Merge tag 'perf-core-for-mingo' 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:

User visible changes:

  * Fix mmap return address truncation to 32-bit in 'perf trace'. (Chang Hyun Park)

  * Support operations for shared futexes. (Davidlohr Bueso)

  * Fix error message for --filter option not coming after tracepoint. (Arnaldo Carvalho de Melo)

Infrastructure changes:

  * Refactor unit and scale function parameters for PMU parsing routines. (Matt Fleming)

  * Improve DSO long names lookup with rbtree, resulting in great speedup for
    workloads with lots of DSOs. (Waiman Long)

  * Fix build breakage on arm64 targets. (Will Deacon)

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

tools/perf/arch/arm64/util/unwind-libunwind.c

@@ -3,6 +3,7 @@
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
+#include "../../util/debug.h"
 
 int libunwind__arch_reg_id(int regnum)
 {

tools/perf/bench/futex-hash.c

@@ -26,6 +26,7 @@ static unsigned int nsecs    = 10;
 /* amount of futexes per thread */
 static unsigned int nfutexes = 1024;
 static bool fshared = false, done = false, silent = false;
+static int futex_flag = 0;
 
 struct timeval start, end, runtime;
 static pthread_mutex_t thread_lock;
@@ -75,8 +76,7 @@ static void *workerfn(void *arg)
 			 * such as internal waitqueue handling, thus enlarging
 			 * the critical region protected by hb->lock.
 			 */
-			ret = futex_wait(&w->futex[i], 1234, NULL,
-					 fshared ? 0 : FUTEX_PRIVATE_FLAG);
+			ret = futex_wait(&w->futex[i], 1234, NULL, futex_flag);
 			if (!silent &&
 			    (!ret || errno != EAGAIN || errno != EWOULDBLOCK))
 				warn("Non-expected futex return call");
@@ -135,6 +135,9 @@ int bench_futex_hash(int argc, const char **argv,
 	if (!worker)
 		goto errmem;
 
+	if (!fshared)
+		futex_flag = FUTEX_PRIVATE_FLAG;
+
 	printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n",
 	       getpid(), nthreads, nfutexes, fshared ? "shared":"private", nsecs);
 

tools/perf/bench/futex-requeue.c

@@ -30,16 +30,18 @@ static u_int32_t futex1 = 0, futex2 = 0;
 static unsigned int nrequeue = 1;
 
 static pthread_t *worker;
-static bool done = 0, silent = 0;
+static bool done = false, silent = false, fshared = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats requeuetime_stats, requeued_stats;
 static unsigned int ncpus, threads_starting, nthreads = 0;
+static int futex_flag = 0;
 
 static const struct option options[] = {
 	OPT_UINTEGER('t', "threads",  &nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
 	OPT_BOOLEAN( 's', "silent",   &silent,   "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",   &fshared,  "Use shared futexes instead of private ones"),
 	OPT_END()
 };
 
@@ -70,7 +72,7 @@ static void *workerfn(void *arg __maybe_unused)
 	pthread_cond_wait(&thread_worker, &thread_lock);
 	pthread_mutex_unlock(&thread_lock);
 
-	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	futex_wait(&futex1, 0, NULL, futex_flag);
 	return NULL;
 }
 
@@ -127,9 +129,12 @@ int bench_futex_requeue(int argc, const char **argv,
 	if (!worker)
 		err(EXIT_FAILURE, "calloc");
 
-	printf("Run summary [PID %d]: Requeuing %d threads (from %p to %p), "
-	       "%d at a time.\n\n",
-	       getpid(), nthreads, &futex1, &futex2, nrequeue);
+	if (!fshared)
+		futex_flag = FUTEX_PRIVATE_FLAG;
+
+	printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), "
+	       "%d at a time.\n\n",  getpid(), nthreads,
+	       fshared ? "shared":"private", &futex1, &futex2, nrequeue);
 
 	init_stats(&requeued_stats);
 	init_stats(&requeuetime_stats);
@@ -156,16 +161,20 @@ int bench_futex_requeue(int argc, const char **argv,
 
 		/* Ok, all threads are patiently blocked, start requeueing */
 		gettimeofday(&start, NULL);
-		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue)
+		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) {
 			/*
 			 * Do not wakeup any tasks blocked on futex1, allowing
 			 * us to really measure futex_wait functionality.
 			 */
-			futex_cmp_requeue(&futex1, 0, &futex2, 0, nrequeue,
-					  FUTEX_PRIVATE_FLAG);
+			futex_cmp_requeue(&futex1, 0, &futex2, 0,
+					  nrequeue, futex_flag);
+		}
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 
+		if (nrequeued > nthreads)
+			nrequeued = nthreads;
+
 		update_stats(&requeued_stats, nrequeued);
 		update_stats(&requeuetime_stats, runtime.tv_usec);
 
