Merge tag 'perf-core-for-mingo-5.7-20200317' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

perf record:

  Alexey Budankov:

  - Fix binding of AIO user space buffers to nodes

maps:

  Dominik b. Czarnota:

  - Fix off by one in strncpy() size argument.

  Arnaldo Carvalho de Melo:

  - Use strstarts() to look for Android libraries.

  Ian Rogers:

  - Give synthetic mmap events an inode generation.

man pages:

  Ian Rogers:

  - Set man page date to last git commit.

perf test:

  Ian Rogers:

  - Print if shell directory isn't present.

perf report:

  Jin Yao:

  - Fix no branch type statistics report issue.

perf expr:

  Jiri Olsa:

  - Fix copy/paste mistake

vendor events:

  Kan Liang:

  - Support metric constraints.

vendor events intel:

  Kan Liang:

  - Add NO_NMI_WATCHDOG metric constraint.

vendor events s390:

  Thomas Richter:

 - Add new deflate counters for IBM z15.

ARM cs-etm:

  Leo Yan:

  - Last branch improvements.

intel-pt:

  Adrian Hunter:

  - Update intel-pt.txt file with new location of the documentation.

  - Add Intel PT man page references.

  - Rename intel-pt.txt and put it in man page format.

perl scripting:

  Michael Petlan:

 - Add common_callchain to fix argument order.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Conflicts:
	tools/perf/util/map.c

9 files changed, 240 insertions, 86 deletions

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index b3b3fe3ea345..62d2f9b9ce1b 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -363,6 +363,23 @@ struct cs_etm_packet_queue
 	return NULL;
 }
 
+static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm,
+				struct cs_etm_traceid_queue *tidq)
+{
+	struct cs_etm_packet *tmp;
+
+	if (etm->sample_branches || etm->synth_opts.last_branch ||
+	    etm->sample_instructions) {
+		/*
+		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
+		 * the next incoming packet.
+		 */
+		tmp = tidq->packet;
+		tidq->packet = tidq->prev_packet;
+		tidq->prev_packet = tmp;
+	}
+}
+
 static void cs_etm__packet_dump(const char *pkt_string)
 {
 	const char *color = PERF_COLOR_BLUE;
@@ -945,7 +962,7 @@ static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq,
 	if (packet->isa == CS_ETM_ISA_T32) {
 		u64 addr = packet->start_addr;
 
-		while (offset > 0) {
+		while (offset) {
 			addr += cs_etm__t32_instr_size(etmq,
 						       trace_chan_id, addr);
 			offset--;
@@ -1134,10 +1151,8 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 
 	cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);
 
-	if (etm->synth_opts.last_branch) {
-		cs_etm__copy_last_branch_rb(etmq, tidq);
+	if (etm->synth_opts.last_branch)
 		sample.branch_stack = tidq->last_branch;
-	}
 
 	if (etm->synth_opts.inject) {
 		ret = cs_etm__inject_event(event, &sample,
@@ -1153,9 +1168,6 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 			"CS ETM Trace: failed to deliver instruction event, error %d\n",
 			ret);
 
-	if (etm->synth_opts.last_branch)
-		cs_etm__reset_last_branch_rb(tidq);
-
 	return ret;
 }
 
@@ -1342,12 +1354,14 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 			  struct cs_etm_traceid_queue *tidq)
 {
 	struct cs_etm_auxtrace *etm = etmq->etm;
-	struct cs_etm_packet *tmp;
 	int ret;
 	u8 trace_chan_id = tidq->trace_chan_id;
-	u64 instrs_executed = tidq->packet->instr_count;
+	u64 instrs_prev;
+
+	/* Get instructions remainder from previous packet */
+	instrs_prev = tidq->period_instructions;
 
-	tidq->period_instructions += instrs_executed;
+	tidq->period_instructions += tidq->packet->instr_count;
 
 	/*
 	 * Record a branch when the last instruction in
@@ -1365,26 +1379,80 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 		 * TODO: allow period to be defined in cycles and clock time
 		 */
 
