Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "With over 300 commits it's been a busy cycle - with most of the work
  concentrated on the tooling side (as it should).

  The main kernel side enhancements were:

   - Add per event callchain limit: Recently we introduced a sysctl to
     tune the max-stack for all events for which callchains were
     requested:

       $ sysctl kernel.perf_event_max_stack
       kernel.perf_event_max_stack = 127

     Now this patch introduces a way to configure this per event, i.e.
     this becomes possible:

       $ perf record -e sched:*/max-stack=2/ -e block:*/max-stack=10/ -a

     allowing finer tuning of how much buffer space callchains use.

     This uses an u16 from the reserved space at the end, leaving
     another u16 for future use.

     There has been interest in even finer tuning, namely to control the
     max stack for kernel and userspace callchains separately.  Further
     discussion is needed, we may for instance use the remaining u16 for
     that and when it is present, assume that the sample_max_stack
     introduced in this patch applies for the kernel, and the u16 left
     is used for limiting the userspace callchain (Arnaldo Carvalho de
     Melo)

   - Optimize AUX event (hardware assisted side-band event) delivery
     (Kan Liang)

   - Rework Intel family name macro usage (this is partially x86 arch
     work) (Dave Hansen)

   - Refine and fix Intel LBR support (David Carrillo-Cisneros)

   - Add support for Intel 'TopDown' events (Andi Kleen)

   - Intel uncore PMU driver fixes and enhancements (Kan Liang)

   - ... other misc changes.

  Here's an incomplete list of the tooling enhancements (but there's
  much more, see the shortlog and the git log for details):

   - Support cross unwinding, i.e.  collecting '--call-graph dwarf'
     perf.data files in one machine and then doing analysis in another
     machine of a different hardware architecture.  This enables, for
     instance, to do:

       $ perf record -a --call-graph dwarf

     on a x86-32 or aarch64 system and then do 'perf report' on it on a
     x86_64 workstation (He Kuang)

   - Allow reading from a backward ring buffer (one setup via
     sys_perf_event_open() with perf_event_attr.write_backward = 1)
     (Wang Nan)

   - Finish merging initial SDT (Statically Defined Traces) support, see
     cset comments for details about how it all works (Masami Hiramatsu)

   - Support attaching eBPF programs to tracepoints (Wang Nan)

   - Add demangling of symbols in programs written in the Rust language
     (David Tolnay)

   - Add support for tracepoints in the python binding, including an
     example, that sets up and parses sched:sched_switch events,
     tools/perf/python/tracepoint.py (Jiri Olsa)

   - Introduce --stdio-color to set up the color output mode selection
     in 'annotate' and 'report', allowing emit color escape sequences
     when redirecting the output of these tools (Arnaldo Carvalho de
     Melo)

   - Add 'callindent' option to 'perf script -F', to indent the Intel PT
     call stack, making this output more ftrace-like (Adrian Hunter,
     Andi Kleen)

   - Allow dumping the object files generated by llvm when processing
     eBPF scriptlet events (Wang Nan)

   - Add stackcollapse.py script to help generating flame graphs (Paolo
     Bonzini)

   - Add --ldlat option to 'perf mem' to specify load latency for loads
     event (e.g. cpu/mem-loads/ ) (Jiri Olsa)

   - Tooling support for Intel TopDown counters, recently added to the
     kernel (Andi Kleen)"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (303 commits)
  perf tests: Add is_printable_array test
  perf tools: Make is_printable_array global
  perf script python: Fix string vs byte array resolving
  perf probe: Warn unmatched function filter correctly
  perf cpu_map: Add more helpers
  perf stat: Balance opening and reading events
  tools: Copy linux/{hash,poison}.h and check for drift
  perf tools: Remove include/linux/list.h from perf's MANIFEST
  tools: Copy the bitops files accessed from the kernel and check for drift
  Remove: kernel unistd*h files from perf's MANIFEST, not used
  perf tools: Remove tools/perf/util/include/linux/const.h
  perf tools: Remove tools/perf/util/include/asm/byteorder.h
  perf tools: Add missing linux/compiler.h include to perf-sys.h
  perf jit: Remove some no-op error handling
  perf jit: Add missing curly braces
  objtool: Initialize variable to silence old compiler
  objtool: Add -I$(srctree)/tools/arch/$(ARCH)/include/uapi
  perf record: Add --tail-synthesize option
  perf session: Don't warn about out of order event if write_backward is used
  perf tools: Enable overwrite settings
  ...

