term__sym_hw(struct parse_events_term **term,
 int parse_events_term__clone(struct parse_events_term **new,
 			     struct parse_events_term *term);
 void parse_events__free_terms(struct list_head *terms);
+int parse_events__merge_arrays(struct parse_events_array *dest,
+			       struct parse_events_array *another);
+void parse_events__clear_array(struct parse_events_array *a);
 int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
-- 
1.8.3.4

[PATCH v6 14/16] perf tools: Enable indices setting syntax for BPF maps

[Wang Nan]

This patch introduce a new syntax to perf event parser:

 # perf record -e './test_bpf_map_3.c/maps:channel.value[0,1,2,3...5]=101/' usleep 2

By utilizing the basic facilities in bpf-loader.c which allow setting
different slots in a BPF map separately, the newly introduced syntax
allows perf to control specific elements in a BPF map.

Test result:

 # cat ./test_bpf_map_3.c
 /************************ BEGIN **************************/
 #include <uapi/linux/bpf.h>
 #define SEC(NAME) __attribute__((section(NAME), used))
 struct bpf_map_def {
 	unsigned int type;
 	unsigned int key_size;
 	unsigned int value_size;
 	unsigned int max_entries;
 };
 static void *(*map_lookup_elem)(struct bpf_map_def *, void *) =
 	(void *)BPF_FUNC_map_lookup_elem;
 static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
 	(void *)BPF_FUNC_trace_printk;
 struct bpf_map_def SEC("maps") channel = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(int),
 	.value_size = sizeof(unsigned char),
 	.max_entries = 100,
 };
 SEC("func=hrtimer_nanosleep rqtp->tv_nsec")
 int func(void *ctx, int err, long nsec)
 {
 	char fmt[] = "%ld\n";
 	long usec = nsec * 0x10624dd3 >> 38; // nsec / 1000
 	int key = (int)usec;
 	unsigned char *pval = map_lookup_elem(&channel, &key);

 	if (!pval)
 		return 0;
 	trace_printk(fmt, sizeof(fmt), (unsigned char)*pval);
 	return 0;
 }
 char _license[] SEC("license") = "GPL";
 int _version SEC("version") = LINUX_VERSION_CODE;
 /************************* END ***************************/

Normal case:
 # echo "" > /sys/kernel/debug/tracing/trace
 # ./perf record -e './test_bpf_map_3.c/maps:channel.value[0,1,2,3...5]=101/' usleep 2
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.012 MB perf.data ]
 # cat /sys/kernel/debug/tracing/trace | grep usleep
           usleep-405   [004] d... 2745423.547822: : 101
 # ./perf record -e './test_bpf_map_3.c/maps:channel.value[0...9,20...29]=102,maps:channel.value[10...19]=103/' usleep 3
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.012 MB perf.data ]
 # ./perf record -e './test_bpf_map_3.c/maps:channel.value[0...9,20...29]=102,maps:channel.value[10...19]=103/' usleep 15
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.012 MB perf.data ]
 # cat /sys/kernel/debug/tracing/trace | grep usleep
           usleep-405   [004] d... 2745423.547822: : 101
           usleep-655   [006] d... 2745434.122814: : 102
           usleep-904   [006] d... 2745439.916264: : 103
 # ./perf record -e './test_bpf_map_3.c/maps:channel.value[all]=104/' usleep 99
 # cat /sys/kernel/debug/tracing/trace | grep usleep
           usleep-405   [004] d... 2745423.547822: : 101
           usleep-655   [006] d... 2745434.122814: : 102
           usleep-904   [006] d... 2745439.916264: : 103
           usleep-1537  [003] d... 2745538.053737: : 104

Error case:
 # ./perf record -e './test_bpf_map_3.c/maps:channel.value[10...1000]=104/' usleep 99
 event syntax error: '..annel.value[10...1000]=104/'
                                   \___ Index too large
 Hint:	Valid config terms:
      	maps:[<arraymap>].value<indices>=[value]
      	maps:[<eventmap>].event<indices>=[event]

      	where <indices> is something like [0,3...5] or [all]
      	(add -v to see detail)
 Run 'perf list' for a list of valid events

