Merge branch 'github.com/Freescale/linux-fslc/4.14-2.0.x-imx' into toradex_4.14-2.0.x-imx-next

Conflicts:
	sound/soc/codecs/sgtl5000.c

37 files changed, 295 insertions, 58 deletions

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index ecdc3770d899..b8f301ea30af 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -780,7 +780,7 @@ ifndef NO_JVMTI
     JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}')
   else
     ifneq (,$(wildcard /usr/sbin/alternatives))
-      JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
+      JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed -e 's%/jre/bin/java.%%g' -e 's%/bin/java.%%g')
     endif
   endif
   ifndef JDIR
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index fbfc055d3f4d..aec62e822bab 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -43,6 +43,8 @@ struct cs_etm_recording {
 	struct auxtrace_record	itr;
 	struct perf_pmu		*cs_etm_pmu;
 	struct perf_evlist	*evlist;
+	int			wrapped_cnt;
+	bool			*wrapped;
 	bool			snapshot_mode;
 	size_t			snapshot_size;
 };
@@ -485,16 +487,131 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	return 0;
 }
 
-static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused,
+static int cs_etm_alloc_wrapped_array(struct cs_etm_recording *ptr, int idx)
+{
+	bool *wrapped;
+	int cnt = ptr->wrapped_cnt;
+
+	/* Make @ptr->wrapped as big as @idx */
+	while (cnt <= idx)
+		cnt++;
+
+	/*
+	 * Free'ed in cs_etm_recording_free().  Using realloc() to avoid
+	 * cross compilation problems where the host's system supports
+	 * reallocarray() but not the target.
+	 */
+	wrapped = realloc(ptr->wrapped, cnt * sizeof(bool));
+	if (!wrapped)
+		return -ENOMEM;
+
+	wrapped[cnt - 1] = false;
+	ptr->wrapped_cnt = cnt;
+	ptr->wrapped = wrapped;
+
+	return 0;
+}
+
+static bool cs_etm_buffer_has_wrapped(unsigned char *buffer,
+				      size_t buffer_size, u64 head)
+{
+	u64 i, watermark;
+	u64 *buf = (u64 *)buffer;
+	size_t buf_size = buffer_size;
+
+	/*
+	 * We want to look the very last 512 byte (chosen arbitrarily) in
+	 * the ring buffer.
+	 */
+	watermark = buf_size - 512;
+
+	/*
+	 * @head is continuously increasing - if its value is equal or greater
+	 * than the size of the ring buffer, it has wrapped around.
+	 */
+	if (head >= buffer_size)
+		return true;
+
+	/*
+	 * The value of @head is somewhere within the size of the ring buffer.
+	 * This can be that there hasn't been enough data to fill the ring
+	 * buffer yet or the trace time was so long that @head has numerically
+	 * wrapped around.  To find we need to check if we have data at the very
+	 * end of the ring buffer.  We can reliably do this because mmap'ed
+	 * pages are zeroed out and there is a fresh mapping with every new
+	 * session.
+	 */
+
+	/* @head is less than 512 byte from the end of the ring buffer */
+	if (head > watermark)
+		watermark = head;
+
+	/*
+	 * Speed things up by using 64 bit transactions (see "u64 *buf" above)
+	 */
+	watermark >>= 3;
+	buf_size >>= 3;
+
+	/*
+	 * If we find trace data at the end of the ring buffer, @head has
+	 * been there and has numerically wrapped around at least once.
+	 */
+	for (i = watermark; i < buf_size; i++)
+		if (buf[i])
+			return true;
+
+	return false;
+}
+
+static int cs_etm_find_snapshot(struct auxtrace_record *itr,
 				int idx, struct auxtrace_mmap *mm,
-				unsigned char *data __maybe_unused,
+				unsigned char *data,
 				u64 *head, u64 *old)
 {
+	int err;
+	bool wrapped;
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+
+	/*
+	 * Allocate memory to keep track of wrapping if this is the first
+	 * time we deal with this *mm.
+	 */
+	if (idx >= ptr->wrapped_cnt) {
+		err = cs_etm_alloc_wrapped_array(ptr, idx);
+		if (err)
+			return err;
+	}
+
+	/*
+	 * Check to see if *head has wrapped around.  If it hasn't only the
+	 * amount of data between *head and *old is snapshot'ed to avoid
+	 * bloating the perf.data file with zeros.  But as soon as *head has
+	 * wrapped around the entire size of the AUX ring buffer it taken.
+	 */
+	wrapped = ptr->wrapped[idx];
+	if (!wrapped && cs_etm_buffer_has_wrapped(data, mm->len, *head)) {
+		wrapped = true;
+		ptr->wrapped[idx] = true;
+	}
+
 	pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n",
 		  __func__, idx, (size_t)*old, (size_t)*head, mm->len);
 
