Skip to content

L
linux
Switch branch/tag
  1. 24 Feb, 2016 26 commits
  3. 23 Feb, 2016 11 commits
  5. 22 Feb, 2016 3 commits
    • Wang Nan's avatar
      perf tools: Introduce bpf-output event · 03e0a7df
      Wang Nan authored 
      Commit a43eec30 ("bpf: introduce bpf_perf_event_output() helper")
adds a helper to enable a BPF program to output data to a perf ring
buffer through a new type of perf event, PERF_COUNT_SW_BPF_OUTPUT. This
patch enables perf to create events of that type. Now a perf user can
use the following cmdline to receive output data from BPF programs:

  # perf record -a -e bpf-output/no-inherit,name=evt/ \
                    -e ./test_bpf_output.c/map:channel.event=evt/ ls /
  # perf script
     perf 1560 [004] 347747.086295:  evt: ffffffff811fd201 sys_write ...
     perf 1560 [004] 347747.086300:  evt: ffffffff811fd201 sys_write ...
     perf 1560 [004] 347747.086315:  evt: ffffffff811fd201 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 bpf-output/no-inherit,name=evt/ \
                    -e ./test_bpf_output.c/map:channel.event=evt/ ls /
  # perf script | grep ls
     ls  2242 [003] 347851.557563:   evt: ffffffff811fd201 sys_write ...
     ls  2242 [003] 347851.557571:   evt: ffffffff811fd201 sys_write ...
Signed-off-by: default avatarWang Nan <wangnan0@huawei.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: Jiri Olsa <jolsa@kernel.org>
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/1456132275-98875-11-git-send-email-wangnan0@huawei.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      03e0a7df
    • Wang Nan's avatar
      perf tools: Apply tracepoint event definition options to BPF script · 95088a59
      Wang Nan authored 
      Users can pass options to tracepoints defined in the BPF script.  For
example:

  # perf record -e ./test.c/no-inherit/ bash
  # dd if=/dev/zero of=/dev/null count=10000
  # exit
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.022 MB perf.data (139 samples) ]

  (no-inherit works, only the sys_read issued by bash are captured, at
   least 10000 sys_read issued by dd are skipped.)

test.c:

  #define SEC(NAME) __attribute__((section(NAME), used))
  SEC("func=sys_read")
  int bpf_func__sys_read(void *ctx)
  {
      return 1;
  }
  char _license[] SEC("license") = "GPL";
  int _version SEC("version") = LINUX_VERSION_CODE;

no-inherit is applied to the kprobe event defined in test.c.
Signed-off-by: default avatarWang Nan <wangnan0@huawei.com>
Tested-by: default avatarArnaldo 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: Jiri Olsa <jolsa@kernel.org>
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/1456132275-98875-10-git-send-email-wangnan0@huawei.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      95088a59
    • Wang Nan's avatar
      perf tools: Enable indices setting syntax for BPF map · e571e029
      Wang Nan authored 
      This patch introduces a new syntax to perf event parser:

 # perf record -e './test_bpf_map_3.c/map: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/map: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/map:channel.value[0...9,20...29]=102,map: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/map:channel.value[0...9,20...29]=102,map: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/map: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/map:channel.value[10...1000]=104/' usleep 99
  event syntax error: '..annel.value[10...1000]=104/'
                                   \___ Index too large
  Hint:	Valid config terms:
      	map:[<arraymap>].value<indices>=[value]
      	map:[<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: default avatarWang Nan <wangnan0@huawei.com>
Acked-by: default avatarJiri Olsa <jolsa@kernel.org>
Tested-by: default avatarArnaldo 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/1456132275-98875-9-git-send-email-wangnan0@huawei.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      e571e029
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7