Merge branch 'perf/urgent' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

18 files changed, 123 insertions, 54 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 43ab5c402f98..f90860d1f897 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -312,7 +312,7 @@ union bpf_attr {
  *     jump into another BPF program
  *     @ctx: context pointer passed to next program
  *     @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
- *     @index: index inside array that selects specific program to run
+ *     @index: 32-bit index inside array that selects specific program to run
  *     Return: 0 on success or negative error
  *
  * int bpf_clone_redirect(skb, ifindex, flags)
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 0f22768c0d4d..34a579f806e3 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -284,11 +284,16 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 	case 0x8d:
 		if (sib == 0x24 && rex_w && !rex_b && !rex_x) {
 
-			/* lea disp(%rsp), reg */
 			*type = INSN_STACK;
-			op->src.type = OP_SRC_ADD;
+			if (!insn.displacement.value) {
+				/* lea (%rsp), reg */
+				op->src.type = OP_SRC_REG;
+			} else {
+				/* lea disp(%rsp), reg */
+				op->src.type = OP_SRC_ADD;
+				op->src.offset = insn.displacement.value;
+			}
 			op->src.reg = CFI_SP;
-			op->src.offset = insn.displacement.value;
 			op->dest.type = OP_DEST_REG;
 			op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r];
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 68a1ffb0a8a5..5a626ef666c2 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -8,8 +8,8 @@ perf-record - Run a command and record its profile into perf.data
 SYNOPSIS
 --------
 [verse]
-'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] <command>
-'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] -- <command> [<options>]
+'perf record' [-e <EVENT> | --event=EVENT] [-a] <command>
+'perf record' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
 
 DESCRIPTION
 -----------
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9092de0f7238..7167df215a42 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -611,7 +611,7 @@ static void print_sample_brstack(struct perf_sample *sample,
 			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
 		}
 
-		printf("0x%"PRIx64, from);
+		printf(" 0x%"PRIx64, from);
 		if (PRINT_FIELD(DSO)) {
 			printf("(");
 			map__fprintf_dsoname(alf.map, stdout);
@@ -706,7 +706,7 @@ static void print_sample_brstackoff(struct perf_sample *sample,
 		if (alt.map && !alt.map->dso->adjust_symbols)
 			to = map__map_ip(alt.map, to);
 
-		printf("0x%"PRIx64, from);
+		printf(" 0x%"PRIx64, from);
 		if (PRINT_FIELD(DSO)) {
 			printf("(");
 			map__fprintf_dsoname(alf.map, stdout);
diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
index 462fc755092e..7a84d73324e3 100755
--- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
@@ -10,6 +10,9 @@
 
 . $(dirname $0)/lib/probe.sh
 
+ld=$(realpath /lib64/ld*.so.* | uniq)
+libc=$(echo $ld | sed 's/ld/libc/g')
+
 trace_libc_inet_pton_backtrace() {
 	idx=0
 	expected[0]="PING.*bytes"
@@ -18,8 +21,8 @@ trace_libc_inet_pton_backtrace() {
 	expected[3]=".*packets transmitted.*"
 	expected[4]="rtt min.*"
 	expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)"
-	expected[6]=".*inet_pton[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$"
-	expected[7]="getaddrinfo[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$"
+	expected[6]=".*inet_pton[[:space:]]\($libc\)$"
+	expected[7]="getaddrinfo[[:space:]]\($libc\)$"
 	expected[8]=".*\(.*/bin/ping.*\)$"
 
 	perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do
@@ -35,7 +38,7 @@ trace_libc_inet_pton_backtrace() {
 }
 
 skip_if_no_perf_probe && \
-perf probe -q /lib64/libc-*.so inet_pton && \
+perf probe -q $libc inet_pton && \
 trace_libc_inet_pton_backtrace
 err=$?
 rm -f ${file}
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index ddb2c6fbdf91..db79017a6e56 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -532,7 +532,7 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
 
 void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
-	list_del(&format->list);
+	list_del_init(&format->list);
 }
 
 void perf_hpp__cancel_cumulate(void)
@@ -606,6 +606,13 @@ next:
 
