linux/tools/perf/util/bpf-loader.c
Wang Nan 7630b3e28d perf tools: Enable passing event to BPF object
A new syntax is added to the parser so that the user can access
predefined perf events in BPF objects.

After this patch, BPF programs for perf are finally able to utilize
bpf_perf_event_read() introduced in commit 35578d798400 ("bpf: Implement
function bpf_perf_event_read() that get the selected hardware PMU
counter").

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/map: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/map: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/map:pmu_map.event=evt/' -a
  event syntax error: '..ps:pmu_map.event=evt/'
                                    \___ Event not found for map setting

  Hint:	Valid config terms:
       	map:[<arraymap>].value=[value]
       	map:[<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/map:pmu_map.event=cycles/' -p 2348
  ERROR: Apply config to BPF failed: Cannot set event to BPF map in multi-thread tracing

Error case 4:
  # perf record -e cycles -e './test_bpf_map_2.c/map: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/map: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

Error case 6:
  # perf record -i -e './test_bpf_map_2.c/map:pmu_map.event=123/' ls /
  event syntax error: '.._map.event=123/'
                                    \___ Incorrect value type for map
  [SNIP]

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Cody P Schafer <dev@codyps.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com>
Cc: Kirill Smelkov <kirr@nexedi.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1456132275-98875-7-git-send-email-wangnan0@huawei.com
Signed-off-by: He Kuang <hekuang@huawei.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-22 12:30:50 -03:00

1484 lines
33 KiB
C

/*
* bpf-loader.c
*
* Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
* Copyright (C) 2015 Huawei Inc.
*/
#include <linux/bpf.h>
#include <bpf/libbpf.h>
#include <bpf/bpf.h>
#include <linux/err.h>
#include <linux/string.h>
#include "perf.h"
#include "debug.h"
#include "bpf-loader.h"
#include "bpf-prologue.h"
#include "llvm-utils.h"
#include "probe-event.h"
#include "probe-finder.h" // for MAX_PROBES
#include "llvm-utils.h"
#define DEFINE_PRINT_FN(name, level) \
static int libbpf_##name(const char *fmt, ...) \
{ \
va_list args; \
int ret; \
\
va_start(args, fmt); \
ret = veprintf(level, verbose, pr_fmt(fmt), args);\
va_end(args); \
return ret; \
}
DEFINE_PRINT_FN(warning, 1)
DEFINE_PRINT_FN(info, 1)
DEFINE_PRINT_FN(debug, 1)
struct bpf_prog_priv {
struct perf_probe_event pev;
bool need_prologue;
struct bpf_insn *insns_buf;
int nr_types;
int *type_mapping;
};
static bool libbpf_initialized;
struct bpf_object *
bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
{
struct bpf_object *obj;
if (!libbpf_initialized) {
libbpf_set_print(libbpf_warning,
libbpf_info,
libbpf_debug);
libbpf_initialized = true;
}
obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name);
if (IS_ERR(obj)) {
pr_debug("bpf: failed to load buffer\n");
return ERR_PTR(-EINVAL);
}
return obj;
}
struct bpf_object *bpf__prepare_load(const char *filename, bool source)
{
struct bpf_object *obj;
if (!libbpf_initialized) {
libbpf_set_print(libbpf_warning,
libbpf_info,
libbpf_debug);
libbpf_initialized = true;
}
if (source) {
int err;
void *obj_buf;
size_t obj_buf_sz;
err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz);
if (err)
return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename);
free(obj_buf);
} else
obj = bpf_object__open(filename);
if (IS_ERR(obj)) {
pr_debug("bpf: failed to load %s\n", filename);
return obj;
}
return obj;
}
void bpf__clear(void)
{
struct bpf_object *obj, *tmp;
bpf_object__for_each_safe(obj, tmp) {
bpf__unprobe(obj);
bpf_object__close(obj);
}
}
static void
clear_prog_priv(struct bpf_program *prog __maybe_unused,
void *_priv)
{
struct bpf_prog_priv *priv = _priv;
cleanup_perf_probe_events(&priv->pev, 1);
zfree(&priv->insns_buf);
zfree(&priv->type_mapping);
free(priv);
}
static int
prog_config__exec(const char *value, struct perf_probe_event *pev)
{
pev->uprobes = true;
pev->target = strdup(value);
if (!pev->target)
return -ENOMEM;
return 0;
}
static int
prog_config__module(const char *value, struct perf_probe_event *pev)
{
pev->uprobes = false;
pev->target = strdup(value);
if (!pev->target)
return -ENOMEM;
return 0;
}
static int
prog_config__bool(const char *value, bool *pbool, bool invert)
{
int err;
bool bool_value;
if (!pbool)
return -EINVAL;
err = strtobool(value, &bool_value);
