Merge tag 'perf-core-for-mingo-4.21-20181217' 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:

- Introduce 'perf record --aio' to use asynchronous IO trace writing, disabled
  by default (Alexey Budankov)

- Add fallback routines to be used in places where we don't have the CPU mode
  (kernel/userspace/hypervisor) and thus must first fallback lookups looking
  at all map trees when trying to resolve symbols (Adrian Hunter)

- Fix error with config term "pt=0", where we should just force "pt=1" and
  warn the user about the former being nonsensical (Adrian Hunter)

- Fix 'perf test' entry where we expect 'sleep' to come in a PERF_RECORD_COMM
  but instead we get 'coreutils' when sleep is provided by some versions of
  the 'coreutils' package (Adrian Hunter)

- Introduce 'perf top --kallsyms file' to match 'perf report --kallsyms', useful
  when dealing with BPF, where symbol resolution happens via kallsyms, not via
  the default vmlinux ELF symtabs (Arnaldo Carvalho de Melo)

- Support 'srccode' output field in 'perf script' (Andi Kleen)

- Introduce basic 'perf annotation' support for the ARC architecture (Eugeniy Paltsev)

- Compute and display average IPC and IPC coverage per symbol in 'perf annotate' and
  'perf report' (Jin Yao)

- Make 'perf top' use ordered_events and process histograms in a separate thread (Jiri Olsa)

- Make 'perf trace' use ordered_events (Jiri Olsa)

- Add support for ETMv3 and PTMv1.1 decoding in cs-etm (Mathieu Poirier)

- Support for ARM A32/T32 instruction sets in CoreSight trace (cs-etm) (Robert Walker)

- Fix 'perf stat' shadow stats for clock events. (Ravi Bangoria)

- Remove needless rb_tree extra indirection from map__find() (Eric Saint-Etienne)

- Fix CSV mode column output for non-cgroup events in 'perf stat' (Stephane Eranian)

- Add sanity check to libtraceevent's is_timestamp_in_us() (Tzvetomir Stoyanov)

- Use ERR_CAST instead of ERR_PTR(PTR_ERR()) (Wen Yang)

- Fix Load_Miss_Real_Latency on SKL/SKX intel vendor event files (Andi Kleen)

- strncpy() fixes triggered by new warnings on gcc 8.2.0 (Arnaldo Carvalho de Melo)

- Handle tracefs syscall tracepoint older 'nr' field in 'perf trace', that got
  renamed to '__syscall_nr' to work in older kernels (Arnaldo Carvalho de Melo)

- Give better hint about devel package for libssl (Arnaldo Carvalho de Melo)

- Fix the 'perf trace' build in architectures lacking explicit mmap.h file (Arnaldo Carvalho de Melo)

- Remove extra rb_tree traversal indirection from map__find() (Eric Saint-Etienne)

- Disable breakpoint tests for 32-bit ARM (Florian Fainelli)

- Fix typos all over the place, mostly in comments, but also in some debug
  messages and JSON files (Ingo Molnar)

- Allow specifying proc-map-timeout in config file (Mark Drayton)

- Fix mmap_flags table generation script (Sihyeon Jang)

- Fix 'size' parameter to snprintf in the 'perf config' code (Sihyeon Jang)

- More libtraceevent renames to make it a proper library (Tzvetomir Stoyanov)

- Implement new API tep_get_ref() in libtraceevent (Tzvetomir Stoyanov)

- Added support for pkg-config in libtraceevent (Tzvetomir Stoyanov)

