#include "util/bpf-loader.h"
#include "callchain.h"
#include "syscalltbl.h"
+#include "rb_resort.h"
#include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
#include <stdlib.h>
-#include <linux/futex.h>
#include <linux/err.h>
-#include <linux/seccomp.h>
#include <linux/filter.h>
#include <linux/audit.h>
#include <sys/ptrace.h>
# define O_CLOEXEC 02000000
#endif
-#ifndef MSG_CMSG_CLOEXEC
-# define MSG_CMSG_CLOEXEC 0x40000000
-#endif
-
struct trace {
struct perf_tool tool;
struct syscalltbl *sctbl;
#define SCA_INT syscall_arg__scnprintf_int
-static size_t syscall_arg__scnprintf_flock(char *bf, size_t size,
- struct syscall_arg *arg)
-{
- int printed = 0, op = arg->val;
-
- if (op == 0)
- return scnprintf(bf, size, "NONE");
-#define P_CMD(cmd) \
- if ((op & LOCK_##cmd) == LOCK_##cmd) { \
- printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #cmd); \
- op &= ~LOCK_##cmd; \
- }
-
- P_CMD(SH);
- P_CMD(EX);
- P_CMD(NB);
- P_CMD(UN);
- P_CMD(MAND);
- P_CMD(RW);
- P_CMD(READ);
- P_CMD(WRITE);
-#undef P_OP
-
- if (op)
- printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", op);
-
- return printed;
-}
-
-#define SCA_FLOCK syscall_arg__scnprintf_flock
-
-static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg)
-{
- enum syscall_futex_args {
- SCF_UADDR = (1 << 0),
- SCF_OP = (1 << 1),
- SCF_VAL = (1 << 2),
- SCF_TIMEOUT = (1 << 3),
- SCF_UADDR2 = (1 << 4),
- SCF_VAL3 = (1 << 5),
- };
- int op = arg->val;
- int cmd = op & FUTEX_CMD_MASK;
- size_t printed = 0;
-
- switch (cmd) {
-#define P_FUTEX_OP(n) case FUTEX_##n: printed = scnprintf(bf, size, #n);
- P_FUTEX_OP(WAIT); arg->mask |= SCF_VAL3|SCF_UADDR2; break;
- P_FUTEX_OP(WAKE); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
- P_FUTEX_OP(FD); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
- P_FUTEX_OP(REQUEUE); arg->mask |= SCF_VAL3|SCF_TIMEOUT; break;
- P_FUTEX_OP(CMP_REQUEUE); arg->mask |= SCF_TIMEOUT; break;
- P_FUTEX_OP(CMP_REQUEUE_PI); arg->mask |= SCF_TIMEOUT; break;
- P_FUTEX_OP(WAKE_OP); break;
- P_FUTEX_OP(LOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
- P_FUTEX_OP(UNLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
- P_FUTEX_OP(TRYLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2; break;
- P_FUTEX_OP(WAIT_BITSET); arg->mask |= SCF_UADDR2; break;
- P_FUTEX_OP(WAKE_BITSET); arg->mask |= SCF_UADDR2; break;
- P_FUTEX_OP(WAIT_REQUEUE_PI); break;
- default: printed = scnprintf(bf, size, "%#x", cmd); break;
- }
-
- if (op & FUTEX_PRIVATE_FLAG)
- printed += scnprintf(bf + printed, size - printed, "|PRIV");
-
- if (op & FUTEX_CLOCK_REALTIME)
- printed += scnprintf(bf + printed, size - printed, "|CLKRT");
-
- return printed;
-}
-
-#define SCA_FUTEX_OP syscall_arg__scnprintf_futex_op
-
static const char *bpf_cmd[] = {
"MAP_CREATE", "MAP_LOOKUP_ELEM", "MAP_UPDATE_ELEM", "MAP_DELETE_ELEM",
"MAP_GET_NEXT_KEY", "PROG_LOAD",
};
static DEFINE_STRARRAY(socket_families);
-#ifndef MSG_PROBE
-#define MSG_PROBE 0x10
-#endif
-#ifndef MSG_WAITFORONE
-#define MSG_WAITFORONE 0x10000
-#endif
-#ifndef MSG_SENDPAGE_NOTLAST
-#define MSG_SENDPAGE_NOTLAST 0x20000
-#endif
-#ifndef MSG_FASTOPEN
-#define MSG_FASTOPEN 0x20000000
-#endif
-
-static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size,
- struct syscall_arg *arg)
-{
- int printed = 0, flags = arg->val;
-
