Merge tag 'perf-tools-for-v5.10-2020-10-15' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - cgroup improvements for 'perf stat', allowing for compact
   specification of events and cgroups in the command line.

 - Support per thread topdown metrics in 'perf stat'.

 - Support sample-read topdown metric group in 'perf record'

 - Show start of latency in addition to its start in 'perf sched
   latency'.

 - Add min, max to 'perf script' futex-contention output, in addition to
   avg.

 - Allow usage of 'perf_event_attr->exclusive' attribute via the new
   ':e' event modifier.

 - Add 'snapshot' command to 'perf record --control', using it with
   Intel PT.

 - Support FIFO file names as alternative options to 'perf record
   --control'.

 - Introduce branch history "streams", to compare 'perf record' runs
   with 'perf diff' based on branch records and report hot streams.

 - Support PE executable symbol tables using libbfd, to profile, for
   instance, wine binaries.

 - Add filter support for option 'perf ftrace -F/--funcs'.

 - Allow configuring the 'disassembler_style' 'perf annotate' knob via
   'perf config'

 - Update CascadelakeX and SkylakeX JSON vendor events files.

 - Add support for parsing perchip/percore JSON vendor events.

 - Add power9 hv_24x7 core level metric events.

 - Add L2 prefetch, ITLB instruction fetch hits JSON events for AMD
   zen1.

 - Enable Family 19h users by matching Zen2 AMD vendor events.

 - Use debuginfod in 'perf probe' when required debug files not found
   locally.

 - Display negative tid in non-sample events in 'perf script'.

 - Make GTK2 support opt-in

 - Add build test with GTK+

 - Add missing -lzstd to the fast path feature detection

 - Add scripts to auto generate 'mmap', 'mremap' string<->id tables for
   use in 'perf trace'.

 - Show python test script in verbose mode.

 - Fix uncore metric expressions

 - Msan uninitialized use fixes.

 - Use condition variables in 'perf bench numa'

 - Autodetect python3 binary in systems without python2.

 - Support md5 build ids in addition to sha1.

 - Add build id 'perf test' regression test.

 - Fix printable strings in python3 scripts.

 - Fix off by ones in 'perf trace' in arches using libaudit.

 - Fix JSON event code for events referencing std arch events.

 - Introduce 'perf test' shell script for Arm CoreSight testing.

 - Add rdtsc() for Arm64 for used in the PERF_RECORD_TIME_CONV metadata
   event and in 'perf test tsc'.

 - 'perf c2c' improvements: Add "RMT Load Hit" metric, "Total Stores",
   fixes and documentation update.

 - Fix usage of reloc_sym in 'perf probe' when using both kallsyms and
   debuginfo files.

 - Do not print 'Metric Groups:' unnecessarily in 'perf list'

 - Refcounting fixes in the event parsing code.

 - Add expand cgroup event 'perf test' entry.

 - Fix out of bounds CPU map access when handling armv8_pmu events in
   'perf stat'.

 - Add build-id injection 'perf bench' benchmark.

 - Enter namespace when reading build-id in 'perf inject'.

 - Do not load map/dso when injecting build-id speeding up the 'perf
   inject' process.

 - Add --buildid-all option to avoid processing all samples, just the
   mmap metadata events.

 - Add feature test to check if libbfd has buildid support

 - Add 'perf test' entry for PE binary format support.

 - Fix typos in power8 PMU vendor events JSON files.

 - Hide libtraceevent non API functions.

* tag 'perf-tools-for-v5.10-2020-10-15' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (113 commits)
  perf c2c: Update documentation for metrics reorganization
  perf c2c: Add metrics "RMT Load Hit"
  perf c2c: Correct LLC load hit metrics
  perf c2c: Change header for LLC local hit
  perf c2c: Use more explicit headers for HITM
  perf c2c: Change header from "LLC Load Hitm" to "Load Hitm"
  perf c2c: Organize metrics based on memory hierarchy
  perf c2c: Display "Total Stores" as a standalone metrics
  perf c2c: Display the total numbers continuously
  perf bench: Use condition variables in numa.
  perf jevents: Fix event code for events referencing std arch events
  perf diff: Support hot streams comparison
  perf streams: Report hot streams
  perf streams: Calculate the sum of total streams hits
  perf streams: Link stream pair
  perf streams: Compare two streams
  perf streams: Get the evsel_streams by evsel_idx
  perf streams: Introduce branch history "streams"
  perf intel-pt: Improve PT documentation slightly
  perf tools: Add support for exclusive groups/events
  ...

1 files changed, 81 insertions, 0 deletions

diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
index bfa782421cbd..62b4c75c966c 100644
--- a/tools/perf/util/tsc.c
+++ b/tools/perf/util/tsc.c
@@ -1,7 +1,16 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+
 #include <linux/compiler.h>
+#include <linux/perf_event.h>
+#include <linux/stddef.h>
 #include <linux/types.h>
 
+#include <asm/barrier.h>
+
+#include "event.h"
+#include "synthetic-events.h"
+#include "debug.h"
 #include "tsc.h"
 
 u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc)
@@ -19,12 +28,84 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
 {
 	u64 quot, rem;
 
+	if (tc->cap_user_time_short)
+		cyc = tc->time_cycles +
+			((cyc - tc->time_cycles) & tc->time_mask);
+
 	quot = cyc >> tc->time_shift;
 	rem  = cyc & (((u64)1 << tc->time_shift) - 1);
 	return tc->time_zero + quot * tc->time_mult +
 	       ((rem * tc->time_mult) >> tc->time_shift);
 }
 
+int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
+			     struct perf_tsc_conversion *tc)
+{
+	u32 seq;
+	int i = 0;
+
+	while (1) {
+		seq = pc->lock;
+		rmb();
+		tc->time_mult = pc->time_mult;
+		tc->time_shift = pc->time_shift;
+		tc->time_zero = pc->time_zero;
+		tc->time_cycles = pc->time_cycles;
+		tc->time_mask = pc->time_mask;
+		tc->cap_user_time_zero = pc->cap_user_time_zero;
+		tc->cap_user_time_short	= pc->cap_user_time_short;
+		rmb();
+		if (pc->lock == seq && !(seq & 1))
+			break;
+		if (++i > 10000) {
+			pr_debug("failed to get perf_event_mmap_page lock\n");
+			return -EINVAL;
+		}
+	}
+
+	if (!tc->cap_user_time_zero)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc,
+				struct perf_tool *tool,
+				perf_event__handler_t process,
+				struct machine *machine)
+{
+	union perf_event event = {
+		.time_conv = {
+			.header = {
+				.type = PERF_RECORD_TIME_CONV,
+				.size = sizeof(struct perf_record_time_conv),
+			},
+		},
+	};
+	struct perf_tsc_conversion tc;
+	int err;
+
+	if (!pc)
+		return 0;
+	err = perf_read_tsc_conversion(pc, &tc);
+	if (err == -EOPNOTSUPP)
+		return 0;
+	if (err)
+		return err;
+
+	pr_debug2("Synthesizing TSC conversion information\n");
+
+	event.time_conv.time_mult  = tc.time_mult;
+	event.time_conv.time_shift = tc.time_shift;
+	event.time_conv.time_zero  = tc.time_zero;
+	event.time_conv.time_cycles = tc.time_cycles;
+	event.time_conv.time_mask = tc.time_mask;
+	event.time_conv.cap_user_time_zero = tc.cap_user_time_zero;
+	event.time_conv.cap_user_time_short = tc.cap_user_time_short;
+
+	return process(tool, &event, NULL, machine);
+}
+
 u64 __weak rdtsc(void)
 {
 	return 0;