-		/* Get number of instructions executed after the sample point */
-		u64 instrs_over = tidq->period_instructions -
-			etm->instructions_sample_period;
+		/*
+		 * Below diagram demonstrates the instruction samples
+		 * generation flows:
+		 *
+		 *    Instrs     Instrs       Instrs       Instrs
+		 *   Sample(n)  Sample(n+1)  Sample(n+2)  Sample(n+3)
+		 *    |            |            |            |
+		 *    V            V            V            V
+		 *   --------------------------------------------------
+		 *            ^                                  ^
+		 *            |                                  |
+		 *         Period                             Period
+		 *    instructions(Pi)                   instructions(Pi')
+		 *
+		 *            |                                  |
+		 *            \---------------- -----------------/
+		 *                             V
+		 *                 tidq->packet->instr_count
+		 *
+		 * Instrs Sample(n...) are the synthesised samples occurring
+		 * every etm->instructions_sample_period instructions - as
+		 * defined on the perf command line.  Sample(n) is being the
+		 * last sample before the current etm packet, n+1 to n+3
+		 * samples are generated from the current etm packet.
+		 *
+		 * tidq->packet->instr_count represents the number of
+		 * instructions in the current etm packet.
+		 *
+		 * Period instructions (Pi) contains the the number of
+		 * instructions executed after the sample point(n) from the
+		 * previous etm packet.  This will always be less than
+		 * etm->instructions_sample_period.
+		 *
+		 * When generate new samples, it combines with two parts
+		 * instructions, one is the tail of the old packet and another
+		 * is the head of the new coming packet, to generate
+		 * sample(n+1); sample(n+2) and sample(n+3) consume the
+		 * instructions with sample period.  After sample(n+3), the rest
+		 * instructions will be used by later packet and it is assigned
+		 * to tidq->period_instructions for next round calculation.
+		 */
 
 		/*
-		 * Calculate the address of the sampled instruction (-1 as
-		 * sample is reported as though instruction has just been
-		 * executed, but PC has not advanced to next instruction)
+		 * Get the initial offset into the current packet instructions;
+		 * entry conditions ensure that instrs_prev is less than
+		 * etm->instructions_sample_period.
 		 */
-		u64 offset = (instrs_executed - instrs_over - 1);
-		u64 addr = cs_etm__instr_addr(etmq, trace_chan_id,
-					      tidq->packet, offset);
+		u64 offset = etm->instructions_sample_period - instrs_prev;
+		u64 addr;
 
-		ret = cs_etm__synth_instruction_sample(
-			etmq, tidq, addr, etm->instructions_sample_period);
-		if (ret)
-			return ret;
+		/* Prepare last branches for instruction sample */
+		if (etm->synth_opts.last_branch)
+			cs_etm__copy_last_branch_rb(etmq, tidq);
 
-		/* Carry remaining instructions into next sample period */
-		tidq->period_instructions = instrs_over;
+		while (tidq->period_instructions >=
+				etm->instructions_sample_period) {
+			/*
+			 * Calculate the address of the sampled instruction (-1
+			 * as sample is reported as though instruction has just
+			 * been executed, but PC has not advanced to next
+			 * instruction)
+			 */
+			addr = cs_etm__instr_addr(etmq, trace_chan_id,
+						  tidq->packet, offset - 1);
+			ret = cs_etm__synth_instruction_sample(
+				etmq, tidq, addr,
+				etm->instructions_sample_period);
+			if (ret)
+				return ret;
+
+			offset += etm->instructions_sample_period;
+			tidq->period_instructions -=
+				etm->instructions_sample_period;
+		}
 	}
 
 	if (etm->sample_branches) {
@@ -1406,15 +1474,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 		}
 	}
 
-	if (etm->sample_branches || etm->synth_opts.last_branch) {
-		/*
-		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
-		 * the next incoming packet.
-		 */
-		tmp = tidq->packet;
-		tidq->packet = tidq->prev_packet;
-		tidq->prev_packet = tmp;
-	}
+	cs_etm__packet_swap(etm, tidq);
 
 	return 0;
 }
@@ -1443,7 +1503,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 {
 	int err = 0;
 	struct cs_etm_auxtrace *etm = etmq->etm;
-	struct cs_etm_packet *tmp;
 
