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
  ...

1 files changed, 79 insertions, 44 deletions

diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 6969f82843ee..6984c77068a3 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -489,7 +489,7 @@ int perf_default_config(const char *var, const char *value,
 	return 0;
 }
 
-int perf_config_from_file(config_fn_t fn, const char *filename, void *data)
+static int perf_config_from_file(config_fn_t fn, const char *filename, void *data)
 {
 	int ret;
 	FILE *f = fopen(filename, "r");
@@ -521,16 +521,66 @@ static int perf_env_bool(const char *k, int def)
 	return v ? perf_config_bool(k, v) : def;
 }
 
-static int perf_config_system(void)
+int perf_config_system(void)
 {
 	return !perf_env_bool("PERF_CONFIG_NOSYSTEM", 0);
 }
 
-static int perf_config_global(void)
+int perf_config_global(void)
 {
 	return !perf_env_bool("PERF_CONFIG_NOGLOBAL", 0);
 }
 
+static char *home_perfconfig(void)
+{
+	const char *home = NULL;
+	char *config;
+	struct stat st;
+
+	home = getenv("HOME");
+
+	/*
+	 * Skip reading user config if:
+	 *   - there is no place to read it from (HOME)
+	 *   - we are asked not to (PERF_CONFIG_NOGLOBAL=1)
+	 */
+	if (!home || !*home || !perf_config_global())
+		return NULL;
+
+	config = strdup(mkpath("%s/.perfconfig", home));
+	if (config == NULL) {
+		pr_warning("Not enough memory to process %s/.perfconfig, ignoring it.", home);
+		return NULL;
+	}
+
+	if (stat(config, &st) < 0)
+		goto out_free;
+
+	if (st.st_uid && (st.st_uid != geteuid())) {
+		pr_warning("File %s not owned by current user or root, ignoring it.", config);
+		goto out_free;
+	}
+
+	if (st.st_size)
+		return config;
+
+out_free:
+	free(config);
+	return NULL;
+}
+
+const char *perf_home_perfconfig(void)
+{
+	static const char *config;
+	static bool failed;
+
+	config = failed ? NULL : home_perfconfig();
+	if (!config)
+		failed = true;
+
+	return config;
+}
+
 static struct perf_config_section *find_section(struct list_head *sections,
 						const char *section_name)
 {
@@ -676,9 +726,6 @@ int perf_config_set__collect(struct perf_config_set *set, const char *file_name,
 static int perf_config_set__init(struct perf_config_set *set)
 {
 	int ret = -1;
-	const char *home = NULL;
-	char *user_config;
-	struct stat st;
 
 	/* Setting $PERF_CONFIG makes perf read _only_ the given config file. */
 	if (config_exclusive_filename)
@@ -687,41 +734,11 @@ static int perf_config_set__init(struct perf_config_set *set)
 		if (perf_config_from_file(collect_config, perf_etc_perfconfig(), set) < 0)
 			goto out;
 	}
-
-	home = getenv("HOME");
-
-	/*
-	 * Skip reading user config if:
-	 *   - there is no place to read it from (HOME)
-	 *   - we are asked not to (PERF_CONFIG_NOGLOBAL=1)
-	 */
-	if (!home || !*home || !perf_config_global())
-		return 0;
-
-	user_config = strdup(mkpath("%s/.perfconfig", home));
-	if (user_config == NULL) {
-		pr_warning("Not enough memory to process %s/.perfconfig, ignoring it.", home);
-		goto out;
-	}
-
-	if (stat(user_config, &st) < 0) {
-		if (errno == ENOENT)
-			ret = 0;
-		goto out_free;
-	}
-
-	ret = 0;
-
-	if (st.st_uid && (st.st_uid != geteuid())) {
-		pr_warning("File %s not owned by current user or root, ignoring it.", user_config);
-		goto out_free;
+	if (perf_config_global() && perf_home_perfconfig()) {
+		if (perf_config_from_file(collect_config, perf_home_perfconfig(), set) < 0)
+			goto out;
 	}
 
-	if (st.st_size)
-		ret = perf_config_from_file(collect_config, user_config, set);
-
-out_free:
-	free(user_config);
 out:
 	return ret;
 }
@@ -738,6 +755,18 @@ struct perf_config_set *perf_config_set__new(void)
 	return set;
 }
 
+struct perf_config_set *perf_config_set__load_file(const char *file)
+{
+	struct perf_config_set *set = zalloc(sizeof(*set));
+
+	if (set) {
+		INIT_LIST_HEAD(&set->sections);
+		perf_config_from_file(collect_config, file, set);
+	}
+
+	return set;
+}
+
 static int perf_config__init(void)
 {
 	if (config_set == NULL)
@@ -746,17 +775,15 @@ static int perf_config__init(void)
 	return config_set == NULL;
 }
 
-int perf_config(config_fn_t fn, void *data)
+int perf_config_set(struct perf_config_set *set,
+		    config_fn_t fn, void *data)
 {
 	int ret = 0;
 	char key[BUFSIZ];
 	struct perf_config_section *section;
 	struct perf_config_item *item;
 
-	if (config_set == NULL && perf_config__init())
-		return -1;
-
-	perf_config_set__for_each_entry(config_set, section, item) {
+	perf_config_set__for_each_entry(set, section, item) {
 		char *value = item->value;
 
 		if (value) {
@@ -778,6 +805,14 @@ out:
 	return ret;
 }
 
+int perf_config(config_fn_t fn, void *data)
+{
+	if (config_set == NULL && perf_config__init())
+		return -1;
+
+	return perf_config_set(config_set, fn, data);
+}
+
 void perf_config__exit(void)
 {
 	perf_config_set__delete(config_set);