perf kwork: Implement 'report' subcommand

Implements framework of 'perf kwork report', which is used to report
time properties such as run time and frequency:

Test cases:

  # perf kwork

   Usage: perf kwork [<options>] {record|report}

      -D, --dump-raw-trace  dump raw trace in ASCII
      -f, --force           don't complain, do it
      -k, --kwork <kwork>   list of kwork to profile (irq, softirq, workqueue, etc)
      -v, --verbose         be more verbose (show symbol address, etc)

  # perf kwork report -h

   Usage: perf kwork report [<options>]

      -C, --cpu <cpu>       list of cpus to profile
      -i, --input <file>    input file name
      -n, --name <name>     event name to profile
      -s, --sort <key[,key2...]>
                            sort by key(s): runtime, max, count
      -S, --with-summary    Show summary with statistics
          --time <str>      Time span for analysis (start,stop)

  # perf kwork report

    Kwork Name                     | Cpu  | Total Runtime | Count     | Max runtime   | Max runtime start   | Max runtime end     |
   --------------------------------------------------------------------------------------------------------------------------------
   --------------------------------------------------------------------------------------------------------------------------------

  # perf kwork report -S

    Kwork Name                     | Cpu  | Total Runtime | Count     | Max runtime   | Max runtime start   | Max runtime end     |
   --------------------------------------------------------------------------------------------------------------------------------
   --------------------------------------------------------------------------------------------------------------------------------
    Total count            :         0
    Total runtime   (msec) :     0.000 (0.000% load average)
    Total time span (msec) :     0.000
   --------------------------------------------------------------------------------------------------------------------------------

  # perf kwork report -C 0,100
  Requested CPU 100 too large. Consider raising MAX_NR_CPUS
  Invalid cpu bitmap

  # perf kwork report -s runtime1
    Error: Unknown --sort key: `runtime1'

   Usage: perf kwork report [<options>]

      -C, --cpu <cpu>       list of cpus to profile
      -i, --input <file>    input file name
      -n, --name <name>     event name to profile
      -s, --sort <key[,key2...]>
                            sort by key(s): runtime, max, count
      -S, --with-summary    Show summary with statistics
          --time <str>      Time span for analysis (start,stop)

  # perf kwork report -i perf_no_exist.data
  failed to open perf_no_exist.data: No such file or directory

  # perf kwork report --time 00FFF,
  Invalid time span

Since there are no report supported events, the output is empty.

Briefly describe the data structure:

1. "class" indicates event type. For example, irq and softiq correspond
to different types.

2. "cluster" refers to a specific event corresponding to a type. For
example, RCU and TIMER in softirq correspond to different clusters,
which contains three types of events: raise, entry, and exit.

3. "atom" includes time of each sample and sample of the previous phase.
(For example, exit corresponds to entry, which is used for timehist.)

Committer notes:

- Add {} for multiline if blocks.

- report_print_work() should either return that ret variable that
  accounts how many bytes were printed or stop accounting and be void.
  Do the former for now to avoid this:

builtin-kwork.c:534:6: error: variable 'ret' set but not used [-Werror,-Wunused-but-set-variable]
        int ret = 0;
            ^
1 error generated.

  When building with:

  ⬢[acme@toolbox perf]$ clang --version
  clang version 13.0.0 (https://github.com/llvm/llvm-project e8991caea8690ec2d17b0b7e1c29bf0da6609076)

Also:

  -       if ((dst_type >= 0) && (dst_type < KWORK_TRACE_MAX)) {
  +       if (dst_type < KWORK_TRACE_MAX) {

Several versions of clang and at least this gcc:

   3    51.40 alpine:3.9                    : FAIL gcc version 8.3.0 (Alpine 8.3.0)
    builtin-kwork.c:411:16: error: comparison of unsigned enum expression >= 0 is
          always true [-Werror,-Wtautological-compare]
            if ((dst_type >= 0) && (dst_type < KWORK_TRACE_MAX)) {

As the first entry in a enum is zero.

Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220709015033.38326-7-yangjihong1@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 161 insertions, 0 deletions

diff --git a/tools/perf/util/kwork.h b/tools/perf/util/kwork.h
index 03203c4deb346..0a86bf47c74d3 100644
--- a/tools/perf/util/kwork.h
+++ b/tools/perf/util/kwork.h
@@ -19,6 +19,105 @@ enum kwork_class_type {
 	KWORK_CLASS_MAX,
 };
 