1 files changed, 539 insertions, 8 deletions

diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 3fe6214..9aed9c3 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -14,6 +14,7 @@
  * GNU General Public License for more details.
  *
  */
+#include <sys/uio.h>
 #include "util.h"
 #include "event.h"
 #include "strlist.h"
@@ -49,7 +50,7 @@ static void print_open_warning(int err, bool uprobe)
 	else
 		pr_warning("Failed to open %cprobe_events: %s\n",
 			   uprobe ? 'u' : 'k',
-			   strerror_r(-err, sbuf, sizeof(sbuf)));
+			   str_error_r(-err, sbuf, sizeof(sbuf)));
 }
 
 static void print_both_open_warning(int kerr, int uerr)
@@ -63,9 +64,9 @@ static void print_both_open_warning(int kerr, int uerr)
 	else {
 		char sbuf[STRERR_BUFSIZE];
 		pr_warning("Failed to open kprobe events: %s.\n",
-			   strerror_r(-kerr, sbuf, sizeof(sbuf)));
+			   str_error_r(-kerr, sbuf, sizeof(sbuf)));
 		pr_warning("Failed to open uprobe events: %s.\n",
-			   strerror_r(-uerr, sbuf, sizeof(sbuf)));
+			   str_error_r(-uerr, sbuf, sizeof(sbuf)));
 	}
 }
 
@@ -177,7 +178,7 @@ static struct strlist *__probe_file__get_namelist(int fd, bool include_group)
 	if (!rawlist)
 		return NULL;
 	sl = strlist__new(NULL, NULL);
-	strlist__for_each(ent, rawlist) {
+	strlist__for_each_entry(ent, rawlist) {
 		ret = parse_probe_trace_command(ent->s, &tev);
 		if (ret < 0)
 			break;
@@ -223,7 +224,7 @@ int probe_file__add_event(int fd, struct probe_trace_event *tev)
 		if (write(fd, buf, strlen(buf)) < (int)strlen(buf)) {
 			ret = -errno;
 			pr_warning("Failed to write event: %s\n",
-				   strerror_r(errno, sbuf, sizeof(sbuf)));
+				   str_error_r(errno, sbuf, sizeof(sbuf)));
 		}
 	}
 	free(buf);
@@ -261,7 +262,7 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
 	return 0;
 error:
 	pr_warning("Failed to delete event: %s\n",
-		   strerror_r(-ret, buf, sizeof(buf)));
+		   str_error_r(-ret, buf, sizeof(buf)));
 	return ret;
 }
 
@@ -280,7 +281,7 @@ int probe_file__get_events(int fd, struct strfilter *filter,
 	if (!namelist)
 		return -ENOENT;
 
-	strlist__for_each(ent, namelist) {
+	strlist__for_each_entry(ent, namelist) {
 		p = strchr(ent->s, ':');
 		if ((p && strfilter__compare(filter, p + 1)) ||
 		    strfilter__compare(filter, ent->s)) {
@@ -298,7 +299,7 @@ int probe_file__del_strlist(int fd, struct strlist *namelist)
 	int ret = 0;
 	struct str_node *ent;
 