if (err)
return err;
*pbool = invert ? !bool_value : bool_value;
return 0;
}
static int
prog_config__inlines(const char *value,
struct perf_probe_event *pev __maybe_unused)
{
return prog_config__bool(value, &probe_conf.no_inlines, true);
}
static int
prog_config__force(const char *value,
struct perf_probe_event *pev __maybe_unused)
{
return prog_config__bool(value, &probe_conf.force_add, false);
}
static struct {
const char *key;
const char *usage;
const char *desc;
int (*func)(const char *, struct perf_probe_event *);
} bpf_prog_config_terms[] = {
{
.key = "exec",
.usage = "exec=<full path of file>",
.desc = "Set uprobe target",
.func = prog_config__exec,
},
{
.key = "module",
.usage = "module=<module name> ",
.desc = "Set kprobe module",
.func = prog_config__module,
},
{
.key = "inlines",
.usage = "inlines=[yes|no] ",
.desc = "Probe at inline symbol",
.func = prog_config__inlines,
},
{
.key = "force",
.usage = "force=[yes|no] ",
.desc = "Forcibly add events with existing name",
.func = prog_config__force,
},
};
static int
do_prog_config(const char *key, const char *value,
struct perf_probe_event *pev)
{
unsigned int i;
pr_debug("config bpf program: %s=%s\n", key, value);
for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++)
if (strcmp(key, bpf_prog_config_terms[i].key) == 0)
return bpf_prog_config_terms[i].func(value, pev);
pr_debug("BPF: ERROR: invalid program config option: %s=%s\n",
key, value);
pr_debug("\nHint: Valid options are:\n");
for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++)
pr_debug("\t%s:\t%s\n", bpf_prog_config_terms[i].usage,
bpf_prog_config_terms[i].desc);
pr_debug("\n");
return -BPF_LOADER_ERRNO__PROGCONF_TERM;
}
static const char *
parse_prog_config_kvpair(const char *config_str, struct perf_probe_event *pev)
{
char *text = strdup(config_str);
char *sep, *line;
const char *main_str = NULL;
int err = 0;
if (!text) {
pr_debug("No enough memory: dup config_str failed\n");
return ERR_PTR(-ENOMEM);
}
line = text;
while ((sep = strchr(line, ';'))) {
char *equ;
*sep = '\0';
equ = strchr(line, '=');
if (!equ) {
pr_warning("WARNING: invalid config in BPF object: %s\n",
line);
pr_warning("\tShould be 'key=value'.\n");
goto nextline;
}
*equ = '\0';
err = do_prog_config(line, equ + 1, pev);
if (err)
break;
nextline:
line = sep + 1;
}
if (!err)
main_str = config_str + (line - text);
free(text);
return err ? ERR_PTR(err) : main_str;
}
static int
parse_prog_config(const char *config_str, struct perf_probe_event *pev)
{
int err;
const char *main_str = parse_prog_config_kvpair(config_str, pev);
if (IS_ERR(main_str))
return PTR_ERR(main_str);
err = parse_perf_probe_command(main_str, pev);
if (err < 0) {
pr_debug("bpf: '%s' is not a valid config string\n",
config_str);
/* parse failed, don't need clear pev. */
return -BPF_LOADER_ERRNO__CONFIG;
}
return 0;
}
static int
config_bpf_program(struct bpf_program *prog)
{
struct perf_probe_event *pev = NULL;
struct bpf_prog_priv *priv = NULL;
const char *config_str;
int err;
/* Initialize per-program probing setting */
probe_conf.no_inlines = false;
probe_conf.force_add = false;
config_str = bpf_program__title(prog, false);
if (IS_ERR(config_str)) {
pr_debug("bpf: unable to get title for program\n");
return PTR_ERR(config_str);
}
priv = calloc(sizeof(*priv), 1);
if (!priv) {
pr_debug("bpf: failed to alloc priv\n");
return -ENOMEM;
}
pev = &priv->pev;
pr_debug("bpf: config program '%s'\n", config_str);
err = parse_prog_config(config_str, pev);
if (err)
goto errout;
if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
pr_debug("bpf: '%s': group for event is set and not '%s'.\n",
config_str, PERF_BPF_PROBE_GROUP);
err = -BPF_LOADER_ERRNO__GROUP;
goto errout;
} else if (!pev->group)
pev->group = strdup(PERF_BPF_PROBE_GROUP);
if (!pev->group) {
pr_debug("bpf: strdup failed\n");
err = -ENOMEM;
goto errout;
}
if (!pev->event) {
pr_debug("bpf: '%s': event name is missing. Section name should be 'key=value'\n",
config_str);
err = -BPF_LOADER_ERRNO__EVENTNAME;
goto errout;
}
pr_debug("bpf: config '%s' is ok\n", config_str);
err = bpf_program__set_private(prog, priv, clear_prog_priv);
if (err) {
pr_debug("Failed to set priv for program '%s'\n", config_str);
goto errout;
}
return 0;
errout:
if (pev)
clear_perf_probe_event(pev);
free(priv);
return err;
}
static int bpf__prepare_probe(void)
{
static int err = 0;
static bool initialized = false;
/*
* Make err static, so if init failed the first, bpf__prepare_probe()
* fails each time without calling init_probe_symbol_maps multiple
* times.
