Linux-libre 4.7.1-gnupck-4.7.1-gnu

1 files changed, 531 insertions, 824 deletions

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 93ac724fb..5c50fe70d 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -34,79 +34,76 @@
 #include "trace-event.h"
 #include "util/parse-events.h"
 #include "util/bpf-loader.h"
+#include "callchain.h"
+#include "syscalltbl.h"
+#include "rb_resort.h"
 
-#include <libaudit.h>
+#include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
 #include <stdlib.h>
-#include <sys/mman.h>
-#include <linux/futex.h>
 #include <linux/err.h>
-
-/* For older distros: */
-#ifndef MAP_STACK
-# define MAP_STACK		0x20000
-#endif
-
-#ifndef MADV_HWPOISON
-# define MADV_HWPOISON		100
-
-#endif
-
-#ifndef MADV_MERGEABLE
-# define MADV_MERGEABLE		12
-#endif
-
-#ifndef MADV_UNMERGEABLE
-# define MADV_UNMERGEABLE	13
-#endif
-
-#ifndef EFD_SEMAPHORE
-# define EFD_SEMAPHORE		1
-#endif
-
-#ifndef EFD_NONBLOCK
-# define EFD_NONBLOCK		00004000
-#endif
-
-#ifndef EFD_CLOEXEC
-# define EFD_CLOEXEC		02000000
-#endif
+#include <linux/filter.h>
+#include <linux/audit.h>
+#include <sys/ptrace.h>
+#include <linux/random.h>
+#include <linux/stringify.h>
 
 #ifndef O_CLOEXEC
 # define O_CLOEXEC		02000000
 #endif
 
-#ifndef SOCK_DCCP
-# define SOCK_DCCP		6
-#endif
-
-#ifndef SOCK_CLOEXEC
-# define SOCK_CLOEXEC		02000000
-#endif
-
-#ifndef SOCK_NONBLOCK
-# define SOCK_NONBLOCK		00004000
-#endif
-
-#ifndef MSG_CMSG_CLOEXEC
-# define MSG_CMSG_CLOEXEC	0x40000000
-#endif
-
-#ifndef PERF_FLAG_FD_NO_GROUP
-# define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
-#endif
-
-#ifndef PERF_FLAG_FD_OUTPUT
-# define PERF_FLAG_FD_OUTPUT		(1UL << 1)
-#endif
-
-#ifndef PERF_FLAG_PID_CGROUP
-# define PERF_FLAG_PID_CGROUP		(1UL << 2) /* pid=cgroup id, per-cpu mode only */
-#endif
-
-#ifndef PERF_FLAG_FD_CLOEXEC
-# define PERF_FLAG_FD_CLOEXEC		(1UL << 3) /* O_CLOEXEC */
-#endif
-
+struct trace {
+	struct perf_tool	tool;
+	struct syscalltbl	*sctbl;
+	struct {
+		int		max;
+		struct syscall  *table;
+		struct {
+			struct perf_evsel *sys_enter,
+					  *sys_exit;
+		}		events;
+	} syscalls;
+	struct record_opts	opts;
+	struct perf_evlist	*evlist;
+	struct machine		*host;
+	struct thread		*current;
+	u64			base_time;
+	FILE			*output;
+	unsigned long		nr_events;
+	struct strlist		*ev_qualifier;
+	struct {
+		size_t		nr;
+		int		*entries;
+	}			ev_qualifier_ids;
+	struct intlist		*tid_list;
+	struct intlist		*pid_list;
+	struct {
+		size_t		nr;
+		pid_t		*entries;
+	}			filter_pids;
+	double			duration_filter;
+	double			runtime_ms;
+	struct {
+		u64		vfs_getname,
+				proc_getname;
+	} stats;
+	unsigned int		max_stack;
+	unsigned int		min_stack;
+	bool			not_ev_qualifier;
+	bool			live;
+	bool			full_time;
+	bool			sched;
+	bool			multiple_threads;
+	bool			summary;
+	bool			summary_only;
+	bool			show_comm;
+	bool			show_tool_stats;
+	bool			trace_syscalls;
+	bool			kernel_syscallchains;
+	bool			force;
+	bool			vfs_getname;
+	int			trace_pgfaults;
+	int			open_id;
+};
 
 struct tp_field {
 	int offset;
@@ -371,221 +368,6 @@ static size_t syscall_arg__scnprintf_int(char *bf, size_t size,
 
