korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-12-15 23:14:31 +08:00
Code Issues Packages Projects Releases Wiki Activity
783,753 Commits 113 Branches 5,294 Tags 3.6 GiB
91ae08a265
Commit Graph

8 Commits

Author SHA1 Message Date
Arnaldo Carvalho de Melo
e0b6d2ef32 perf trace: Handle "bpf-output" events associated with "__augmented_syscalls__" BPF map 
Add an example BPF script that writes syscalls:sys_enter_openat raw
tracepoint payloads augmented with the first 64 bytes of the "filename"
syscall pointer arg.

Then catch it and print it just like with things written to the
"__bpf_stdout__" map associated with a PERF_COUNT_SW_BPF_OUTPUT software
event, by just letting the default tracepoint handler in 'perf trace',
trace__event_handler(), to use bpf_output__fprintf(trace, sample), just
like it does with all other PERF_COUNT_SW_BPF_OUTPUT events, i.e. just
do a dump on the payload, so that we can check if what is being printed
has at least the first 64 bytes of the "filename" arg:

The augmented_syscalls.c eBPF script:

  # cat tools/perf/examples/bpf/augmented_syscalls.c
  // SPDX-License-Identifier: GPL-2.0

  #include <stdio.h>

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

  struct syscall_enter_openat_args {
	unsigned long long common_tp_fields;
	long		   syscall_nr;
	long		   dfd;
	char		   *filename_ptr;
	long		   flags;
	long		   mode;
  };

  struct augmented_enter_openat_args {
	struct syscall_enter_openat_args args;
	char				 filename[64];
  };

  int syscall_enter(openat)(struct syscall_enter_openat_args *args)
  {
	struct augmented_enter_openat_args augmented_args;

	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
	probe_read_str(&augmented_args.filename, sizeof(augmented_args.filename), args->filename_ptr);
	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
			  &augmented_args, sizeof(augmented_args));
	return 1;
  }

  license(GPL);
  #

So it will just prepare a raw_syscalls:sys_enter payload for the
"openat" syscall.

This will eventually be done for all syscalls with pointer args,
globally or just when the user asks, using some spec, which args of
which syscalls it wants "expanded" this way, we'll probably start with
just all the syscalls that have char * pointers with familiar names, the
ones we already handle with the probe:vfs_getname kprobe if it is in
place hooking the kernel getname_flags() function used to copy from user
the paths.

Running it we get:

  # perf trace -e perf/tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
     0.000 (         ): __augmented_syscalls__:X?.C......................`\..................../etc/ld.so.cache..#......,....ao.k...............k......1.".........
     0.006 (         ): syscalls:sys_enter_openat:dfd: CWD, filename: 0x5c600da8, flags: CLOEXEC
     0.008 ( 0.005 ms): cat/31292 openat(dfd: CWD, filename: 0x5c600da8, flags: CLOEXEC                 ) = 3
     0.036 (         ): __augmented_syscalls__:X?.C.......................\..................../lib64/libc.so.6......... .\....#........?.......=.C..../.".........
     0.037 (         ): syscalls:sys_enter_openat:dfd: CWD, filename: 0x5c808ce0, flags: CLOEXEC
     0.039 ( 0.007 ms): cat/31292 openat(dfd: CWD, filename: 0x5c808ce0, flags: CLOEXEC                 ) = 3
     0.323 (         ): __augmented_syscalls__:X?.C.....................P....................../etc/passwd......>.C....@................>.C.....,....ao.>.C........
     0.325 (         ): syscalls:sys_enter_openat:dfd: CWD, filename: 0xe8be50d6
     0.327 ( 0.004 ms): cat/31292 openat(dfd: CWD, filename: 0xe8be50d6                                 ) = 3
  #

We need to go on optimizing this to avoid seding trash or zeroes in the
pointer content payload, using the return from bpf_probe_read_str(), but
to keep things simple at this stage and make incremental progress, lets
leave it at that for now.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-g360n1zbj6bkbk6q0qo11c28@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 2018-08-08 15:55:57 -03:00
Arnaldo Carvalho de Melo
53a5d7b800 perf bpf: Add bpf/stdio.h wrapper to bpf_perf_event_output function 
That, together with the map __bpf_output__ that is already handled by
'perf trace' to print that event's contents as strings provides a
debugging facility, to show it in use, print a simple string everytime
the syscalls:sys_enter_openat() syscall tracepoint is hit:

  # cat tools/perf/examples/bpf/hello.c
  #include <stdio.h>

  int syscall_enter(openat)(void *args)
  {
	  puts("Hello, world\n");
	  return 0;
  }

  license(GPL);
  #
  # perf trace -e openat,tools/perf/examples/bpf/hello.c cat /etc/passwd > /dev/null
     0.016 (         ): __bpf_stdout__:Hello, world
     0.018 ( 0.010 ms): cat/9079 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
     0.057 (         ): __bpf_stdout__:Hello, world
     0.059 ( 0.011 ms): cat/9079 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
     0.417 (         ): __bpf_stdout__:Hello, world
     0.419 ( 0.009 ms): cat/9079 openat(dfd: CWD, filename: /etc/passwd) = 3
  #