-	*old = *head;
-	*head += mm->len;
+	/* No wrap has occurred, we can just use *head and *old. */
+	if (!wrapped)
+		return 0;
+
+	/*
+	 * *head has wrapped around - adjust *head and *old to pickup the
+	 * entire content of the AUX buffer.
+	 */
+	if (*head >= mm->len) {
+		*old = *head - mm->len;
+	} else {
+		*head += mm->len;
+		*old = *head - mm->len;
+	}
 
 	return 0;
 }
@@ -535,6 +652,8 @@ static void cs_etm_recording_free(struct auxtrace_record *itr)
 {
 	struct cs_etm_recording *ptr =
 			container_of(itr, struct cs_etm_recording, itr);
+
+	zfree(&ptr->wrapped);
 	free(ptr);
 }
 
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index 0b2054007314..c8c86a0c9b79 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -5,16 +5,48 @@
 #include "util.h"
 #include "machine.h"
 #include "api/fs/fs.h"
+#include "debug.h"
+#include "symbol.h"
 
-int arch__fix_module_text_start(u64 *start, const char *name)
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
 {
+	u64 m_start = *start;
 	char path[PATH_MAX];
 
 	snprintf(path, PATH_MAX, "module/%.*s/sections/.text",
 				(int)strlen(name) - 2, name + 1);
-
-	if (sysfs__read_ull(path, (unsigned long long *)start) < 0)
-		return -1;
+	if (sysfs__read_ull(path, (unsigned long long *)start) < 0) {
+		pr_debug2("Using module %s start:%#lx\n", path, m_start);
+		*start = m_start;
+	} else {
+		/* Successful read of the modules segment text start address.
+		 * Calculate difference between module start address
+		 * in memory and module text segment start address.
+		 * For example module load address is 0x3ff8011b000
+		 * (from /proc/modules) and module text segment start
+		 * address is 0x3ff8011b870 (from file above).
+		 *
+		 * Adjust the module size and subtract the GOT table
+		 * size located at the beginning of the module.
+		 */
+		*size -= (*start - m_start);
+	}
 
 	return 0;
 }
+
+/* On s390 kernel text segment start is located at very low memory addresses,
+ * for example 0x10000. Modules are located at very high memory addresses,
+ * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment
+ * and beginning of first module's text segment is very big.
+ * Therefore do not fill this gap and do not assign it to the kernel dso map.
+ */
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
+		/* Last kernel symbol mapped to end of page */
+		p->end = roundup(p->end, page_size);
+	else
+		p->end = c->start;
+	pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end);
+}
diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index 05920e3edf7a..47357973b55b 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <errno.h>
+#include "../../util/debug.h"
 #ifndef REMOTE_UNWIND_LIBUNWIND
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
-#include "../../util/debug.h"
 #endif
 
 #ifdef HAVE_ARCH_X86_64_SUPPORT
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 997875c770b1..275f1c3c73b6 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -378,8 +378,10 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags,
 
