perf/core improvements and fixes

index 93ac724fb635..6485576f3337 100644
@@ -1618,6 +1618,7 @@ 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;

index 6485576f3337..0c8bcb94934e 100644
@@ -40,6 +40,10 @@
 #include <sys/mman.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>
 
 /* For older distros: */
 #ifndef MAP_STACK

@@ -1001,6 +1005,46 @@ static const char *tioctls[] = {
 static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
 #endif /* defined(__i386__) || defined(__x86_64__) */
 
+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
+
+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
+
 #define STRARRAY(arg, name, array) \
 	  .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
 	  .arg_parm	 = { [arg] = &strarray__##array, }

@@ -1234,6 +1278,9 @@ static struct syscall_fmt {
 	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
 	{ .name	    = "rt_tgsigqueueinfo", .errmsg = true,
 	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
+	{ .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 */

index 0c8bcb94934e..c45c1cfeb866 100644
@@ -44,6 +44,7 @@
 #include <linux/filter.h>
 #include <linux/audit.h>
 #include <sys/ptrace.h>
+#include <linux/random.h>
 
 /* For older distros: */
 #ifndef MAP_STACK

@@ -1045,6 +1046,29 @@ static size_t syscall_arg__scnprintf_seccomp_flags(char *bf, size_t size,
 
 #define SCA_SECCOMP_FLAGS syscall_arg__scnprintf_seccomp_flags
 
+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, }

@@ -1137,6 +1161,8 @@ static struct syscall_fmt {
 	{ .name	    = "getdents64", .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "getitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
+	{ .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 */ }, },

index fd2868490d00..70ff7c14bea6 100644
@@ -46,3 +46,34 @@ u64 rdtsc(void)
 
 	return low | ((u64)high) << 32;
 }
+
+int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc,
+				struct perf_tool *tool,
+				perf_event__handler_t process,
+				struct machine *machine)
+{
+	union perf_event event = {
+		.time_conv = {
+			.header = {
+				.type = PERF_RECORD_TIME_CONV,
+				.size = sizeof(struct time_conv_event),
+			},
+		},
+	};
+	struct perf_tsc_conversion tc;
+	int err;
+
+	err = perf_read_tsc_conversion(pc, &tc);
+	if (err == -EOPNOTSUPP)
+		return 0;
+	if (err)
+		return err;
+
+	pr_debug2("Synthesizing TSC conversion information\n");
+
+	event.time_conv.time_mult  = tc.time_mult;
+	event.time_conv.time_shift = tc.time_shift;
+	event.time_conv.time_zero  = tc.time_zero;
+
+	return process(tool, &event, NULL, machine);
+}

index d1a2d104f2bc..e5afa8fe1bf1 100644
@@ -748,6 +748,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.auxtrace_info	= perf_event__repipe_op2_synth,
 			.auxtrace	= perf_event__repipe_auxtrace,
 			.auxtrace_error	= perf_event__repipe_op2_synth,
+			.time_conv	= perf_event__repipe_op2_synth,
 			.finished_round	= perf_event__repipe_oe_synth,
 			.build_id	= perf_event__repipe_op2_synth,
 			.id_index	= perf_event__repipe_op2_synth,

index 515510ecc76a..410035c6e300 100644
@@ -29,6 +29,7 @@
 #include "util/data.h"
 #include "util/perf_regs.h"
 #include "util/auxtrace.h"
+#include "util/tsc.h"
 #include "util/parse-branch-options.h"
 #include "util/parse-regs-options.h"
 #include "util/llvm-utils.h"

@@ -512,6 +513,15 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
 
 static void snapshot_sig_handler(int sig);
 
+int __weak
+perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused,
+			    struct perf_tool *tool __maybe_unused,
+			    perf_event__handler_t process __maybe_unused,
+			    struct machine *machine __maybe_unused)
+{
+	return 0;
+}
+
 static int record__synthesize(struct record *rec)
 {
 	struct perf_session *session = rec->session;