  Usage: perf record [<options>] [<command>]
     or: perf record [<options>] -- <command> [<options>]

     -e, --event <event>   event selector. use 'perf list' to list available events

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
---
 tools/perf/util/parse-events.c |  5 ++-
 tools/perf/util/parse-events.l | 13 ++++++-
 tools/perf/util/parse-events.y | 85 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 100 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f229663..03d18f4 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -660,9 +660,10 @@ parse_events_config_bpf(struct parse_events_evlist *data,
 						 sizeof(errbuf));
 			data->error->help = strdup(
 "Hint:\tValid config terms:\n"
-"     \tmaps:[<arraymap>].value=[value]\n"
-"     \tmaps:[<eventmap>].event=[event]\n"
+"     \tmaps:[<arraymap>].value<indices>=[value]\n"
+"     \tmaps:[<eventmap>].event<indices>=[event]\n"
 "\n"
+"     \twhere <indices> is something like [0,3...5] or [all]\n"
 "     \t(add -v to see detail)");
 			data->error->str = strdup(errbuf);
 			if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE)
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 4387728..8bb3437 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -9,8 +9,8 @@
 %{
 #include <errno.h>
 #include "../perf.h"
-#include "parse-events-bison.h"
 #include "parse-events.h"
+#include "parse-events-bison.h"
 
 char *parse_events_get_text(yyscan_t yyscanner);
 YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
@@ -111,6 +111,7 @@ do {							\
 %x mem
 %s config
 %x event
+%x array
 
 group		[^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu	[^,{}/]+[/][^/]*[/][^,{}/]*
@@ -176,6 +177,14 @@ modifier_bp	[rwx]{1,3}
 
 }
 
+<array>{
+"]"			{ BEGIN(config); return ']'; }
+{num_dec}		{ return value(yyscanner, 10); }
+{num_hex}		{ return value(yyscanner, 16); }
+,			{ return ','; }
+"\.\.\."		{ return PE_ARRAY_RANGE; }
+}
+
 <config>{
 	/*
 	 * Please update parse_events_formats_error_string any time
@@ -196,6 +205,8 @@ no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
+\[all\]			{ return PE_ARRAY_ALL; }
+"["			{ BEGIN(array); return '['; }
 }
 
 <mem>{
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index c3cbd7a..7e93b9f 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -48,6 +48,7 @@ static inc_group_count(struct list_head *list,
 %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
 %token PE_ERROR
 %token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
+%token PE_ARRAY_ALL PE_ARRAY_RANGE
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
@@ -84,6 +85,9 @@ static inc_group_count(struct list_head *list,
 %type <head> group_def
 %type <head> group
 %type <head> groups
+%type <array> array
+%type <array> array_term
+%type <array> array_terms
 
 %union
 {
@@ -95,6 +99,7 @@ static inc_group_count(struct list_head *list,
 		char *sys;
 		char *event;
 	} tracepoint_name;
+	struct parse_events_array array;
 }
 %%
 
