[tip:perf/urgent] perf trace: Handle "bpf-output" events associated with "__augmented_syscalls__" BPF map

[tip-bot for Arnaldo Carvalho de Melo]

Commit-ID:  e0b6d2ef329098bd9780ec00a75db3b11922031a
Gitweb:     https://git.kernel.org/tip/e0b6d2ef329098bd9780ec00a75db3b11922031a
Author:     Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
AuthorDate: Tue, 7 Aug 2018 15:40:13 -0300
Committer:  Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
CommitDate: Wed, 8 Aug 2018 15:55:57 -0300

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@xxxxxxxxx>
Cc: David Ahern <dsahern@xxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Wang Nan <wangnan0@xxxxxxxxxx>
Link: https://lkml.kernel.org/n/tip-g360n1zbj6bkbk6q0qo11c28@xxxxxxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 tools/perf/builtin-trace.c                   |  7 ++++
 tools/perf/examples/bpf/augmented_syscalls.c | 55 ++++++++++++++++++++++++++++
 2 files changed, 62 insertions(+)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 7232a7302580..9b4e24217c46 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3240,6 +3240,13 @@ int cmd_trace(int argc, const char **argv)
 				       "cgroup monitoring only available in system-wide mode");
 	}
 
+	err = bpf__setup_output_event(trace.evlist, "__augmented_syscalls__");
+	if (err) {
+		bpf__strerror_setup_output_event(trace.evlist, err, bf, sizeof(bf));
+		pr_err("ERROR: Setup trace syscalls enter failed: %s\n", bf);
+		goto out;
+	}
+
 	err = bpf__setup_stdout(trace.evlist);
 	if (err) {
 		bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf));
diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
new file mode 100644
index 000000000000..69a31386d8cd
--- /dev/null
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Augment the openat syscall with the contents of the filename pointer argument.
+ *
+ * Test it with:
+ *
+ * perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
+ *
+ * It'll catch some openat syscalls related to the dynamic linked and
+ * the last one should be the one for '/etc/passwd'.
+ *
+ * This matches what is marshalled into the raw_syscall:sys_enter payload
+ * expected by the 'perf trace' beautifiers, and can be used by them unmodified,
+ * which will be done as that feature is implemented in the next csets, for now
+ * it will appear in a dump done by the default tracepoint handler in 'perf trace',
+ * that uses bpf_output__fprintf() to just dump those contents, as done with
+ * the bpf-output event associated with the __bpf_output__ map declared in
+ * tools/perf/include/bpf/stdio.h.
+ */
+
+#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);