@@ -549,6 +559,11 @@ static int record__synthesize(struct record *rec)
 		}
 	}
 
+	err = perf_event__synth_time_conv(rec->evlist->mmap[0].base, tool,
+					  process_synthesized_event, machine);
+	if (err)
+		goto out;
+
 	if (rec->opts.full_auxtrace) {
 		err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
 					session, process_synthesized_event);

index dad55d04ffdd..b68959037688 100644
@@ -45,6 +45,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_STAT]			= "STAT",
 	[PERF_RECORD_STAT_ROUND]		= "STAT_ROUND",
 	[PERF_RECORD_EVENT_UPDATE]		= "EVENT_UPDATE",
+	[PERF_RECORD_TIME_CONV]			= "TIME_CONV",
 };
 
 const char *perf_event__name(unsigned int id)

index 6bb1c928350d..8d363d5e65a2 100644
@@ -233,6 +233,7 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_STAT			= 76,
 	PERF_RECORD_STAT_ROUND			= 77,
 	PERF_RECORD_EVENT_UPDATE		= 78,
+	PERF_RECORD_TIME_CONV			= 79,
 	PERF_RECORD_HEADER_MAX
 };
 

@@ -469,6 +470,13 @@ struct stat_round_event {
 	u64				time;
 };
 
+struct time_conv_event {
+	struct perf_event_header header;
+	u64 time_shift;
+	u64 time_mult;
+	u64 time_zero;
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;

@@ -497,6 +505,7 @@ union perf_event {
 	struct stat_config_event	stat_config;
 	struct stat_event		stat;
 	struct stat_round_event		stat_round;
+	struct time_conv_event		time_conv;
 };
 
 void perf_event__print_totals(void);

index 4abd85c6346d..ef370557fb9a 100644
@@ -409,6 +409,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->stat = process_stat_stub;
 	if (tool->stat_round == NULL)
 		tool->stat_round = process_stat_round_stub;
+	if (tool->time_conv == NULL)
+		tool->time_conv = process_event_op2_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)

@@ -794,6 +796,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_STAT]		  = perf_event__stat_swap,
 	[PERF_RECORD_STAT_ROUND]	  = perf_event__stat_round_swap,
 	[PERF_RECORD_EVENT_UPDATE]	  = perf_event__event_update_swap,
+	[PERF_RECORD_TIME_CONV]		  = perf_event__all64_swap,
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 

@@ -1341,6 +1344,9 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		return tool->stat(tool, event, session);
 	case PERF_RECORD_STAT_ROUND:
 		return tool->stat_round(tool, event, session);
+	case PERF_RECORD_TIME_CONV:
+		session->time_conv = event->time_conv;
+		return tool->time_conv(tool, event, session);
 	default:
 		return -EINVAL;
 	}

index 5f792e35d4c1..f96fc9e8c52e 100644
@@ -26,6 +26,7 @@ struct perf_session {
 	struct itrace_synth_opts *itrace_synth_opts;
 	struct list_head	auxtrace_index;
 	struct trace_event	tevent;
+	struct time_conv_event	time_conv;
 	bool			repipe;
 	bool			one_mmap;
 	void			*one_mmap_addr;

index 55de4cffcd4e..ac2590a3de2d 100644
@@ -57,6 +57,7 @@ struct perf_tool {
 			id_index,
 			auxtrace_info,
 			auxtrace_error,
+			time_conv,
 			thread_map,
 			cpu_map,
 			stat_config,

index a8b78f1b3243..280ddc067556 100644
@@ -3,10 +3,20 @@
 
 #include <linux/types.h>
 
+#include "event.h"
 #include "../arch/x86/util/tsc.h"
 
 u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
 u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
 u64 rdtsc(void);
 
+struct perf_event_mmap_page;
+struct perf_tool;
+struct machine;
+
+int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc,
+				struct perf_tool *tool,
+				perf_event__handler_t process,
+				struct machine *machine);
+
 #endif

index 70ff7c14bea6..357f1b13b5ae 100644
@@ -7,7 +7,6 @@
 #include <linux/types.h>
 #include "../../util/debug.h"
 #include "../../util/tsc.h"
-#include "tsc.h"
 