+enum kwork_report_type {
+	KWORK_REPORT_RUNTIME,
+};
+
+enum kwork_trace_type {
+	KWORK_TRACE_ENTRY,
+	KWORK_TRACE_EXIT,
+	KWORK_TRACE_MAX,
+};
+
+/*
+ * data structure:
+ *
+ *                 +==================+ +============+ +======================+
+ *                 |      class       | |    work    | |         atom         |
+ *                 +==================+ +============+ +======================+
+ * +------------+  |  +-----+         | |  +------+  | |  +-------+   +-----+ |
+ * | perf_kwork | +-> | irq | --------|+-> | eth0 | --+-> | raise | - | ... | --+   +-----------+
+ * +-----+------+ ||  +-----+         |||  +------+  |||  +-------+   +-----+ | |   |           |
+ *       |        ||                  |||            |||                      | +-> | atom_page |
+ *       |        ||                  |||            |||  +-------+   +-----+ |     |           |
+ *       |  class_list                |||            |+-> | entry | - | ... | ----> |           |
+ *       |        ||                  |||            |||  +-------+   +-----+ |     |           |
+ *       |        ||                  |||            |||                      | +-> |           |
+ *       |        ||                  |||            |||  +-------+   +-----+ | |   |           |
+ *       |        ||                  |||            |+-> | exit  | - | ... | --+   +-----+-----+
+ *       |        ||                  |||            | |  +-------+   +-----+ |           |
+ *       |        ||                  |||            | |                      |           |
+ *       |        ||                  |||  +-----+   | |                      |           |
+ *       |        ||                  |+-> | ... |   | |                      |           |
+ *       |        ||                  | |  +-----+   | |                      |           |
+ *       |        ||                  | |            | |                      |           |
+ *       |        ||  +---------+     | |  +-----+   | |  +-------+   +-----+ |           |
+ *       |        +-> | softirq | -------> | RCU | ---+-> | raise | - | ... | --+   +-----+-----+
+ *       |        ||  +---------+     | |  +-----+   |||  +-------+   +-----+ | |   |           |
+ *       |        ||                  | |            |||                      | +-> | atom_page |
+ *       |        ||                  | |            |||  +-------+   +-----+ |     |           |
+ *       |        ||                  | |            |+-> | entry | - | ... | ----> |           |
+ *       |        ||                  | |            |||  +-------+   +-----+ |     |           |
+ *       |        ||                  | |            |||                      | +-> |           |
+ *       |        ||                  | |            |||  +-------+   +-----+ | |   |           |
+ *       |        ||                  | |            |+-> | exit  | - | ... | --+   +-----+-----+
+ *       |        ||                  | |            | |  +-------+   +-----+ |           |
+ *       |        ||                  | |            | |                      |           |
+ *       |        ||  +-----------+   | |  +-----+   | |                      |           |
+ *       |        +-> | workqueue | -----> | ... |   | |                      |           |
+ *       |         |  +-----------+   | |  +-----+   | |                      |           |
+ *       |         +==================+ +============+ +======================+           |
+ *       |                                                                                |
+ *       +---->  atom_page_list  ---------------------------------------------------------+
+ *
+ */
+
+struct kwork_atom {
+	struct list_head list;
+	u64 time;
+	struct kwork_atom *prev;
+
+	void *page_addr;
+	unsigned long bit_inpage;
+};
+
+#define NR_ATOM_PER_PAGE 128
+struct kwork_atom_page {
+	struct list_head list;
+	struct kwork_atom atoms[NR_ATOM_PER_PAGE];
+	DECLARE_BITMAP(bitmap, NR_ATOM_PER_PAGE);
+};
+
+struct kwork_class;
+struct kwork_work {
+	/*
+	 * class field
+	 */
+	struct rb_node node;
+	struct kwork_class *class;
+
+	/*
+	 * work field
+	 */
+	u64 id;
+	int cpu;
+	char *name;
+
+	/*
+	 * atom field
+	 */
+	u64 nr_atoms;
+	struct list_head atom_list[KWORK_TRACE_MAX];
+
+	/*
+	 * runtime report
+	 */
+	u64 max_runtime;
+	u64 max_runtime_start;
+	u64 max_runtime_end;
+	u64 total_runtime;
+};
+
 struct kwork_class {
 	struct list_head list;
 	const char *name;
@@ -26,19 +125,81 @@ struct kwork_class {
 
 	unsigned int nr_tracepoints;
 	const struct evsel_str_handler *tp_handlers;
+
+	struct rb_root_cached work_root;
+
+	int (*class_init)(struct kwork_class *class,
+			  struct perf_session *session);
+
+	void (*work_init)(struct kwork_class *class,
+			  struct kwork_work *work,
+			  struct evsel *evsel,
+			  struct perf_sample *sample,
+			  struct machine *machine);
+
+	void (*work_name)(struct kwork_work *work,
+			  char *buf, int len);
+};
+
+struct perf_kwork;
+struct trace_kwork_handler {
+	int (*entry_event)(struct perf_kwork *kwork,
+			   struct kwork_class *class, struct evsel *evsel,
+			   struct perf_sample *sample, struct machine *machine);
+
+	int (*exit_event)(struct perf_kwork *kwork,
+			  struct kwork_class *class, struct evsel *evsel,
+			  struct perf_sample *sample, struct machine *machine);
 };
 
 struct perf_kwork {
 	/*
 	 * metadata
 	 */
+	struct perf_tool tool;
 	struct list_head class_list;
+	struct list_head atom_page_list;
+	struct list_head sort_list, cmp_id;
+	struct rb_root_cached sorted_work_root;
+	const struct trace_kwork_handler *tp_handler;
+
+	/*
+	 * profile filters
+	 */
+	const char *profile_name;
+
+	const char *cpu_list;
+	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+
+	const char *time_str;
+	struct perf_time_interval ptime;
 
 	/*
 	 * options for command
 	 */
 	bool force;
 	const char *event_list_str;
+	enum kwork_report_type report;
+
+	/*
+	 * options for subcommand
+	 */
+	bool summary;
+	const char *sort_order;
+
+	/*
+	 * statistics
+	 */
+	u64 timestart;
+	u64 timeend;
+
+	unsigned long nr_events;
+	unsigned long nr_lost_chunks;
+	unsigned long nr_lost_events;
+
+	u64 all_runtime;
+	u64 all_count;
+	u64 nr_skipped_events[KWORK_TRACE_MAX + 1];
 };
 
 #endif  /* PERF_UTIL_KWORK_H */