Merge tag 'perf-tools-for-v5.12-2020-02-19' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "New features:

   - Support instruction latency in 'perf report', with both memory
     latency (weight) and instruction latency information, users can
     locate expensive load instructions and understand time spent in
     different stages.

   - Extend 'perf c2c' to display the number of loads which were blocked
     by data or address conflict.

   - Add 'perf stat' support for L2 topdown events in systems such as
     Intel's Sapphire rapids server.

   - Add support for PERF_SAMPLE_CODE_PAGE_SIZE in various tools, as a
     sort key, for instance:

        perf report --stdio --sort=comm,symbol,code_page_size

   - New 'perf daemon' command to run long running sessions while
     providing a way to control the enablement of events without
     restarting a traditional 'perf record' session.

   - Enable counting events for BPF programs in 'perf stat' just like
     for other targets (tid, cgroup, cpu, etc), e.g.:

        # perf stat -e ref-cycles,cycles -b 254 -I 1000
           1.487903822            115,200      ref-cycles
           1.487903822             86,012      cycles
           2.489147029             80,560      ref-cycles
           2.489147029             73,784      cycles
        ^C

     The example above counts 'cycles' and 'ref-cycles' of BPF program
     of id 254. It is similar to bpftool-prog-profile command, but more
     flexible.

   - Support the new layout for PERF_RECORD_MMAP2 to carry the DSO
     build-id using infrastructure generalised from the eBPF subsystem,
     removing the need for traversing the perf.data file to collect
     build-ids at the end of 'perf record' sessions and helping with
     long running sessions where binaries can get replaced in updates,
     leading to possible mis-resolution of symbols.

   - Support filtering by hex address in 'perf script'.

   - Support DSO filter in 'perf script', like in other perf tools.

   - Add namespaces support to 'perf inject'

   - Add support for SDT (Dtrace Style Markers) events on ARM64.

  perf record:

   - Fix handling of eventfd() when draining a buffer in 'perf record'.

   - Improvements to the generation of metadata events for pre-existing
     threads (mmaps, comm, etc), speeding up the work done at the start
     of system wide or per CPU 'perf record' sessions.

  Hardware tracing:

   - Initial support for tracing KVM with Intel PT.

   - Intel PT fixes for IPC

   - Support Intel PT PSB (synchronization packets) events.

   - Automatically group aux-output events to overcome --filter syntax.

   - Enable PERF_SAMPLE_DATA_SRC on ARMs SPE.

   - Update ARM's CoreSight hardware tracing OpenCSD library to v1.0.0.

  perf annotate TUI:

   - Fix handling of 'k' ("show line number") hotkey

   - Fix jump parsing for C++ code.

  perf probe:

   - Add protection to avoid endless loop.

  cgroups:

   - Avoid reading cgroup mountpoint multiple times, caching it.

   - Fix handling of cgroup v1/v2 in mixed hierarchy.

  Symbol resolving:

   - Add OCaml symbol demangling.

   - Further fixes for handling PE executables when using perf with Wine
     and .exe/.dll files.

   - Fix 'perf unwind' DSO handling.

   - Resolve symbols against debug file first, to deal with artifacts
     related to LTO.

   - Fix gap between kernel end and module start on powerpc.

  Reporting tools:

   - The DSO filter shouldn't show samples in unresolved maps.

   - Improve debuginfod support in various tools.

  build ids:

   - Fix 16-byte build ids in 'perf buildid-cache', add a 'perf test'
     entry for that case.

  perf test:

   - Support for PERF_SAMPLE_WEIGHT_STRUCT.

   - Add test case for PERF_SAMPLE_CODE_PAGE_SIZE.

   - Shell based tests for 'perf daemon's commands ('start', 'stop,
     'reconfig', 'list', etc).

   - ARM cs-etm 'perf test' fixes.

   - Add parse-metric memory bandwidth testcase.

  Compiler related:

   - Fix 'perf probe' kretprobe issue caused by gcc 11 bug when used
     with -fpatchable-function-entry.

   - Fix ARM64 build with gcc 11's -Wformat-overflow.

   - Fix unaligned access in sample parsing test.

   - Fix printf conversion specifier for IP addresses on arm64, s390 and
     powerpc.

  Arch specific:

   - Support exposing Performance Monitor Counter SPRs as part of
     extended regs on powerpc.

   - Add JSON 'perf stat' metrics for ARM64's imx8mp, imx8mq and imx8mn
     DDR, fix imx8mm ones.

   - Fix common and uarch events for ARM64's A76 and Ampere eMag"

* tag 'perf-tools-for-v5.12-2020-02-19' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (148 commits)
  perf buildid-cache: Don't skip 16-byte build-ids
  perf buildid-cache: Add test for 16-byte build-id
  perf symbol: Remove redundant libbfd checks
  perf test: Output the sub testing result in cs-etm
  perf test: Suppress logs in cs-etm testing
  perf tools: Fix arm64 build error with gcc-11
  perf intel-pt: Add documentation for tracing virtual machines
  perf intel-pt: Split VM-Entry and VM-Exit branches
  perf intel-pt: Adjust sample flags for VM-Exit
  perf intel-pt: Allow for a guest kernel address filter
  perf intel-pt: Support decoding of guest kernel
  perf machine: Factor out machine__idle_thread()
  perf machine: Factor out machines__find_guest()
  perf intel-pt: Amend decoder to track the NR flag
  perf intel-pt: Retain the last PIP packet payload as is
  perf intel_pt: Add vmlaunch and vmresume as branches
  perf script: Add branch types for VM-Entry and VM-Exit
  perf auxtrace: Automatically group aux-output events
  perf test: Fix unaligned access in sample parsing test
  perf tools: Support arch specific PERF_SAMPLE_WEIGHT_STRUCT processing
  ...