 static void fmt_free(struct perf_hpp_fmt *fmt)
 {
+	/*
+	 * At this point fmt should be completely
+	 * unhooked, if not it's a bug.
+	 */
+	BUG_ON(!list_empty(&fmt->list));
+	BUG_ON(!list_empty(&fmt->sort_list));
+
 	if (fmt->free)
 		fmt->free(fmt);
 }
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index be09d77cade0..a971caf3759d 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -685,6 +685,8 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 {
 	struct symbol *sym = node->sym;
 	u64 left, right;
+	struct dso *left_dso = NULL;
+	struct dso *right_dso = NULL;
 
 	if (callchain_param.key == CCKEY_SRCLINE) {
 		enum match_result match = match_chain_srcline(node, cnode);
@@ -696,12 +698,14 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 	if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
 		left = cnode->ms.sym->start;
 		right = sym->start;
+		left_dso = cnode->ms.map->dso;
+		right_dso = node->map->dso;
 	} else {
 		left = cnode->ip;
 		right = node->ip;
 	}
 
-	if (left == right) {
+	if (left == right && left_dso == right_dso) {
 		if (node->branch) {
 			cnode->branch_count++;
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 9183913a6174..04f35db063ee 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -310,10 +310,11 @@ static char *get_config_name(struct list_head *head_terms)
 static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
 	    struct perf_event_attr *attr,
-	    char *name, struct cpu_map *cpus,
+	    char *name, struct perf_pmu *pmu,
 	    struct list_head *config_terms, bool auto_merge_stats)
 {
 	struct perf_evsel *evsel;
+	struct cpu_map *cpus = pmu ? pmu->cpus : NULL;
 
 	event_attr_init(attr);
 
@@ -324,7 +325,7 @@ __add_event(struct list_head *list, int *idx,
 	(*idx)++;
 	evsel->cpus        = cpu_map__get(cpus);
 	evsel->own_cpus    = cpu_map__get(cpus);
-	evsel->system_wide = !!cpus;
+	evsel->system_wide = pmu ? pmu->is_uncore : false;
 	evsel->auto_merge_stats = auto_merge_stats;
 
 	if (name)
@@ -1240,7 +1241,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	if (!head_config) {
 		attr.type = pmu->type;
-		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu->cpus, NULL, auto_merge_stats);
+		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
 		return evsel ? 0 : -ENOMEM;
 	}
 
@@ -1261,7 +1262,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 		return -EINVAL;
 
 	evsel = __add_event(list, &parse_state->idx, &attr,
-			    get_config_name(head_config), pmu->cpus,
+			    get_config_name(head_config), pmu,
 			    &config_terms, auto_merge_stats);
 	if (evsel) {
 		evsel->unit = info.unit;
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index ea2426daf7e8..38a42bdf1492 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -8,6 +8,9 @@
 
 %{
 #include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
 #include "../perf.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
@@ -53,9 +56,8 @@ static int str(yyscan_t scanner, int token)
 	return token;
 }
 
-static bool isbpf(yyscan_t scanner)
+static bool isbpf_suffix(char *text)
 {
-	char *text = parse_events_get_text(scanner);
 	int len = strlen(text);
 
 	if (len < 2)
@@ -68,6 +70,17 @@ static bool isbpf(yyscan_t scanner)
 	return false;
 }
 
+static bool isbpf(yyscan_t scanner)
+{
+	char *text = parse_events_get_text(scanner);
+	struct stat st;
+
+	if (!isbpf_suffix(text))
+		return false;
+
+	return stat(text, &st) == 0;
+}
+
 /*
  * This function is called when the parser gets two kind of input:
  *
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 0b11dfc0af44..94cf2c29fed6 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -471,17 +471,36 @@ static void pmu_read_sysfs(void)
 	closedir(dir);
 }
 
+static struct cpu_map *__pmu_cpumask(const char *path)
+{
+	FILE *file;
+	struct cpu_map *cpus;
+
+	file = fopen(path, "r");
+	if (!file)
+		return NULL;
+
+	cpus = cpu_map__read(file);
+	fclose(file);
+	return cpus;
+}
+
+/*
+ * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64)
+ * may have a "cpus" file.
+ */
+#define CPUS_TEMPLATE_UNCORE	"%s/bus/event_source/devices/%s/cpumask"
+#define CPUS_TEMPLATE_CPU	"%s/bus/event_source/devices/%s/cpus"
+
 static struct cpu_map *pmu_cpumask(const char *name)
 {
-	struct stat st;
 	char path[PATH_MAX];
-	FILE *file;
 	struct cpu_map *cpus;
 	const char *sysfs = sysfs__mountpoint();
 	const char *templates[] = {
-		 "%s/bus/event_source/devices/%s/cpumask",
-		 "%s/bus/event_source/devices/%s/cpus",
-		 NULL
+		CPUS_TEMPLATE_UNCORE,
+		CPUS_TEMPLATE_CPU,
+		NULL
 	};
 	const char **template;
 