- if (flags == 0)
- return scnprintf(bf, size, "NONE");
-#define P_MSG_FLAG(n) \
- if (flags & MSG_##n) { \
- printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
- flags &= ~MSG_##n; \
- }
-
- P_MSG_FLAG(OOB);
- P_MSG_FLAG(PEEK);
- P_MSG_FLAG(DONTROUTE);
- P_MSG_FLAG(TRYHARD);
- P_MSG_FLAG(CTRUNC);
- P_MSG_FLAG(PROBE);
- P_MSG_FLAG(TRUNC);
- P_MSG_FLAG(DONTWAIT);
- P_MSG_FLAG(EOR);
- P_MSG_FLAG(WAITALL);
- P_MSG_FLAG(FIN);
- P_MSG_FLAG(SYN);
- P_MSG_FLAG(CONFIRM);
- P_MSG_FLAG(RST);
- P_MSG_FLAG(ERRQUEUE);
- P_MSG_FLAG(NOSIGNAL);
- P_MSG_FLAG(MORE);
- P_MSG_FLAG(WAITFORONE);
- P_MSG_FLAG(SENDPAGE_NOTLAST);
- P_MSG_FLAG(FASTOPEN);
- P_MSG_FLAG(CMSG_CLOEXEC);
-#undef P_MSG_FLAG
-
- if (flags)
- printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
- return printed;
-}
-
-#define SCA_MSG_FLAGS syscall_arg__scnprintf_msg_flags
-
static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size,
struct syscall_arg *arg)
{
#define SCA_FILENAME syscall_arg__scnprintf_filename
-static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
- struct syscall_arg *arg)
-{
- int printed = 0, flags = arg->val;
-
- if (!(flags & O_CREAT))
- arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
-
- if (flags == 0)
- return scnprintf(bf, size, "RDONLY");
-#define P_FLAG(n) \
- if (flags & O_##n) { \
- printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
- flags &= ~O_##n; \
- }
-
- P_FLAG(APPEND);
- P_FLAG(ASYNC);
- P_FLAG(CLOEXEC);
- P_FLAG(CREAT);
- P_FLAG(DIRECT);
- P_FLAG(DIRECTORY);
- P_FLAG(EXCL);
- P_FLAG(LARGEFILE);
- P_FLAG(NOATIME);
- P_FLAG(NOCTTY);
-#ifdef O_NONBLOCK
- P_FLAG(NONBLOCK);
-#elif O_NDELAY
- P_FLAG(NDELAY);
-#endif
-#ifdef O_PATH
- P_FLAG(PATH);
-#endif
- P_FLAG(RDWR);
-#ifdef O_DSYNC
- if ((flags & O_SYNC) == O_SYNC)
- printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", "SYNC");
- else {
- P_FLAG(DSYNC);
- }
-#else
- P_FLAG(SYNC);
-#endif
- P_FLAG(TRUNC);
- P_FLAG(WRONLY);
-#undef P_FLAG
-
- if (flags)
- printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
- return printed;
-}
-
-#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
-
static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size,
struct syscall_arg *arg)
{
#define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags
-static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
-{
- int sig = arg->val;
-
- switch (sig) {
-#define P_SIGNUM(n) case SIG##n: return scnprintf(bf, size, #n)
- P_SIGNUM(HUP);
- P_SIGNUM(INT);
- P_SIGNUM(QUIT);
- P_SIGNUM(ILL);
- P_SIGNUM(TRAP);
- P_SIGNUM(ABRT);
- P_SIGNUM(BUS);
- P_SIGNUM(FPE);
- P_SIGNUM(KILL);
- P_SIGNUM(USR1);
- P_SIGNUM(SEGV);
- P_SIGNUM(USR2);
- P_SIGNUM(PIPE);
- P_SIGNUM(ALRM);
- P_SIGNUM(TERM);
- P_SIGNUM(CHLD);
- P_SIGNUM(CONT);
- P_SIGNUM(STOP);
- P_SIGNUM(TSTP);
- P_SIGNUM(TTIN);
- P_SIGNUM(TTOU);
- P_SIGNUM(URG);
- P_SIGNUM(XCPU);
- P_SIGNUM(XFSZ);
- P_SIGNUM(VTALRM);
- P_SIGNUM(PROF);
- P_SIGNUM(WINCH);
- P_SIGNUM(IO);
- P_SIGNUM(PWR);
- P_SIGNUM(SYS);
-#ifdef SIGEMT
- P_SIGNUM(EMT);
-#endif
-#ifdef SIGSTKFLT
- P_SIGNUM(STKFLT);
-#endif
-#ifdef SIGSWI
- P_SIGNUM(SWI);
-#endif
- default: break;
- }
-
- return scnprintf(bf, size, "%#x", sig);
-}
-
-#define SCA_SIGNUM syscall_arg__scnprintf_signum
-
#if defined(__i386__) || defined(__x86_64__)
/*
* FIXME: Make this available to all arches.