 	/* Allocate and initialize all memory on CPU#0: */
 	if (init_cpu0) {
-		orig_mask = bind_to_node(0);
-		bind_to_memnode(0);
+		int node = numa_node_of_cpu(0);
+
+		orig_mask = bind_to_node(node);
+		bind_to_memnode(node);
 	}
 
 	bytes = bytes0 + HPSIZE;
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 32e64a8a6443..bec7a2f1fb4d 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2454,6 +2454,7 @@ static int build_cl_output(char *cl_sort, bool no_source)
 	bool add_sym   = false;
 	bool add_dso   = false;
 	bool add_src   = false;
+	int ret = 0;
 
 	if (!buf)
 		return -ENOMEM;
@@ -2472,7 +2473,8 @@ static int build_cl_output(char *cl_sort, bool no_source)
 			add_dso = true;
 		} else if (strcmp(tok, "offset")) {
 			pr_err("unrecognized sort token: %s\n", tok);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err;
 		}
 	}
 
@@ -2495,13 +2497,15 @@ static int build_cl_output(char *cl_sort, bool no_source)
 		add_sym ? "symbol," : "",
 		add_dso ? "dso," : "",
 		add_src ? "cl_srcline," : "",
-		"node") < 0)
-		return -ENOMEM;
+		"node") < 0) {
+		ret = -ENOMEM;
+		goto err;
+	}
 
 	c2c.show_src = add_src;
-
+err:
 	free(buf);
-	return 0;
+	return ret;
 }
 
 static int setup_coalesce(const char *coalesce, bool no_source)
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 25a42acabee1..13a33fb71a6d 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -162,7 +162,7 @@ static int set_tracing_cpumask(struct cpu_map *cpumap)
 	int last_cpu;
 
 	last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1);
-	mask_size = (last_cpu + 3) / 4 + 1;
+	mask_size = last_cpu / 4 + 2; /* one more byte for EOS */
 	mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */
 
 	cpumask = malloc(mask_size);
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index a0f7ed2b869b..3c364798093b 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -189,7 +189,7 @@ static void add_man_viewer(const char *name)
 	while (*p)
 		p = &((*p)->next);
 	*p = zalloc(sizeof(**p) + len + 1);
-	strncpy((*p)->name, name, len);
+	strcpy((*p)->name, name);
 }
 
 static int supported_man_viewer(const char *name, size_t len)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 9e693ce4b73b..ce786f363476 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -687,6 +687,7 @@ static char *compact_gfp_flags(char *gfp_flags)
 			new = realloc(new_flags, len + strlen(cpt) + 2);
 			if (new == NULL) {
 				free(new_flags);
+				free(orig_flags);
 				return NULL;
 			}
 
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index c0065923a525..e1ac51aaedcf 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -712,6 +712,16 @@ __cmd_probe(int argc, const char **argv)
 
 		ret = perf_add_probe_events(params.events, params.nevents);
 		if (ret < 0) {
+
+			/*
+			 * When perf_add_probe_events() fails it calls
+			 * cleanup_perf_probe_events(pevs, npevs), i.e.
+			 * cleanup_perf_probe_events(params.events, params.nevents), which
+			 * will call clear_perf_probe_event(), so set nevents to zero
+			 * to avoid cleanup_params() to call clear_perf_probe_event() again
+			 * on the same pevs.
+			 */
+			params.nevents = 0;
 			pr_err_with_code("  Error: Failed to add events.", ret);
 			return ret;
 		}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 52486c90ab93..0801e0ffba4a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2769,8 +2769,11 @@ int cmd_stat(int argc, const char **argv)
 			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
 				run_idx + 1);
 
+		if (run_idx != 0)
+			perf_evlist__reset_prev_raw_counts(evsel_list);
+
 		status = run_perf_stat(argc, argv);
-		if (forever && status != -1) {
+		if (forever && status != -1 && !interval) {
 			print_counters(NULL, argc, argv);
 			perf_stat__reset_stats();
 		}
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 96f62dd7e3ed..d4ebd0956114 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -25,7 +25,7 @@ static inline unsigned long long rdclock(void)
 }
 
