1 files changed, 33 insertions, 120 deletions

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d3c757769b96..86e06f136f40 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -15,7 +15,6 @@
  */
 
 #include "util/record.h"
-#include <traceevent/event-parse.h>
 #include <api/fs/tracing_path.h>
 #include <bpf/bpf.h>
 #include "util/bpf_map.h"
@@ -80,6 +79,10 @@
 #include <linux/ctype.h>
 #include <perf/mmap.h>
 
+#ifdef HAVE_LIBTRACEEVENT
+#include <traceevent/event-parse.h>
+#endif
+
 #ifndef O_CLOEXEC
 # define O_CLOEXEC		02000000
 #endif
@@ -88,6 +91,8 @@
 # define F_LINUX_SPECIFIC_BASE	1024
 #endif
 
+#define RAW_SYSCALL_ARGS_NUM	6
+
 /*
  * strtoul: Go from a string to a value, i.e. for msr: MSR_FS_BASE to 0xc0000100
  */
@@ -108,7 +113,7 @@ struct syscall_fmt {
 		const char *sys_enter,
 			   *sys_exit;
 	}	   bpf_prog_name;
-	struct syscall_arg_fmt arg[6];
+	struct syscall_arg_fmt arg[RAW_SYSCALL_ARGS_NUM];
 	u8	   nr_args;
 	bool	   errpid;
 	bool	   timeout;
@@ -120,7 +125,6 @@ struct trace {
 	struct syscalltbl	*sctbl;
 	struct {
 		struct syscall  *table;
-		struct bpf_map  *map;
 		struct { // per syscall BPF_MAP_TYPE_PROG_ARRAY
 			struct bpf_map  *sys_enter,
 					*sys_exit;
@@ -924,6 +928,8 @@ static struct syscall_fmt syscall_fmts[] = {
 	  .arg = { [0] = { .scnprintf = SCA_PTR, /* brk */ }, }, },
 	{ .name     = "clock_gettime",
 	  .arg = { [0] = STRARRAY(clk_id, clockid), }, },
+	{ .name	    = "clock_nanosleep",
+	  .arg = { [2] = { .scnprintf = SCA_TIMESPEC,  /* rqtp */ }, }, },
 	{ .name	    = "clone",	    .errpid = true, .nr_args = 5,
 	  .arg = { [0] = { .name = "flags",	    .scnprintf = SCA_CLONE_FLAGS, },
 		   [1] = { .name = "child_stack",   .scnprintf = SCA_HEX, },
@@ -1053,7 +1059,8 @@ static struct syscall_fmt syscall_fmts[] = {
 	  .arg = { [0] = { .scnprintf = SCA_FDAT,	/* dfd */ },
 		   [2] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
 	{ .name	    = "perf_event_open",
-	  .arg = { [2] = { .scnprintf = SCA_INT,	/* cpu */ },
+	  .arg = { [0] = { .scnprintf = SCA_PERF_ATTR,  /* attr */ },
+		   [2] = { .scnprintf = SCA_INT,	/* cpu */ },
 		   [3] = { .scnprintf = SCA_FD,		/* group_fd */ },
 		   [4] = { .scnprintf = SCA_PERF_FLAGS, /* flags */ }, }, },
 	{ .name	    = "pipe2",
@@ -1220,16 +1227,6 @@ struct syscall {
 };
 
 /*
- * Must match what is in the BPF program:
- *
- * tools/perf/examples/bpf/augmented_raw_syscalls.c
- */
-struct bpf_map_syscall_entry {
-	bool	enabled;
-	u16	string_args_len[6];
-};
-
-/*
  * We need to have this 'calculated' boolean because in some cases we really
  * don't know what is the duration of a syscall, for instance, when we start
  * a session and some threads are waiting for a syscall to finish, say 'poll',
@@ -1535,8 +1532,8 @@ static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
 }
 
 static pid_t workload_pid = -1;
-static bool done = false;
-static bool interrupted = false;
+static volatile sig_atomic_t done = false;
+static volatile sig_atomic_t interrupted = false;
 
 static void sighandler_interrupt(int sig __maybe_unused)
 {
@@ -1658,7 +1655,7 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
 {
 	int idx;
 