@@ -490,20 +509,25 @@ static struct cpu_map *pmu_cpumask(const char *name)
 
 	for (template = templates; *template; template++) {
 		snprintf(path, PATH_MAX, *template, sysfs, name);
-		if (stat(path, &st) == 0)
-			break;
+		cpus = __pmu_cpumask(path);
+		if (cpus)
+			return cpus;
 	}
 
-	if (!*template)
-		return NULL;
+	return NULL;
+}
 
-	file = fopen(path, "r");
-	if (!file)
-		return NULL;
+static bool pmu_is_uncore(const char *name)
+{
+	char path[PATH_MAX];
+	struct cpu_map *cpus;
+	const char *sysfs = sysfs__mountpoint();
 
-	cpus = cpu_map__read(file);
-	fclose(file);
-	return cpus;
+	snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name);
+	cpus = __pmu_cpumask(path);
+	cpu_map__put(cpus);
+
+	return !!cpus;
 }
 
 /*
@@ -638,6 +662,8 @@ static struct perf_pmu *pmu_lookup(const char *name)
 
 	pmu->cpus = pmu_cpumask(name);
 
+	pmu->is_uncore = pmu_is_uncore(name);
+
 	INIT_LIST_HEAD(&pmu->format);
 	INIT_LIST_HEAD(&pmu->aliases);
 	list_splice(&format, &pmu->format);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 060f6abba8ed..7ca675598b43 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -22,6 +22,7 @@ struct perf_pmu {
 	char *name;
 	__u32 type;
 	bool selectable;
+	bool is_uncore;
 	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ceac0848469d..b3fd62f7e4c9 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -374,6 +374,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->mmap2 = process_event_stub;
 	if (tool->comm == NULL)
 		tool->comm = process_event_stub;
+	if (tool->namespaces == NULL)
+		tool->namespaces = process_event_stub;
 	if (tool->fork == NULL)
 		tool->fork = process_event_stub;
 	if (tool->exit == NULL)
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
index 4ba726c90870..54af60462130 100644
--- a/tools/perf/util/xyarray.h
+++ b/tools/perf/util/xyarray.h
@@ -23,12 +23,12 @@ static inline void *xyarray__entry(struct xyarray *xy, int x, int y)
 
 static inline int xyarray__max_y(struct xyarray *xy)
 {
-	return xy->max_x;
+	return xy->max_y;
 }
 
 static inline int xyarray__max_x(struct xyarray *xy)
 {
-	return xy->max_y;
+	return xy->max_x;
 }
 
 #endif /* _PERF_XYARRAY_H_ */
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 0dafba2c1e7d..bd9c6b31a504 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -92,7 +92,6 @@ unsigned int do_ring_perf_limit_reasons;
 unsigned int crystal_hz;
 unsigned long long tsc_hz;
 int base_cpu;
-int do_migrate;
 double discover_bclk(unsigned int family, unsigned int model);
 unsigned int has_hwp;	/* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */
 			/* IA32_HWP_REQUEST, IA32_HWP_STATUS */
@@ -303,9 +302,6 @@ int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg
 
 int cpu_migrate(int cpu)
 {
-	if (!do_migrate)
-		return 0;
-
 	CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
 	CPU_SET_S(cpu, cpu_affinity_setsize, cpu_affinity_set);
 	if (sched_setaffinity(0, cpu_affinity_setsize, cpu_affinity_set) == -1)
@@ -5007,7 +5003,6 @@ void cmdline(int argc, char **argv)
 		{"hide",	required_argument,	0, 'H'},	// meh, -h taken by --help
 		{"Joules",	no_argument,		0, 'J'},
 		{"list",	no_argument,		0, 'l'},
-		{"migrate",	no_argument,		0, 'm'},
 		{"out",		required_argument,	0, 'o'},
 		{"quiet",	no_argument,		0, 'q'},
 		{"show",	required_argument,	0, 's'},
@@ -5019,7 +5014,7 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:Jmo:qST:v",
+	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v",
 				long_options, &option_index)) != -1) {
 		switch (opt) {
 		case 'a':
@@ -5062,9 +5057,6 @@ void cmdline(int argc, char **argv)
 			list_header_only++;
 			quiet++;
 			break;
-		case 'm':
-			do_migrate = 1;
-			break;
 		case 'o':
 			outf = fopen_or_die(optarg, "w");
 			break;
diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile
index 0f5e347b068d..152823b6cb21 100644
--- a/tools/testing/selftests/mqueue/Makefile
+++ b/tools/testing/selftests/mqueue/Makefile
@@ -5,8 +5,8 @@ TEST_GEN_PROGS := mq_open_tests mq_perf_tests
 include ../lib.mk
 