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 			     struct perf_tsc_conversion *tc)

deleted file mode 100644
index 2edc4d31065c..000000000000
@@ -1,17 +0,0 @@
-#ifndef TOOLS_PERF_ARCH_X86_UTIL_TSC_H__
-#define TOOLS_PERF_ARCH_X86_UTIL_TSC_H__
-
-#include <linux/types.h>
-
-struct perf_tsc_conversion {
-	u16 time_shift;
-	u32 time_mult;
-	u64 time_zero;
-};
-
-struct perf_event_mmap_page;
-
-int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
-			     struct perf_tsc_conversion *tc);
-
-#endif /* TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ */

76 lines not on this page · raw message

index ad0c0bb1fbc7..52fcef3074fe 100644
@@ -17,6 +17,7 @@
 #include "strlist.h"
 #include <elf.h>
 
+#include "tsc.h"
 #include "session.h"
 #include "jit.h"
 #include "jitdump.h"

@@ -33,6 +34,7 @@ struct jit_buf_desc {
 	size_t           bufsize;
 	FILE             *in;
 	bool		 needs_bswap; /* handles cross-endianess */
+	bool		 use_arch_timestamp;
 	void		 *debug_data;
 	size_t		 nr_debug_entries;
 	uint32_t         code_load_count;

@@ -158,13 +160,16 @@ jit_open(struct jit_buf_desc *jd, const char *name)
 		header.flags      = bswap_64(header.flags);
 	}
 
+	jd->use_arch_timestamp = header.flags & JITDUMP_FLAGS_ARCH_TIMESTAMP;
+
 	if (verbose > 2)
-		pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\n",
+		pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\nuse_arch_timestamp=%d\n",
 			header.version,
 			header.total_size,
 			(unsigned long long)header.timestamp,
 			header.pid,
-			header.elf_mach);
+			header.elf_mach,
+			jd->use_arch_timestamp);
 
 	if (header.flags & JITDUMP_FLAGS_RESERVED) {
 		pr_err("jitdump file contains invalid or unsupported flags 0x%llx\n",

@@ -172,10 +177,15 @@ jit_open(struct jit_buf_desc *jd, const char *name)
 		goto error;
 	}
 
+	if (jd->use_arch_timestamp && !jd->session->time_conv.time_mult) {
+		pr_err("jitdump file uses arch timestamps but there is no timestamp conversion\n");
+		goto error;
+	}
+
 	/*
 	 * validate event is using the correct clockid
 	 */
-	if (jit_validate_events(jd->session)) {
+	if (!jd->use_arch_timestamp && jit_validate_events(jd->session)) {
 		pr_err("error, jitted code must be sampled with perf record -k 1\n");
 		goto error;
 	}

@@ -329,6 +339,23 @@ jit_inject_event(struct jit_buf_desc *jd, union perf_event *event)
 	return 0;
 }
 
+static uint64_t convert_timestamp(struct jit_buf_desc *jd, uint64_t timestamp)
+{
+	struct perf_tsc_conversion tc;
+
+	if (!jd->use_arch_timestamp)
+		return timestamp;
+
+	tc.time_shift = jd->session->time_conv.time_shift;
+	tc.time_mult  = jd->session->time_conv.time_mult;
+	tc.time_zero  = jd->session->time_conv.time_zero;
+
+	if (!tc.time_mult)
+		return 0;
+
+	return tsc_to_perf_time(timestamp, &tc);
+}
+
 static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 {
 	struct perf_sample sample;

@@ -410,7 +437,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 		id->tid  = tid;
 	}
 	if (jd->sample_type & PERF_SAMPLE_TIME)
-		id->time = jr->load.p.timestamp;
+		id->time = convert_timestamp(jd, jr->load.p.timestamp);
 
 	/*
 	 * create pseudo sample to induce dso hit increment

@@ -499,7 +526,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 		id->tid  = tid;
 	}
 	if (jd->sample_type & PERF_SAMPLE_TIME)
-		id->time = jr->load.p.timestamp;
+		id->time = convert_timestamp(jd, jr->load.p.timestamp);
 
 	/*
 	 * create pseudo sample to induce dso hit increment

index b66c1f503d9e..bcacd20d0c1c 100644
@@ -23,9 +23,12 @@
 #define JITHEADER_VERSION 1
 
 enum jitdump_flags_bits {
+	JITDUMP_FLAGS_ARCH_TIMESTAMP_BIT,
 	JITDUMP_FLAGS_MAX_BIT,
 };
 