This is part of an ongoing experimentation on making eBPF scripts as
consumed by perf to be as concise as possible and using familiar
concepts such as stdio.h functions, that end up just wrapping the
existing BPF functions, trying to hide as much boilerplate as possible
while using just conventions and C preprocessor tricks.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-4tiaqlx5crf0fwpe7a6j84x7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 2018-08-08 15:55:55 -03:00
Arnaldo Carvalho de Melo
dda9ac966d perf bpf: Add 'syscall_enter' probe helper for syscall enter tracepoints 
Allowing one to hook into the syscalls:sys_enter_NAME tracepoints,
an example is provided that hooks into the 'openat' syscall.

Using it with the probe:vfs_getname probe into getname_flags to get the
filename args as it is copied from userspace:

  # perf probe -l
  probe:vfs_getname    (on getname_flags:73@acme/git/linux/fs/namei.c with pathname)
  # perf trace -e probe:*getname,tools/perf/examples/bpf/sys_enter_openat.c cat /etc/passwd > /dev/null
     0.000 probe:vfs_getname:(ffffffffbd2a8983) pathname="/etc/ld.so.preload"
     0.022 syscalls:sys_enter_openat:dfd: CWD, filename: 0xafbe8da8, flags: CLOEXEC
     0.027 probe:vfs_getname:(ffffffffbd2a8983) pathname="/etc/ld.so.cache"
     0.054 syscalls:sys_enter_openat:dfd: CWD, filename: 0xafdf0ce0, flags: CLOEXEC
     0.057 probe:vfs_getname:(ffffffffbd2a8983) pathname="/lib64/libc.so.6"
     0.316 probe:vfs_getname:(ffffffffbd2a8983) pathname="/usr/lib/locale/locale-archive"
     0.375 syscalls:sys_enter_openat:dfd: CWD, filename: 0xe2b2b0b4
     0.379 probe:vfs_getname:(ffffffffbd2a8983) pathname="/etc/passwd"
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2po9jcqv1qgj0koxlg8kkg30@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 2018-08-08 15:55:44 -03:00
Arnaldo Carvalho de Melo
d8fc764d0b perf bpf: Add probe() helper to reduce kprobes boilerplate 
So that kprobe definitions become:

  int probe(function, variables)(void *ctx, int err, var1, var2, ...)

The existing 5sec.c, got converted and goes from:

  SEC("func=hrtimer_nanosleep rqtp->tv_sec")
  int func(void *ctx, int err, long sec)
  {
  }

To:

  int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
  {
  }

If we decide to add tv_nsec as well, then it becomes:

  $ cat tools/perf/examples/bpf/5sec.c
  #include <bpf.h>

  int probe(hrtimer_nanosleep, rqtp->tv_sec rqtp->tv_nsec)(void *ctx, int err, long sec, long nsec)
  {
	  return sec == 5;
  }

  license(GPL);
  $

And if we run it, system wide as before and run some 'sleep' with values
for the tv_nsec field, we get:

  # perf trace --no-syscalls -e tools/perf/examples/bpf/5sec.c
     0.000 perf_bpf_probe:hrtimer_nanosleep:(ffffffff9811b5f0) tv_sec=5 tv_nsec=100000000
  9641.650 perf_bpf_probe:hrtimer_nanosleep:(ffffffff9811b5f0) tv_sec=5 tv_nsec=123450001
  ^C#

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-1v9r8f6ds5av0w9pcwpeknyl@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 2018-05-15 14:31:24 -03:00
Arnaldo Carvalho de Melo
1f477305ab perf bpf: Add license(NAME) helper 
To further reduce boilerplate.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-vst6hj335s0ebxzqltes3nsc@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 2018-05-15 14:31:24 -03:00
Arnaldo Carvalho de Melo
7542b767b0 perf bpf: Add kprobe example to catch 5s naps 
Description:

. Disable strace like syscall tracing (--no-syscalls), or try tracing
  just some (-e *sleep).

. Attach a filter function to a kernel function, returning when it should
  be considered, i.e. appear on the output:

  $ cat tools/perf/examples/bpf/5sec.c
  #include <bpf.h>

  SEC("func=hrtimer_nanosleep rqtp->tv_sec")
  int func(void *ctx, int err, long sec)
  {
	  return sec == 5;
  }

  char _license[] SEC("license") = "GPL";
  int _version SEC("version") = LINUX_VERSION_CODE;
  $

. Run it system wide, so that any sleep of >= 5 seconds and < than 6
  seconds gets caught.