-	strlist__for_each(ent, namelist) {
+	strlist__for_each_entry(ent, namelist) {
 		ret = __del_trace_probe_event(fd, ent);
 		if (ret < 0)
 			break;
@@ -324,3 +325,533 @@ int probe_file__del_events(int fd, struct strfilter *filter)
 
 	return ret;
 }
+
+/* Caller must ensure to remove this entry from list */
+static void probe_cache_entry__delete(struct probe_cache_entry *entry)
+{
+	if (entry) {
+		BUG_ON(!list_empty(&entry->node));
+
+		strlist__delete(entry->tevlist);
+		clear_perf_probe_event(&entry->pev);
+		zfree(&entry->spev);
+		free(entry);
+	}
+}
+
+static struct probe_cache_entry *
+probe_cache_entry__new(struct perf_probe_event *pev)
+{
+	struct probe_cache_entry *entry = zalloc(sizeof(*entry));
+
+	if (entry) {
+		INIT_LIST_HEAD(&entry->node);
+		entry->tevlist = strlist__new(NULL, NULL);
+		if (!entry->tevlist)
+			zfree(&entry);
+		else if (pev) {
+			entry->spev = synthesize_perf_probe_command(pev);
+			if (!entry->spev ||
+			    perf_probe_event__copy(&entry->pev, pev) < 0) {
+				probe_cache_entry__delete(entry);
+				return NULL;
+			}
+		}
+	}
+
+	return entry;
+}
+
+int probe_cache_entry__get_event(struct probe_cache_entry *entry,
+				 struct probe_trace_event **tevs)
+{
+	struct probe_trace_event *tev;
+	struct str_node *node;
+	int ret, i;
+
+	ret = strlist__nr_entries(entry->tevlist);
+	if (ret > probe_conf.max_probes)
+		return -E2BIG;
+
+	*tevs = zalloc(ret * sizeof(*tev));
+	if (!*tevs)
+		return -ENOMEM;
+
+	i = 0;
+	strlist__for_each_entry(node, entry->tevlist) {
+		tev = &(*tevs)[i++];
+		ret = parse_probe_trace_command(node->s, tev);
+		if (ret < 0)
+			break;
+	}
+	return i;
+}
+
+/* For the kernel probe caches, pass target = NULL or DSO__NAME_KALLSYMS */
+static int probe_cache__open(struct probe_cache *pcache, const char *target)
+{
+	char cpath[PATH_MAX];
+	char sbuildid[SBUILD_ID_SIZE];
+	char *dir_name = NULL;
+	bool is_kallsyms = false;
+	int ret, fd;
+
+	if (target && build_id_cache__cached(target)) {
+		/* This is a cached buildid */
+		strncpy(sbuildid, target, SBUILD_ID_SIZE);
+		dir_name = build_id_cache__linkname(sbuildid, NULL, 0);
+		goto found;
+	}
+
+	if (!target || !strcmp(target, DSO__NAME_KALLSYMS)) {
+		target = DSO__NAME_KALLSYMS;
+		is_kallsyms = true;
+		ret = sysfs__sprintf_build_id("/", sbuildid);
+	} else
+		ret = filename__sprintf_build_id(target, sbuildid);
+
+	if (ret < 0) {
+		pr_debug("Failed to get build-id from %s.\n", target);
+		return ret;
+	}
+
+	/* If we have no buildid cache, make it */
+	if (!build_id_cache__cached(sbuildid)) {
+		ret = build_id_cache__add_s(sbuildid, target,
+					    is_kallsyms, NULL);
+		if (ret < 0) {
+			pr_debug("Failed to add build-id cache: %s\n", target);
+			return ret;
+		}
+	}
+
+	dir_name = build_id_cache__cachedir(sbuildid, target, is_kallsyms,
+					    false);
+found:
+	if (!dir_name) {
+		pr_debug("Failed to get cache from %s\n", target);
+		return -ENOMEM;
+	}
+
+	snprintf(cpath, PATH_MAX, "%s/probes", dir_name);
+	fd = open(cpath, O_CREAT | O_RDWR, 0644);
+	if (fd < 0)
+		pr_debug("Failed to open cache(%d): %s\n", fd, cpath);
+	free(dir_name);
+	pcache->fd = fd;
+
+	return fd;
+}
+
