Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/…

…linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "Various fixes.

  The -g perf report lockup you reported is only partially addressed,
  patches that fix the excessive runtime are still being worked on"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86: Fix uncore PCI fixed counter handling
  uprobes: Fix utask->depth accounting in handle_trampoline()
  perf/x86: Add constraint for IVB CYCLE_ACTIVITY:CYCLES_LDM_PENDING
  perf: Fix up MMAP2 buffer space reservation
  perf tools: Add attr->mmap2 support
  perf kvm: Fix sample_type manipulation
  perf evlist: Fix id pos in perf_evlist__open()
  perf trace: Handle perf.data files with no tracepoints
  perf session: Separate progress bar update when processing events
  perf trace: Check if MAP_32BIT is defined
  perf hists: Fix formatting of long symbol names
  perf evlist: Fix parsing with no sample_id_all bit set
  perf tools: Add test for parsing with no sample_id_all bit
  perf trace: Check control+C more often

arch/x86/kernel/cpu/perf_event_intel.c

@@ -124,6 +124,7 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
 	INTEL_UEVENT_CONSTRAINT(0x0148, 0x4), /* L1D_PEND_MISS.PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMTPY */
 	INTEL_UEVENT_CONSTRAINT(0x019c, 0xf), /* IDQ_UOPS_NOT_DELIVERED.CORE */
+	INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_LDM_PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
 	INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x06a3, 0xf), /* CYCLE_ACTIVITY.STALLS_LDM_PENDING */

arch/x86/kernel/cpu/perf_event_intel_uncore.c

@@ -2808,7 +2808,7 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve
 			return c;
 	}
 
-	if (event->hw.config == ~0ULL)
+	if (event->attr.config == UNCORE_FIXED_EVENT)
 		return &constraint_fixed;
 
 	if (type->constraints) {
@@ -3112,7 +3112,9 @@ static int uncore_pmu_event_init(struct perf_event *event)
 		 */
 		if (pmu->type->single_fixed && pmu->pmu_idx > 0)
 			return -EINVAL;
-		hwc->config = ~0ULL;
+
+		/* fixed counters have event field hardcoded to zero */
+		hwc->config = 0ULL;
 	} else {
 		hwc->config = event->attr.config & pmu->type->event_mask;
 		if (pmu->type->ops->hw_config) {

kernel/events/core.c

@@ -5039,6 +5039,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 		mmap_event->event_id.header.size += sizeof(mmap_event->maj);
 		mmap_event->event_id.header.size += sizeof(mmap_event->min);
 		mmap_event->event_id.header.size += sizeof(mmap_event->ino);
+		mmap_event->event_id.header.size += sizeof(mmap_event->ino_generation);
 	}
 
 	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);

kernel/events/uprobes.c

@@ -1682,12 +1682,10 @@ static bool handle_trampoline(struct pt_regs *regs)
 		tmp = ri;
 		ri = ri->next;
 		kfree(tmp);
+		utask->depth--;
 
 		if (!chained)
 			break;
-
-		utask->depth--;
-
 		BUG_ON(!ri);
 	}
 

tools/perf/Makefile

@@ -394,6 +394,8 @@ ifeq ($(ARCH),x86)
 LIB_OBJS += $(OUTPUT)tests/perf-time-to-tsc.o
 endif
 LIB_OBJS += $(OUTPUT)tests/code-reading.o
+LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
+LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -439,7 +441,6 @@ PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT)
 ifneq ($(OUTPUT),)
   CFLAGS += -I$(OUTPUT)
 endif
-LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
 
 ifdef NO_LIBELF
 EXTLIBS := $(filter-out -lelf,$(EXTLIBS))

tools/perf/builtin-annotate.c

@@ -277,6 +277,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		.tool = {
 			.sample	= process_sample_event,
 			.mmap	= perf_event__process_mmap,
+			.mmap2	= perf_event__process_mmap2,
 			.comm	= perf_event__process_comm,
 			.exit	= perf_event__process_exit,
 			.fork	= perf_event__process_fork,

tools/perf/builtin-inject.c

@@ -123,6 +123,19 @@ static int perf_event__repipe_mmap(struct perf_tool *tool,
 	return err;
 }
 