@@ -175,7 +184,7 @@ int bench_futex_requeue(int argc, const char **argv,
 		}
 
 		/* everybody should be blocked on futex2, wake'em up */
-		nrequeued = futex_wake(&futex2, nthreads, FUTEX_PRIVATE_FLAG);
+		nrequeued = futex_wake(&futex2, nthreads, futex_flag);
 		if (nthreads != nrequeued)
 			warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
 
@@ -184,7 +193,6 @@ int bench_futex_requeue(int argc, const char **argv,
 			if (ret)
 				err(EXIT_FAILURE, "pthread_join");
 		}
-
 	}
 
 	/* cleanup & report results */

tools/perf/bench/futex-wake.c

@@ -31,16 +31,18 @@ static u_int32_t futex1 = 0;
 static unsigned int nwakes = 1;
 
 pthread_t *worker;
-static bool done = false, silent = false;
+static bool done = false, silent = false, fshared = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats waketime_stats, wakeup_stats;
 static unsigned int ncpus, threads_starting, nthreads = 0;
+static int futex_flag = 0;
 
 static const struct option options[] = {
 	OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('w', "nwakes",  &nwakes,   "Specify amount of threads to wake at once"),
 	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",  &fshared,  "Use shared futexes instead of private ones"),
 	OPT_END()
 };
 
@@ -58,7 +60,7 @@ static void *workerfn(void *arg __maybe_unused)
 	pthread_cond_wait(&thread_worker, &thread_lock);
 	pthread_mutex_unlock(&thread_lock);
 
-	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	futex_wait(&futex1, 0, NULL, futex_flag);
 	return NULL;
 }
 
@@ -130,9 +132,12 @@ int bench_futex_wake(int argc, const char **argv,
 	if (!worker)
 		err(EXIT_FAILURE, "calloc");
 
-	printf("Run summary [PID %d]: blocking on %d threads (at futex %p), "
+	if (!fshared)
+		futex_flag = FUTEX_PRIVATE_FLAG;
+
+	printf("Run summary [PID %d]: blocking on %d threads (at [%s] futex %p), "
 	       "waking up %d at a time.\n\n",
-	       getpid(), nthreads, &futex1, nwakes);
+	       getpid(), nthreads, fshared ? "shared":"private",  &futex1, nwakes);
 
 	init_stats(&wakeup_stats);
 	init_stats(&waketime_stats);
@@ -160,7 +165,7 @@ int bench_futex_wake(int argc, const char **argv,
 		/* Ok, all threads are patiently blocked, start waking folks up */
 		gettimeofday(&start, NULL);
 		while (nwoken != nthreads)
-			nwoken += futex_wake(&futex1, nwakes, FUTEX_PRIVATE_FLAG);
+			nwoken += futex_wake(&futex1, nwakes, futex_flag);
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 

tools/perf/builtin-trace.c

@@ -1695,7 +1695,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 			   union perf_event *event __maybe_unused,
 			   struct perf_sample *sample)
 {
-	int ret;
+	long ret;
 	u64 duration = 0;
 	struct thread *thread;
 	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
@@ -1748,7 +1748,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 
 	if (sc->fmt == NULL) {
 signed_print:
-		fprintf(trace->output, ") = %d", ret);
+		fprintf(trace->output, ") = %ld", ret);
 	} else if (ret < 0 && sc->fmt->errmsg) {
 		char bf[STRERR_BUFSIZE];
 		const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
@@ -1758,7 +1758,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	} else if (ret == 0 && sc->fmt->timeout)
 		fprintf(trace->output, ") = 0 Timeout");
 	else if (sc->fmt->hexret)
-		fprintf(trace->output, ") = %#x", ret);
+		fprintf(trace->output, ") = %#lx", ret);
 	else
 		goto signed_print;
 

tools/perf/util/dso.c

@@ -653,6 +653,65 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
 	return dso;
 }
 