 override define RUN_TESTS
-	$(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]"
-	$(OUTPUT)//mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]"
+	@$(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]"
+	@$(OUTPUT)/mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]"
 endef
 
 override define EMIT_TESTS
diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
index 00f286661dcd..dd4162fc0419 100644
--- a/tools/testing/selftests/networking/timestamping/rxtimestamp.c
+++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
@@ -341,7 +341,7 @@ int main(int argc, char **argv)
 			return 0;
 		case 'n':
 			t = atoi(optarg);
-			if (t > ARRAY_SIZE(test_cases))
+			if (t >= ARRAY_SIZE(test_cases))
 				error(1, 0, "Invalid test case: %d", t);
 			all_tests = false;
 			test_cases[t].enabled = true;
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index a2c53a3d223d..de2f9ec8a87f 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -397,7 +397,7 @@ static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy,
 	}
 }
 
-static int copy_page(int ufd, unsigned long offset)
+static int __copy_page(int ufd, unsigned long offset, bool retry)
 {
 	struct uffdio_copy uffdio_copy;
 
@@ -418,7 +418,7 @@ static int copy_page(int ufd, unsigned long offset)
 		fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n",
 			uffdio_copy.copy), exit(1);
 	} else {
-		if (test_uffdio_copy_eexist) {
+		if (test_uffdio_copy_eexist && retry) {
 			test_uffdio_copy_eexist = false;
 			retry_copy_page(ufd, &uffdio_copy, offset);
 		}
@@ -427,6 +427,16 @@ static int copy_page(int ufd, unsigned long offset)
 	return 0;
 }
 
+static int copy_page_retry(int ufd, unsigned long offset)
+{
+	return __copy_page(ufd, offset, true);
+}
+
+static int copy_page(int ufd, unsigned long offset)
+{
+	return __copy_page(ufd, offset, false);
+}
+
 static void *uffd_poll_thread(void *arg)
 {
 	unsigned long cpu = (unsigned long) arg;
@@ -544,7 +554,7 @@ static void *background_thread(void *arg)
 	for (page_nr = cpu * nr_pages_per_cpu;
 	     page_nr < (cpu+1) * nr_pages_per_cpu;
 	     page_nr++)
-		copy_page(uffd, page_nr * page_size);
+		copy_page_retry(uffd, page_nr * page_size);
 
 	return NULL;
 }
@@ -779,7 +789,7 @@ static void retry_uffdio_zeropage(int ufd,
 	}
 }
 
-static int uffdio_zeropage(int ufd, unsigned long offset)
+static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
 {
 	struct uffdio_zeropage uffdio_zeropage;
 	int ret;
@@ -814,7 +824,7 @@ static int uffdio_zeropage(int ufd, unsigned long offset)
 			fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n",
 				uffdio_zeropage.zeropage), exit(1);
 		} else {
-			if (test_uffdio_zeropage_eexist) {
+			if (test_uffdio_zeropage_eexist && retry) {
 				test_uffdio_zeropage_eexist = false;
 				retry_uffdio_zeropage(ufd, &uffdio_zeropage,
 						      offset);
@@ -830,6 +840,11 @@ static int uffdio_zeropage(int ufd, unsigned long offset)
 	return 0;
 }
 
+static int uffdio_zeropage(int ufd, unsigned long offset)
+{
+	return __uffdio_zeropage(ufd, offset, false);
+}
+
 /* exercise UFFDIO_ZEROPAGE */
 static int userfaultfd_zeropage_test(void)
 {
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 97f187e2663f..0a74a20ca32b 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -20,7 +20,7 @@ BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64)
 BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
 BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
 
-CFLAGS := -O2 -g -std=gnu99 -pthread -Wall
+CFLAGS := -O2 -g -std=gnu99 -pthread -Wall -no-pie
 
 UNAME_M := $(shell uname -m)
 CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)