 #define SCA_INT syscall_arg__scnprintf_int
 
-static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
-					       struct syscall_arg *arg)
-{
-	int printed = 0, prot = arg->val;
-
-	if (prot == PROT_NONE)
-		return scnprintf(bf, size, "NONE");
-#define	P_MMAP_PROT(n) \
-	if (prot & PROT_##n) { \
-		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
-		prot &= ~PROT_##n; \
-	}
-
-	P_MMAP_PROT(EXEC);
-	P_MMAP_PROT(READ);
-	P_MMAP_PROT(WRITE);
-#ifdef PROT_SEM
-	P_MMAP_PROT(SEM);
-#endif
-	P_MMAP_PROT(GROWSDOWN);
-	P_MMAP_PROT(GROWSUP);
-#undef P_MMAP_PROT
-
-	if (prot)
-		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", prot);
-
-	return printed;
-}
-
-#define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
-
-static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
-						struct syscall_arg *arg)
-{
-	int printed = 0, flags = arg->val;
-
-#define	P_MMAP_FLAG(n) \
-	if (flags & MAP_##n) { \
-		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
-		flags &= ~MAP_##n; \
-	}
-
-	P_MMAP_FLAG(SHARED);
-	P_MMAP_FLAG(PRIVATE);
-#ifdef MAP_32BIT
-	P_MMAP_FLAG(32BIT);
-#endif
-	P_MMAP_FLAG(ANONYMOUS);
-	P_MMAP_FLAG(DENYWRITE);
-	P_MMAP_FLAG(EXECUTABLE);
-	P_MMAP_FLAG(FILE);
-	P_MMAP_FLAG(FIXED);
-	P_MMAP_FLAG(GROWSDOWN);
-#ifdef MAP_HUGETLB
-	P_MMAP_FLAG(HUGETLB);
-#endif
-	P_MMAP_FLAG(LOCKED);
-	P_MMAP_FLAG(NONBLOCK);
-	P_MMAP_FLAG(NORESERVE);
-	P_MMAP_FLAG(POPULATE);
-	P_MMAP_FLAG(STACK);
-#ifdef MAP_UNINITIALIZED
-	P_MMAP_FLAG(UNINITIALIZED);
-#endif
-#undef P_MMAP_FLAG
-
-	if (flags)
-		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
-	return printed;
-}
-
-#define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
-
-static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
-						  struct syscall_arg *arg)
-{
-	int printed = 0, flags = arg->val;
-
-#define P_MREMAP_FLAG(n) \
-	if (flags & MREMAP_##n) { \
-		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
-		flags &= ~MREMAP_##n; \
-	}
-
-	P_MREMAP_FLAG(MAYMOVE);
-#ifdef MREMAP_FIXED
-	P_MREMAP_FLAG(FIXED);
-#endif
-#undef P_MREMAP_FLAG
-
-	if (flags)
-		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
-	return printed;
-}
-
-#define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags
-
-static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
-						      struct syscall_arg *arg)
-{
-	int behavior = arg->val;
-
-	switch (behavior) {
-#define	P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n)
-	P_MADV_BHV(NORMAL);
-	P_MADV_BHV(RANDOM);
-	P_MADV_BHV(SEQUENTIAL);
-	P_MADV_BHV(WILLNEED);
-	P_MADV_BHV(DONTNEED);
-	P_MADV_BHV(REMOVE);
-	P_MADV_BHV(DONTFORK);
-	P_MADV_BHV(DOFORK);
-	P_MADV_BHV(HWPOISON);
-#ifdef MADV_SOFT_OFFLINE
-	P_MADV_BHV(SOFT_OFFLINE);
-#endif
-	P_MADV_BHV(MERGEABLE);
-	P_MADV_BHV(UNMERGEABLE);
-#ifdef MADV_HUGEPAGE
-	P_MADV_BHV(HUGEPAGE);
-#endif
-#ifdef MADV_NOHUGEPAGE
-	P_MADV_BHV(NOHUGEPAGE);
-#endif
-#ifdef MADV_DONTDUMP
-	P_MADV_BHV(DONTDUMP);
-#endif
-#ifdef MADV_DODUMP
-	P_MADV_BHV(DODUMP);
-#endif
-#undef P_MADV_PHV
-	default: break;
-	}
-
-	return scnprintf(bf, size, "%#x", behavior);
-}
-
-#define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior
-
-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",
@@ -652,110 +434,6 @@ static const char *socket_families[] = {
 };
 static DEFINE_STRARRAY(socket_families);
 
-#ifndef SOCK_TYPE_MASK
-#define SOCK_TYPE_MASK 0xf
-#endif
-
-static size_t syscall_arg__scnprintf_socket_type(char *bf, size_t size,
-						      struct syscall_arg *arg)
-{
-	size_t printed;
-	int type = arg->val,
-	    flags = type & ~SOCK_TYPE_MASK;
-
-	type &= SOCK_TYPE_MASK;
-	/*
- 	 * Can't use a strarray, MIPS may override for ABI reasons.
- 	 */
-	switch (type) {
-#define	P_SK_TYPE(n) case SOCK_##n: printed = scnprintf(bf, size, #n); break;
-	P_SK_TYPE(STREAM);
-	P_SK_TYPE(DGRAM);
-	P_SK_TYPE(RAW);
-	P_SK_TYPE(RDM);
-	P_SK_TYPE(SEQPACKET);
-	P_SK_TYPE(DCCP);
-	P_SK_TYPE(PACKET);
-#undef P_SK_TYPE
-	default:
-		printed = scnprintf(bf, size, "%#x", type);
-	}
-
-#define	P_SK_FLAG(n) \
-	if (flags & SOCK_##n) { \
-		printed += scnprintf(bf + printed, size - printed, "|%s", #n); \
-		flags &= ~SOCK_##n; \
-	}
-
-	P_SK_FLAG(CLOEXEC);
-	P_SK_FLAG(NONBLOCK);
-#undef P_SK_FLAG
-
-	if (flags)
-		printed += scnprintf(bf + printed, size - printed, "|%#x", flags);
-
-	return printed;
-}
-
-#define SCA_SK_TYPE syscall_arg__scnprintf_socket_type
-
-#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)
 {
@@ -788,116 +466,6 @@ static size_t syscall_arg__scnprintf_filename(char *bf, size_t size,
 
 #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_perf_flags(char *bf, size_t size,
-						struct syscall_arg *arg)
-{
-	int printed = 0, flags = arg->val;
-
-	if (flags == 0)
-		return 0;
-
-#define	P_FLAG(n) \
-	if (flags & PERF_FLAG_##n) { \
-		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
-		flags &= ~PERF_FLAG_##n; \
-	}
-
-	P_FLAG(FD_NO_GROUP);
-	P_FLAG(FD_OUTPUT);
-	P_FLAG(PID_CGROUP);
-	P_FLAG(FD_CLOEXEC);
-#undef P_FLAG
-
-	if (flags)
-		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
-	return printed;
-}
-
-#define SCA_PERF_FLAGS syscall_arg__scnprintf_perf_flags
-
-static size_t syscall_arg__scnprintf_eventfd_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_FLAG(n) \
-	if (flags & EFD_##n) { \
-		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
-		flags &= ~EFD_##n; \
-	}
-
-	P_FLAG(SEMAPHORE);
-	P_FLAG(CLOEXEC);
-	P_FLAG(NONBLOCK);
-#undef P_FLAG
-
-	if (flags)
-		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
-	return printed;
-}
-
-#define SCA_EFD_FLAGS syscall_arg__scnprintf_eventfd_flags
-
 static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size,
 						struct syscall_arg *arg)
 {
@@ -921,59 +489,6 @@ static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size,
 