@@ -601,6 +606,86 @@ PE_TERM
 	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
 	$$ = term;
 }
+|
+PE_NAME array '=' PE_NAME
+{
+	struct parse_events_term *term;
+	int i;
+
+	ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, $4, &@1, &@4));
+
+	term->array = $2;
+	$$ = term;
+}
+|
+PE_NAME array '=' PE_VALUE
+{
+	struct parse_events_term *term;
+
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, $4, &@1, &@4));
+	term->array = $2;
+	$$ = term;
+}
+
+array:
+'[' array_terms ']'
+{
+	$$ = $2;
+}
+|
+PE_ARRAY_ALL
+{
+	$$.nr_ranges = 0;
+	$$.ranges = NULL;
+}
+
+array_terms:
+array_terms ',' array_term
+{
+	struct parse_events_array new_array;
+
+	new_array.nr_ranges = $1.nr_ranges + $3.nr_ranges;
+	new_array.ranges = malloc(sizeof(new_array.ranges[0]) *
+				  new_array.nr_ranges);
+	ABORT_ON(!new_array.ranges);
+	memcpy(&new_array.ranges[0], $1.ranges,
+	       $1.nr_ranges * sizeof(new_array.ranges[0]));
+	memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges,
+	       $3.nr_ranges * sizeof(new_array.ranges[0]));
+	free($1.ranges);
+	free($3.ranges);
+	$$ = new_array;
+}
+|
+array_term
+
+array_term:
+PE_VALUE
+{
+	struct parse_events_array array;
+
+	array.nr_ranges = 1;
+	array.ranges = malloc(sizeof(array.ranges[0]));
+	ABORT_ON(!array.ranges);
+	array.ranges[0].start = $1;
+	array.ranges[0].length = 1;
+	$$ = array;
+}
+|
+PE_VALUE PE_ARRAY_RANGE PE_VALUE
+{
+	struct parse_events_array array;
+
+	ABORT_ON($3 < $1);
+	array.nr_ranges = 1;
+	array.ranges = malloc(sizeof(array.ranges[0]));
+	ABORT_ON(!array.ranges);
+	array.ranges[0].start = $1;
+	array.ranges[0].length = $3 - $1 + 1;
+	$$ = array;
+}
 
 sep_dc: ':' |
 
-- 
1.8.3.4

[PATCH v6 15/16] perf tools: Introduce bpf-output event

[Wang Nan]

Commit a43eec304259a6c637f4014a6d4767159b6a3aa3 (bpf: introduce
bpf_perf_event_output() helper) add a helper to enable BPF program
output data to perf ring buffer through a new type of perf event
PERF_COUNT_SW_BPF_OUTPUT. This patch enable perf to create perf
event of that type. Now perf user can use following cmdline to
receive output data from BPF programs:

 # ./perf record -a -e evt=bpf-output/no-inherit/ \
                    -e ./test_bpf_output.c/maps:channel.event=evt/ ls /
 # ./perf script
	perf 12927 [004] 355971.129276:          0 evt=bpf-output/no-inherit/:  ffffffff811ed5f1 sys_write
	perf 12927 [004] 355971.129279:          0 evt=bpf-output/no-inherit/:  ffffffff811ed5f1 sys_write
	...

Test result:
 # cat ./test_bpf_output.c
 /************************ BEGIN **************************/
 #include <uapi/linux/bpf.h>
 struct bpf_map_def {
 	unsigned int type;
 	unsigned int key_size;
 	unsigned int value_size;
 	unsigned int max_entries;
 };

 #define SEC(NAME) __attribute__((section(NAME), used))
 static u64 (*ktime_get_ns)(void) =
 	(void *)BPF_FUNC_ktime_get_ns;
 static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
 	(void *)BPF_FUNC_trace_printk;
 static int (*get_smp_processor_id)(void) =
 	(void *)BPF_FUNC_get_smp_processor_id;
 static int (*perf_event_output)(void *, struct bpf_map_def *, int, void *, unsigned long) =
 	(void *)BPF_FUNC_perf_event_output;

 struct bpf_map_def SEC("maps") channel = {
 	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
 	.key_size = sizeof(int),
 	.value_size = sizeof(u32),
 	.max_entries = __NR_CPUS__,
 };

 SEC("func_write=sys_write")
 int func_write(void *ctx)
 {
 	struct {
 		u64 ktime;
 		int cpuid;
 	} __attribute__((packed)) output_data;
 	char error_data[] = "Error: failed to output: %d\n";

 	output_data.cpuid = get_smp_processor_id();
 	output_data.ktime = ktime_get_ns();
 	int err = perf_event_output(ctx, &channel, get_smp_processor_id(),
 				    &output_data, sizeof(output_data));
 	if (err)
 		trace_printk(error_data, sizeof(error_data), err);
 	return 0;
 }
 char _license[] SEC("license") = "GPL";
 int _version SEC("version") = LINUX_VERSION_CODE;
 /************************ END ***************************/