 	/* Handle start tracing packet */
 	if (tidq->prev_packet->sample_type == CS_ETM_EMPTY)
@@ -1451,6 +1510,11 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 
 	if (etmq->etm->synth_opts.last_branch &&
 	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+		u64 addr;
+
+		/* Prepare last branches for instruction sample */
+		cs_etm__copy_last_branch_rb(etmq, tidq);
+
 		/*
 		 * Generate a last branch event for the branches left in the
 		 * circular buffer at the end of the trace.
@@ -1458,7 +1522,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 		 * Use the address of the end of the last reported execution
 		 * range
 		 */
-		u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+		addr = cs_etm__last_executed_instr(tidq->prev_packet);
 
 		err = cs_etm__synth_instruction_sample(
 			etmq, tidq, addr,
@@ -1478,15 +1542,11 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 	}
 
 swap_packet:
-	if (etm->sample_branches || etm->synth_opts.last_branch) {
-		/*
-		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
-		 * the next incoming packet.
-		 */
-		tmp = tidq->packet;
-		tidq->packet = tidq->prev_packet;
-		tidq->prev_packet = tmp;
-	}
+	cs_etm__packet_swap(etm, tidq);
+
+	/* Reset last branches after flush the trace */
+	if (etm->synth_opts.last_branch)
+		cs_etm__reset_last_branch_rb(tidq);
 
 	return err;
 }
@@ -1507,11 +1567,16 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
 	 */
 	if (etmq->etm->synth_opts.last_branch &&
 	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+		u64 addr;
+
+		/* Prepare last branches for instruction sample */
+		cs_etm__copy_last_branch_rb(etmq, tidq);
+
 		/*
 		 * Use the address of the end of the last reported execution
 		 * range.
 		 */
-		u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+		addr = cs_etm__last_executed_instr(tidq->prev_packet);
 
 		err = cs_etm__synth_instruction_sample(
 			etmq, tidq, addr,
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
index 1928f2a3dddc..eaad29243c23 100644
--- a/tools/perf/util/expr.l
+++ b/tools/perf/util/expr.l
@@ -79,10 +79,10 @@ symbol		{spec}*{sym}*{spec}*{sym}*
 	{
 		int start_token;
 
-		start_token = parse_events_get_extra(yyscanner);
+		start_token = expr_get_extra(yyscanner);
 
 		if (start_token) {
-			parse_events_set_extra(NULL, yyscanner);
+			expr_set_extra(NULL, yyscanner);
 			return start_token;
 		}
 	}
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index b342f744b1fc..53d96611e6a6 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -44,8 +44,8 @@ static inline int is_no_dso_memory(const char *filename)
 
 static inline int is_android_lib(const char *filename)
 {
-	return !strncmp(filename, "/data/app-lib", 13) ||
-	       !strncmp(filename, "/system/lib", 11);
+	return strstarts(filename, "/data/app-lib/") ||
+	       strstarts(filename, "/system/lib/");
 }
 
 static inline bool replace_android_lib(const char *filename, char *newfilename)
@@ -65,7 +65,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 
 	app_abi_length = strlen(app_abi);
 
-	if (!strncmp(filename, "/data/app-lib", 13)) {
+	if (strstarts(filename, "/data/app-lib/")) {
 		char *apk_path;
 
 		if (!app_abi_length)
@@ -89,7 +89,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 		return true;
 	}
 
-	if (!strncmp(filename, "/system/lib/", 12)) {
+	if (strstarts(filename, "/system/lib/")) {
 		char *ndk, *app;
 		const char *arch;
 		size_t ndk_length;
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 02aee946b6c1..c3a8c701609a 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -22,6 +22,8 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
 #include <subcmd/parse-options.h>
+#include <api/fs/fs.h>
+#include "util.h"
 
 struct metric_event *metricgroup__lookup(struct rblist *metric_events,
 					 struct evsel *evsel,
@@ -399,13 +401,85 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 	strlist__delete(metriclist);
 }
 