*/
if (initialized)
return err;
initialized = true;
err = init_probe_symbol_maps(false);
if (err < 0)
pr_debug("Failed to init_probe_symbol_maps\n");
probe_conf.max_probes = MAX_PROBES;
return err;
}
static int
preproc_gen_prologue(struct bpf_program *prog, int n,
struct bpf_insn *orig_insns, int orig_insns_cnt,
struct bpf_prog_prep_result *res)
{
struct probe_trace_event *tev;
struct perf_probe_event *pev;
struct bpf_prog_priv *priv;
struct bpf_insn *buf;
size_t prologue_cnt = 0;
int i, err;
err = bpf_program__get_private(prog, (void **)&priv);
if (err || !priv)
goto errout;
pev = &priv->pev;
if (n < 0 || n >= priv->nr_types)
goto errout;
/* Find a tev belongs to that type */
for (i = 0; i < pev->ntevs; i++) {
if (priv->type_mapping[i] == n)
break;
}
if (i >= pev->ntevs) {
pr_debug("Internal error: prologue type %d not found\n", n);
return -BPF_LOADER_ERRNO__PROLOGUE;
}
tev = &pev->tevs[i];
buf = priv->insns_buf;
err = bpf__gen_prologue(tev->args, tev->nargs,
buf, &prologue_cnt,
BPF_MAXINSNS - orig_insns_cnt);
if (err) {
const char *title;
title = bpf_program__title(prog, false);
if (!title)
title = "[unknown]";
pr_debug("Failed to generate prologue for program %s\n",
title);
return err;
}
memcpy(&buf[prologue_cnt], orig_insns,
sizeof(struct bpf_insn) * orig_insns_cnt);
res->new_insn_ptr = buf;
res->new_insn_cnt = prologue_cnt + orig_insns_cnt;
res->pfd = NULL;
return 0;
errout:
pr_debug("Internal error in preproc_gen_prologue\n");
return -BPF_LOADER_ERRNO__PROLOGUE;
}
/*
* compare_tev_args is reflexive, transitive and antisymmetric.
* I can proof it but this margin is too narrow to contain.
*/
static int compare_tev_args(const void *ptev1, const void *ptev2)
{
int i, ret;
const struct probe_trace_event *tev1 =
*(const struct probe_trace_event **)ptev1;
const struct probe_trace_event *tev2 =
*(const struct probe_trace_event **)ptev2;
ret = tev2->nargs - tev1->nargs;
if (ret)
return ret;
for (i = 0; i < tev1->nargs; i++) {
struct probe_trace_arg *arg1, *arg2;
struct probe_trace_arg_ref *ref1, *ref2;
arg1 = &tev1->args[i];
arg2 = &tev2->args[i];
ret = strcmp(arg1->value, arg2->value);
if (ret)
return ret;
ref1 = arg1->ref;
ref2 = arg2->ref;
while (ref1 && ref2) {
ret = ref2->offset - ref1->offset;
if (ret)
return ret;
ref1 = ref1->next;
ref2 = ref2->next;
}
if (ref1 || ref2)
return ref2 ? 1 : -1;
}
return 0;
}
/*
* Assign a type number to each tevs in a pev.
* mapping is an array with same slots as tevs in that pev.
* nr_types will be set to number of types.