static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
#endif /* defined(__i386__) || defined(__x86_64__) */
-#ifndef SECCOMP_SET_MODE_STRICT
-#define SECCOMP_SET_MODE_STRICT 0
-#endif
-#ifndef SECCOMP_SET_MODE_FILTER
-#define SECCOMP_SET_MODE_FILTER 1
-#endif
-
-static size_t syscall_arg__scnprintf_seccomp_op(char *bf, size_t size, struct syscall_arg *arg)
-{
- int op = arg->val;
- size_t printed = 0;
-
- switch (op) {
-#define P_SECCOMP_SET_MODE_OP(n) case SECCOMP_SET_MODE_##n: printed = scnprintf(bf, size, #n); break
- P_SECCOMP_SET_MODE_OP(STRICT);
- P_SECCOMP_SET_MODE_OP(FILTER);
-#undef P_SECCOMP_SET_MODE_OP
- default: printed = scnprintf(bf, size, "%#x", op); break;
- }
-
- return printed;
-}
-
-#define SCA_SECCOMP_OP syscall_arg__scnprintf_seccomp_op
-
-#ifndef SECCOMP_FILTER_FLAG_TSYNC
-#define SECCOMP_FILTER_FLAG_TSYNC 1
-#endif
-
-static size_t syscall_arg__scnprintf_seccomp_flags(char *bf, size_t size,
- struct syscall_arg *arg)
-{
- int printed = 0, flags = arg->val;
-
-#define P_FLAG(n) \
- if (flags & SECCOMP_FILTER_FLAG_##n) { \
- printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
- flags &= ~SECCOMP_FILTER_FLAG_##n; \
- }
-
- P_FLAG(TSYNC);
-#undef P_FLAG
-
- if (flags)
- printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
- return printed;
-}
-
-#define SCA_SECCOMP_FLAGS syscall_arg__scnprintf_seccomp_flags
-
#ifndef GRND_NONBLOCK
#define GRND_NONBLOCK 0x0001
#endif
.arg_parm = { [arg] = &strarray__##array, }
#include "trace/beauty/eventfd.c"
-#include "trace/beauty/pid.c"
+#include "trace/beauty/flock.c"
+#include "trace/beauty/futex_op.c"
#include "trace/beauty/mmap.c"
#include "trace/beauty/mode_t.c"
+#include "trace/beauty/msg_flags.c"
+#include "trace/beauty/open_flags.c"
#include "trace/beauty/perf_event_open.c"
+#include "trace/beauty/pid.c"
#include "trace/beauty/sched_policy.c"
+#include "trace/beauty/seccomp.c"
+#include "trace/beauty/signum.c"
#include "trace/beauty/socket_type.c"
#include "trace/beauty/waitid_options.c"
return trace__process_event(trace, machine, event, sample);
}
+static char *trace__machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp)
+{
+ struct machine *machine = vmachine;
+
+ if (machine->kptr_restrict_warned)
+ return NULL;
+
+ if (symbol_conf.kptr_restrict) {
+ pr_warning("Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
+ "Check /proc/sys/kernel/kptr_restrict.\n\n"
+ "Kernel samples will not be resolved.\n");
+ machine->kptr_restrict_warned = true;
+ return NULL;
+ }
+
+ return machine__resolve_kernel_addr(vmachine, addrp, modp);
+}
+
static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
{
int err = symbol__init(NULL);
if (trace->host == NULL)
return -ENOMEM;
- if (trace_event__register_resolver(trace->host, machine__resolve_kernel_addr) < 0)
+ if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0)
return -errno;
err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
"%ld", val);
}
}
- } else {
+ } else if (IS_ERR(sc->tp_format)) {
+ /*
+ * If we managed to read the tracepoint /format file, then we
+ * may end up not having any args, like with gettid(), so only
+ * print the raw args when we didn't manage to read it.