+static void metricgroup__add_metric_weak_group(struct strbuf *events,
+					       const char **ids,
+					       int idnum)
+{
+	bool no_group = false;
+	int i;
+
+	for (i = 0; i < idnum; i++) {
+		pr_debug("found event %s\n", ids[i]);
+		/*
+		 * Duration time maps to a software event and can make
+		 * groups not count. Always use it outside a
+		 * group.
+		 */
+		if (!strcmp(ids[i], "duration_time")) {
+			if (i > 0)
+				strbuf_addf(events, "}:W,");
+			strbuf_addf(events, "duration_time");
+			no_group = true;
+			continue;
+		}
+		strbuf_addf(events, "%s%s",
+			i == 0 || no_group ? "{" : ",",
+			ids[i]);
+		no_group = false;
+	}
+	if (!no_group)
+		strbuf_addf(events, "}:W");
+}
+
+static void metricgroup__add_metric_non_group(struct strbuf *events,
+					      const char **ids,
+					      int idnum)
+{
+	int i;
+
+	for (i = 0; i < idnum; i++)
+		strbuf_addf(events, ",%s", ids[i]);
+}
+
+static void metricgroup___watchdog_constraint_hint(const char *name, bool foot)
+{
+	static bool violate_nmi_constraint;
+
+	if (!foot) {
+		pr_warning("Splitting metric group %s into standalone metrics.\n", name);
+		violate_nmi_constraint = true;
+		return;
+	}
+
+	if (!violate_nmi_constraint)
+		return;
+
+	pr_warning("Try disabling the NMI watchdog to comply NO_NMI_WATCHDOG metric constraint:\n"
+		   "    echo 0 > /proc/sys/kernel/nmi_watchdog\n"
+		   "    perf stat ...\n"
+		   "    echo 1 > /proc/sys/kernel/nmi_watchdog\n");
+}
+
+static bool metricgroup__has_constraint(struct pmu_event *pe)
+{
+	if (!pe->metric_constraint)
+		return false;
+
+	if (!strcmp(pe->metric_constraint, "NO_NMI_WATCHDOG") &&
+	    sysctl__nmi_watchdog_enabled()) {
+		metricgroup___watchdog_constraint_hint(pe->metric_name, false);
+		return true;
+	}
+
+	return false;
+}
+
 static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 				   struct list_head *group_list)
 {
 	struct pmu_events_map *map = perf_pmu__find_map(NULL);
 	struct pmu_event *pe;
-	int ret = -EINVAL;
-	int i, j;
+	int i, ret = -EINVAL;
 
 	if (!map)
 		return 0;
@@ -422,7 +496,6 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 			const char **ids;
 			int idnum;
 			struct egroup *eg;
-			bool no_group = false;
 
 			pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
 
@@ -431,27 +504,11 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 				continue;
 			if (events->len > 0)
 				strbuf_addf(events, ",");
-			for (j = 0; j < idnum; j++) {
-				pr_debug("found event %s\n", ids[j]);
-				/*
-				 * Duration time maps to a software event and can make
-				 * groups not count. Always use it outside a
-				 * group.
-				 */
-				if (!strcmp(ids[j], "duration_time")) {
-					if (j > 0)
-						strbuf_addf(events, "}:W,");
-					strbuf_addf(events, "duration_time");
-					no_group = true;
-					continue;
-				}
-				strbuf_addf(events, "%s%s",
-					j == 0 || no_group ? "{" : ",",
-					ids[j]);
-				no_group = false;
-			}
-			if (!no_group)
-				strbuf_addf(events, "}:W");
+
+			if (metricgroup__has_constraint(pe))
+				metricgroup__add_metric_non_group(events, ids, idnum);
+			else
+				metricgroup__add_metric_weak_group(events, ids, idnum);
 
 			eg = malloc(sizeof(struct egroup));
 			if (!eg) {
@@ -493,6 +550,10 @@ static int metricgroup__add_metric_list(const char *list, struct strbuf *events,
 		}
 	}
 	free(nlist);
+
+	if (!ret)
+		metricgroup___watchdog_constraint_hint(NULL, true);
+
 	return ret;
 }
 
