Skip to contentSkip to conversation

perf fixes

GIT PULL Ingo Molnar 1 participant 1 message Apr 16, 2014

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

# HEAD: ad466db5b0c302e85ad96c42a43194c234cbd862 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf into perf/urgent

Tooling fixes, plus a simple hardware-enablement patch for the Intel RAPL PMU (energy use measurement) on Haswell CPUs, which I hope is still fine at this stage.

Thanks,

Ingo

------------------>
Adrian Hunter (1):
perf tools: Fix double free in perf test 21 (code-reading.c)

Andi Kleen (1):
perf stat: Initialize statistics correctly

Arnaldo Carvalho de Melo (2):
perf callchains: Disable unwind libraries when libelf isn't found
MAINTAINERS: Change e-mail to kernel.org one

Cody P Schafer (1):
perf tools: Instead of redirecting flex output, use -o

Masami Hiramatsu (1):
perf probe: Fix to handle errors in line_range searching

Namhyung Kim (5):
perf top: Fix documentation of invalid -s option
tools lib traceevent: Print event name when show warning if possible tools lib traceevent: Do not call warning() directly perf probe: Fix --line option behavior
perf probe: Use dwarf_getcfi_elf() instead of dwarf_getcfi()

Ramkumar Ramachandra (4):
perf tools: Pick up libdw without explicit LIBDW_DIR perf bench: Update manpage to mention numa and futex perf bench: Fix segfault at the end of an 'all' execution perf bench: Set more defaults in the 'numa' suite

Vince Weaver (1):
perf/x86: Enable DRAM RAPL support on Intel Haswell

 MAINTAINERS                                 |   2 +-
 arch/x86/kernel/cpu/perf_event_intel_rapl.c |  33 ++++++++-
 tools/lib/traceevent/event-parse.c          | 109 +++++++++++++++++-----------
 tools/perf/Documentation/perf-bench.txt     |  22 ++++++
 tools/perf/Documentation/perf-top.txt       |   1 -
 tools/perf/Makefile.perf                    |   4 +-
 tools/perf/bench/numa.c                     |   4 +
 tools/perf/builtin-stat.c                   |  11 ++-
 tools/perf/config/Makefile                  |   7 +-
 tools/perf/tests/code-reading.c             |   1 +
 tools/perf/util/probe-finder.c              |  15 ++--
 11 files changed, 148 insertions(+), 61 deletions(-)
MAINTAINERS +1 -1
index 6dc67b1..80399ff 100644
@@ -6782,7 +6782,7 @@ PERFORMANCE EVENTS SUBSYSTEM
 M:	Peter Zijlstra <[email protected]>
 M:	Paul Mackerras <[email protected]>
 M:	Ingo Molnar <[email protected]>
-M:	Arnaldo Carvalho de Melo <[email protected]>
+M:	Arnaldo Carvalho de Melo <[email protected]>
 L:	[email protected]
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
 S:	Supported
arch/x86/kernel/cpu/perf_event_intel_rapl.c +30 -3
index 059218e..4b9a9e9 100644
@@ -59,7 +59,7 @@
 #define INTEL_RAPL_PKG		0x2	/* pseudo-encoding */
 #define RAPL_IDX_RAM_NRG_STAT	2	/* DRAM */
 #define INTEL_RAPL_RAM		0x3	/* pseudo-encoding */
-#define RAPL_IDX_PP1_NRG_STAT	3	/* DRAM */
+#define RAPL_IDX_PP1_NRG_STAT	3	/* gpu */
 #define INTEL_RAPL_PP1		0x4	/* pseudo-encoding */
 
 /* Clients have PP0, PKG */
@@ -72,6 +72,12 @@
 			 1<<RAPL_IDX_PKG_NRG_STAT|\
 			 1<<RAPL_IDX_RAM_NRG_STAT)
 