 #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.
@@ -1001,105 +516,125 @@ static const char *tioctls[] = {
 static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
 #endif /* defined(__i386__) || defined(__x86_64__) */
 
+#ifndef GRND_NONBLOCK
+#define GRND_NONBLOCK	0x0001
+#endif
+#ifndef GRND_RANDOM
+#define GRND_RANDOM	0x0002
+#endif
+
+static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
+						   struct syscall_arg *arg)
+{
+	int printed = 0, flags = arg->val;
+
+#define	P_FLAG(n) \
+	if (flags & GRND_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~GRND_##n; \
+	}
+
+	P_FLAG(RANDOM);
+	P_FLAG(NONBLOCK);
+#undef P_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
+}
+
+#define SCA_GETRANDOM_FLAGS syscall_arg__scnprintf_getrandom_flags
+
 #define STRARRAY(arg, name, array) \
 	  .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
 	  .arg_parm	 = { [arg] = &strarray__##array, }
 
+#include "trace/beauty/eventfd.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"
+
 static struct syscall_fmt {
 	const char *name;
 	const char *alias;
 	size_t	   (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg);
 	void	   *arg_parm[6];
 	bool	   errmsg;
+	bool	   errpid;
 	bool	   timeout;
 	bool	   hexret;
 } syscall_fmts[] = {
 	{ .name	    = "access",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */
-			     [1] = SCA_ACCMODE,  /* mode */ }, },
+	  .arg_scnprintf = { [1] = SCA_ACCMODE,  /* mode */ }, },
 	{ .name	    = "arch_prctl", .errmsg = true, .alias = "prctl", },
 	{ .name	    = "bpf",	    .errmsg = true, STRARRAY(0, cmd, bpf_cmd), },
 	{ .name	    = "brk",	    .hexret = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
-	{ .name	    = "chdir",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "chmod",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "chroot",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
+	{ .name	    = "chdir",	    .errmsg = true, },
+	{ .name	    = "chmod",	    .errmsg = true, },
+	{ .name	    = "chroot",	    .errmsg = true, },
 	{ .name     = "clock_gettime",  .errmsg = true, STRARRAY(0, clk_id, clockid), },
+	{ .name	    = "clone",	    .errpid = true, },
 	{ .name	    = "close",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, },
 	{ .name	    = "connect",    .errmsg = true, },
-	{ .name	    = "creat",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "dup",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "dup2",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "dup3",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	{ .name	    = "creat",	    .errmsg = true, },
+	{ .name	    = "dup",	    .errmsg = true, },
+	{ .name	    = "dup2",	    .errmsg = true, },
+	{ .name	    = "dup3",	    .errmsg = true, },
 	{ .name	    = "epoll_ctl",  .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
 	{ .name	    = "eventfd2",   .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
-	{ .name	    = "faccessat",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "fadvise64",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "fallocate",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "fchdir",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "fchmod",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	{ .name	    = "faccessat",  .errmsg = true, },
+	{ .name	    = "fadvise64",  .errmsg = true, },
+	{ .name	    = "fallocate",  .errmsg = true, },
+	{ .name	    = "fchdir",	    .errmsg = true, },
+	{ .name	    = "fchmod",	    .errmsg = true, },
 	{ .name	    = "fchmodat",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "fchown",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+	{ .name	    = "fchown",	    .errmsg = true, },
 	{ .name	    = "fchownat",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
 	{ .name	    = "fcntl",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [1] = SCA_STRARRAY, /* cmd */ },
+	  .arg_scnprintf = { [1] = SCA_STRARRAY, /* cmd */ },
 	  .arg_parm	 = { [1] = &strarray__fcntl_cmds, /* cmd */ }, },
-	{ .name	    = "fdatasync",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	{ .name	    = "fdatasync",  .errmsg = true, },
 	{ .name	    = "flock",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [1] = SCA_FLOCK, /* cmd */ }, },
-	{ .name	    = "fsetxattr",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "fstat",	    .errmsg = true, .alias = "newfstat",
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "fstatat",    .errmsg = true, .alias = "newfstatat",
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "fstatfs",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "fsync",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "ftruncate", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	  .arg_scnprintf = { [1] = SCA_FLOCK, /* cmd */ }, },
+	{ .name	    = "fsetxattr",  .errmsg = true, },
+	{ .name	    = "fstat",	    .errmsg = true, .alias = "newfstat", },
+	{ .name	    = "fstatat",    .errmsg = true, .alias = "newfstatat", },
+	{ .name	    = "fstatfs",    .errmsg = true, },
+	{ .name	    = "fsync",    .errmsg = true, },
+	{ .name	    = "ftruncate", .errmsg = true, },
 	{ .name	    = "futex",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
 	{ .name	    = "futimesat", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "getdents",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "getdents64", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+	{ .name	    = "getdents",   .errmsg = true, },
+	{ .name	    = "getdents64", .errmsg = true, },
 	{ .name	    = "getitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
+	{ .name	    = "getpid",	    .errpid = true, },
+	{ .name	    = "getpgid",    .errpid = true, },
+	{ .name	    = "getppid",    .errpid = true, },
+	{ .name	    = "getrandom",  .errmsg = true,
+	  .arg_scnprintf = { [2] = SCA_GETRANDOM_FLAGS, /* flags */ }, },
 	{ .name	    = "getrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
-	{ .name	    = "getxattr",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "inotify_add_watch",	    .errmsg = true,
-	  .arg_scnprintf = { [1] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "getxattr",   .errmsg = true, },
+	{ .name	    = "inotify_add_watch",	    .errmsg = true, },
 	{ .name	    = "ioctl",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
+	  .arg_scnprintf = {
 #if defined(__i386__) || defined(__x86_64__)
 /*
  * FIXME: Make this available to all arches.
@@ -1113,41 +648,28 @@ static struct syscall_fmt {
 	{ .name	    = "keyctl",	    .errmsg = true, STRARRAY(0, option, keyctl_options), },
 	{ .name	    = "kill",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
-	{ .name	    = "lchown",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "lgetxattr",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "lchown",    .errmsg = true, },
+	{ .name	    = "lgetxattr",  .errmsg = true, },
 	{ .name	    = "linkat",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-	{ .name	    = "listxattr",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "llistxattr", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "lremovexattr",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "listxattr",  .errmsg = true, },
+	{ .name	    = "llistxattr", .errmsg = true, },
+	{ .name	    = "lremovexattr",  .errmsg = true, },
 	{ .name	    = "lseek",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [2] = SCA_STRARRAY, /* whence */ },
+	  .arg_scnprintf = { [2] = SCA_STRARRAY, /* whence */ },
 	  .arg_parm	 = { [2] = &strarray__whences, /* whence */ }, },
-	{ .name	    = "lsetxattr",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "lstat",	    .errmsg = true, .alias = "newlstat",
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "lsxattr",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "lsetxattr",  .errmsg = true, },
+	{ .name	    = "lstat",	    .errmsg = true, .alias = "newlstat", },
+	{ .name	    = "lsxattr",    .errmsg = true, },
 	{ .name     = "madvise",    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX,	 /* start */
 			     [2] = SCA_MADV_BHV, /* behavior */ }, },
-	{ .name	    = "mkdir",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "mkdir",    .errmsg = true, },