+static int perf_event__repipe_mmap2(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine)
+{
+	int err;
+
+	err = perf_event__process_mmap2(tool, event, sample, machine);
+	perf_event__repipe(tool, event, sample, machine);
+
+	return err;
+}
+
 static int perf_event__repipe_fork(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct perf_sample *sample,
@@ -339,6 +352,7 @@ static int __cmd_inject(struct perf_inject *inject)
 
 	if (inject->build_ids || inject->sched_stat) {
 		inject->tool.mmap	  = perf_event__repipe_mmap;
+		inject->tool.mmap2	  = perf_event__repipe_mmap2;
 		inject->tool.fork	  = perf_event__repipe_fork;
 		inject->tool.tracing_data = perf_event__repipe_tracing_data;
 	}
@@ -390,6 +404,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 		.tool = {
 			.sample		= perf_event__repipe_sample,
 			.mmap		= perf_event__repipe,
+			.mmap2		= perf_event__repipe,
 			.comm		= perf_event__repipe,
 			.fork		= perf_event__repipe,
 			.exit		= perf_event__repipe,

tools/perf/builtin-kvm.c

@@ -1165,16 +1165,16 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 		struct perf_event_attr *attr = &pos->attr;
 
 		/* make sure these *are* set */
-		attr->sample_type |= PERF_SAMPLE_TID;
-		attr->sample_type |= PERF_SAMPLE_TIME;
-		attr->sample_type |= PERF_SAMPLE_CPU;
-		attr->sample_type |= PERF_SAMPLE_RAW;
+		perf_evsel__set_sample_bit(pos, TID);
+		perf_evsel__set_sample_bit(pos, TIME);
+		perf_evsel__set_sample_bit(pos, CPU);
+		perf_evsel__set_sample_bit(pos, RAW);
 		/* make sure these are *not*; want as small a sample as possible */
-		attr->sample_type &= ~PERF_SAMPLE_PERIOD;
-		attr->sample_type &= ~PERF_SAMPLE_IP;
-		attr->sample_type &= ~PERF_SAMPLE_CALLCHAIN;
-		attr->sample_type &= ~PERF_SAMPLE_ADDR;
-		attr->sample_type &= ~PERF_SAMPLE_READ;
+		perf_evsel__reset_sample_bit(pos, PERIOD);
+		perf_evsel__reset_sample_bit(pos, IP);
+		perf_evsel__reset_sample_bit(pos, CALLCHAIN);
+		perf_evsel__reset_sample_bit(pos, ADDR);
+		perf_evsel__reset_sample_bit(pos, READ);
 		attr->mmap = 0;
 		attr->comm = 0;
 		attr->task = 0;

tools/perf/builtin-mem.c

@@ -190,6 +190,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 		.tool = {
 			.sample		= process_sample_event,
 			.mmap		= perf_event__process_mmap,
+			.mmap2		= perf_event__process_mmap2,
 			.comm		= perf_event__process_comm,
 			.lost		= perf_event__process_lost,
 			.fork		= perf_event__process_fork,

tools/perf/builtin-report.c

@@ -744,6 +744,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		.tool = {
 			.sample		 = process_sample_event,
 			.mmap		 = perf_event__process_mmap,
+			.mmap2		 = perf_event__process_mmap2,
 			.comm		 = perf_event__process_comm,
 			.exit		 = perf_event__process_exit,
 			.fork		 = perf_event__process_fork,

tools/perf/builtin-script.c

@@ -542,6 +542,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 static struct perf_tool perf_script = {
 	.sample		 = process_sample_event,
 	.mmap		 = perf_event__process_mmap,
+	.mmap2		 = perf_event__process_mmap2,
 	.comm		 = perf_event__process_comm,
 	.exit		 = perf_event__process_exit,
 	.fork		 = perf_event__process_fork,

tools/perf/builtin-trace.c

@@ -100,7 +100,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 	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);
@@ -994,6 +996,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 			handler = evsel->handler.func;
 			handler(trace, evsel, &sample);
+
+			if (done)
+				goto out_unmap_evlist;
 		}
 	}
 

tools/perf/tests/builtin-test.c

@@ -111,6 +111,10 @@ static struct test {
 		.desc = "Test using a dummy software event to keep tracking",
 		.func = test__keep_tracking,
 	},
+	{
+		.desc = "Test parsing with no sample_id_all bit set",
+		.func = test__parse_no_sample_id_all,
+	},
 	{
 		.func = NULL,
 	},