+/* Servers have PP0, PKG, RAM, PP1 */
+#define RAPL_IDX_HSW	(1<<RAPL_IDX_PP0_NRG_STAT|\
+			 1<<RAPL_IDX_PKG_NRG_STAT|\
+			 1<<RAPL_IDX_RAM_NRG_STAT|\
+			 1<<RAPL_IDX_PP1_NRG_STAT)
+
 /*
  * event code: LSB 8 bits, passed in attr->config
  * any other bit is reserved
@@ -425,6 +431,24 @@ static struct attribute *rapl_events_cln_attr[] = {
 	NULL,
 };
 
+static struct attribute *rapl_events_hsw_attr[] = {
+	EVENT_PTR(rapl_cores),
+	EVENT_PTR(rapl_pkg),
+	EVENT_PTR(rapl_gpu),
+	EVENT_PTR(rapl_ram),
+
+	EVENT_PTR(rapl_cores_unit),
+	EVENT_PTR(rapl_pkg_unit),
+	EVENT_PTR(rapl_gpu_unit),
+	EVENT_PTR(rapl_ram_unit),
+
+	EVENT_PTR(rapl_cores_scale),
+	EVENT_PTR(rapl_pkg_scale),
+	EVENT_PTR(rapl_gpu_scale),
+	EVENT_PTR(rapl_ram_scale),
+	NULL,
+};
+
 static struct attribute_group rapl_pmu_events_group = {
 	.name = "events",
 	.attrs = NULL, /* patched at runtime */
@@ -631,11 +655,14 @@ static int __init rapl_pmu_init(void)
 	switch (boot_cpu_data.x86_model) {
 	case 42: /* Sandy Bridge */
 	case 58: /* Ivy Bridge */
-	case 60: /* Haswell */
-	case 69: /* Haswell-Celeron */
 		rapl_cntr_mask = RAPL_IDX_CLN;
 		rapl_pmu_events_group.attrs = rapl_events_cln_attr;
 		break;
+	case 60: /* Haswell */
+	case 69: /* Haswell-Celeron */
+		rapl_cntr_mask = RAPL_IDX_HSW;
+		rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
+		break;
 	case 45: /* Sandy Bridge-EP */
 	case 62: /* IvyTown */
 		rapl_cntr_mask = RAPL_IDX_SRV;
tools/lib/traceevent/event-parse.c +66 -43

360 lines not on this page · raw message

tools/perf/Documentation/perf-bench.txt +22 -0
index 7065cd6..4464ad7 100644
@@ -48,6 +48,12 @@ SUBSYSTEM
 'mem'::
 	Memory access performance.
 
+'numa'::
+	NUMA scheduling and MM benchmarks.
+
+'futex'::
+	Futex stressing benchmarks.
+
 'all'::
 	All benchmark subsystems.
 
@@ -187,6 +193,22 @@ Show only the result with page faults before memset.
 --no-prefault::
 Show only the result without page faults before memset.
 
+SUITES FOR 'numa'
+~~~~~~~~~~~~~~~~~
+*mem*::
+Suite for evaluating NUMA workloads.
+
+SUITES FOR 'futex'
+~~~~~~~~~~~~~~~~~~
+*hash*::
+Suite for evaluating hash tables.
+
+*wake*::
+Suite for evaluating wake calls.
+
+*requeue*::
+Suite for evaluating requeue calls.
+
 SEE ALSO
 --------
 linkperf:perf[1]
tools/perf/Documentation/perf-top.txt +0 -1
index cdd8d49..976b00c 100644
@@ -87,7 +87,6 @@ Default is to monitor all CPUS.
 --realtime=<priority>::
 	Collect data with this RT SCHED_FIFO priority.
 
