linux-kernel - [PATCH 04/18] perf trace: Fix setting of augmented payload when using eBPF + raw

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20181106120612.8262-5-acme@kernel.org>
Date:   Tue,  6 Nov 2018 09:05:58 -0300
From:   Arnaldo Carvalho de Melo <acme@...nel.org>
To:     Ingo Molnar <mingo@...nel.org>
Cc:     Clark Williams <williams@...hat.com>, linux-kernel@...r.kernel.org,
        linux-perf-users@...r.kernel.org,
        Arnaldo Carvalho de Melo <acme@...hat.com>,
        Adrian Hunter <adrian.hunter@...el.com>,
        David Ahern <dsahern@...il.com>, Jiri Olsa <jolsa@...nel.org>,
        Namhyung Kim <namhyung@...nel.org>,
        Wang Nan <wangnan0@...wei.com>
Subject: [PATCH 04/18] perf trace: Fix setting of augmented payload when using eBPF + raw_syscalls

From: Arnaldo Carvalho de Melo <acme@...hat.com>

For now with BPF raw_augmented we hook into raw_syscalls:sys_enter and
there we get all 6 syscall args plus the tracepoint common fields
(sizeof(long)) and the syscall_nr (another long). So we check if that is
the case and if so don't look after the sc->args_size, but always after
the full raw_syscalls:sys_enter payload, which is fixed.

We'll revisit this later to pass s->args_size to the BPF augmenter (now
tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it copies only
what we need for each syscall, like what happens when we use
syscalls:sys_enter_NAME, so that we reduce the kernel/userspace traffic
to just what is needed for each syscall.

Cc: Adrian Hunter <adrian.hunter@...el.com>
Cc: David Ahern <dsahern@...il.com>
Cc: Jiri Olsa <jolsa@...nel.org>
Cc: Namhyung Kim <namhyung@...nel.org>
Cc: Wang Nan <wangnan0@...wei.com>
Link: https://lkml.kernel.org/n/tip-nlslrg8apxdsobt4pwl3n7ur@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@...hat.com>
---
 tools/perf/builtin-trace.c | 37 ++++++++++++++++++++++++++++++-------
 1 file changed, 30 insertions(+), 7 deletions(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f582ca575883..835619476370 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -108,6 +108,7 @@ struct trace {
 	} stats;
 	unsigned int		max_stack;
 	unsigned int		min_stack;
+	bool			raw_augmented_syscalls;
 	bool			not_ev_qualifier;
 	bool			live;
 	bool			full_time;
@@ -1724,13 +1725,28 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
 	return printed;
 }
 
-static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size)
+static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, bool raw_augmented)
 {
 	void *augmented_args = NULL;
+	/*
+	 * For now with BPF raw_augmented we hook into raw_syscalls:sys_enter
+	 * and there we get all 6 syscall args plus the tracepoint common
+	 * fields (sizeof(long)) and the syscall_nr (another long). So we check
+	 * if that is the case and if so don't look after the sc->args_size,
+	 * but always after the full raw_syscalls:sys_enter payload, which is
+	 * fixed.
+	 *
+	 * We'll revisit this later to pass s->args_size to the BPF augmenter
+	 * (now tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it
+	 * copies only what we need for each syscall, like what happens when we
+	 * use syscalls:sys_enter_NAME, so that we reduce the kernel/userspace
+	 * traffic to just what is needed for each syscall.
+	 */
+	int args_size = raw_augmented ? (8 * (int)sizeof(long)) : sc->args_size;
 
-	*augmented_args_size = sample->raw_size - sc->args_size;
+	*augmented_args_size = sample->raw_size - args_size;
 	if (*augmented_args_size > 0)
-		augmented_args = sample->raw_data + sc->args_size;
+		augmented_args = sample->raw_data + args_size;
 
 	return augmented_args;
 }
@@ -1780,7 +1796,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	 * here and avoid using augmented syscalls when the evsel is the raw_syscalls one.
 	 */
 	if (evsel != trace->syscalls.events.sys_enter)
-		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
+		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls);
 	ttrace->entry_time = sample->time;
 	msg = ttrace->entry_str;
 	printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
@@ -1833,7 +1849,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
 		goto out_put;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
+	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls);
 	syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
 	fprintf(trace->output, "%s", msg);
 	err = 0;
@@ -3501,8 +3517,15 @@ int cmd_trace(int argc, const char **argv)
 		evsel->handler = trace__sys_enter;
 
 		evlist__for_each_entry(trace.evlist, evsel) {
-			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_") ||
-			    strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0) {
+			bool raw_syscalls_sys_exit = strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0;
+
+			if (raw_syscalls_sys_exit) {
+				trace.raw_augmented_syscalls = true;
+				goto init_augmented_syscall_tp;
+			}
+
+			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
+init_augmented_syscall_tp:
 				perf_evsel__init_augmented_syscall_tp(evsel);
 				perf_evsel__init_augmented_syscall_tp_ret(evsel);
 				evsel->handler = trace__sys_exit;
-- 
2.14.4