2 files changed, 79 insertions, 34 deletions

diff --git a/tools/lib/api/fs/cgroup.c b/tools/lib/api/fs/cgroup.c
index 889a6eb4aaca..1573dae4259d 100644
--- a/tools/lib/api/fs/cgroup.c
+++ b/tools/lib/api/fs/cgroup.c
@@ -8,12 +8,29 @@
 #include <string.h>
 #include "fs.h"
 
+struct cgroupfs_cache_entry {
+	char	subsys[32];
+	char	mountpoint[PATH_MAX];
+};
+
+/* just cache last used one */
+static struct cgroupfs_cache_entry cached;
+
 int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys)
 {
 	FILE *fp;
-	char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1];
-	char path_v1[PATH_MAX + 1], path_v2[PATH_MAX + 2], *path;
-	char *token, *saved_ptr = NULL;
+	char *line = NULL;
+	size_t len = 0;
+	char *p, *path;
+	char mountpoint[PATH_MAX];
+
+	if (!strcmp(cached.subsys, subsys)) {
+		if (strlen(cached.mountpoint) < maxlen) {
+			strcpy(buf, cached.mountpoint);
+			return 0;
+		}
+		return -1;
+	}
 
 	fp = fopen("/proc/mounts", "r");
 	if (!fp)
@@ -22,45 +39,63 @@ int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys)
 	/*
 	 * in order to handle split hierarchy, we need to scan /proc/mounts
 	 * and inspect every cgroupfs mount point to find one that has
-	 * perf_event subsystem
+	 * the given subsystem.  If we found v1, just use it.  If not we can
+	 * use v2 path as a fallback.
 	 */
-	path_v1[0] = '\0';
-	path_v2[0] = '\0';
+	mountpoint[0] = '\0';
 
-	while (fscanf(fp, "%*s %"__stringify(PATH_MAX)"s %"__stringify(PATH_MAX)"s %"
-				__stringify(PATH_MAX)"s %*d %*d\n",
-				mountpoint, type, tokens) == 3) {
+	/*
+	 * The /proc/mounts has the follow format:
+	 *
+	 *   <devname> <mount point> <fs type> <options> ...
+	 *
+	 */
+	while (getline(&line, &len, fp) != -1) {
+		/* skip devname */
+		p = strchr(line, ' ');
+		if (p == NULL)
+			continue;
+
+		/* save the mount point */
+		path = ++p;
+		p = strchr(p, ' ');
+		if (p == NULL)
+			continue;
 
-		if (!path_v1[0] && !strcmp(type, "cgroup")) {
+		*p++ = '\0';
 
-			token = strtok_r(tokens, ",", &saved_ptr);
+		/* check filesystem type */
+		if (strncmp(p, "cgroup", 6))
+			continue;
 
-			while (token != NULL) {
-				if (subsys && !strcmp(token, subsys)) {
-					strcpy(path_v1, mountpoint);
-					break;
-				}
-				token = strtok_r(NULL, ",", &saved_ptr);
-			}
+		if (p[6] == '2') {
+			/* save cgroup v2 path */
+			strcpy(mountpoint, path);
+			continue;
 		}
 
-		if (!path_v2[0] && !strcmp(type, "cgroup2"))
-			strcpy(path_v2, mountpoint);
+		/* now we have cgroup v1, check the options for subsystem */
+		p += 7;
 
-		if (path_v1[0] && path_v2[0])
-			break;
+		p = strstr(p, subsys);
+		if (p == NULL)
+			continue;
+
+		/* sanity check: it should be separated by a space or a comma */
+		if (!strchr(" ,", p[-1]) || !strchr(" ,", p[strlen(subsys)]))
+			continue;
+
+		strcpy(mountpoint, path);
+		break;
 	}
+	free(line);
 	fclose(fp);
 
-	if (path_v1[0])
-		path = path_v1;
-	else if (path_v2[0])
-		path = path_v2;
-	else
-		return -1;
+	strncpy(cached.subsys, subsys, sizeof(cached.subsys) - 1);
+	strcpy(cached.mountpoint, mountpoint);
 
-	if (strlen(path) < maxlen) {
-		strcpy(buf, path);
+	if (mountpoint[0] && strlen(mountpoint) < maxlen) {
+		strcpy(buf, mountpoint);
 		return 0;
 	}
 	return -1;
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index 988c539bedb6..d82054225fcc 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -23,10 +23,20 @@ struct perf_record_mmap2 {
 	__u64			 start;
 	__u64			 len;
 	__u64			 pgoff;
-	__u32			 maj;
-	__u32			 min;
-	__u64			 ino;
-	__u64			 ino_generation;
+	union {
+		struct {
+			__u32	 maj;
+			__u32	 min;
+			__u64	 ino;
+			__u64	 ino_generation;
+		};
+		struct {
+			__u8	 build_id_size;
+			__u8	 __reserved_1;
+			__u16	 __reserved_2;
+			__u8	 build_id[20];
+		};
+	};
 	__u32			 prot;
 	__u32			 flags;
 	char			 filename[PATH_MAX];