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

1 files changed, 186 insertions, 0 deletions

diff --git a/tools/perf/util/srccode.c b/tools/perf/util/srccode.c
new file mode 100644
index 000000000000..fcc8630f6dff
--- /dev/null
+++ b/tools/perf/util/srccode.c
@@ -0,0 +1,186 @@
+/*
+ * Manage printing of source lines
+ * Copyright (c) 2017, Intel Corporation.
+ * Author: Andi Kleen
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#include "linux/list.h"
+#include <stdlib.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <assert.h>
+#include <string.h>
+#include "srccode.h"
+#include "debug.h"
+#include "util.h"
+
+#define MAXSRCCACHE (32*1024*1024)
+#define MAXSRCFILES     64
+#define SRC_HTAB_SZ	64
+
+struct srcfile {
+	struct hlist_node hash_nd;
+	struct list_head nd;
+	char *fn;
+	char **lines;
+	char *map;
+	unsigned numlines;
+	size_t maplen;
+};
+
+static struct hlist_head srcfile_htab[SRC_HTAB_SZ];
+static LIST_HEAD(srcfile_list);
+static long map_total_sz;
+static int num_srcfiles;
+
+static unsigned shash(unsigned char *s)
+{
+	unsigned h = 0;
+	while (*s)
+		h = 65599 * h + *s++;
+	return h ^ (h >> 16);
+}
+
+static int countlines(char *map, int maplen)
+{
+	int numl;
+	char *end = map + maplen;
+	char *p = map;
+
+	if (maplen == 0)
+		return 0;
+	numl = 0;
+	while (p < end && (p = memchr(p, '\n', end - p)) != NULL) {
+		numl++;
+		p++;
+	}
+	if (p < end)
+		numl++;
+	return numl;
+}
+
+static void fill_lines(char **lines, int maxline, char *map, int maplen)
+{
+	int l;
+	char *end = map + maplen;
+	char *p = map;
+
+	if (maplen == 0 || maxline == 0)
+		return;
+	l = 0;
+	lines[l++] = map;
+	while (p < end && (p = memchr(p, '\n', end - p)) != NULL) {
+		if (l >= maxline)
+			return;
+		lines[l++] = ++p;
+	}
+	if (p < end)
+		lines[l] = p;
+}
+
+static void free_srcfile(struct srcfile *sf)
+{
+	list_del(&sf->nd);
+	hlist_del(&sf->hash_nd);
+	map_total_sz -= sf->maplen;
+	munmap(sf->map, sf->maplen);
+	free(sf->lines);
+	free(sf->fn);
+	free(sf);
+	num_srcfiles--;
+}
+
+static struct srcfile *find_srcfile(char *fn)
+{
+	struct stat st;
+	struct srcfile *h;
+	int fd;
+	unsigned long sz;
+	unsigned hval = shash((unsigned char *)fn) % SRC_HTAB_SZ;
+
+	hlist_for_each_entry (h, &srcfile_htab[hval], hash_nd) {
+		if (!strcmp(fn, h->fn)) {
+			/* Move to front */
+			list_del(&h->nd);
+			list_add(&h->nd, &srcfile_list);
+			return h;
+		}
+	}
+
+	/* Only prune if there is more than one entry */
+	while ((num_srcfiles > MAXSRCFILES || map_total_sz > MAXSRCCACHE) &&
+	       srcfile_list.next != &srcfile_list) {
+		assert(!list_empty(&srcfile_list));
+		h = list_entry(srcfile_list.prev, struct srcfile, nd);
+		free_srcfile(h);
+	}
+
+	fd = open(fn, O_RDONLY);
+	if (fd < 0 || fstat(fd, &st) < 0) {
+		pr_debug("cannot open source file %s\n", fn);
+		return NULL;
+	}
+
+	h = malloc(sizeof(struct srcfile));
+	if (!h)
+		return NULL;
+
+	h->fn = strdup(fn);
+	if (!h->fn)
+		goto out_h;
+
+	h->maplen = st.st_size;
+	sz = (h->maplen + page_size - 1) & ~(page_size - 1);
+	h->map = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0);
+	close(fd);
+	if (h->map == (char *)-1) {
+		pr_debug("cannot mmap source file %s\n", fn);
+		goto out_fn;
+	}
+	h->numlines = countlines(h->map, h->maplen);
+	h->lines = calloc(h->numlines, sizeof(char *));
+	if (!h->lines)
+		goto out_map;
+	fill_lines(h->lines, h->numlines, h->map, h->maplen);
+	list_add(&h->nd, &srcfile_list);
+	hlist_add_head(&h->hash_nd, &srcfile_htab[hval]);
+	map_total_sz += h->maplen;
+	num_srcfiles++;
+	return h;
+
+out_map:
+	munmap(h->map, sz);
+out_fn:
+	free(h->fn);
+out_h:
+	free(h);
+	return NULL;
+}
+
+/* Result is not 0 terminated */
+char *find_sourceline(char *fn, unsigned line, int *lenp)
+{
+	char *l, *p;
+	struct srcfile *sf = find_srcfile(fn);
+	if (!sf)
+		return NULL;
+	line--;
+	if (line >= sf->numlines)
+		return NULL;
+	l = sf->lines[line];
+	if (!l)
+		return NULL;
+	p = memchr(l, '\n', sf->map + sf->maplen - l);
+	*lenp = p - l;
+	return l;
+}