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

Pull perf updates from Ingo Molnar:
 "Kernel side updates:

   - Fix and enhance poll support (Jiri Olsa)

   - Re-enable inheritance optimization (Jiri Olsa)

   - Enhance Intel memory events support (Stephane Eranian)

   - Refactor the Intel uncore driver to be more maintainable (Zheng
     Yan)

   - Enhance and fix Intel CPU and uncore PMU drivers (Peter Zijlstra,
     Andi Kleen)

   - [ plus various smaller fixes/cleanups ]

  User visible tooling updates:

   - Add +field argument support for --field option, so that one can add
     fields to the default list of fields to show, ie now one can just
     do:

         perf report --fields +pid

     And the pid will appear in addition to the default fields (Jiri
     Olsa)

   - Add +field argument support for --sort option (Jiri Olsa)

   - Honour -w in the report tools (report, top), allowing to specify
     the widths for the histogram entries columns (Namhyung Kim)

   - Properly show submicrosecond times in 'perf kvm stat' (Christian
     Borntraeger)

   - Add beautifier for mremap flags param in 'trace' (Alex Snast)

   - perf script: Allow callchains if any event samples them

   - Don't truncate Intel style addresses in 'annotate' (Alex Converse)

   - Allow profiling when kptr_restrict == 1 for non root users, kernel
     samples will just remain unresolved (Andi Kleen)

   - Allow configuring default options for callchains in config file
     (Namhyung Kim)

   - Support operations for shared futexes.  (Davidlohr Bueso)

   - "perf kvm stat report" improvements by Alexander Yarygin:
       -  Save pid string in opts.target.pid
       -  Enable the target.system_wide flag
       -  Unify the title bar output

   - [ plus lots of other fixes and small improvements.  ]

  Tooling infrastructure changes:

   - Refactor unit and scale function parameters for PMU parsing
     routines (Matt Fleming)

   - Improve DSO long names lookup with rbtree, resulting in great
     speedup for workloads with lots of DSOs (Waiman Long)

   - We were not handling POLLHUP notifications for event file
     descriptors

     Fix it by filtering entries in the events file descriptor array
     after poll() returns, refcounting mmaps so that when the last fd
     pointing to a perf mmap goes away we do the unmap (Arnaldo Carvalho
     de Melo)

   - Intel PT prep work, from Adrian Hunter, including:
       - Let a user specify a PMU event without any config terms
       - Add perf-with-kcore script
       - Let default config be defined for a PMU
       - Add perf_pmu__scan_file()
       - Add a 'perf test' for tracking with sched_switch
       - Add 'flush' callback to scripting API

   - Use ring buffer consume method to look like other tools (Arnaldo
     Carvalho de Melo)

   - hists browser (used in top and report) refactorings, getting rid of
     unused variables and reducing source code size by handling similar
     cases in a fewer functions (Namhyung Kim).

   - Replace thread unsafe strerror() with strerror_r() accross the
     whole tools/perf/ tree (Masami Hiramatsu)

   - Rename ordered_samples to ordered_events and allow setting a queue
     size for ordering events (Jiri Olsa)

   - [ plus lots of fixes, cleanups and other improvements ]"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (198 commits)
  perf/x86: Tone down kernel messages when the PMU check fails in a virtual environment
  perf/x86/intel/uncore: Fix minor race in box set up
  perf record: Fix error message for --filter option not coming after tracepoint
  perf tools: Fix build breakage on arm64 targets
  perf symbols: Improve DSO long names lookup speed with rbtree
  perf symbols: Encapsulate dsos list head into struct dsos
  perf bench futex: Sanitize -q option in requeue
  perf bench futex: Support operations for shared futexes
  perf trace: Fix mmap return address truncation to 32-bit
  perf tools: Refactor unit and scale function parameters
  perf tools: Fix line number in the config file error message
  perf tools: Convert {record,top}.call-graph option to call-graph.record-mode
  perf tools: Introduce perf_callchain_config()
  perf callchain: Move some parser functions to callchain.c
  perf tools: Move callchain config from record_opts to callchain_param
  perf hists browser: Fix callchain print bug on TUI
  perf tools: Use ACCESS_ONCE() instead of volatile cast
  perf tools: Modify error code for when perf_session__new() fails
  perf tools: Fix perf record as non root with kptr_restrict == 1
  perf stat: Fix --per-core on multi socket systems
  ...

1 files changed, 88 insertions, 33 deletions

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 7a811eb..93a41ca 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -2,6 +2,8 @@
 #include <sys/types.h>
 #include <unistd.h>
 #include <stdio.h>
+#include <stdbool.h>
+#include <stdarg.h>
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
@@ -14,8 +16,8 @@
 
 struct perf_pmu_alias {
 	char *name;
-	struct list_head terms;
-	struct list_head list;
+	struct list_head terms; /* HEAD struct parse_events_term -> list */
+	struct list_head list;  /* ELEM */
 	char unit[UNIT_MAX_LEN+1];
 	double scale;
 };
@@ -208,6 +210,19 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	return 0;
 }
 
+static inline bool pmu_alias_info_file(char *name)
+{
+	size_t len;
+
+	len = strlen(name);
+	if (len > 5 && !strcmp(name + len - 5, ".unit"))
+		return true;
+	if (len > 6 && !strcmp(name + len - 6, ".scale"))
+		return true;
+
+	return false;
+}
+
 /*
  * Process all the sysfs attributes located under the directory
  * specified in 'dir' parameter.
@@ -216,7 +231,6 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 {
 	struct dirent *evt_ent;
 	DIR *event_dir;
-	size_t len;
 	int ret = 0;
 
 	event_dir = opendir(dir);
@@ -232,13 +246,9 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 			continue;
 