-	if (nr_args == 6 && sc->fmt && sc->fmt->nr_args != 0)
+	if (nr_args == RAW_SYSCALL_ARGS_NUM && sc->fmt && sc->fmt->nr_args != 0)
 		nr_args = sc->fmt->nr_args;
 
 	sc->arg_fmt = calloc(nr_args, sizeof(*sc->arg_fmt));
@@ -1730,7 +1727,7 @@ syscall_arg_fmt__init_array(struct syscall_arg_fmt *arg, struct tep_format_field
 			 len >= 2 && strcmp(field->name + len - 2, "fd") == 0) {
 			/*
 			 * /sys/kernel/tracing/events/syscalls/sys_enter*
-			 * egrep 'field:.*fd;' .../format|sed -r 's/.*field:([a-z ]+) [a-z_]*fd.+/\1/g'|sort|uniq -c
+			 * grep -E 'field:.*fd;' .../format|sed -r 's/.*field:([a-z ]+) [a-z_]*fd.+/\1/g'|sort|uniq -c
 			 * 65 int
 			 * 23 unsigned int
 			 * 7 unsigned long
@@ -1791,11 +1788,11 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 #endif
 	sc = trace->syscalls.table + id;
 	if (sc->nonexistent)
-		return 0;
+		return -EEXIST;
 
 	if (name == NULL) {
 		sc->nonexistent = true;
-		return 0;
+		return -EEXIST;
 	}
 
 	sc->name = name;
@@ -1809,11 +1806,18 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 		sc->tp_format = trace_event__tp_format("syscalls", tp_name);
 	}
 
-	if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? 6 : sc->tp_format->format.nr_fields))
-		return -ENOMEM;
-
-	if (IS_ERR(sc->tp_format))
+	/*
+	 * Fails to read trace point format via sysfs node, so the trace point
+	 * doesn't exist.  Set the 'nonexistent' flag as true.
+	 */
+	if (IS_ERR(sc->tp_format)) {
+		sc->nonexistent = true;
 		return PTR_ERR(sc->tp_format);
+	}
+
+	if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ?
+					RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields))
+		return -ENOMEM;
 
 	sc->args = sc->tp_format->format.fields;
 	/*
@@ -2131,11 +2135,8 @@ static struct syscall *trace__syscall_info(struct trace *trace,
 	    (err = trace__read_syscall_info(trace, id)) != 0)
 		goto out_cant_read;
 
-	if (trace->syscalls.table[id].name == NULL) {
-		if (trace->syscalls.table[id].nonexistent)
-			return NULL;
+	if (trace->syscalls.table && trace->syscalls.table[id].nonexistent)
 		goto out_cant_read;
-	}
 
 	return &trace->syscalls.table[id];
 
@@ -2728,8 +2729,10 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel,
 				offset = format_field__intval(field, sample, evsel->needs_swap);
 				syscall_arg.len = offset >> 16;
 				offset &= 0xffff;
+#ifdef HAVE_LIBTRACEEVENT_TEP_FIELD_IS_RELATIVE
 				if (field->flags & TEP_FIELD_IS_RELATIVE)
 					offset += field->offset + field->size;
+#endif
 			}
 
 			val = (uintptr_t)(sample->raw_data + offset);
@@ -3250,7 +3253,6 @@ static void trace__set_bpf_map_filtered_pids(struct trace *trace)
 
 static void trace__set_bpf_map_syscalls(struct trace *trace)
 {
-	trace->syscalls.map = trace__find_bpf_map_by_name(trace, "syscalls");
 	trace->syscalls.prog_array.sys_enter = trace__find_bpf_map_by_name(trace, "syscalls_sys_enter");
 	trace->syscalls.prog_array.sys_exit  = trace__find_bpf_map_by_name(trace, "syscalls_sys_exit");
 }
@@ -3330,80 +3332,6 @@ static int trace__bpf_prog_sys_exit_fd(struct trace *trace, int id)
 	return sc ? bpf_program__fd(sc->bpf_prog.sys_exit) : bpf_program__fd(trace->syscalls.unaugmented_prog);
 }
 
