Merge tag 'perf-tools-2020-08-10' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

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

   - Introduce controlling how 'perf stat' and 'perf record' works via a
     control file descriptor, allowing starting with events configured
     but disabled until commands are received via the control file
     descriptor. This allows, for instance for tools such as Intel VTune
     to make further use of perf as its Linux platform driver.

   - Improve 'perf record' to to register in a perf.data file header the
     clockid used to help later correlate things like syslog files and
     perf events recorded.

   - Add basic syscall and find_next_bit benchmarks to 'perf bench'.

   - Allow using computed metrics in calculating other metrics. For
     instance:

	  {
	    .metric_expr    = "l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit",
	    .metric_name    = "DCache_L2_All_Hits",
	  },
	  {
	    .metric_expr    = "max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss",
	    .metric_name    = "DCache_L2_All_Miss",
	  },
	  {
	     .metric_expr    = "dcache_l2_all_hits + dcache_l2_all_miss",
	     .metric_name    = "DCache_L2_All",
	  }

   - Add suport for 'd_ratio', '>' and '<' operators to the expression
     resolver used in calculating metrics in 'perf stat'.

  Support for new kernel features:

   - Support TEXT_POKE and KSYMBOL_TYPE_OOL perf metadata events to cope
     with things like ftrace, trampolines, i.e. changes in the kernel
     text that gets in the way of properly decoding Intel PT hardware
     traces, for instance.

  Intel PT:

   - Add various knobs to reduce the volume of Intel PT traces by
     reducing the level of details such as decoding just some types of
     packets (e.g., FUP/TIP, PSB+), also filtering by time range.

   - Add new itrace options (log flags to the 'd' option, error flags to
     the 'e' one, etc), controlling how Intel PT is transformed into
     perf events, document some missing options (e.g., how to synthesize
     callchains).

  BPF:

   - Properly report BPF errors when parsing events.

   - Do not setup side-band events if LIBBPF is not linked, fixing a
     segfault.

  Libraries:

   - Improvements to the libtraceevent plugin mechanism.

   - Improve libtracevent support for KVM trace events SVM exit reasons.

   - Add a libtracevent plugins for decoding syscalls/sys_enter_futex
     and for tlb_flush.

   - Ensure sample_period is set libpfm4 events in 'perf test'.

   - Fixup libperf namespacing, to make sure what is in libperf has the
     perf_ namespace while what is now only in tools/perf/ doesn't use
     that prefix.

  Arch specific:

   - Improve the testing of vendor events and metrics in 'perf test'.

   - Allow no ARM CoreSight hardware tracer sink to be specified on
     command line.

   - Fix arm_spe_x recording when mixed with other perf events.

   - Add s390 idle functions 'psw_idle' and 'psw_idle_exit' to list of
     idle symbols.

   - List kernel supplied event aliases for arm64 in 'perf list'.

   - Add support for extended register capability in PowerPC 9 and 10.

   - Added nest IMC power9 metric events.

  Miscellaneous:

   - No need to setup sample_regs_intr/sample_regs_user for dummy
     events.

   - Update various copies of kernel headers, some causing perf to
     handle new syscalls, MSRs, etc.

   - Improve usage of flex and yacc, enabling warnings and addressing
     the fallout.

   - Add missing '--output' option to 'perf kmem' so that it can pass it
     along to 'perf record'.

   - 'perf probe' fixes related to adding multiple probes on the same
     address for the same event.

   - Make 'perf probe' warn if the target function is a GNU indirect
     function.

   - Remove //anon mmap events from 'perf inject jit' to fix supporting
     both using ELF files for generated functions and the perf-PID.map
     approaches"

* tag 'perf-tools-2020-08-10' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (144 commits)
  perf record: Skip side-band event setup if HAVE_LIBBPF_SUPPORT is not set
  perf tools powerpc: Add support for extended regs in power10
  perf tools powerpc: Add support for extended register capability
  tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
  tools arch x86: Sync asm/cpufeatures.h with the kernel sources
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  tools headers UAPI: update linux/in.h copy
  tools headers API: Update close_range affected files
  perf script: Add 'tod' field to display time of day
  perf script: Change the 'enum perf_output_field' enumerators to be 64 bits
  perf data: Add support to store time of day in CTF data conversion
  perf tools: Move clockid_res_ns under clock struct
  perf header: Store clock references for -k/--clockid option
  perf tools: Add clockid_name function
  perf clockid: Move parse_clockid() to new clockid object
  tools lib traceevent: Handle possible strdup() error in tep_add_plugin_path() API
  libtraceevent: Fixed description of tep_add_plugin_path() API
  libtraceevent: Fixed type in PRINT_FMT_STING
  libtraceevent: Fixed broken indentation in parse_ip4_print_args()
  libtraceevent: Improve error handling of tep_plugin_add_option() API
  ...