--s <symbol>::
 --sym-annotate=<symbol>::
         Annotate this symbol.
 
tools/perf/Makefile.perf +2 -2
index 50d875d..e969233 100644
@@ -192,13 +192,13 @@ endif
 export PERL_PATH
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
-	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c
+	$(QUIET_FLEX)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
 
 $(OUTPUT)util/parse-events-bison.c: util/parse-events.y
 	$(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c -p parse_events_
 
 $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
-	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c
+	$(QUIET_FLEX)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
 
 $(OUTPUT)util/pmu-bison.c: util/pmu.y
 	$(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c -p perf_pmu_
tools/perf/bench/numa.c +4 -0
index 97d86d8..ebfa163 100644
@@ -1593,6 +1593,10 @@ static void init_params(struct params *p, const char *name, int argc, const char
 	p->data_rand_walk		= true;
 	p->nr_loops			= -1;
 	p->init_random			= true;
+	p->mb_global_str		= "1";
+	p->nr_proc			= 1;
+	p->nr_threads			= 1;
+	p->nr_secs			= 5;
 	p->run_all			= argc == 1;
 }
 
tools/perf/builtin-stat.c +9 -2
index 8b0e1c9..65a151e 100644
@@ -174,13 +174,20 @@ static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
 
 static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
-	memset(evsel->priv, 0, sizeof(struct perf_stat));
+	int i;
+	struct perf_stat *ps = evsel->priv;
+
+	for (i = 0; i < 3; i++)
+		init_stats(&ps->res_stats[i]);
 }
 
 static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
 	evsel->priv = zalloc(sizeof(struct perf_stat));
-	return evsel->priv == NULL ? -ENOMEM : 0;
+	if (evsel == NULL)
+		return -ENOMEM;
+	perf_evsel__reset_stat_priv(evsel);
+	return 0;
 }
 
 static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
tools/perf/config/Makefile +4 -3
index c234182..ee21fa9 100644
@@ -65,10 +65,9 @@ ifndef NO_LIBELF
   ifdef LIBDW_DIR
     LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
     LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
-
-    FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
-    FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
   endif
+  FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
 endif
 
 # include ARCH specific config
@@ -278,6 +277,8 @@ else
       NO_LIBELF := 1
       NO_DWARF := 1
       NO_DEMANGLE := 1
+      NO_LIBUNWIND := 1
+      NO_LIBDW_DWARF_UNWIND := 1
     else
       msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
     endif
tools/perf/tests/code-reading.c +1 -0
index 653a8fe..bfb1869 100644
@@ -504,6 +504,7 @@ static int do_test_code_reading(bool try_kcore)
 		if (ret < 0) {
 			if (!excl_kernel) {
 				excl_kernel = true;
+				perf_evlist__set_maps(evlist, NULL, NULL);
 				perf_evlist__delete(evlist);
 				evlist = NULL;
 				continue;
tools/perf/util/probe-finder.c +9 -6
index df02386..5627621 100644
@@ -985,7 +985,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 
 #if _ELFUTILS_PREREQ(0, 142)
 	/* Get the call frame information from this dwarf */
-	pf->cfi = dwarf_getcfi(dbg->dbg);
+	pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg));
 #endif
 
 	off = 0;
@@ -1441,13 +1441,15 @@ static int line_range_walk_cb(const char *fname, int lineno,
 			      void *data)
 {
 	struct line_finder *lf = data;
+	int err;
 
 	if ((strtailcmp(fname, lf->fname) != 0) ||
 	    (lf->lno_s > lineno || lf->lno_e < lineno))
 		return 0;
 
-	if (line_range_add_line(fname, lineno, lf->lr) < 0)
-		return -EINVAL;
+	err = line_range_add_line(fname, lineno, lf->lr);
+	if (err < 0 && err != -EEXIST)
+		return err;
 
 	return 0;
 }
@@ -1473,14 +1475,15 @@ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 
 static int line_range_inline_cb(Dwarf_Die *in_die, void *data)
 {
-	find_line_range_by_line(in_die, data);
+	int ret = find_line_range_by_line(in_die, data);
 
 	/*
 	 * We have to check all instances of inlined function, because
 	 * some execution paths can be optimized out depends on the
-	 * function argument of instances
+	 * function argument of instances. However, if an error occurs,
+	 * it should be handled by the caller.
 	 */
-	return 0;
+	return ret < 0 ? ret : 0;
 }
 
 /* Search function definition from function name */