+static int probe_cache__load(struct probe_cache *pcache)
+{
+	struct probe_cache_entry *entry = NULL;
+	char buf[MAX_CMDLEN], *p;
+	int ret = 0;
+	FILE *fp;
+
+	fp = fdopen(dup(pcache->fd), "r");
+	if (!fp)
+		return -EINVAL;
+
+	while (!feof(fp)) {
+		if (!fgets(buf, MAX_CMDLEN, fp))
+			break;
+		p = strchr(buf, '\n');
+		if (p)
+			*p = '\0';
+		/* #perf_probe_event or %sdt_event */
+		if (buf[0] == '#' || buf[0] == '%') {
+			entry = probe_cache_entry__new(NULL);
+			if (!entry) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			if (buf[0] == '%')
+				entry->sdt = true;
+			entry->spev = strdup(buf + 1);
+			if (entry->spev)
+				ret = parse_perf_probe_command(buf + 1,
+								&entry->pev);
+			else
+				ret = -ENOMEM;
+			if (ret < 0) {
+				probe_cache_entry__delete(entry);
+				goto out;
+			}
+			list_add_tail(&entry->node, &pcache->entries);
+		} else {	/* trace_probe_event */
+			if (!entry) {
+				ret = -EINVAL;
+				goto out;
+			}
+			strlist__add(entry->tevlist, buf);
+		}
+	}
+out:
+	fclose(fp);
+	return ret;
+}
+
+static struct probe_cache *probe_cache__alloc(void)
+{
+	struct probe_cache *pcache = zalloc(sizeof(*pcache));
+
+	if (pcache) {
+		INIT_LIST_HEAD(&pcache->entries);
+		pcache->fd = -EINVAL;
+	}
+	return pcache;
+}
+
+void probe_cache__purge(struct probe_cache *pcache)
+{
+	struct probe_cache_entry *entry, *n;
+
+	list_for_each_entry_safe(entry, n, &pcache->entries, node) {
+		list_del_init(&entry->node);
+		probe_cache_entry__delete(entry);
+	}
+}
+
+void probe_cache__delete(struct probe_cache *pcache)
+{
+	if (!pcache)
+		return;
+
+	probe_cache__purge(pcache);
+	if (pcache->fd > 0)
+		close(pcache->fd);
+	free(pcache);
+}
+
+struct probe_cache *probe_cache__new(const char *target)
+{
+	struct probe_cache *pcache = probe_cache__alloc();
+	int ret;
+
+	if (!pcache)
+		return NULL;
+
+	ret = probe_cache__open(pcache, target);
+	if (ret < 0) {
+		pr_debug("Cache open error: %d\n", ret);
+		goto out_err;
+	}
+
+	ret = probe_cache__load(pcache);
+	if (ret < 0) {
+		pr_debug("Cache read error: %d\n", ret);
+		goto out_err;
+	}
+
+	return pcache;
+
+out_err:
+	probe_cache__delete(pcache);
+	return NULL;
+}
+
+static bool streql(const char *a, const char *b)
+{
+	if (a == b)
+		return true;
+
+	if (!a || !b)
+		return false;
+
+	return !strcmp(a, b);
+}
+
+struct probe_cache_entry *
+probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev)
+{
+	struct probe_cache_entry *entry = NULL;
+	char *cmd = synthesize_perf_probe_command(pev);
+
+	if (!cmd)
+		return NULL;
+
+	for_each_probe_cache_entry(entry, pcache) {
+		if (pev->sdt) {
+			if (entry->pev.event &&
+			    streql(entry->pev.event, pev->event) &&
+			    (!pev->group ||
+			     streql(entry->pev.group, pev->group)))
+				goto found;
+
+			continue;
+		}
+		/* Hit if same event name or same command-string */
+		if ((pev->event &&
+		     (streql(entry->pev.group, pev->group) &&
+		      streql(entry->pev.event, pev->event))) ||
+		    (!strcmp(entry->spev, cmd)))
+			goto found;
+	}
+	entry = NULL;
+
+found:
+	free(cmd);
+	return entry;
+}
+
+struct probe_cache_entry *
+probe_cache__find_by_name(struct probe_cache *pcache,