 #ifndef MAX_NR_CPUS
-#define MAX_NR_CPUS			1024
+#define MAX_NR_CPUS			2048
 #endif
 
 extern const char *input_name;
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index d51dc9ca8861..6f9f247b4516 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -342,11 +342,12 @@ static struct fixed {
 	const char *name;
 	const char *event;
 } fixed[] = {
-	{ "inst_retired.any", "event=0xc0" },
-	{ "inst_retired.any_p", "event=0xc0" },
-	{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" },
-	{ "cpu_clk_unhalted.thread", "event=0x3c" },
-	{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" },
+	{ "inst_retired.any", "event=0xc0,period=2000003" },
+	{ "inst_retired.any_p", "event=0xc0,period=2000003" },
+	{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03,period=2000003" },
+	{ "cpu_clk_unhalted.thread", "event=0x3c,period=2000003" },
+	{ "cpu_clk_unhalted.core", "event=0x3c,period=2000003" },
+	{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1,period=2000003" },
 	{ NULL, NULL},
 };
 
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 3c3f3e029e33..2ecb86876f10 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -52,7 +52,7 @@ static void *thread_fn(void *arg)
 {
 	struct thread_data *td = arg;
 	ssize_t ret;
-	int go;
+	int go = 0;
 
 	if (thread_init(td))
 		return NULL;
diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c
index a693bcf017ea..44c16fd11bf6 100644
--- a/tools/perf/tests/perf-hooks.c
+++ b/tools/perf/tests/perf-hooks.c
@@ -20,12 +20,11 @@ static void sigsegv_handler(int sig __maybe_unused)
 static void the_hook(void *_hook_flags)
 {
 	int *hook_flags = _hook_flags;
-	int *p = NULL;
 
 	*hook_flags = 1234;
 
 	/* Generate a segfault, test perf_hooks__recover */
-	*p = 0;
+	raise(SIGSEGV);
 }
 
 int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused)
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 2a9ef080efd0..a8a516dec4ed 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -30,6 +30,10 @@ if [ $err -ne 0 ] ; then
 	exit $err
 fi
 
+# Do not use whatever ~/.perfconfig file, it may change the output
+# via trace.{show_timestamp,show_prefix,etc}
+export PERF_CONFIG=/dev/null
+
 trace_open_vfs_getname
 err=$?
 rm -f ${file}
diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c
index 1be3b4cf0827..82346ca06f17 100644
--- a/tools/perf/trace/beauty/ioctl.c
+++ b/tools/perf/trace/beauty/ioctl.c
@@ -22,7 +22,7 @@
 static size_t ioctl__scnprintf_tty_cmd(int nr, int dir, char *bf, size_t size)
 {
 	static const char *ioctl_tty_cmd[] = {
-	"TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
+	[_IOC_NR(TCGETS)] = "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
 	"TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL", "TIOCSCTTY",
 	"TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI", "TIOCGWINSZ", "TIOCSWINSZ",
 	"TIOCMGET", "TIOCMBIS", "TIOCMBIC", "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR",
diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c
index 4ca799aadb4e..93d6b7240285 100644
--- a/tools/perf/ui/tui/helpline.c
+++ b/tools/perf/ui/tui/helpline.c
@@ -24,7 +24,7 @@ static void tui_helpline__push(const char *msg)
 	SLsmg_set_color(0);
 	SLsmg_write_nstring((char *)msg, SLtt_Screen_Cols);
 	SLsmg_refresh();
-	strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0';
+	strlcpy(ui_helpline__current, msg, sz);
 }
 
 static int tui_helpline__show(const char *format, va_list ap)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 398d4cc2f0e4..2a8d2a6723f6 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -868,16 +868,14 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp)
 	*namep = strdup(name);
 
 	if (*namep == NULL)
-		goto out_free_name;
+		goto out;
 
 	(*rawp)[0] = tmp;
 	*rawp = ltrim(*rawp);
 
 	return 0;
 
-out_free_name:
-	free((void *)namep);
-	*namep = NULL;
+out:
 	return -1;
 }
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 383674f448fc..f93846edc1e0 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -701,7 +701,10 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size)
 	unsigned char *bitmap;
 	int last_cpu = cpu_map__cpu(map, map->nr - 1);
 