*/
static int map_prologue(struct perf_probe_event *pev, int *mapping,
int *nr_types)
{
int i, type = 0;
struct probe_trace_event **ptevs;
size_t array_sz = sizeof(*ptevs) * pev->ntevs;
ptevs = malloc(array_sz);
if (!ptevs) {
pr_debug("No ehough memory: alloc ptevs failed\n");
return -ENOMEM;
}
pr_debug("In map_prologue, ntevs=%d\n", pev->ntevs);
for (i = 0; i < pev->ntevs; i++)
ptevs[i] = &pev->tevs[i];
qsort(ptevs, pev->ntevs, sizeof(*ptevs),
compare_tev_args);
for (i = 0; i < pev->ntevs; i++) {
int n;
n = ptevs[i] - pev->tevs;
if (i == 0) {
mapping[n] = type;
pr_debug("mapping[%d]=%d\n", n, type);
continue;
}
if (compare_tev_args(ptevs + i, ptevs + i - 1) == 0)
mapping[n] = type;
else
mapping[n] = ++type;
pr_debug("mapping[%d]=%d\n", n, mapping[n]);
}
free(ptevs);
*nr_types = type + 1;
return 0;
}
static int hook_load_preprocessor(struct bpf_program *prog)
{
struct perf_probe_event *pev;
struct bpf_prog_priv *priv;
bool need_prologue = false;
int err, i;
err = bpf_program__get_private(prog, (void **)&priv);
if (err || !priv) {
pr_debug("Internal error when hook preprocessor\n");
return -BPF_LOADER_ERRNO__INTERNAL;
}
pev = &priv->pev;
for (i = 0; i < pev->ntevs; i++) {
struct probe_trace_event *tev = &pev->tevs[i];
if (tev->nargs > 0) {
need_prologue = true;
break;
}
}
/*
* Since all tevs don't have argument, we don't need generate
* prologue.
*/
if (!need_prologue) {
priv->need_prologue = false;
return 0;
}
priv->need_prologue = true;
priv->insns_buf = malloc(sizeof(struct bpf_insn) * BPF_MAXINSNS);
if (!priv->insns_buf) {
pr_debug("No enough memory: alloc insns_buf failed\n");
return -ENOMEM;
}
priv->type_mapping = malloc(sizeof(int) * pev->ntevs);
if (!priv->type_mapping) {
pr_debug("No enough memory: alloc type_mapping failed\n");
return -ENOMEM;
}
memset(priv->type_mapping, -1,
sizeof(int) * pev->ntevs);
err = map_prologue(pev, priv->type_mapping, &priv->nr_types);
if (err)
return err;
err = bpf_program__set_prep(prog, priv->nr_types,
preproc_gen_prologue);
return err;
}
int bpf__probe(struct bpf_object *obj)
{
int err = 0;
struct bpf_program *prog;
struct bpf_prog_priv *priv;
struct perf_probe_event *pev;
err = bpf__prepare_probe();
if (err) {
pr_debug("bpf__prepare_probe failed\n");
return err;
}
bpf_object__for_each_program(prog, obj) {
err = config_bpf_program(prog);
if (err)
goto out;
err = bpf_program__get_private(prog, (void **)&priv);
if (err || !priv)
goto out;
pev = &priv->pev;
err = convert_perf_probe_events(pev, 1);
if (err < 0) {
pr_debug("bpf_probe: failed to convert perf probe events");
goto out;
}
err = apply_perf_probe_events(pev, 1);
if (err < 0) {
pr_debug("bpf_probe: failed to apply perf probe events");
goto out;
}
/*
* After probing, let's consider prologue, which
* adds program fetcher to BPF programs.
*
* hook_load_preprocessorr() hooks pre-processor
* to bpf_program, let it generate prologue
* dynamically during loading.