1 files changed, 123 insertions, 0 deletions

diff --git a/tools/lib/traceevent/plugins/plugin_futex.c b/tools/lib/traceevent/plugins/plugin_futex.c
new file mode 100644
index 000000000000..eb7c9f8a850a
--- /dev/null
+++ b/tools/lib/traceevent/plugins/plugin_futex.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2017 National Instruments Corp.
+ *
+ * Author: Julia Cartwright <julia@ni.com>
+ *
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/futex.h>
+
+#include "event-parse.h"
+
+#define ARRAY_SIZE(_a) (sizeof(_a) / sizeof((_a)[0]))
+
+struct futex_args {
+	unsigned long long	uaddr;
+	unsigned long long	op;
+	unsigned long long	val;
+	unsigned long long	utime; /* or val2 */
+	unsigned long long	uaddr2;
+	unsigned long long	val3;
+};
+
+struct futex_op {
+	const char	*name;
+	const char	*fmt_val;
+	const char	*fmt_utime;
+	const char	*fmt_uaddr2;
+	const char	*fmt_val3;
+};
+
+static const struct futex_op futex_op_tbl[] = {
+	{            "FUTEX_WAIT", " val=0x%08llx", " utime=0x%08llx",               NULL,             NULL },
+	{            "FUTEX_WAKE",     " val=%llu",              NULL,               NULL,             NULL },
+	{              "FUTEX_FD",     " val=%llu",              NULL,               NULL,             NULL },
+	{         "FUTEX_REQUEUE",     " val=%llu",      " val2=%llu", " uaddr2=0x%08llx",             NULL },
+	{     "FUTEX_CMP_REQUEUE",     " val=%llu",      " val2=%llu", " uaddr2=0x%08llx", " val3=0x%08llx" },
+	{         "FUTEX_WAKE_OP",     " val=%llu",      " val2=%llu", " uaddr2=0x%08llx", " val3=0x%08llx" },
+	{         "FUTEX_LOCK_PI",            NULL, " utime=0x%08llx",               NULL,             NULL },
+	{       "FUTEX_UNLOCK_PI",            NULL,              NULL,               NULL,             NULL },
+	{      "FUTEX_TRYLOCK_PI",            NULL,              NULL,               NULL,             NULL },
+	{     "FUTEX_WAIT_BITSET", " val=0x%08llx", " utime=0x%08llx",               NULL, " val3=0x%08llx" },
+	{     "FUTEX_WAKE_BITSET",     " val=%llu",              NULL,               NULL, " val3=0x%08llx" },
+	{ "FUTEX_WAIT_REQUEUE_PI", " val=0x%08llx", " utime=0x%08llx", " uaddr2=0x%08llx", " val3=0x%08llx" },
+	{  "FUTEX_CMP_REQUEUE_PI",     " val=%llu",      " val2=%llu", " uaddr2=0x%08llx", " val3=0x%08llx" },
+};
+
+
+static void futex_print(struct trace_seq *s, const struct futex_args *args,
+			const struct futex_op *fop)
+{
+	trace_seq_printf(s, " uaddr=0x%08llx", args->uaddr);
+
+	if (fop->fmt_val)
+		trace_seq_printf(s, fop->fmt_val, args->val);
+
+	if (fop->fmt_utime)
+		trace_seq_printf(s,fop->fmt_utime, args->utime);
+
+	if (fop->fmt_uaddr2)
+		trace_seq_printf(s, fop->fmt_uaddr2, args->uaddr2);
+
+	if (fop->fmt_val3)
+		trace_seq_printf(s, fop->fmt_val3, args->val3);
+}
+
+static int futex_handler(struct trace_seq *s, struct tep_record *record,
+			 struct tep_event *event, void *context)
+{
+	const struct futex_op *fop;
+	struct futex_args args;
+	unsigned long long cmd;
+
+	if (tep_get_field_val(s, event, "uaddr", record, &args.uaddr, 1))
+		return 1;
+
+	if (tep_get_field_val(s, event, "op", record, &args.op, 1))
+		return 1;
+
+	if (tep_get_field_val(s, event, "val", record, &args.val, 1))
+		return 1;
+
+	if (tep_get_field_val(s, event, "utime", record, &args.utime, 1))
+		return 1;
+
+	if (tep_get_field_val(s, event, "uaddr2", record, &args.uaddr2, 1))
+		return 1;
+
+	if (tep_get_field_val(s, event, "val3", record, &args.val3, 1))
+		return 1;
+
+	cmd = args.op & FUTEX_CMD_MASK;
+	if (cmd >= ARRAY_SIZE(futex_op_tbl))
+		return 1;
+
+	fop = &futex_op_tbl[cmd];
+
+	trace_seq_printf(s, "op=%s", fop->name);
+
+	if (args.op & FUTEX_PRIVATE_FLAG)
+		trace_seq_puts(s, "|FUTEX_PRIVATE_FLAG");
+
+	if (args.op & FUTEX_CLOCK_REALTIME)
+		trace_seq_puts(s, "|FUTEX_CLOCK_REALTIME");
+
+	futex_print(s, &args, fop);
+	return 0;
+}
+
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
+{
+	tep_register_event_handler(tep, -1, "syscalls", "sys_enter_futex",
+				   futex_handler, NULL);
+	return 0;
+}
+
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
+{
+	tep_unregister_event_handler(tep, -1, "syscalls", "sys_enter_futex",
+				     futex_handler, NULL);
+}