 		/*
-		 * skip .unit and .scale info files
-		 * parsed in perf_pmu__new_alias()
+		 * skip info files parsed in perf_pmu__new_alias()
 		 */
-		len = strlen(name);
-		if (len > 5 && !strcmp(name + len - 5, ".unit"))
-			continue;
-		if (len > 6 && !strcmp(name + len - 6, ".scale"))
+		if (pmu_alias_info_file(name))
 			continue;
 
 		snprintf(path, PATH_MAX, "%s/%s", dir, name);
@@ -387,6 +397,12 @@ static struct cpu_map *pmu_cpumask(const char *name)
 	return cpus;
 }
 
+struct perf_event_attr *__attribute__((weak))
+perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+{
+	return NULL;
+}
+
 static struct perf_pmu *pmu_lookup(const char *name)
 {
 	struct perf_pmu *pmu;
@@ -421,6 +437,9 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	pmu->name = strdup(name);
 	pmu->type = type;
 	list_add_tail(&pmu->list, &pmus);
+
+	pmu->default_config = perf_pmu__get_default_config(pmu);
+
 	return pmu;
 }
 
@@ -479,28 +498,24 @@ pmu_find_format(struct list_head *formats, char *name)
 }
 
 /*
- * Returns value based on the format definition (format parameter)
+ * Sets value based on the format definition (format parameter)
  * and unformated value (value parameter).
- *
- * TODO maybe optimize a little ;)
  */
-static __u64 pmu_format_value(unsigned long *format, __u64 value)
+static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
+			     bool zero)
 {
 	unsigned long fbit, vbit;
-	__u64 v = 0;
 
 	for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) {
 
 		if (!test_bit(fbit, format))
 			continue;
 
-		if (!(value & (1llu << vbit++)))
-			continue;
-
-		v |= (1llu << fbit);
+		if (value & (1llu << vbit++))
+			*v |= (1llu << fbit);
+		else if (zero)
+			*v &= ~(1llu << fbit);
 	}
-
-	return v;
 }
 
 /*
@@ -509,7 +524,8 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value)
  */
 static int pmu_config_term(struct list_head *formats,
 			   struct perf_event_attr *attr,
-			   struct parse_events_term *term)
+			   struct parse_events_term *term,
+			   bool zero)
 {
 	struct perf_pmu_format *format;
 	__u64 *vp;
@@ -548,18 +564,19 @@ static int pmu_config_term(struct list_head *formats,
 	 * non-hardcoded terms, here's the place to translate
 	 * them into value.
 	 */
-	*vp |= pmu_format_value(format->bits, term->val.num);
+	pmu_format_value(format->bits, term->val.num, vp, zero);
 	return 0;
 }
 
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
-			   struct list_head *head_terms)
+			   struct list_head *head_terms,
+			   bool zero)
 {
 	struct parse_events_term *term;
 
 	list_for_each_entry(term, head_terms, list)
-		if (pmu_config_term(formats, attr, term))
+		if (pmu_config_term(formats, attr, term, zero))
 			return -EINVAL;
 
 	return 0;
@@ -573,8 +590,10 @@ int perf_pmu__config_terms(struct list_head *formats,
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms)
 {
+	bool zero = !!pmu->default_config;
+
 	attr->type = pmu->type;
-	return perf_pmu__config_terms(&pmu->format, attr, head_terms);
+	return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero);
 }
 
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
@@ -634,7 +653,7 @@ static int check_unit_scale(struct perf_pmu_alias *alias,
  * defined for the alias
  */
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
-			  const char **unit, double *scale)
+			  struct perf_pmu_info *info)
 {
 	struct parse_events_term *term, *h;
 	struct perf_pmu_alias *alias;
@@ -644,8 +663,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	 * Mark unit and scale as not set
 	 * (different from default values, see below)
 	 */
-	*unit   = NULL;
-	*scale  = 0.0;
+	info->unit   = NULL;
+	info->scale  = 0.0;
 
 	list_for_each_entry_safe(term, h, head_terms, list) {
 		alias = pmu_find_alias(pmu, term);
@@ -655,7 +674,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 		if (ret)
 			return ret;
 
-		ret = check_unit_scale(alias, unit, scale);
+		ret = check_unit_scale(alias, &info->unit, &info->scale);
 		if (ret)
 			return ret;
 
@@ -668,11 +687,11 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	 * set defaults as for evsel
 	 * unit cannot left to NULL
 	 */
-	if (*unit == NULL)
-		*unit   = "";
+	if (info->unit == NULL)
+		info->unit   = "";
 
-	if (*scale == 0.0)
-		*scale  = 1.0;
+	if (info->scale == 0.0)
+		info->scale  = 1.0;
 
 	return 0;
 }
@@ -794,3 +813,39 @@ bool pmu_have_event(const char *pname, const char *name)
 	}
 	return false;
 }
+
+static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs;
+
+	sysfs = sysfs__mountpoint();
+	if (!sysfs)
+		return NULL;
+
+	snprintf(path, PATH_MAX,
+		 "%s" EVENT_SOURCE_DEVICE_PATH "%s/%s", sysfs, pmu->name, name);
+
+	if (stat(path, &st) < 0)
+		return NULL;
+
+	return fopen(path, "r");
+}
+
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+			...)
+{
+	va_list args;
+	FILE *file;
+	int ret = EOF;
+
+	va_start(args, fmt);
+	file = perf_pmu__open_file(pmu, name);
+	if (file) {
+		ret = vfscanf(file, fmt, args);
+		fclose(file);
+	}
+	va_end(args);
+	return ret;
+}