Merge tag 'perf-tools-for-v6.0-2022-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - Introduce 'perf lock contention' subtool, using new lock contention
   tracepoints and using BPF for in kernel aggregation and then
   userspace processing using the perf tooling infrastructure for
   resolving symbols, target specification, etc.

   Since the new lock contention tracepoints don't provide lock names,
   get up to 8 stack traces and display the first non-lock function
   symbol name as a caller:

    $ perf lock report -F acquired,contended,avg_wait,wait_total

                    Name   acquired  contended     avg wait    total wait

     update_blocked_a...         40         40      3.61 us     144.45 us
     kernfs_fop_open+...          5          5      3.64 us      18.18 us
      _nohz_idle_balance          3          3      2.65 us       7.95 us
     tick_do_update_j...          1          1      6.04 us       6.04 us
      ep_scan_ready_list          1          1      3.93 us       3.93 us

   Supports the usual 'perf record' + 'perf report' workflow as well as
   a BCC/bpftrace like mode where you start the tool and then press
   control+C to get results:

     $ sudo perf lock contention -b
    ^C
    contended   total wait     max wait     avg wait         type   caller

            42    192.67 us     13.64 us      4.59 us     spinlock   queue_work_on+0x20
            23     85.54 us     10.28 us      3.72 us     spinlock   worker_thread+0x14a
             6     13.92 us      6.51 us      2.32 us        mutex   kernfs_iop_permission+0x30
             3     11.59 us     10.04 us      3.86 us        mutex   kernfs_dop_revalidate+0x3c
             1      7.52 us      7.52 us      7.52 us     spinlock   kthread+0x115
             1      7.24 us      7.24 us      7.24 us     rwlock:W   sys_epoll_wait+0x148
             2      7.08 us      3.99 us      3.54 us     spinlock   delayed_work_timer_fn+0x1b
             1      6.41 us      6.41 us      6.41 us     spinlock   idle_balance+0xa06
             2      2.50 us      1.83 us      1.25 us        mutex   kernfs_iop_lookup+0x2f
             1      1.71 us      1.71 us      1.71 us        mutex   kernfs_iop_getattr+0x2c
    ...

 - Add new 'perf kwork' tool to trace time properties of kernel work
   (such as softirq, and workqueue), uses eBPF skeletons to collect info
   in kernel space, aggregating data that then gets processed by the
   userspace tool, e.g.:

    # perf kwork report

     Kwork Name      | Cpu | Total Runtime | Count | Max runtime | Max runtime start | Max runtime end |
    ----------------------------------------------------------------------------------------------------
     nvme0q5:130     | 004 |      1.101 ms |    49 |    0.051 ms |    26035.056403 s |  26035.056455 s |
     amdgpu:162      | 002 |      0.176 ms |     9 |    0.046 ms |    26035.268020 s |  26035.268066 s |
     nvme0q24:149    | 023 |      0.161 ms |    55 |    0.009 ms |    26035.655280 s |  26035.655288 s |
     nvme0q20:145    | 019 |      0.090 ms |    33 |    0.014 ms |    26035.939018 s |  26035.939032 s |
     nvme0q31:156    | 030 |      0.075 ms |    21 |    0.010 ms |    26035.052237 s |  26035.052247 s |
     nvme0q8:133     | 007 |      0.062 ms |    12 |    0.021 ms |    26035.416840 s |  26035.416861 s |
     nvme0q6:131     | 005 |      0.054 ms |    22 |    0.010 ms |    26035.199919 s |  26035.199929 s |
     nvme0q19:144    | 018 |      0.052 ms |    14 |    0.010 ms |    26035.110615 s |  26035.110625 s |
     nvme0q7:132     | 006 |      0.049 ms |    13 |    0.007 ms |    26035.125180 s |  26035.125187 s |
     nvme0q18:143    | 017 |      0.033 ms |    14 |    0.007 ms |    26035.169698 s |  26035.169705 s |
     nvme0q17:142    | 016 |      0.013 ms |     1 |    0.013 ms |    26035.565147 s |  26035.565160 s |
     enp5s0-rx-0:164 | 006 |      0.004 ms |     4 |    0.002 ms |    26035.928882 s |  26035.928884 s |
     enp5s0-tx-0:166 | 008 |      0.003 ms |     3 |    0.002 ms |    26035.870923 s |  26035.870925 s |
    --------------------------------------------------------------------------------------------------------

   See commit log messages for more examples with extra options to limit
   the events time window, etc.

 - Add support for new AMD IBS (Instruction Based Sampling) features:

   With the DataSrc extensions, the source of data can be decoded among:
     - Local L3 or other L1/L2 in CCX.
     - A peer cache in a near CCX.
     - Data returned from DRAM.
     - A peer cache in a far CCX.
     - DRAM address map with "long latency" bit set.
     - Data returned from MMIO/Config/PCI/APIC.
     - Extension Memory (S-Link, GenZ, etc - identified by the CS target
       and/or address map at DF's choice).
     - Peer Agent Memory.

 - Support hardware tracing with Intel PT on guest machines, combining
   the traces with the ones in the host machine.

 - Add a "-m" option to 'perf buildid-list' to show kernel and modules
   build-ids, to display all of the information needed to do external
   symbolization of kernel stack traces, such as those collected by
   bpf_get_stackid().

 - Add arch TSC frequency information to perf.data file headers.

 - Handle changes in the binutils disassembler function signatures in
   perf, bpftool and bpf_jit_disasm (Acked by the bpftool maintainer).