*/
err = hook_load_preprocessor(prog);
if (err)
goto out;
}
out:
return err < 0 ? err : 0;
}
#define EVENTS_WRITE_BUFSIZE 4096
int bpf__unprobe(struct bpf_object *obj)
{
int err, ret = 0;
struct bpf_program *prog;
struct bpf_prog_priv *priv;
bpf_object__for_each_program(prog, obj) {
int i;
err = bpf_program__get_private(prog, (void **)&priv);
if (err || !priv)
continue;
for (i = 0; i < priv->pev.ntevs; i++) {
struct probe_trace_event *tev = &priv->pev.tevs[i];
char name_buf[EVENTS_WRITE_BUFSIZE];
struct strfilter *delfilter;
snprintf(name_buf, EVENTS_WRITE_BUFSIZE,
"%s:%s", tev->group, tev->event);
name_buf[EVENTS_WRITE_BUFSIZE - 1] = '\0';
delfilter = strfilter__new(name_buf, NULL);
if (!delfilter) {
pr_debug("Failed to create filter for unprobing\n");
ret = -ENOMEM;
continue;
}
err = del_perf_probe_events(delfilter);
strfilter__delete(delfilter);
if (err) {
pr_debug("Failed to delete %s\n", name_buf);
ret = err;
continue;
}
}
}
return ret;
}
int bpf__load(struct bpf_object *obj)
{
int err;
err = bpf_object__load(obj);
if (err) {
pr_debug("bpf: load objects failed\n");
return err;
}
return 0;
}
int bpf__foreach_tev(struct bpf_object *obj,
bpf_prog_iter_callback_t func,
void *arg)
{
struct bpf_program *prog;
int err;
bpf_object__for_each_program(prog, obj) {
struct probe_trace_event *tev;
struct perf_probe_event *pev;
struct bpf_prog_priv *priv;
int i, fd;
err = bpf_program__get_private(prog,
(void **)&priv);
if (err || !priv) {
pr_debug("bpf: failed to get private field\n");
return -BPF_LOADER_ERRNO__INTERNAL;
}
pev = &priv->pev;
for (i = 0; i < pev->ntevs; i++) {
tev = &pev->tevs[i];
if (priv->need_prologue) {
int type = priv->type_mapping[i];
fd = bpf_program__nth_fd(prog, type);
} else {
fd = bpf_program__fd(prog);
}
if (fd < 0) {
pr_debug("bpf: failed to get file descriptor\n");
return fd;
}
err = (*func)(tev, fd, arg);
if (err) {
pr_debug("bpf: call back failed, stop iterate\n");
return err;
}
}
}
return 0;
}
enum bpf_map_op_type {
BPF_MAP_OP_SET_VALUE,
BPF_MAP_OP_SET_EVSEL,
};
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;
struct perf_evsel *evsel;
} v;
};
struct bpf_map_priv {
struct list_head ops_list;
};
static void
bpf_map_op__delete(struct bpf_map_op *op)
{
if (!list_empty(&op->list))
list_del(&op->list);
free(op);
}
static void
bpf_map_priv__purge(struct bpf_map_priv *priv)
{
struct bpf_map_op *pos, *n;
list_for_each_entry_safe(pos, n, &priv->ops_list, list) {
list_del_init(&pos->list);
bpf_map_op__delete(pos);
}
}
static void
bpf_map_priv__clear(struct bpf_map *map __maybe_unused,
void *_priv)
{
struct bpf_map_priv *priv = _priv;
bpf_map_priv__purge(priv);
free(priv);
}
static struct bpf_map_op *
bpf_map_op__new(void)
{
struct bpf_map_op *op;
op = zalloc(sizeof(*op));
if (!op) {
pr_debug("Failed to alloc bpf_map_op\n");
return ERR_PTR(-ENOMEM);
}
INIT_LIST_HEAD(&op->list);
op->key_type = BPF_MAP_KEY_ALL;
return op;
}
static int
bpf_map__add_op(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;
}
if (!priv) {
priv = zalloc(sizeof(*priv));
if (!priv) {
pr_debug("No enough memory to alloc map private\n");
return -ENOMEM;
}
INIT_LIST_HEAD(&priv->ops_list);
if (bpf_map__set_private(map, priv, bpf_map_priv__clear)) {
free(priv);
return -BPF_LOADER_ERRNO__INTERNAL;
}
}
list_add_tail(&op->list, &priv->ops_list);
return 0;
}
static struct bpf_map_op *
bpf_map__add_newop(struct bpf_map *map)
{
struct bpf_map_op *op;
int err;
op = bpf_map_op__new();
if (IS_ERR(op))
return op;
err = bpf_map__add_op(map, op);
if (err) {
bpf_map_op__delete(op);
return ERR_PTR(err);
}
return op;
}
static int
__bpf_map__config_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__add_newop(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_map__config_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) {
pr_debug("ERROR: wrong value type for 'value'\n");
return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
}
return __bpf_map__config_value(map, term);
}
static int
__bpf_map__config_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__add_newop(map);
if (IS_ERR(op))
return PTR_ERR(op);
op->op_type = BPF_MAP_OP_SET_EVSEL;
op->v.evsel = evsel;
return 0;
}
static int
bpf_map__config_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) {
pr_debug("ERROR: wrong value type for 'event'\n");
return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
}
return __bpf_map__config_event(map, term, evlist);
}