+/*
+ * Find a matching entry and/or link current entry to RB tree.
+ * Either one of the dso or name parameter must be non-NULL or the
+ * function will not work.
+ */
+static struct dso *dso__findlink_by_longname(struct rb_root *root,
+					     struct dso *dso, const char *name)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node  *parent = NULL;
+
+	if (!name)
+		name = dso->long_name;
+	/*
+	 * Find node with the matching name
+	 */
+	while (*p) {
+		struct dso *this = rb_entry(*p, struct dso, rb_node);
+		int rc = strcmp(name, this->long_name);
+
+		parent = *p;
+		if (rc == 0) {
+			/*
+			 * In case the new DSO is a duplicate of an existing
+			 * one, print an one-time warning & put the new entry
+			 * at the end of the list of duplicates.
+			 */
+			if (!dso || (dso == this))
+				return this;	/* Find matching dso */
+			/*
+			 * The core kernel DSOs may have duplicated long name.
+			 * In this case, the short name should be different.
+			 * Comparing the short names to differentiate the DSOs.
+			 */
+			rc = strcmp(dso->short_name, this->short_name);
+			if (rc == 0) {
+				pr_err("Duplicated dso name: %s\n", name);
+				return NULL;
+			}
+		}
+		if (rc < 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+	if (dso) {
+		/* Add new node and rebalance tree */
+		rb_link_node(&dso->rb_node, parent, p);
+		rb_insert_color(&dso->rb_node, root);
+	}
+	return NULL;
+}
+
+static inline struct dso *
+dso__find_by_longname(const struct rb_root *root, const char *name)
+{
+	return dso__findlink_by_longname((struct rb_root *)root, NULL, name);
+}
+
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 {
 	if (name == NULL)
@@ -755,6 +814,7 @@ struct dso *dso__new(const char *name)
 		dso->a2l_fails = 1;
 		dso->kernel = DSO_TYPE_USER;
 		dso->needs_swap = DSO_SWAP__UNSET;
+		RB_CLEAR_NODE(&dso->rb_node);
 		INIT_LIST_HEAD(&dso->node);
 		INIT_LIST_HEAD(&dso->data.open_entry);
 	}
@@ -765,6 +825,10 @@ struct dso *dso__new(const char *name)
 void dso__delete(struct dso *dso)
 {
 	int i;
+
+	if (!RB_EMPTY_NODE(&dso->rb_node))
+		pr_err("DSO %s is still in rbtree when being deleted!\n",
+		       dso->long_name);
 	for (i = 0; i < MAP__NR_TYPES; ++i)
 		symbols__delete(&dso->symbols[i]);
 
@@ -851,35 +915,34 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 	return have_build_id;
 }
 
-void dsos__add(struct list_head *head, struct dso *dso)
+void dsos__add(struct dsos *dsos, struct dso *dso)
 {
-	list_add_tail(&dso->node, head);
+	list_add_tail(&dso->node, &dsos->head);
+	dso__findlink_by_longname(&dsos->root, dso, NULL);
 }
 
-struct dso *dsos__find(const struct list_head *head, const char *name, bool cmp_short)
+struct dso *dsos__find(const struct dsos *dsos, const char *name,
+		       bool cmp_short)
 {
 	struct dso *pos;
 
 	if (cmp_short) {
-		list_for_each_entry(pos, head, node)
+		list_for_each_entry(pos, &dsos->head, node)
 			if (strcmp(pos->short_name, name) == 0)
 				return pos;
 		return NULL;
 	}
-	list_for_each_entry(pos, head, node)
-		if (strcmp(pos->long_name, name) == 0)
-			return pos;
-	return NULL;
+	return dso__find_by_longname(&dsos->root, name);
 }
 
-struct dso *__dsos__findnew(struct list_head *head, const char *name)
+struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
 {
-	struct dso *dso = dsos__find(head, name, false);
+	struct dso *dso = dsos__find(dsos, name, false);
 
 	if (!dso) {
 		dso = dso__new(name);
 		if (dso != NULL) {
-			dsos__add(head, dso);
+			dsos__add(dsos, dso);
 			dso__set_basename(dso);
 		}
 	}

tools/perf/util/dso.h

@@ -90,8 +90,18 @@ struct dso_cache {
 	char data[0];
 };
 
+/*
+ * DSOs are put into both a list for fast iteration and rbtree for fast
+ * long name lookup.
+ */
+struct dsos {
+	struct list_head head;
+	struct rb_root	 root;	/* rbtree root sorted by long name */
+};
+
 struct dso {
 	struct list_head node;
+	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
 	void		 *a2l;
@@ -224,10 +234,10 @@ struct map *dso__new_map(const char *name);
 struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
 				const char *short_name, int dso_type);
 
-void dsos__add(struct list_head *head, struct dso *dso);
-struct dso *dsos__find(const struct list_head *head, const char *name,
+void dsos__add(struct dsos *dsos, struct dso *dso);
+struct dso *dsos__find(const struct dsos *dsos, const char *name,
 		       bool cmp_short);
-struct dso *__dsos__findnew(struct list_head *head, const char *name);
+struct dso *__dsos__findnew(struct dsos *dsos, const char *name);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
 
 size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,