 - Fix building the perf perl binding with the newest gcc in distros
   such as fedora rawhide, where some new warnings were breaking the
   build as perf uses -Werror.

 - Add 'perf test' entry for branch stack sampling.

 - Add ARM SPE system wide 'perf test' entry.

 - Add user space counter reading tests to 'perf test'.

 - Build with python3 by default, if available.

 - Add python converter script for the vendor JSON event files.

 - Update vendor JSON files for most Intel cores.

 - Add vendor JSON File for Intel meteorlake.

 - Add Arm Cortex-A78C and X1C JSON vendor event files.

 - Add workaround to symbol address reading from ELF files without phdr,
   falling back to the previoous equation.

 - Convert legacy map definition to BTF-defined in the perf BPF script
   test.

 - Rework prologue generation code to stop using libbpf deprecated APIs.

 - Add default hybrid events for 'perf stat' on x86.

 - Add topdown metrics in the default 'perf stat' on the hybrid machines
   (big/little cores).

 - Prefer sampled CPU when exporting JSON in 'perf data convert'

 - Fix ('perf stat CSV output linter') and ("Check branch stack
   sampling") 'perf test' entries on s390.

* tag 'perf-tools-for-v6.0-2022-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (169 commits)
  perf stat: Refactor __run_perf_stat() common code
  perf lock: Print the number of lost entries for BPF
  perf lock: Add --map-nr-entries option
  perf lock: Introduce struct lock_contention
  perf scripting python: Do not build fail on deprecation warnings
  genelf: Use HAVE_LIBCRYPTO_SUPPORT, not the never defined HAVE_LIBCRYPTO
  perf build: Suppress openssl v3 deprecation warnings in libcrypto feature test
  perf parse-events: Break out tracepoint and printing
  perf parse-events: Don't #define YY_EXTRA_TYPE
  tools bpftool: Don't display disassembler-four-args feature test
  tools bpftool: Fix compilation error with new binutils
  tools bpf_jit_disasm: Don't display disassembler-four-args feature test
  tools bpf_jit_disasm: Fix compilation error with new binutils
  tools perf: Fix compilation error with new binutils
  tools include: add dis-asm-compat.h to handle version differences
  tools build: Don't display disassembler-four-args feature test
  tools build: Add feature test for init_disassemble_info API changes
  perf test: Add ARM SPE system wide test
  perf tools: Rework prologue generation code
  perf bpf: Convert legacy map definition to BTF-defined
  ...

1 files changed, 257 insertions, 0 deletions

diff --git a/tools/perf/util/kwork.h b/tools/perf/util/kwork.h
new file mode 100644
index 000000000000..320c0a6d2e08
--- /dev/null
+++ b/tools/perf/util/kwork.h
@@ -0,0 +1,257 @@
+#ifndef PERF_UTIL_KWORK_H
+#define PERF_UTIL_KWORK_H
+
+#include "perf.h"
+
+#include "util/tool.h"
+#include "util/event.h"
+#include "util/evlist.h"
+#include "util/session.h"
+#include "util/time-utils.h"
+
+#include <linux/list.h>
+#include <linux/bitmap.h>
+
+enum kwork_class_type {
+	KWORK_CLASS_IRQ,
+	KWORK_CLASS_SOFTIRQ,
+	KWORK_CLASS_WORKQUEUE,
+	KWORK_CLASS_MAX,
+};
+
+enum kwork_report_type {
+	KWORK_REPORT_RUNTIME,
+	KWORK_REPORT_LATENCY,
+	KWORK_REPORT_TIMEHIST,
+};
+
+enum kwork_trace_type {
+	KWORK_TRACE_RAISE,
+	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;
+
+	/*
+	 * latency report
+	 */
+	u64 max_latency;
+	u64 max_latency_start;
+	u64 max_latency_end;
+	u64 total_latency;
+};
+
+struct kwork_class {
+	struct list_head list;
+	const char *name;
+	enum kwork_class_type type;
+
+	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 (*raise_event)(struct perf_kwork *kwork,
+			   struct kwork_class *class, struct evsel *evsel,
+			   struct perf_sample *sample, struct machine *machine);
+
+	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;
+	bool show_callchain;
+	unsigned int max_stack;
+	bool use_bpf;
+
+	/*
+	 * 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];
+};
+
+struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork,
+				       struct kwork_class *class,
+				       struct kwork_work *key);
+
+#ifdef HAVE_BPF_SKEL
+
+int perf_kwork__trace_prepare_bpf(struct perf_kwork *kwork);
+int perf_kwork__report_read_bpf(struct perf_kwork *kwork);
+void perf_kwork__report_cleanup_bpf(void);
+
+void perf_kwork__trace_start(void);
+void perf_kwork__trace_finish(void);
+
+#else  /* !HAVE_BPF_SKEL */
+
+static inline int
+perf_kwork__trace_prepare_bpf(struct perf_kwork *kwork __maybe_unused)
+{
+	return -1;
+}
+
+static inline int
+perf_kwork__report_read_bpf(struct perf_kwork *kwork __maybe_unused)
+{
+	return -1;
+}
+
+static inline void perf_kwork__report_cleanup_bpf(void) {}
+
+static inline void perf_kwork__trace_start(void) {}
+static inline void perf_kwork__trace_finish(void) {}
+
+#endif  /* HAVE_BPF_SKEL */
+
+#endif  /* PERF_UTIL_KWORK_H */