+			  const char *group, const char *event)
+{
+	struct probe_cache_entry *entry = NULL;
+
+	for_each_probe_cache_entry(entry, pcache) {
+		/* Hit if same event name or same command-string */
+		if (streql(entry->pev.group, group) &&
+		    streql(entry->pev.event, event))
+			goto found;
+	}
+	entry = NULL;
+
+found:
+	return entry;
+}
+
+int probe_cache__add_entry(struct probe_cache *pcache,
+			   struct perf_probe_event *pev,
+			   struct probe_trace_event *tevs, int ntevs)
+{
+	struct probe_cache_entry *entry = NULL;
+	char *command;
+	int i, ret = 0;
+
+	if (!pcache || !pev || !tevs || ntevs <= 0) {
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	/* Remove old cache entry */
+	entry = probe_cache__find(pcache, pev);
+	if (entry) {
+		list_del_init(&entry->node);
+		probe_cache_entry__delete(entry);
+	}
+
+	ret = -ENOMEM;
+	entry = probe_cache_entry__new(pev);
+	if (!entry)
+		goto out_err;
+
+	for (i = 0; i < ntevs; i++) {
+		if (!tevs[i].point.symbol)
+			continue;
+
+		command = synthesize_probe_trace_command(&tevs[i]);
+		if (!command)
+			goto out_err;
+		strlist__add(entry->tevlist, command);
+		free(command);
+	}
+	list_add_tail(&entry->node, &pcache->entries);
+	pr_debug("Added probe cache: %d\n", ntevs);
+	return 0;
+
+out_err:
+	pr_debug("Failed to add probe caches\n");
+	probe_cache_entry__delete(entry);
+	return ret;
+}
+
+#ifdef HAVE_GELF_GETNOTE_SUPPORT
+static unsigned long long sdt_note__get_addr(struct sdt_note *note)
+{
+	return note->bit32 ? (unsigned long long)note->addr.a32[0]
+		 : (unsigned long long)note->addr.a64[0];
+}
+
+int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
+{
+	struct probe_cache_entry *entry = NULL;
+	struct list_head sdtlist;
+	struct sdt_note *note;
+	char *buf;
+	char sdtgrp[64];
+	int ret;
+
+	INIT_LIST_HEAD(&sdtlist);
+	ret = get_sdt_note_list(&sdtlist, pathname);
+	if (ret < 0) {
+		pr_debug("Failed to get sdt note: %d\n", ret);
+		return ret;
+	}
+	list_for_each_entry(note, &sdtlist, note_list) {
+		ret = snprintf(sdtgrp, 64, "sdt_%s", note->provider);
+		if (ret < 0)
+			break;
+		/* Try to find same-name entry */
+		entry = probe_cache__find_by_name(pcache, sdtgrp, note->name);
+		if (!entry) {
+			entry = probe_cache_entry__new(NULL);
+			if (!entry) {
+				ret = -ENOMEM;
+				break;
+			}
+			entry->sdt = true;
+			ret = asprintf(&entry->spev, "%s:%s=%s", sdtgrp,
+					note->name, note->name);
+			if (ret < 0)
+				break;
+			entry->pev.event = strdup(note->name);
+			entry->pev.group = strdup(sdtgrp);
+			list_add_tail(&entry->node, &pcache->entries);
+		}
+		ret = asprintf(&buf, "p:%s/%s %s:0x%llx",
+				sdtgrp, note->name, pathname,
+				sdt_note__get_addr(note));
+		if (ret < 0)
+			break;
+		strlist__add(entry->tevlist, buf);
+		free(buf);
+		entry = NULL;
+	}
+	if (entry) {
+		list_del_init(&entry->node);
+		probe_cache_entry__delete(entry);
+	}
+	cleanup_sdt_note_list(&sdtlist);
+	return ret;
+}
+#endif
+
+static int probe_cache_entry__write(struct probe_cache_entry *entry, int fd)
+{
+	struct str_node *snode;
+	struct stat st;
+	struct iovec iov[3];
+	const char *prefix = entry->sdt ? "%" : "#";
+	int ret;