+#define JITDUMP_FLAGS_ARCH_TIMESTAMP	(1ULL << JITDUMP_FLAGS_ARCH_TIMESTAMP_BIT)
+
 #define JITDUMP_FLAGS_RESERVED (JITDUMP_FLAGS_MAX_BIT < 64 ? \
 				(~((1ULL << JITDUMP_FLAGS_MAX_BIT) - 1)) : 0)
 

index 280ddc067556..d5b11e2b85e0 100644
@@ -4,7 +4,16 @@
 #include <linux/types.h>
 
 #include "event.h"
-#include "../arch/x86/util/tsc.h"
+
+struct perf_tsc_conversion {
+	u16 time_shift;
+	u32 time_mult;
+	u64 time_zero;
+};
+struct perf_event_mmap_page;
+
+int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
+			     struct perf_tsc_conversion *tc);
 
 u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
 u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);

index d66f9ad4df2e..7dc30637cf66 100644
@@ -438,6 +438,11 @@ struct auxtrace_record *intel_bts_recording_init(int *err)
 	if (!intel_bts_pmu)
 		return NULL;
 
+	if (setenv("JITDUMP_USE_ARCH_TIMESTAMP", "1", 1)) {
+		*err = -errno;
+		return NULL;
+	}
+
 	btsr = zalloc(sizeof(struct intel_bts_recording));
 	if (!btsr) {
 		*err = -ENOMEM;

index a3395179c9ee..a07b9605e93b 100644
@@ -1027,6 +1027,11 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 	if (!intel_pt_pmu)
 		return NULL;
 
+	if (setenv("JITDUMP_USE_ARCH_TIMESTAMP", "1", 1)) {
+		*err = -errno;
+		return NULL;
+	}
+
 	ptr = zalloc(sizeof(struct intel_pt_recording));
 	if (!ptr) {
 		*err = -ENOMEM;

index adef23b1352e..bf34468a99cb 100644
@@ -602,14 +602,13 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
 
 static __u64 pmu_format_max_value(const unsigned long *format)
 {
-	int w;
+	__u64 w = 0;
+	int fbit;
 
-	w = bitmap_weight(format, PERF_PMU_FORMAT_BITS);
-	if (!w)
-		return 0;
-	if (w < 64)
-		return (1ULL << w) - 1;
-	return -1;
+	for_each_set_bit(fbit, format, PERF_PMU_FORMAT_BITS)
+		w |= (1ULL << fbit);
+
+	return w;
 }
 
 /*

index c45c1cfeb866..99daeed55a9b 100644
@@ -2400,6 +2400,14 @@ 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 __maybe_unused,
+				 struct perf_sample *sample)
+{
+	if (trace->base_time == 0 && !trace->full_time)
+		trace->base_time = sample->time;
+}
+
 static int trace__process_sample(struct perf_tool *tool,
 				 union perf_event *event,
 				 struct perf_sample *sample,

@@ -2414,8 +2422,7 @@ 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;

@@ -2553,9 +2560,6 @@ 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;

@@ -2567,6 +2571,8 @@ 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",

index 99daeed55a9b..d309f4535a45 100644
@@ -2401,10 +2401,19 @@ static bool skip_sample(struct trace *trace, struct perf_sample *sample)
 }
 
 static void trace__set_base_time(struct trace *trace,
-				 struct perf_evsel *evsel __maybe_unused,
+				 struct perf_evsel *evsel,
 				 struct perf_sample *sample)
 {
-	if (trace->base_time == 0 && !trace->full_time)
+	/*
+	 * 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;
 }
 

index 738ce226002b..3fd7c2c72f4a 100644
@@ -226,7 +226,8 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 		perf_evsel__init(evsel, attr, idx);
 
 	if (perf_evsel__is_bpf_output(evsel)) {
-		evsel->attr.sample_type |= PERF_SAMPLE_RAW;
+		evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
+					    PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD),
 		evsel->attr.sample_period = 1;
 	}