 # ./perf record -a -e evt=bpf-output/no-inherit/ \
                    -e ./test_bpf_output.c/maps:channel.event=evt/ ls /
 # ./perf script | grep ls
              ls  4085 [000] 2746114.230215: evt=bpf-output/no-inherit/:  ffffffff811ed5f1 sys_write (/lib/modules/4.3.0-rc4+/build/vmlinux)
              ls  4085 [000] 2746114.230244: evt=bpf-output/no-inherit/:  ffffffff811ed5f1 sys_write (/lib/modules/4.3.0-rc4+/build/vmlinux)

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
---
 tools/perf/util/bpf-loader.c   | 5 ++---
 tools/perf/util/evsel.c        | 5 +++++
 tools/perf/util/evsel.h        | 8 ++++++++
 tools/perf/util/parse-events.l | 1 +
 4 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 6c25de8..92b815e 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1312,13 +1312,12 @@ apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
 		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH;
 	}
 
+	if (perf_evsel__is_bpf_output(evsel))
+		check_pass = true;
 	if (attr->type == PERF_TYPE_RAW)
 		check_pass = true;
 	if (attr->type == PERF_TYPE_HARDWARE)
 		check_pass = true;
-	if (attr->type == PERF_TYPE_SOFTWARE &&
-			attr->config == PERF_COUNT_SW_BPF_OUTPUT)
-		check_pass = true;
 	if (!check_pass) {
 		pr_debug("ERROR: Event type is wrong for map %s\n", name);
 		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1911dc8..87bc915 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -225,6 +225,11 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 	if (evsel != NULL)
 		perf_evsel__init(evsel, attr, idx);
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		evsel->attr.sample_type |= PERF_SAMPLE_RAW;
+		evsel->attr.sample_period = 1;
+	}
+
 	return evsel;
 }
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 5f6dd57..235fcc2 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -365,6 +365,14 @@ static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
 #undef FUNCTION_EVENT
 }
 
+static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+
+	return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
+		(attr->type == PERF_TYPE_SOFTWARE);
+}
+
 struct perf_attr_details {
 	bool freq;
 	bool verbose;
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 8bb3437..27d567f 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -249,6 +249,7 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
 	/*
 	 * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
-- 
1.8.3.4

[PATCH v6 16/16] perf data: Support converting data from bpf_perf_event_output()

[Wang Nan]

bpf_perf_event_output() outputs data through sample->raw_data. This
patch adds support to convert those data into CTF. A python script
then can be used to process output data from BPF programs.

Test result:

 # cat ./test_bpf_output_2.c
 /************************ BEGIN **************************/
 #include <uapi/linux/bpf.h>
 struct bpf_map_def {
 	unsigned int type;
 	unsigned int key_size;
 	unsigned int value_size;
 	unsigned int max_entries;
 };
 #define SEC(NAME) __attribute__((section(NAME), used))
 static u64 (*ktime_get_ns)(void) =
 	(void *)BPF_FUNC_ktime_get_ns;
 static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
 	(void *)BPF_FUNC_trace_printk;
 static int (*get_smp_processor_id)(void) =
 	(void *)BPF_FUNC_get_smp_processor_id;
 static int (*perf_event_output)(void *, struct bpf_map_def *, int, void *, unsigned long) =
 	(void *)BPF_FUNC_perf_event_output;

 struct bpf_map_def SEC("maps") channel = {
 	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
 	.key_size = sizeof(int),
 	.value_size = sizeof(u32),
 	.max_entries = __NR_CPUS__,
 };

 static inline int __attribute__((always_inline))
 func(void *ctx, int type)
 {
 	struct {
 		u64 ktime;
 		int type;
 	} __attribute__((packed)) output_data;
 	char error_data[] = "Error: failed to output\n";
 	int err;

 	output_data.type = type;
 	output_data.ktime = ktime_get_ns();
 	err = perf_event_output(ctx, &channel, get_smp_processor_id(),
 				&output_data, sizeof(output_data));
 	if (err)
 		trace_printk(error_data, sizeof(error_data));
 	return 0;
 }
 SEC("func_begin=sys_nanosleep")
 int func_begin(void *ctx) {return func(ctx, 1);}
 SEC("func_end=sys_nanosleep%return")
 int func_end(void *ctx) { return func(ctx, 2);}
 char _license[] SEC("license") = "GPL";
 int _version SEC("version") = LINUX_VERSION_CODE;
 /************************* END ***************************/

