[PATCH 10/15] perf record: Apply config to BPF objects before recording

[Arnaldo Carvalho de Melo]

From: Wang Nan <wangnan0@xxxxxxxxxx>

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/map: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_1.c/map: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@xxxxxxxxxx>
Tested-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Cc: Alexei Starovoitov <ast@xxxxxxxxxx>
Cc: Brendan Gregg <brendan.d.gregg@xxxxxxxxx>
Cc: Cody P Schafer <dev@xxxxxxxxxx>
Cc: He Kuang <hekuang@xxxxxxxxxx>
Cc: Jeremie Galarneau <jeremie.galarneau@xxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Kirill Smelkov <kirr@xxxxxxxxxx>
Cc: Li Zefan <lizefan@xxxxxxxxxx>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@xxxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Zefan Li <lizefan@xxxxxxxxxx>
Cc: pi3orama@xxxxxxx
Link: http://lkml.kernel.org/r/1456132275-98875-6-git-send-email-wangnan0@xxxxxxxxxx
Signed-off-by: He Kuang <hekuang@xxxxxxxxxx>
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 tools/perf/builtin-record.c  |  11 +++
 tools/perf/util/bpf-loader.c | 184 +++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/bpf-loader.h |  15 ++++
 3 files changed, 210 insertions(+)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index cf3a28d83066..7d11162b6c41 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>
@@ -536,6 +537,16 @@ 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 caeef9ec0124..dbbd17ca6d6f 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"
@@ -994,6 +995,182 @@ 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:
+				err = foreach_key_array_all(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;
+		}
+	}
+
+	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)
@@ -1148,3 +1325,10 @@ 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 cc46a07b1a62..5d3b931f9baa 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
-- 
2.5.0