 	{ .name	    = "mkdirat",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
-			     [1] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "mknod",      .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+	{ .name	    = "mknod",      .errmsg = true, },
 	{ .name	    = "mknodat",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
 	{ .name	    = "mlock",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
 	{ .name	    = "mlockall",   .errmsg = true,
@@ -1155,8 +677,7 @@ static struct syscall_fmt {
 	{ .name	    = "mmap",	    .hexret = true,
 	  .arg_scnprintf = { [0] = SCA_HEX,	  /* addr */
 			     [2] = SCA_MMAP_PROT, /* prot */
-			     [3] = SCA_MMAP_FLAGS, /* flags */
-			     [4] = SCA_FD, 	  /* fd */ }, },
+			     [3] = SCA_MMAP_FLAGS, /* flags */ }, },
 	{ .name	    = "mprotect",   .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* start */
 			     [2] = SCA_MMAP_PROT, /* prot */ }, },
@@ -1173,60 +694,43 @@ static struct syscall_fmt {
 	{ .name	    = "name_to_handle_at", .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
 	{ .name	    = "newfstatat", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
 	{ .name	    = "open",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME,   /* filename */
-			     [1] = SCA_OPEN_FLAGS, /* flags */ }, },
+	  .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
 	{ .name	    = "open_by_handle_at", .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
 			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
 	{ .name	    = "openat",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-			     [1] = SCA_FILENAME, /* filename */
 			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
 	{ .name	    = "perf_event_open", .errmsg = true,
-	  .arg_scnprintf = { [1] = SCA_INT, /* pid */
-			     [2] = SCA_INT, /* cpu */
+	  .arg_scnprintf = { [2] = SCA_INT, /* cpu */
 			     [3] = SCA_FD,  /* group_fd */
 			     [4] = SCA_PERF_FLAGS,  /* flags */ }, },
 	{ .name	    = "pipe2",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
 	{ .name	    = "poll",	    .errmsg = true, .timeout = true, },
 	{ .name	    = "ppoll",	    .errmsg = true, .timeout = true, },
-	{ .name	    = "pread",	    .errmsg = true, .alias = "pread64",
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "preadv",	    .errmsg = true, .alias = "pread",
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	{ .name	    = "pread",	    .errmsg = true, .alias = "pread64", },
+	{ .name	    = "preadv",	    .errmsg = true, .alias = "pread", },
 	{ .name	    = "prlimit64",  .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
-	{ .name	    = "pwrite",	    .errmsg = true, .alias = "pwrite64",
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "pwritev",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "read",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "readlink",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* path */ }, },
+	{ .name	    = "pwrite",	    .errmsg = true, .alias = "pwrite64", },
+	{ .name	    = "pwritev",    .errmsg = true, },
+	{ .name	    = "read",	    .errmsg = true, },
+	{ .name	    = "readlink",   .errmsg = true, },
 	{ .name	    = "readlinkat", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-			     [1] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "readv",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+	{ .name	    = "readv",	    .errmsg = true, },
 	{ .name	    = "recvfrom",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [3] = SCA_MSG_FLAGS, /* flags */ }, },
+	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
 	{ .name	    = "recvmmsg",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [3] = SCA_MSG_FLAGS, /* flags */ }, },
+	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
 	{ .name	    = "recvmsg",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [2] = SCA_MSG_FLAGS, /* flags */ }, },
-	{ .name	    = "removexattr", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	  .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
+	{ .name	    = "removexattr", .errmsg = true, },
 	{ .name	    = "renameat",   .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-	{ .name	    = "rmdir",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "rmdir",    .errmsg = true, },
 	{ .name	    = "rt_sigaction", .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
 	{ .name	    = "rt_sigprocmask",  .errmsg = true, STRARRAY(0, how, sighow), },
@@ -1234,22 +738,24 @@ static struct syscall_fmt {
 	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
 	{ .name	    = "rt_tgsigqueueinfo", .errmsg = true,
 	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
+	{ .name	    = "sched_setscheduler",   .errmsg = true,
+	  .arg_scnprintf = { [1] = SCA_SCHED_POLICY, /* policy */ }, },
+	{ .name	    = "seccomp", .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_SECCOMP_OP, /* op */
+			     [1] = SCA_SECCOMP_FLAGS, /* flags */ }, },
 	{ .name	    = "select",	    .errmsg = true, .timeout = true, },
 	{ .name	    = "sendmmsg",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [3] = SCA_MSG_FLAGS, /* flags */ }, },
+	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
 	{ .name	    = "sendmsg",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [2] = SCA_MSG_FLAGS, /* flags */ }, },
+	  .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
 	{ .name	    = "sendto",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [3] = SCA_MSG_FLAGS, /* flags */ }, },
+	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
+	{ .name	    = "set_tid_address", .errpid = true, },
 	{ .name	    = "setitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
+	{ .name	    = "setpgid",    .errmsg = true, },
 	{ .name	    = "setrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
-	{ .name	    = "setxattr",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "shutdown",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	{ .name	    = "setxattr",   .errmsg = true, },
+	{ .name	    = "shutdown",   .errmsg = true, },
 	{ .name	    = "socket",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
 			     [1] = SCA_SK_TYPE, /* type */ },
@@ -1258,10 +764,8 @@ static struct syscall_fmt {
 	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
 			     [1] = SCA_SK_TYPE, /* type */ },
 	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
-	{ .name	    = "stat",	    .errmsg = true, .alias = "newstat",
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "statfs",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "stat",	    .errmsg = true, .alias = "newstat", },
+	{ .name	    = "statfs",	    .errmsg = true, },
 	{ .name	    = "swapoff",    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, },
 	{ .name	    = "swapon",	    .errmsg = true,
@@ -1272,25 +776,21 @@ static struct syscall_fmt {
 	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
 	{ .name	    = "tkill",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
-	{ .name	    = "truncate",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* path */ }, },
+	{ .name	    = "truncate",   .errmsg = true, },
 	{ .name	    = "uname",	    .errmsg = true, .alias = "newuname", },
 	{ .name	    = "unlinkat",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-			     [1] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "utime",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+	{ .name	    = "utime",  .errmsg = true, },
 	{ .name	    = "utimensat",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "utimes",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "vmsplice",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "write",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "writev",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, },
+	{ .name	    = "utimes",  .errmsg = true, },
+	{ .name	    = "vmsplice",  .errmsg = true, },
+	{ .name	    = "wait4",	    .errpid = true,
+	  .arg_scnprintf = { [2] = SCA_WAITID_OPTIONS, /* options */ }, },
+	{ .name	    = "waitid",	    .errpid = true,
+	  .arg_scnprintf = { [3] = SCA_WAITID_OPTIONS, /* options */ }, },
+	{ .name	    = "write",	    .errmsg = true, },
+	{ .name	    = "writev",	    .errmsg = true, },
 };
 