-	bitmap = zalloc((last_cpu + 7) / 8);
+	if (buf == NULL)
+		return 0;
+
+	bitmap = zalloc(last_cpu / 8 + 1);
 	if (bitmap == NULL) {
 		buf[0] = '\0';
 		return 0;
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 2346cecb8ea2..5131304ea3a8 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -271,7 +271,7 @@ static int string_set_value(struct bt_ctf_field *field, const char *string)
 				if (i > 0)
 					strncpy(buffer, string, i);
 			}
-			strncat(buffer + p, numstr, 4);
+			memcpy(buffer + p, numstr, 4);
 			p += 3;
 		}
 	}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 0cf6f537f980..3ab81e8e079e 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -587,6 +587,9 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
 {
 	char bf[128];
 
+	if (!evsel)
+		goto out_unknown;
+
 	if (evsel->name)
 		return evsel->name;
 
@@ -623,7 +626,10 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
 
 	evsel->name = strdup(bf);
 
-	return evsel->name ?: "unknown";
+	if (evsel->name)
+		return evsel->name;
+out_unknown:
+	return "unknown";
 }
 
 const char *perf_evsel__group_name(struct perf_evsel *evsel)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 696f2654826b..c892bb4f26c3 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1063,7 +1063,7 @@ static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 lev
 
 	scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path);
 	if (sysfs__read_str(file, &cache->map, &len)) {
-		free(cache->map);
+		free(cache->size);
 		free(cache->type);
 		return -1;
 	}
@@ -1122,7 +1122,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
 	return 0;
 }
 
-#define MAX_CACHES 2000
+#define MAX_CACHES (MAX_NR_CPUS * 4)
 
 static int write_cache(struct feat_fd *ff,
 		       struct perf_evlist *evlist __maybe_unused)
@@ -1882,8 +1882,10 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 	/* On s390 the socket_id number is not related to the numbers of cpus.
 	 * The socket_id number might be higher than the numbers of cpus.
 	 * This depends on the configuration.
+	 * AArch64 is the same.
 	 */
-	if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4))
+	if (ph->env.arch && (!strncmp(ph->env.arch, "s390", 4)
+			  || !strncmp(ph->env.arch, "aarch64", 7)))
 		do_core_id_test = false;
 
 	for (i = 0; i < (u32)cpu_nr; i++) {
@@ -2901,6 +2903,13 @@ int perf_session__read_header(struct perf_session *session)
 			   file->path);
 	}
 
+	if (f_header.attr_size == 0) {
+		pr_err("ERROR: The %s file's attr size field is 0 which is unexpected.\n"
+		       "Was the 'perf record' command properly terminated?\n",
+		       file->path);
+		return -EINVAL;
+	}
+
 	nr_attrs = f_header.attrs.size / f_header.attr_size;
 	lseek(fd, f_header.attrs.offset, SEEK_SET);
 
@@ -2983,7 +2992,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 	size += sizeof(struct perf_event_header);
 	size += ids * sizeof(u64);
 
-	ev = malloc(size);
+	ev = zalloc(size);
 
 	if (ev == NULL)
 		return -ENOMEM;
@@ -3081,7 +3090,7 @@ int perf_event__process_feature(struct perf_tool *tool,
 		return 0;
 
 	ff.buf  = (void *)fe->data;
-	ff.size = event->header.size - sizeof(event->header);
+	ff.size = event->header.size - sizeof(*fe);
 	ff.ph = &session->header;
 
 	if (feat_ops[feat].process(&ff, NULL))
@@ -3171,7 +3180,7 @@ perf_event__synthesize_event_update_name(struct perf_tool *tool,
 	if (ev == NULL)
 		return -ENOMEM;
 
-	strncpy(ev->data, evsel->name, len);
+	strlcpy(ev->data, evsel->name, len + 1);
 	err = process(tool, (union perf_event*) ev, NULL, NULL);
 	free(ev);
 	return err;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 5b8bc1fd943d..c1f9615b02f7 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1504,7 +1504,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 	return 0;
 }
 