-static void trace__init_bpf_map_syscall_args(struct trace *trace, int id, struct bpf_map_syscall_entry *entry)
-{
-	struct syscall *sc = trace__syscall_info(trace, NULL, id);
-	int arg = 0;
-
-	if (sc == NULL)
-		goto out;
-
-	for (; arg < sc->nr_args; ++arg) {
-		entry->string_args_len[arg] = 0;
-		if (sc->arg_fmt[arg].scnprintf == SCA_FILENAME) {
-			/* Should be set like strace -s strsize */
-			entry->string_args_len[arg] = PATH_MAX;
-		}
-	}
-out:
-	for (; arg < 6; ++arg)
-		entry->string_args_len[arg] = 0;
-}
-static int trace__set_ev_qualifier_bpf_filter(struct trace *trace)
-{
-	int fd = bpf_map__fd(trace->syscalls.map);
-	struct bpf_map_syscall_entry value = {
-		.enabled = !trace->not_ev_qualifier,
-	};
-	int err = 0;
-	size_t i;
-
-	for (i = 0; i < trace->ev_qualifier_ids.nr; ++i) {
-		int key = trace->ev_qualifier_ids.entries[i];
-
-		if (value.enabled) {
-			trace__init_bpf_map_syscall_args(trace, key, &value);
-			trace__init_syscall_bpf_progs(trace, key);
-		}
-
-		err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
-		if (err)
-			break;
-	}
-
-	return err;
-}
-
-static int __trace__init_syscalls_bpf_map(struct trace *trace, bool enabled)
-{
-	int fd = bpf_map__fd(trace->syscalls.map);
-	struct bpf_map_syscall_entry value = {
-		.enabled = enabled,
-	};
-	int err = 0, key;
-
-	for (key = 0; key < trace->sctbl->syscalls.nr_entries; ++key) {
-		if (enabled)
-			trace__init_bpf_map_syscall_args(trace, key, &value);
-
-		err = bpf_map_update_elem(fd, &key, &value, BPF_ANY);
-		if (err)
-			break;
-	}
-
-	return err;
-}
-
-static int trace__init_syscalls_bpf_map(struct trace *trace)
-{
-	bool enabled = true;
-
-	if (trace->ev_qualifier_ids.nr)
-		enabled = trace->not_ev_qualifier;
-
-	return __trace__init_syscalls_bpf_map(trace, enabled);
-}
-
 static struct bpf_program *trace__find_usable_bpf_prog_entry(struct trace *trace, struct syscall *sc)
 {
 	struct tep_format_field *field, *candidate_field;
@@ -3618,16 +3546,6 @@ static void trace__set_bpf_map_syscalls(struct trace *trace __maybe_unused)
 {
 }
 
-static int trace__set_ev_qualifier_bpf_filter(struct trace *trace __maybe_unused)
-{
-	return 0;
-}
-
-static int trace__init_syscalls_bpf_map(struct trace *trace __maybe_unused)
-{
-	return 0;
-}
-
 static struct bpf_program *trace__find_bpf_program_by_title(struct trace *trace __maybe_unused,
 							    const char *name __maybe_unused)
 {
@@ -3661,8 +3579,6 @@ static bool trace__only_augmented_syscalls_evsels(struct trace *trace)
 
 static int trace__set_ev_qualifier_filter(struct trace *trace)
 {
-	if (trace->syscalls.map)
-		return trace__set_ev_qualifier_bpf_filter(trace);
 	if (trace->syscalls.events.sys_enter)
 		return trace__set_ev_qualifier_tp_filter(trace);
 	return 0;
@@ -4036,9 +3952,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_mem;
 
-	if (trace->syscalls.map)
-		trace__init_syscalls_bpf_map(trace);
-
 	if (trace->syscalls.prog_array.sys_enter)
 		trace__init_syscalls_bpf_prog_array_maps(trace);
 
@@ -4092,8 +4005,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	}
 
 	trace->multiple_threads = perf_thread_map__pid(evlist->core.threads, 0) == -1 ||
-				  evlist->core.threads->nr > 1 ||
-				  evlist__first(evlist)->core.attr.inherit;
+		perf_thread_map__nr(evlist->core.threads) > 1 ||
+		evlist__first(evlist)->core.attr.inherit;
 
 	/*
 	 * Now that we already used evsel->core.attr to ask the kernel to setup the