 static int syscall_fmt__cmp(const void *name, const void *fmtp)
@@ -1398,59 +898,6 @@ fail:
 
 static const size_t trace__entry_str_size = 2048;
 
-struct trace {
-	struct perf_tool	tool;
-	struct {
-		int		machine;
-		int		open_id;
-	}			audit;
-	struct {
-		int		max;
-		struct syscall  *table;
-		struct {
-			struct perf_evsel *sys_enter,
-					  *sys_exit;
-		}		events;
-	} syscalls;
-	struct record_opts	opts;
-	struct perf_evlist	*evlist;
-	struct machine		*host;
-	struct thread		*current;
-	u64			base_time;
-	FILE			*output;
-	unsigned long		nr_events;
-	struct strlist		*ev_qualifier;
-	struct {
-		size_t		nr;
-		int		*entries;
-	}			ev_qualifier_ids;
-	struct intlist		*tid_list;
-	struct intlist		*pid_list;
-	struct {
-		size_t		nr;
-		pid_t		*entries;
-	}			filter_pids;
-	double			duration_filter;
-	double			runtime_ms;
-	struct {
-		u64		vfs_getname,
-				proc_getname;
-	} stats;
-	bool			not_ev_qualifier;
-	bool			live;
-	bool			full_time;
-	bool			sched;
-	bool			multiple_threads;
-	bool			summary;
-	bool			summary_only;
-	bool			show_comm;
-	bool			show_tool_stats;
-	bool			trace_syscalls;
-	bool			force;
-	bool			vfs_getname;
-	int			trace_pgfaults;
-};
-
 static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
 {
 	struct thread_trace *ttrace = thread__priv(thread);
@@ -1618,6 +1065,7 @@ static int trace__process_event(struct trace *trace, struct machine *machine,
 		color_fprintf(trace->output, PERF_COLOR_RED,
 			      "LOST %" PRIu64 " events!\n", event->lost.lost);
 		ret = machine__process_lost_event(machine, event, sample);
+		break;
 	default:
 		ret = machine__process_event(machine, event, sample);
 		break;
@@ -1635,6 +1083,24 @@ static int trace__tool_process(struct perf_tool *tool,
 	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);
@@ -1646,7 +1112,7 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 	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,
@@ -1661,7 +1127,7 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 static int syscall__set_arg_fmts(struct syscall *sc)
 {
 	struct format_field *field;
-	int idx = 0;
+	int idx = 0, len;
 
 	sc->arg_scnprintf = calloc(sc->nr_args, sizeof(void *));
 	if (sc->arg_scnprintf == NULL)
@@ -1673,8 +1139,31 @@ static int syscall__set_arg_fmts(struct syscall *sc)
 	for (field = sc->args; field; field = field->next) {
 		if (sc->fmt && sc->fmt->arg_scnprintf[idx])
 			sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
+		else if (strcmp(field->type, "const char *") == 0 &&
+			 (strcmp(field->name, "filename") == 0 ||
+			  strcmp(field->name, "path") == 0 ||
+			  strcmp(field->name, "pathname") == 0))
+			sc->arg_scnprintf[idx] = SCA_FILENAME;
 		else if (field->flags & FIELD_IS_POINTER)
 			sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
+		else if (strcmp(field->type, "pid_t") == 0)
+			sc->arg_scnprintf[idx] = SCA_PID;
+		else if (strcmp(field->type, "umode_t") == 0)
+			sc->arg_scnprintf[idx] = SCA_MODE_T;
+		else if ((strcmp(field->type, "int") == 0 ||
+			  strcmp(field->type, "unsigned int") == 0 ||
+			  strcmp(field->type, "long") == 0) &&
+			 (len = strlen(field->name)) >= 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
+			 * 65 int
+			 * 23 unsigned int
+			 * 7 unsigned long
+			 */
+			sc->arg_scnprintf[idx] = SCA_FD;
+		}
 		++idx;
 	}
 