+ */
int i = 0;
while (i < 6) {
if (sc->is_exit) {
if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
- fprintf(trace->output, "%-70s\n", ttrace->entry_str);
+ fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
}
} else {
ttrace->entry_pending = true;
return printed;
}
+DEFINE_RESORT_RB(syscall_stats, a->msecs > b->msecs,
+ struct stats *stats;
+ double msecs;
+ int syscall;
+)
+{
+ struct int_node *source = rb_entry(nd, struct int_node, rb_node);
+ struct stats *stats = source->priv;
+
+ entry->syscall = source->i;
+ entry->stats = stats;
+ entry->msecs = stats ? (u64)stats->n * (avg_stats(stats) / NSEC_PER_MSEC) : 0;
+}
+
static size_t thread__dump_stats(struct thread_trace *ttrace,
struct trace *trace, FILE *fp)
{
- struct stats *stats;
size_t printed = 0;
struct syscall *sc;
- struct int_node *inode = intlist__first(ttrace->syscall_stats);
+ struct rb_node *nd;
+ DECLARE_RESORT_RB_INTLIST(syscall_stats, ttrace->syscall_stats);
- if (inode == NULL)
+ if (syscall_stats == NULL)
return 0;
printed += fprintf(fp, "\n");
printed += fprintf(fp, " (msec) (msec) (msec) (msec) (%%)\n");
printed += fprintf(fp, " --------------- -------- --------- --------- --------- --------- ------\n");
- /* each int_node is a syscall */
- while (inode) {
- stats = inode->priv;
+ resort_rb__for_each(nd, syscall_stats) {
+ struct stats *stats = syscall_stats_entry->stats;
if (stats) {
double min = (double)(stats->min) / NSEC_PER_MSEC;
double max = (double)(stats->max) / NSEC_PER_MSEC;
pct = avg ? 100.0 * stddev_stats(stats)/avg : 0.0;
avg /= NSEC_PER_MSEC;
- sc = &trace->syscalls.table[inode->i];
+ sc = &trace->syscalls.table[syscall_stats_entry->syscall];
printed += fprintf(fp, " %-15s", sc->name);
printed += fprintf(fp, " %8" PRIu64 " %9.3f %9.3f %9.3f",
- n, avg * n, min, avg);
+ n, syscall_stats_entry->msecs, min, avg);
printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct);
}
-
- inode = intlist__next(inode);
}
+ resort_rb__delete(syscall_stats);
printed += fprintf(fp, "\n\n");
return printed;
}
-/* struct used to pass data to per-thread function */
-struct summary_data {
- FILE *fp;
- struct trace *trace;
- size_t printed;
-};
-
-static int trace__fprintf_one_thread(struct thread *thread, void *priv)
+static size_t trace__fprintf_thread(FILE *fp, struct thread *thread, struct trace *trace)
{
- struct summary_data *data = priv;
- FILE *fp = data->fp;
- size_t printed = data->printed;
- struct trace *trace = data->trace;
+ size_t printed = 0;
struct thread_trace *ttrace = thread__priv(thread);
double ratio;
printed += fprintf(fp, ", %lu majfaults", ttrace->pfmaj);
if (ttrace->pfmin)
printed += fprintf(fp, ", %lu minfaults", ttrace->pfmin);
- printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
+ if (trace->sched)
+ printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
+ else if (fputc('\n', fp) != EOF)
+ ++printed;
+
printed += thread__dump_stats(ttrace, trace, fp);
- data->printed += printed;
+ return printed;
+}
- return 0;
+static unsigned long thread__nr_events(struct thread_trace *ttrace)
+{
+ return ttrace ? ttrace->nr_events : 0;
+}
+
+DEFINE_RESORT_RB(threads, (thread__nr_events(a->thread->priv) < thread__nr_events(b->thread->priv)),
+ struct thread *thread;
+)
+{
+ entry->thread = rb_entry(nd, struct thread, rb_node);
}
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
{
- struct summary_data data = {
- .fp = fp,
- .trace = trace
- };
- data.printed = trace__fprintf_threads_header(fp);
+ DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host);
+ size_t printed = trace__fprintf_threads_header(fp);
+ struct rb_node *nd;
- machine__for_each_thread(trace->host, trace__fprintf_one_thread, &data);
+ if (threads == NULL) {
+ fprintf(fp, "%s", "Error sorting output by nr_events!\n");
+ return 0;
+ }
+
+ resort_rb__for_each(nd, threads)
+ printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
- return data.printed;
+ resort_rb__delete(threads);
+
+ return printed;
}
static int trace__set_duration(const struct option *opt, const char *str,
mmap_pages_user_set = false;
if (trace.max_stack == UINT_MAX) {
- trace.max_stack = sysctl_perf_event_max_stack;
+ trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl_perf_event_max_stack;
max_stack_user_set = false;
}
#ifdef HAVE_DWARF_UNWIND_SUPPORT
- if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled)
+ if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled && trace.trace_syscalls)
record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false);
#endif