 # ./perf record -e evt=bpf-output/no-inherit/ \
                 -e ./test_bpf_output_2.c/maps:channel.event=evt/ \
                 usleep 100000
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.012 MB perf.data (2 samples) ]

 # ./perf script
          usleep 14942 92503.198504: evt=bpf-output/no-inherit/:  ffffffff810e0ba1 sys_nanosleep (/lib/modules/4.3.0....
          usleep 14942 92503.298562: evt=bpf-output/no-inherit/:  ffffffff810585e9 kretprobe_trampoline_holder (/lib....

 # ./perf data convert --to-ctf ./out.ctf
 [ perf data convert: Converted 'perf.data' into CTF data './out.ctf' ]
 [ perf data convert: Converted and wrote 0.000 MB (2 samples) ]

 # babeltrace ./out.ctf
 [01:41:43.198504134] (+?.?????????) evt=bpf-output/no-inherit/: { cpu_id = 0 }, { perf_ip = 0xFFFFFFFF810E0BA1, perf_tid = 14942, perf_pid = 14942, perf_id = 1044, raw_len = 3, raw_data = [ [0] = 0x32C0C07B, [1] = 0x5421, [2] = 0x1 ] }
 [01:41:43.298562257] (+0.100058123) evt=bpf-output/no-inherit/: { cpu_id = 0 }, { perf_ip = 0xFFFFFFFF810585E9, perf_tid = 14942, perf_pid = 14942, perf_id = 1044, raw_len = 3, raw_data = [ [0] = 0x38B77FAA, [1] = 0x5421, [2] = 0x2 ] }

 # cat ./test_bpf_output_2.py
 from babeltrace import TraceCollection
 tc = TraceCollection(
 tc.add_trace('./out.ctf', 'ctf')
 d = {1:[], 2:[]}
 for event in tc.events:
     if not event.name.startswith('evt=bpf-output/no-inherit/'):
         continue
     raw_data = event['raw_data']
     (time, type) = ((raw_data[0] + (raw_data[1] << 32)), raw_data[2])
     d[type].append(time)
 print(list(map(lambda i: d[2][i] - d[1][i], range(len(d[1]))))));

 # python3 ./test_bpf_output_2.py
 [100056879]

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
---
 tools/perf/util/data-convert-bt.c | 112 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 111 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 34cd1e4..62ccf8d 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -352,6 +352,84 @@ static int add_tracepoint_values(struct ctf_writer *cw,
 	return ret;
 }
 