@@ -1685,7 +1174,7 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 {
 	char tp_name[128];
 	struct syscall *sc;
-	const char *name = audit_syscall_to_name(id, trace->audit.machine);
+	const char *name = syscalltbl__name(trace->sctbl, id);
 
 	if (name == NULL)
 		return -1;
@@ -1760,7 +1249,7 @@ static int trace__validate_ev_qualifier(struct trace *trace)
 
 	strlist__for_each(pos, trace->ev_qualifier) {
 		const char *sc = pos->s;
-		int id = audit_name_to_syscall(sc, trace->audit.machine);
+		int id = syscalltbl__id(trace->sctbl, sc);
 
 		if (id < 0) {
 			if (err == 0) {
@@ -1846,7 +1335,12 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
 						     "%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) {
@@ -1987,7 +1481,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 			goto out_put;
 	}
 
-	if (!trace->summary_only)
+	if (!(trace->duration_filter || trace->summary_only || trace->min_stack))
 		trace__printf_interrupted_entry(trace, sample);
 
 	ttrace->entry_time = sample->time;
@@ -1998,9 +1492,9 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 					   args, trace, thread);
 
 	if (sc->is_exit) {
-		if (!trace->duration_filter && !trace->summary_only) {
+		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;
@@ -2018,6 +1512,29 @@ out_put:
 	return err;
 }
 
+static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evsel,
+				    struct perf_sample *sample,
+				    struct callchain_cursor *cursor)
+{
+	struct addr_location al;
+
+	if (machine__resolve(trace->host, &al, sample) < 0 ||
+	    thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, trace->max_stack))
+		return -1;
+
+	return 0;
+}
+
+static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sample)
+{
+	/* TODO: user-configurable print_opts */
+	const unsigned int print_opts = EVSEL__PRINT_SYM |
+				        EVSEL__PRINT_DSO |
+				        EVSEL__PRINT_UNKNOWN_AS_ADDR;
+
+	return sample__fprintf_callchain(sample, 38, print_opts, &callchain_cursor, trace->output);
+}
+
 static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 			   union perf_event *event __maybe_unused,
 			   struct perf_sample *sample)
@@ -2025,7 +1542,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	long ret;
 	u64 duration = 0;
 	struct thread *thread;
-	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
+	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1, callchain_ret = 0;
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	struct thread_trace *ttrace;
 
@@ -2042,7 +1559,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 
 	ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
 
-	if (id == trace->audit.open_id && ret >= 0 && ttrace->filename.pending_open) {
+	if (id == trace->open_id && ret >= 0 && ttrace->filename.pending_open) {
 		trace__set_fd_pathname(thread, ret, ttrace->filename.name);
 		ttrace->filename.pending_open = false;
 		++trace->stats.vfs_getname;
@@ -2057,6 +1574,15 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	} else if (trace->duration_filter)
 		goto out;
 
+	if (sample->callchain) {
+		callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
+		if (callchain_ret == 0) {
+			if (callchain_cursor.nr < trace->min_stack)
+				goto out;
+			callchain_ret = 1;
+		}
+	}
+
 	if (trace->summary_only)
 		goto out;
 
@@ -2073,7 +1599,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	if (sc->fmt == NULL) {
 signed_print:
 		fprintf(trace->output, ") = %ld", ret);
-	} else if (ret < 0 && sc->fmt->errmsg) {
+	} else if (ret < 0 && (sc->fmt->errmsg || sc->fmt->errpid)) {
 		char bf[STRERR_BUFSIZE];
 		const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
 			   *e = audit_errno_to_name(-ret);
@@ -2083,10 +1609,24 @@ signed_print:
 		fprintf(trace->output, ") = 0 Timeout");
 	else if (sc->fmt->hexret)
 		fprintf(trace->output, ") = %#lx", ret);
-	else
+	else if (sc->fmt->errpid) {
+		struct thread *child = machine__find_thread(trace->host, ret, ret);
+
+		if (child != NULL) {
+			fprintf(trace->output, ") = %ld", ret);
+			if (child->comm_set)
+				fprintf(trace->output, " (%s)", thread__comm_str(child));
+			thread__put(child);
+		}
+	} else
 		goto signed_print;
 
 	fputc('\n', trace->output);
+
+	if (callchain_ret > 0)
+		trace__fprintf_callchain(trace, sample);
+	else if (callchain_ret < 0)
+		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
 out:
 	ttrace->entry_pending = false;
 	err = 0;
@@ -2217,6 +1757,17 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 				union perf_event *event __maybe_unused,
 				struct perf_sample *sample)
 {
+	int callchain_ret = 0;
+
+	if (sample->callchain) {
+		callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
+		if (callchain_ret == 0) {
+			if (callchain_cursor.nr < trace->min_stack)
+				goto out;
+			callchain_ret = 1;
+		}
+	}
+
 	trace__printf_interrupted_entry(trace, sample);
 	trace__fprintf_tstamp(trace, sample->time, trace->output);
 
@@ -2234,6 +1785,12 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 	}
 
 	fprintf(trace->output, ")\n");
+
+	if (callchain_ret > 0)
+		trace__fprintf_callchain(trace, sample);
+	else if (callchain_ret < 0)
+		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+out:
 	return 0;
 }
 
@@ -2264,8 +1821,19 @@ static int trace__pgfault(struct trace *trace,
 	char map_type = 'd';
 	struct thread_trace *ttrace;
 	int err = -1;
+	int callchain_ret = 0;
 