-static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
+static int64_t hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
 {
 	struct hists *hists = a->hists;
 	struct perf_hpp_fmt *fmt;
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 36483db032e8..3f02a5e284b2 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -394,7 +394,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 	size_t size;
 	u16 idr_size;
 	const char *sym;
-	uint32_t count;
+	uint64_t count;
 	int ret, csize, usize;
 	pid_t pid, tid;
 	struct {
@@ -417,7 +417,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 		return -1;
 
 	filename = event->mmap2.filename;
-	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%u.so",
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
 			jd->dir,
 			pid,
 			count);
@@ -530,7 +530,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 		return -1;
 
 	filename = event->mmap2.filename;
-	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%"PRIu64,
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
 	         jd->dir,
 	         pid,
 		 jr->move.code_index);
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 2bdaac048a0a..da59a9e9543b 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -225,14 +225,14 @@ static int detect_kbuild_dir(char **kbuild_dir)
 	const char *prefix_dir = "";
 	const char *suffix_dir = "";
 
+	/* _UTSNAME_LENGTH is 65 */
+	char release[128];
+
 	char *autoconf_path;
 
 	int err;
 
 	if (!test_dir) {
-		/* _UTSNAME_LENGTH is 65 */
-		char release[128];
-
 		err = fetch_kernel_version(NULL, release,
 					   sizeof(release));
 		if (err)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 968fd0454e6b..5145c6a84c47 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -156,6 +156,9 @@ void machine__delete_threads(struct machine *machine)
 
 void machine__exit(struct machine *machine)
 {
+	if (machine == NULL)
+		return;
+
 	machine__destroy_kernel_maps(machine);
 	map_groups__exit(&machine->kmaps);
 	dsos__exit(&machine->dsos);
@@ -1230,6 +1233,7 @@ static int machine__set_modules_path(struct machine *machine)
 	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
 int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
+				u64 *size __maybe_unused,
 				const char *name __maybe_unused)
 {
 	return 0;
@@ -1241,7 +1245,7 @@ static int machine__create_module(void *arg, const char *name, u64 start,
 	struct machine *machine = arg;
 	struct map *map;
 
-	if (arch__fix_module_text_start(&start, name) < 0)
+	if (arch__fix_module_text_start(&start, &size, name) < 0)
 		return -1;
 
 	map = machine__findnew_module_map(machine, start, name);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 13041b036a5b..ec339cdf854c 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -213,7 +213,7 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
-int arch__fix_module_text_start(u64 *start, const char *name);
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name);
 
 int __machine__load_kallsyms(struct machine *machine, const char *filename,
 			     enum map_type type, bool no_kcore);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 4e7bd2750122..63db9872c880 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "symbol.h"
+#include <assert.h>
 #include <errno.h>
 #include <inttypes.h>
 #include <limits.h>
@@ -737,6 +738,8 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 			}
 
 			after->start = map->end;
+			after->pgoff += map->end - pos->start;
+			assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end));
 			__map_groups__insert(pos->groups, after);
 			if (verbose >= 2 && !use_browser)
 				map__fprintf(after, fp);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index da55081aefc6..c49e8ea1a42c 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1145,6 +1145,9 @@ static void dump_read(struct perf_evsel *evsel, union perf_event *event)
 	       evsel ? perf_evsel__name(evsel) : "FAIL",
 	       event->read.value);
 
+	if (!evsel)
+		return;
+
 	read_format = evsel->attr.read_format;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 37363869c9a1..eadc9a2aef16 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -271,7 +271,7 @@ static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list,
 	struct perf_evsel *c2;
 
 	evlist__for_each_entry (evsel_list, c2) {
-		if (!strcasecmp(c2->name, name))
+		if (!strcasecmp(c2->name, name) && !c2->collect_stat)
 			return c2;
 	}
 	return NULL;
@@ -310,7 +310,8 @@ void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list)
 			if (leader) {
 				/* Search in group */
 				for_each_group_member (oc, leader) {
-					if (!strcasecmp(oc->name, metric_names[i])) {
+					if (!strcasecmp(oc->name, metric_names[i]) &&
+						!oc->collect_stat) {
 						found = true;
 						break;
 					}
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index c9bae5fb8b47..d028c2786802 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -154,6 +154,15 @@ static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 	evsel->prev_raw_counts = NULL;
 }
 