+	/* Save stat for rollback */
+	ret = fstat(fd, &st);
+	if (ret < 0)
+		return ret;
+
+	pr_debug("Writing cache: %s%s\n", prefix, entry->spev);
+	iov[0].iov_base = (void *)prefix; iov[0].iov_len = 1;
+	iov[1].iov_base = entry->spev; iov[1].iov_len = strlen(entry->spev);
+	iov[2].iov_base = (void *)"\n"; iov[2].iov_len = 1;
+	ret = writev(fd, iov, 3);
+	if (ret < (int)iov[1].iov_len + 2)
+		goto rollback;
+
+	strlist__for_each_entry(snode, entry->tevlist) {
+		iov[0].iov_base = (void *)snode->s;
+		iov[0].iov_len = strlen(snode->s);
+		iov[1].iov_base = (void *)"\n"; iov[1].iov_len = 1;
+		ret = writev(fd, iov, 2);
+		if (ret < (int)iov[0].iov_len + 1)
+			goto rollback;
+	}
+	return 0;
+
+rollback:
+	/* Rollback to avoid cache file corruption */
+	if (ret > 0)
+		ret = -1;
+	if (ftruncate(fd, st.st_size) < 0)
+		ret = -2;
+
+	return ret;
+}
+
+int probe_cache__commit(struct probe_cache *pcache)
+{
+	struct probe_cache_entry *entry;
+	int ret = 0;
+
+	/* TBD: if we do not update existing entries, skip it */
+	ret = lseek(pcache->fd, 0, SEEK_SET);
+	if (ret < 0)
+		goto out;
+
+	ret = ftruncate(pcache->fd, 0);
+	if (ret < 0)
+		goto out;
+
+	for_each_probe_cache_entry(entry, pcache) {
+		ret = probe_cache_entry__write(entry, pcache->fd);
+		pr_debug("Cache committed: %d\n", ret);
+		if (ret < 0)
+			break;
+	}
+out:
+	return ret;
+}
+
+static bool probe_cache_entry__compare(struct probe_cache_entry *entry,
+				       struct strfilter *filter)
+{
+	char buf[128], *ptr = entry->spev;
+
+	if (entry->pev.event) {
+		snprintf(buf, 128, "%s:%s", entry->pev.group, entry->pev.event);
+		ptr = buf;
+	}
+	return strfilter__compare(filter, ptr);
+}
+
+int probe_cache__filter_purge(struct probe_cache *pcache,
+			      struct strfilter *filter)
+{
+	struct probe_cache_entry *entry, *tmp;
+
+	list_for_each_entry_safe(entry, tmp, &pcache->entries, node) {
+		if (probe_cache_entry__compare(entry, filter)) {
+			pr_info("Removed cached event: %s\n", entry->spev);
+			list_del_init(&entry->node);
+			probe_cache_entry__delete(entry);
+		}
+	}
+	return 0;
+}
+
+static int probe_cache__show_entries(struct probe_cache *pcache,
+				     struct strfilter *filter)
+{
+	struct probe_cache_entry *entry;
+
+	for_each_probe_cache_entry(entry, pcache) {
+		if (probe_cache_entry__compare(entry, filter))
+			printf("%s\n", entry->spev);
+	}
+	return 0;
+}
+
+/* Show all cached probes */
+int probe_cache__show_all_caches(struct strfilter *filter)
+{
+	struct probe_cache *pcache;
+	struct strlist *bidlist;
+	struct str_node *nd;
+	char *buf = strfilter__string(filter);
+
+	pr_debug("list cache with filter: %s\n", buf);
+	free(buf);
+
+	bidlist = build_id_cache__list_all(true);
+	if (!bidlist) {
+		pr_debug("Failed to get buildids: %d\n", errno);
+		return -EINVAL;
+	}
+	strlist__for_each_entry(nd, bidlist) {
+		pcache = probe_cache__new(nd->s);
+		if (!pcache)
+			continue;
+		if (!list_empty(&pcache->entries)) {
+			buf = build_id_cache__origname(nd->s);
+			printf("%s (%s):\n", buf, nd->s);
+			free(buf);
+			probe_cache__show_entries(pcache, filter);
+		}
+		probe_cache__delete(pcache);
+	}
+	strlist__delete(bidlist);
+
+	return 0;
+}