. Ask for callgraphs using DWARF info, so that userspace can be unwound

. While this is running, run something like "sleep 5s".

  # perf trace --no-syscalls -e tools/perf/examples/bpf/5sec.c/call-graph=dwarf/
     0.000 perf_bpf_probe:func:(ffffffff9811b5f0) tv_sec=5
                                       hrtimer_nanosleep ([kernel.kallsyms])
                                       __x64_sys_nanosleep ([kernel.kallsyms])
                                       do_syscall_64 ([kernel.kallsyms])
                                       entry_SYSCALL_64 ([kernel.kallsyms])
                                       __GI___nanosleep (/usr/lib64/libc-2.26.so)
                                       rpl_nanosleep (/usr/bin/sleep)
                                       xnanosleep (/usr/bin/sleep)
                                       main (/usr/bin/sleep)
                                       __libc_start_main (/usr/lib64/libc-2.26.so)
                                       _start (/usr/bin/sleep)
  ^C#

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2nmxth2l2h09f9gy85lyexcq@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 2018-05-15 14:31:24 -03:00
Arnaldo Carvalho de Melo
dd8e4ead6e perf bpf: Add bpf.h to be used in eBPF proggies 
So, the first helper is the one shortening a variable/function section
attribute, from, for instance:

  char _license[] __attribute__((section("license"), used)) = "GPL";

to:

  char _license[] SEC("license") = "GPL";

Convert empty.c to that and it becomes:

  # cat ~acme/lib/examples/perf/bpf/empty.c
  #include <bpf.h>

  char _license[] SEC("license") = "GPL";
  int _version SEC("version") = LINUX_VERSION_CODE;
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-zmeg52dlvy51rdlhyumfl5yf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 2018-05-15 14:31:23 -03:00
Arnaldo Carvalho de Melo
8f12a2ff00 perf bpf: Add 'examples' directories 
The first one is the bare minimum that bpf infrastructure accepts before
it expects actual events to be set up:

  $ cat tools/perf/examples/bpf/empty.c
  char _license[] __attribute__((section("license"), used)) = "GPL";
  int _version __attribute__((section("version"), used)) = LINUX_VERSION_CODE;
  $

If you remove that "version" line, then it will be refused with:

  # perf trace -e tools/perf/examples/bpf/empty.c
  event syntax error: 'tools/perf/examples/bpf/empty.c'
                       \___ Failed to load tools/perf/examples/bpf/empty.c from source: 'version' section incorrect or lost

  (add -v to see detail)
  Run 'perf list' for a list of valid events

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

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

The next ones will, step by step, show simple filters, then the needs
for headers will be made clear, it will be put in place and tested with
new examples, rinse, repeat.

Back to using this first one to test the perf+bpf infrastructure:

If we run it will fail, as no functions are present connecting with,
say, a tracepoint or a function using the kprobes or uprobes
infrastructure:

  # perf trace -e tools/perf/examples/bpf/empty.c
  WARNING: event parser found nothing
  invalid or unsupported event: 'tools/perf/examples/bpf/empty.c'
  Run 'perf list' for a list of valid events

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

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

But, if we set things up to dump the generated object file to a file,
and do this after having run 'make install', still on the developer's
$HOME directory:

  # cat ~/.perfconfig
  [llvm]

	dump-obj = true
  #
  # perf trace -e ~acme/lib/examples/perf/bpf/empty.c
  LLVM: dumping /home/acme/lib/examples/perf/bpf/empty.o
  WARNING: event parser found nothing
  invalid or unsupported event: '/home/acme/lib/examples/perf/bpf/empty.c'
  <SNIP>
  #

We can look at the dumped object file:

  # ls -la ~acme/lib/examples/perf/bpf/empty.o
  -rw-r--r--. 1 root root 576 May  4 12:10 /home/acme/lib/examples/perf/bpf/empty.o
  # file ~acme/lib/examples/perf/bpf/empty.o
  /home/acme/lib/examples/perf/bpf/empty.o: ELF 64-bit LSB relocatable, *unknown arch 0xf7* version 1 (SYSV), not stripped
  # readelf -sw ~acme/lib/examples/perf/bpf/empty.o

  Symbol table '.symtab' contains 3 entries:
     Num:    Value          Size Type    Bind   Vis      Ndx Name
       0: 0000000000000000     0 NOTYPE  LOCAL  DEFAULT  UND
       1: 0000000000000000     0 NOTYPE  GLOBAL DEFAULT    3 _license
       2: 0000000000000000     0 NOTYPE  GLOBAL DEFAULT    4 _version
  #
  # tools/bpf/bpftool/bpftool --pretty ~acme/lib/examples/perf/bpf/empty.o
  null
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-y7dkhakejz3013o0w21n98xd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 2018-05-15 14:31:23 -03:00