+static void perf_evsel__reset_prev_raw_counts(struct perf_evsel *evsel)
+{
+	if (evsel->prev_raw_counts) {
+		evsel->prev_raw_counts->aggr.val = 0;
+		evsel->prev_raw_counts->aggr.ena = 0;
+		evsel->prev_raw_counts->aggr.run = 0;
+       }
+}
+
 static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
 {
 	int ncpus = perf_evsel__nr_cpus(evsel);
@@ -204,6 +213,14 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist)
 	}
 }
 
+void perf_evlist__reset_prev_raw_counts(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel)
+		perf_evsel__reset_prev_raw_counts(evsel);
+}
+
 static void zero_per_pkg(struct perf_evsel *counter)
 {
 	if (counter->per_pkg_mask)
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 96326b1f9443..bdfbed8e2df2 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -100,6 +100,7 @@ void perf_stat__collect_metric_expr(struct perf_evlist *);
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct perf_evlist *evlist);
 void perf_evlist__reset_stats(struct perf_evlist *evlist);
+void perf_evlist__reset_prev_raw_counts(struct perf_evlist *evlist);
 
 int perf_stat_process_counter(struct perf_stat_config *config,
 			      struct perf_evsel *counter);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3936f69f385c..27bffcb213eb 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -93,6 +93,11 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
+void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	p->end = c->start;
+}
+
 const char * __weak arch__normalize_symbol_name(const char *name)
 {
 	return name;
@@ -219,7 +224,7 @@ void symbols__fixup_end(struct rb_root *symbols)
 		curr = rb_entry(nd, struct symbol, rb_node);
 
 		if (prev->end == prev->start && prev->end != curr->start)
-			prev->end = curr->start;
+			arch__symbols__fixup_end(prev, curr);
 	}
 
 	/* Last entry */
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 698c65e603a8..95ac21be8481 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -351,6 +351,7 @@ const char *arch__normalize_symbol_name(const char *name);
 #define SYMBOL_A 0
 #define SYMBOL_B 1
 
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
 int arch__compare_symbol_names(const char *namea, const char *nameb);
 int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 				 unsigned int n);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1dbcd3c8dee0..177436c8e026 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -160,14 +160,24 @@ struct comm *thread__comm(const struct thread *thread)
 
 struct comm *thread__exec_comm(const struct thread *thread)
 {
-	struct comm *comm, *last = NULL;
+	struct comm *comm, *last = NULL, *second_last = NULL;
 
 	list_for_each_entry(comm, &thread->comm_list, list) {
 		if (comm->exec)
 			return comm;
+		second_last = last;
 		last = comm;
 	}
 
+	/*
+	 * 'last' with no start time might be the parent's comm of a synthesized
+	 * thread (created by processing a synthesized fork event). For a main
+	 * thread, that is very probably wrong. Prefer a later comm to avoid
+	 * that case.
+	 */
+	if (second_last && !last->start && thread->pid_ == thread->tid)
+		return second_last;
+
 	return last;
 }
 
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
index 7ffe562e7ae7..2627b038b6f2 100644
--- a/tools/perf/util/xyarray.h
+++ b/tools/perf/util/xyarray.h
@@ -2,6 +2,7 @@
 #ifndef _PERF_XYARRAY_H_
 #define _PERF_XYARRAY_H_ 1
 
+#include <linux/compiler.h>
 #include <sys/types.h>
 
 struct xyarray {
@@ -10,7 +11,7 @@ struct xyarray {
 	size_t entries;
 	size_t max_x;
 	size_t max_y;
-	char contents[];
+	char contents[] __aligned(8);
 };
 
 struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size);