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+
+	if (sample->callchain) {
+		callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
+		if (callchain_ret == 0) {
+			if (callchain_cursor.nr < trace->min_stack)
+				goto out_put;
+			callchain_ret = 1;
+		}
+	}
+
 	ttrace = thread__trace(thread, trace->output);
 	if (ttrace == NULL)
 		goto out_put;
@@ -2307,6 +1875,11 @@ static int trace__pgfault(struct trace *trace,
 	print_location(trace->output, sample, &al, true, false);
 
 	fprintf(trace->output, " (%c%c)\n", map_type, al.level);
+
+	if (callchain_ret > 0)
+		trace__fprintf_callchain(trace, sample);
+	else if (callchain_ret < 0)
+		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
 out:
 	err = 0;
 out_put:
@@ -2326,6 +1899,23 @@ static bool skip_sample(struct trace *trace, struct perf_sample *sample)
 	return false;
 }
 
+static void trace__set_base_time(struct trace *trace,
+				 struct perf_evsel *evsel,
+				 struct perf_sample *sample)
+{
+	/*
+	 * BPF events were not setting PERF_SAMPLE_TIME, so be more robust
+	 * and don't use sample->time unconditionally, we may end up having
+	 * some other event in the future without PERF_SAMPLE_TIME for good
+	 * reason, i.e. we may not be interested in its timestamps, just in
+	 * it taking place, picking some piece of information when it
+	 * appears in our event stream (vfs_getname comes to mind).
+	 */
+	if (trace->base_time == 0 && !trace->full_time &&
+	    (evsel->attr.sample_type & PERF_SAMPLE_TIME))
+		trace->base_time = sample->time;
+}
+
 static int trace__process_sample(struct perf_tool *tool,
 				 union perf_event *event,
 				 struct perf_sample *sample,
@@ -2340,8 +1930,7 @@ static int trace__process_sample(struct perf_tool *tool,
 	if (skip_sample(trace, sample))
 		return 0;
 
-	if (!trace->full_time && trace->base_time == 0)
-		trace->base_time = sample->time;
+	trace__set_base_time(trace, evsel, sample);
 
 	if (handler) {
 		++trace->nr_events;
@@ -2450,8 +2039,7 @@ static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
 	return true;
 }
 
-static int perf_evlist__add_pgfault(struct perf_evlist *evlist,
-				    u64 config)
+static struct perf_evsel *perf_evsel__new_pgfault(u64 config)
 {
 	struct perf_evsel *evsel;
 	struct perf_event_attr attr = {
@@ -2465,13 +2053,10 @@ static int perf_evlist__add_pgfault(struct perf_evlist *evlist,
 	event_attr_init(&attr);
 
 	evsel = perf_evsel__new(&attr);
-	if (!evsel)
-		return -ENOMEM;
+	if (evsel)
+		evsel->handler = trace__pgfault;
 
-	evsel->handler = trace__pgfault;
-	perf_evlist__add(evlist, evsel);
-
-	return 0;
+	return evsel;
 }
 
 static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample)
@@ -2479,9 +2064,6 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st
 	const u32 type = event->header.type;
 	struct perf_evsel *evsel;
 
-	if (!trace->full_time && trace->base_time == 0)
-		trace->base_time = sample->time;
-
 	if (type != PERF_RECORD_SAMPLE) {
 		trace__process_event(trace, trace->host, event, sample);
 		return;
@@ -2493,6 +2075,8 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st
 		return;
 	}
 
+	trace__set_base_time(trace, evsel, sample);
+
 	if (evsel->attr.type == PERF_TYPE_TRACEPOINT &&
 	    sample->raw_data == NULL) {
 		fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
@@ -2527,6 +2111,15 @@ static int trace__add_syscall_newtp(struct trace *trace)
 	perf_evlist__add(evlist, sys_enter);
 	perf_evlist__add(evlist, sys_exit);
 
+	if (callchain_param.enabled && !trace->kernel_syscallchains) {
+		/*
+		 * We're interested only in the user space callchain
+		 * leading to the syscall, allow overriding that for
+		 * debugging reasons using --kernel_syscall_callchains
+		 */
+		sys_exit->attr.exclude_callchain_kernel = 1;
+	}
+
 	trace->syscalls.events.sys_enter = sys_enter;
 	trace->syscalls.events.sys_exit  = sys_exit;
 
@@ -2565,7 +2158,7 @@ out_enomem:
 static int trace__run(struct trace *trace, int argc, const char **argv)
 {
 	struct perf_evlist *evlist = trace->evlist;
-	struct perf_evsel *evsel;
+	struct perf_evsel *evsel, *pgfault_maj = NULL, *pgfault_min = NULL;
 	int err = -1, i;
 	unsigned long before;
 	const bool forks = argc > 0;
@@ -2579,14 +2172,19 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (trace->trace_syscalls)
 		trace->vfs_getname = perf_evlist__add_vfs_getname(evlist);
 
-	if ((trace->trace_pgfaults & TRACE_PFMAJ) &&
-	    perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ)) {
-		goto out_error_mem;
+	if ((trace->trace_pgfaults & TRACE_PFMAJ)) {
+		pgfault_maj = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MAJ);
+		if (pgfault_maj == NULL)
+			goto out_error_mem;
+		perf_evlist__add(evlist, pgfault_maj);
 	}
 