tools/perf/tests/parse-no-sample-id-all.c

@@ -0,0 +1,108 @@
+#include <sys/types.h>
+#include <stddef.h>
+
+#include "tests.h"
+
+#include "event.h"
+#include "evlist.h"
+#include "header.h"
+#include "util.h"
+
+static int process_event(struct perf_evlist **pevlist, union perf_event *event)
+{
+	struct perf_sample sample;
+
+	if (event->header.type == PERF_RECORD_HEADER_ATTR) {
+		if (perf_event__process_attr(NULL, event, pevlist)) {
+			pr_debug("perf_event__process_attr failed\n");
+			return -1;
+		}
+		return 0;
+	}
+
+	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
+		return -1;
+
+	if (!*pevlist)
+		return -1;
+
+	if (perf_evlist__parse_sample(*pevlist, event, &sample)) {
+		pr_debug("perf_evlist__parse_sample failed\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int process_events(union perf_event **events, size_t count)
+{
+	struct perf_evlist *evlist = NULL;
+	int err = 0;
+	size_t i;
+
+	for (i = 0; i < count && !err; i++)
+		err = process_event(&evlist, events[i]);
+
+	if (evlist)
+		perf_evlist__delete(evlist);
+
+	return err;
+}
+
+struct test_attr_event {
+	struct attr_event attr;
+	u64 id;
+};
+
+/**
+ * test__parse_no_sample_id_all - test parsing with no sample_id_all bit set.
+ *
+ * This function tests parsing data produced on kernel's that do not support the
+ * sample_id_all bit.  Without the sample_id_all bit, non-sample events (such as
+ * mmap events) do not have an id sample appended, and consequently logic
+ * designed to determine the id will not work.  That case happens when there is
+ * more than one selected event, so this test processes three events: 2
+ * attributes representing the selected events and one mmap event.
+ *
+ * Return: %0 on success, %-1 if the test fails.
+ */
+int test__parse_no_sample_id_all(void)
+{
+	int err;
+
+	struct test_attr_event event1 = {
+		.attr = {
+			.header = {
+				.type = PERF_RECORD_HEADER_ATTR,
+				.size = sizeof(struct test_attr_event),
+			},
+		},
+		.id = 1,
+	};
+	struct test_attr_event event2 = {
+		.attr = {
+			.header = {
+				.type = PERF_RECORD_HEADER_ATTR,
+				.size = sizeof(struct test_attr_event),
+			},
+		},
+		.id = 2,
+	};
+	struct mmap_event event3 = {
+		.header = {
+			.type = PERF_RECORD_MMAP,
+			.size = sizeof(struct mmap_event),
+		},
+	};
+	union perf_event *events[] = {
+		(union perf_event *)&event1,
+		(union perf_event *)&event2,
+		(union perf_event *)&event3,
+	};
+
+	err = process_events(events, ARRAY_SIZE(events));
+	if (err)
+		return -1;
+
+	return 0;
+}

tools/perf/tests/perf-record.c

@@ -50,7 +50,7 @@ int test__PERF_RECORD(void)
 	struct perf_sample sample;
 	const char *cmd = "sleep";
 	const char *argv[] = { cmd, "1", NULL, };
-	char *bname;
+	char *bname, *mmap_filename;
 	u64 prev_time = 0;
 	bool found_cmd_mmap = false,
 	     found_libc_mmap = false,
@@ -212,6 +212,7 @@ int test__PERF_RECORD(void)
 
 				if ((type == PERF_RECORD_COMM ||
 				     type == PERF_RECORD_MMAP ||
+				     type == PERF_RECORD_MMAP2 ||
 				     type == PERF_RECORD_FORK ||
 				     type == PERF_RECORD_EXIT) &&
 				     (pid_t)event->comm.pid != evlist->workload.pid) {
@@ -220,7 +221,8 @@ int test__PERF_RECORD(void)
 				}
 
 				if ((type == PERF_RECORD_COMM ||
-				     type == PERF_RECORD_MMAP) &&
+				     type == PERF_RECORD_MMAP ||
+				     type == PERF_RECORD_MMAP2) &&
 				     event->comm.pid != event->comm.tid) {
 					pr_debug("%s with different pid/tid!\n", name);
 					++errs;
@@ -236,7 +238,12 @@ int test__PERF_RECORD(void)
 				case PERF_RECORD_EXIT:
 					goto found_exit;
 				case PERF_RECORD_MMAP:
-					bname = strrchr(event->mmap.filename, '/');
+					mmap_filename = event->mmap.filename;
+					goto check_bname;
+				case PERF_RECORD_MMAP2:
+					mmap_filename = event->mmap2.filename;
+				check_bname:
+					bname = strrchr(mmap_filename, '/');
 					if (bname != NULL) {
 						if (!found_cmd_mmap)
 							found_cmd_mmap = !strcmp(bname + 1, cmd);
@@ -245,7 +252,7 @@ int test__PERF_RECORD(void)
 						if (!found_ld_mmap)
 							found_ld_mmap = !strncmp(bname + 1, "ld", 2);
 					} else if (!found_vdso_mmap)
-						found_vdso_mmap = !strcmp(event->mmap.filename, "[vdso]");
+						found_vdso_mmap = !strcmp(mmap_filename, "[vdso]");
 					break;
 
 				case PERF_RECORD_SAMPLE:

tools/perf/tests/tests.h

@@ -39,5 +39,6 @@ int test__perf_time_to_tsc(void);
 int test__code_reading(void);
 int test__sample_parsing(void);
 int test__keep_tracking(void);
+int test__parse_no_sample_id_all(void);
 
 #endif /* TESTS_H */