+static int
+add_bpf_output_values(struct bt_ctf_event_class *event_class,
+		      struct bt_ctf_event *event,
+		      struct perf_sample *sample)
+{
+	struct bt_ctf_field_type *len_type, *seq_type;
+	struct bt_ctf_field *len_field, *seq_field;
+	unsigned int raw_size = sample->raw_size;
+	unsigned int nr_elements = raw_size / sizeof(u32);
+	unsigned int i;
+	int ret;
+
+	if (nr_elements * sizeof(u32) != raw_size)
+		pr_warning("Incorrect raw_size (%u) in bpf output event, skip %lu bytes\n",
+			   raw_size, nr_elements * sizeof(u32) - raw_size);
+
+	len_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_len");
+	len_field = bt_ctf_field_create(len_type);
+	if (!len_field) {
+		pr_err("failed to create 'raw_len' for bpf output event\n");
+		ret = -1;
+		goto put_len_type;
+	}
+
+	ret = bt_ctf_field_unsigned_integer_set_value(len_field, nr_elements);
+	if (ret) {
+		pr_err("failed to set field value for raw_len\n");
+		goto put_len_field;
+	}
+	ret = bt_ctf_event_set_payload(event, "raw_len", len_field);
+	if (ret) {
+		pr_err("failed to set payload to raw_len\n");
+		goto put_len_field;
+	}
+
+	seq_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_data");
+	seq_field = bt_ctf_field_create(seq_type);
+	if (!seq_field) {
+		pr_err("failed to create 'raw_data' for bpf output event\n");
+		ret = -1;
+		goto put_seq_type;
+	}
+
+	ret = bt_ctf_field_sequence_set_length(seq_field, len_field);
+	if (ret) {
+		pr_err("failed to set length of 'raw_data'\n");
+		goto put_seq_field;
+	}
+
+	for (i = 0; i < nr_elements; i++) {
+		struct bt_ctf_field *elem_field =
+			bt_ctf_field_sequence_get_field(seq_field, i);
+
+		ret = bt_ctf_field_unsigned_integer_set_value(elem_field,
+				((u32 *)(sample->raw_data))[i]);
+
+		bt_ctf_field_put(elem_field);
+		if (ret) {
+			pr_err("failed to set raw_data[%d]\n", i);
+			goto put_seq_field;
+		}
+	}
+
+	ret = bt_ctf_event_set_payload(event, "raw_data", seq_field);
+	if (ret)
+		pr_err("failed to set payload for raw_data\n");
+
+put_seq_field:
+	bt_ctf_field_put(seq_field);
+put_seq_type:
+	bt_ctf_field_type_put(seq_type);
+put_len_field:
+	bt_ctf_field_put(len_field);
+put_len_type:
+	bt_ctf_field_type_put(len_type);
+	return ret;
+}
+
 static int add_generic_values(struct ctf_writer *cw,
 			      struct bt_ctf_event *event,
 			      struct perf_evsel *evsel,
@@ -597,6 +675,12 @@ static int process_sample_event(struct perf_tool *tool,
 			return -1;
 	}
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		ret = add_bpf_output_values(event_class, event, sample);
+		if (ret)
+			return -1;
+	}
+
 	cs = ctf_stream(cw, get_sample_cpu(cw, sample, evsel));
 	if (cs) {
 		if (is_flush_needed(cs))
@@ -744,6 +828,25 @@ static int add_tracepoint_types(struct ctf_writer *cw,
 	return ret;
 }
 
+static int add_bpf_output_types(struct ctf_writer *cw,
+				struct bt_ctf_event_class *class)
+{
+	struct bt_ctf_field_type *len_type = cw->data.u32;
+	struct bt_ctf_field_type *seq_base_type = cw->data.u32_hex;
+	struct bt_ctf_field_type *seq_type;
+	int ret;
+
+	ret = bt_ctf_event_class_add_field(class, len_type, "raw_len");
+	if (ret)
+		return ret;
+
+	seq_type = bt_ctf_field_type_sequence_create(seq_base_type, "raw_len");
+	if (!seq_type)
+		return -1;
+
+	return bt_ctf_event_class_add_field(class, seq_type, "raw_data");
+}
+
 static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 			     struct bt_ctf_event_class *event_class)
 {
@@ -755,7 +858,8 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 	 *                              ctf event header
 	 *   PERF_SAMPLE_READ         - TODO
 	 *   PERF_SAMPLE_CALLCHAIN    - TODO
-	 *   PERF_SAMPLE_RAW          - tracepoint fields are handled separately
+	 *   PERF_SAMPLE_RAW          - tracepoint fields and BPF output
+	 *                              are handled separately
 	 *   PERF_SAMPLE_BRANCH_STACK - TODO
 	 *   PERF_SAMPLE_REGS_USER    - TODO
 	 *   PERF_SAMPLE_STACK_USER   - TODO
@@ -824,6 +928,12 @@ static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel)
 			goto err;
 	}
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		ret = add_bpf_output_types(cw, event_class);
+		if (ret)
+			goto err;
+	}
+
 	ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class);
 	if (ret) {
 		pr("Failed to add event class into stream.\n");
-- 
1.8.3.4