-	if ((trace->trace_pgfaults & TRACE_PFMIN) &&
-	    perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN))
-		goto out_error_mem;
+	if ((trace->trace_pgfaults & TRACE_PFMIN)) {
+		pgfault_min = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MIN);
+		if (pgfault_min == NULL)
+			goto out_error_mem;
+		perf_evlist__add(evlist, pgfault_min);
+	}
 
 	if (trace->sched &&
 	    perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
@@ -2605,7 +2203,45 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
-	perf_evlist__config(evlist, &trace->opts);
+	perf_evlist__config(evlist, &trace->opts, NULL);
+
+	if (callchain_param.enabled) {
+		bool use_identifier = false;
+
+		if (trace->syscalls.events.sys_exit) {
+			perf_evsel__config_callchain(trace->syscalls.events.sys_exit,
+						     &trace->opts, &callchain_param);
+			use_identifier = true;
+		}
+
+		if (pgfault_maj) {
+			perf_evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param);
+			use_identifier = true;
+		}
+
+		if (pgfault_min) {
+			perf_evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param);
+			use_identifier = true;
+		}
+
+		if (use_identifier) {
+		       /*
+			* Now we have evsels with different sample_ids, use
+			* PERF_SAMPLE_IDENTIFIER to map from sample to evsel
+			* from a fixed position in each ring buffer record.
+			*
+			* As of this the changeset introducing this comment, this
+			* isn't strictly needed, as the fields that can come before
+			* PERF_SAMPLE_ID are all used, but we'll probably disable
+			* some of those for things like copying the payload of
+			* pointer syscall arguments, and for vfs_getname we don't
+			* need PERF_SAMPLE_ADDR and PERF_SAMPLE_IP, so do this
+			* here as a warning we need to use PERF_SAMPLE_IDENTIFIER.
+			*/
+			perf_evlist__set_sample_bit(evlist, IDENTIFIER);
+			perf_evlist__reset_sample_bit(evlist, ID);
+		}
+	}
 
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
@@ -2883,15 +2519,29 @@ static size_t trace__fprintf_threads_header(FILE *fp)
 	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");
@@ -2900,9 +2550,8 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
 	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;
@@ -2913,34 +2562,23 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
 			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;
 
@@ -2956,25 +2594,45 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 		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;
+	}
 
-	return data.printed;
+	resort_rb__for_each(nd, threads)
+		printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
+
+	resort_rb__delete(threads);
+
+	return printed;
 }
 
 static int trace__set_duration(const struct option *opt, const char *str,
@@ -3070,10 +2728,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 	struct trace trace = {
-		.audit = {
-			.machine = audit_detect_machine(),
-			.open_id = audit_name_to_syscall("open", trace.audit.machine),
-		},
 		.syscalls = {
 			. max = -1,
 		},
@@ -3091,6 +2745,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		.output = stderr,
 		.show_comm = true,
 		.trace_syscalls = true,
+		.kernel_syscallchains = false,
+		.max_stack = UINT_MAX,
 	};
 	const char *output_name = NULL;
 	const char *ev_qualifier_str = NULL;
@@ -3136,10 +2792,24 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Trace pagefaults", parse_pagefaults, "maj"),
 	OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"),
 	OPT_BOOLEAN('f', "force", &trace.force, "don't complain, do it"),
+	OPT_CALLBACK(0, "call-graph", &trace.opts,
+		     "record_mode[,record_size]", record_callchain_help,
+		     &record_parse_callchain_opt),
+	OPT_BOOLEAN(0, "kernel-syscall-graph", &trace.kernel_syscallchains,
+		    "Show the kernel callchains on the syscall exit path"),
+	OPT_UINTEGER(0, "min-stack", &trace.min_stack,
+		     "Set the minimum stack depth when parsing the callchain, "
+		     "anything below the specified depth will be ignored."),
+	OPT_UINTEGER(0, "max-stack", &trace.max_stack,
+		     "Set the maximum stack depth when parsing the callchain, "
+		     "anything beyond the specified depth will be ignored. "
+		     "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
 	OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
 	OPT_END()
 	};
+	bool __maybe_unused max_stack_user_set = true;
+	bool mmap_pages_user_set = true;
 	const char * const trace_subcommands[] = { "record", NULL };
 	int err;
 	char bf[BUFSIZ];
@@ -3148,8 +2818,9 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 	signal(SIGFPE, sighandler_dump_stack);
 
 	trace.evlist = perf_evlist__new();
+	trace.sctbl = syscalltbl__new();
 
-	if (trace.evlist == NULL) {
+	if (trace.evlist == NULL || trace.sctbl == NULL) {
 		pr_err("Not enough memory to run!\n");
 		err = -ENOMEM;
 		goto out;
@@ -3158,11 +2829,40 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 	argc = parse_options_subcommand(argc, argv, trace_options, trace_subcommands,
 				 trace_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 
+	err = bpf__setup_stdout(trace.evlist);
+	if (err) {
+		bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf));
+		pr_err("ERROR: Setup BPF stdout failed: %s\n", bf);
+		goto out;
+	}
+
+	err = -1;
+
 	if (trace.trace_pgfaults) {
 		trace.opts.sample_address = true;
 		trace.opts.sample_time = true;
 	}
 
+	if (trace.opts.mmap_pages == UINT_MAX)
+		mmap_pages_user_set = false;
+
+	if (trace.max_stack == UINT_MAX) {
+		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 && trace.trace_syscalls)
+		record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false);
+#endif
+
+	if (callchain_param.enabled) {
+		if (!mmap_pages_user_set && geteuid() == 0)
+			trace.opts.mmap_pages = perf_event_mlock_kb_in_pages() * 4;
+
+		symbol_conf.use_callchain = true;
+	}
+
 	if (trace.evlist->nr_entries > 0)
 		evlist__set_evsel_handler(trace.evlist, trace__event_handler);
 
@@ -3179,6 +2879,11 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		return -1;
 	}
 
+	if (!trace.trace_syscalls && ev_qualifier_str) {
+		pr_err("The -e option can't be used with --no-syscalls.\n");
+		goto out;
+	}
+
 	if (output_name != NULL) {
 		err = trace__open_output(&trace, output_name);
 		if (err < 0) {
@@ -3187,6 +2892,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 	}
 
+	trace.open_id = syscalltbl__id(trace.sctbl, "open");
+
 	if (ev_qualifier_str != NULL) {
 		const char *s = ev_qualifier_str;
 		struct strlist_config slist_config = {