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 3b664fa673a6..ab7108d22428 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -98,20 +98,29 @@ static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity)
 {
 	void *data;
 	size_t mmap_len;
-	unsigned long node_mask;
+	unsigned long *node_mask;
+	unsigned long node_index;
+	int err = 0;
 
 	if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
 		data = map->aio.data[idx];
 		mmap_len = mmap__mmap_len(map);
-		node_mask = 1UL << cpu__get_node(cpu);
-		if (mbind(data, mmap_len, MPOL_BIND, &node_mask, 1, 0)) {
-			pr_err("Failed to bind [%p-%p] AIO buffer to node %d: error %m\n",
-				data, data + mmap_len, cpu__get_node(cpu));
+		node_index = cpu__get_node(cpu);
+		node_mask = bitmap_alloc(node_index + 1);
+		if (!node_mask) {
+			pr_err("Failed to allocate node mask for mbind: error %m\n");
 			return -1;
 		}
+		set_bit(node_index, node_mask);
+		if (mbind(data, mmap_len, MPOL_BIND, node_mask, node_index + 1 + 1, 0)) {
+			pr_err("Failed to bind [%p-%p] AIO buffer to node %lu: error %m\n",
+				data, data + mmap_len, node_index);
+			err = -1;
+		}
+		bitmap_free(node_mask);
 	}
 
-	return 0;
+	return err;
 }
 #else /* !HAVE_LIBNUMA_SUPPORT */
 static int perf_mmap__aio_alloc(struct mmap *map, int idx)
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index d89cb0da90f8..76c6052b12e2 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -16,6 +16,7 @@
 #include <linux/ctype.h>
 #include "cgroup.h"
 #include <api/fs/fs.h>
+#include "util.h"
 
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
@@ -1097,7 +1098,6 @@ static void print_footer(struct perf_stat_config *config)
 {
 	double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
 	FILE *output = config->output;
-	int n;
 
 	if (!config->null_run)
 		fprintf(output, "\n");
@@ -1131,9 +1131,7 @@ static void print_footer(struct perf_stat_config *config)
 	}
 	fprintf(output, "\n\n");
 
-	if (config->print_free_counters_hint &&
-	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
-	    n > 0)
+	if (config->print_free_counters_hint && sysctl__nmi_watchdog_enabled())
 		fprintf(output,
 "Some events weren't counted. Try disabling the NMI watchdog:\n"
 "	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index dd3e6f43fb86..3f28af39f9c6 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -345,6 +345,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			continue;
 
 		event->mmap2.ino = (u64)ino;
+		event->mmap2.ino_generation = 0;
 
 		/*
 		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 969ae560dad9..d707c9624dd9 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -55,6 +55,24 @@ int sysctl__max_stack(void)
 	return sysctl_perf_event_max_stack;
 }
 
+bool sysctl__nmi_watchdog_enabled(void)
+{
+	static bool cached;
+	static bool nmi_watchdog;
+	int value;
+
+	if (cached)
+		return nmi_watchdog;
+
+	if (sysctl__read_int("kernel/nmi_watchdog", &value) < 0)
+		return false;
+
+	nmi_watchdog = (value > 0) ? true : false;
+	cached = true;
+
+	return nmi_watchdog;
+}
+
 bool test_attr__enabled;
 
 bool perf_host  = true;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 9969b8b46f7c..f486fdd3a538 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -29,6 +29,8 @@ size_t hex_width(u64 v);
 
 int sysctl__max_stack(void);
 
+bool sysctl__nmi_watchdog_enabled(void);
+
 int fetch_kernel_version(unsigned int *puint,
 			 char *str, size_t str_sz);
 #define KVER_VERSION(x)		(((x) >> 16) & 0xff)