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_map__config_value},
{"event", bpf_map__config_event},
};
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 "map:<mapname>.<config opt>" */
char *map_name = strdup(term->config + sizeof("map:") - 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 doesn't 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 map config option '%s'\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, "map:")) {
key_scan_pos = sizeof("map:") - 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;
}
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:
case BPF_MAP_TYPE_PERF_EVENT_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_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,
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;
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;
}
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)
static const char *bpf_loader_strerror_table[NR_ERRNO] = {
[ERRCODE_OFFSET(CONFIG)] = "Invalid config string",
[ERRCODE_OFFSET(GROUP)] = "Invalid group name",
[ERRCODE_OFFSET(EVENTNAME)] = "No event name found in config string",
[ERRCODE_OFFSET(INTERNAL)] = "BPF loader internal error",
[ERRCODE_OFFSET(COMPILE)] = "Error when compiling BPF scriptlet",
[ERRCODE_OFFSET(PROGCONF_TERM)] = "Invalid program config term in config string",
[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 (missing '=')",
[ERRCODE_OFFSET(OBJCONF_MAP_OPT)] = "Invalid object map config option",
[ERRCODE_OFFSET(OBJCONF_MAP_NOTEXIST)] = "Target map doesn't 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",
[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
bpf_loader_strerror(int err, char *buf, size_t size)
{
char sbuf[STRERR_BUFSIZE];
const char *msg;
if (!buf || !size)
return -1;
err = err > 0 ? err : -err;
if (err >= __LIBBPF_ERRNO__START)
return libbpf_strerror(err, buf, size);
if (err >= __BPF_LOADER_ERRNO__START && err < __BPF_LOADER_ERRNO__END) {
msg = bpf_loader_strerror_table[ERRNO_OFFSET(err)];
snprintf(buf, size, "%s", msg);
buf[size - 1] = '\0';
return 0;
}
if (err >= __BPF_LOADER_ERRNO__END)
snprintf(buf, size, "Unknown bpf loader error %d", err);
else
snprintf(buf, size, "%s",
strerror_r(err, sbuf, sizeof(sbuf)));
buf[size - 1] = '\0';
return -1;
}
#define bpf__strerror_head(err, buf, size) \
char sbuf[STRERR_BUFSIZE], *emsg;\
if (!size)\
return 0;\
if (err < 0)\
err = -err;\
bpf_loader_strerror(err, sbuf, sizeof(sbuf));\
emsg = sbuf;\
switch (err) {\
default:\
scnprintf(buf, size, "%s", emsg);\
break;
#define bpf__strerror_entry(val, fmt...)\
case val: {\
scnprintf(buf, size, fmt);\
break;\
}
#define bpf__strerror_end(buf, size)\
}\
buf[size - 1] = '\0';
int bpf__strerror_prepare_load(const char *filename, bool source,
int err, char *buf, size_t size)
{
size_t n;
int ret;
n = snprintf(buf, size, "Failed to load %s%s: ",
filename, source ? " from source" : "");
if (n >= size) {
buf[size - 1] = '\0';
return 0;
}
buf += n;
size -= n;
ret = bpf_loader_strerror(err, buf, size);
buf[size - 1] = '\0';
return ret;
}
int bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
int err, char *buf, size_t size)
{
bpf__strerror_head(err, buf, size);
case BPF_LOADER_ERRNO__PROGCONF_TERM: {
scnprintf(buf, size, "%s (add -v to see detail)", emsg);
break;
}
bpf__strerror_entry(EEXIST, "Probe point exist. Try 'perf probe -d \"*\"' and set 'force=yes'");
bpf__strerror_entry(EACCES, "You need to be root");
bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0");
bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file");
bpf__strerror_end(buf, size);
return 0;
}
int bpf__strerror_load(struct bpf_object *obj,
int err, char *buf, size_t size)
{
bpf__strerror_head(err, buf, size);
case LIBBPF_ERRNO__KVER: {
unsigned int obj_kver = bpf_object__get_kversion(obj);
unsigned int real_kver;
if (fetch_kernel_version(&real_kver, NULL, 0)) {
scnprintf(buf, size, "Unable to fetch kernel version");
break;
}
if (obj_kver != real_kver) {
scnprintf(buf, size,
"'version' ("KVER_FMT") doesn't match running kernel ("KVER_FMT")",
KVER_PARAM(obj_kver),
KVER_PARAM(real_kver));
break;
}
scnprintf(buf, size, "Failed to load program for unknown reason");
break;
}
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 with this map type");
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_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,
"Cannot set event to BPF map 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;
}