Merge tag 'perf-tools-for-v5.13-2021-04-29' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "perf stat:

   - Add support for hybrid PMUs to support systems such as Intel
     Alderlake and its BIG/little core/atom cpus.

   - Introduce 'bperf' to share hardware PMCs with BPF.

   - New --iostat option to collect and present IO stats on Intel
     hardware.

     This functionality is based on recently introduced sysfs attributes
     for Intel® Xeon® Scalable processor family (code name Skylake-SP)
     in commit bb42b3d39781 ("perf/x86/intel/uncore: Expose an Uncore
     unit to IIO PMON mapping")

     It is intended to provide four I/O performance metrics in MB per
     each PCIe root port:

       - Inbound Read: I/O devices below root port read from the host memory
       - Inbound Write: I/O devices below root port write to the host memory
       - Outbound Read: CPU reads from I/O devices below root port
       - Outbound Write: CPU writes to I/O devices below root port

   - Align CSV output for summary.

   - Clarify --null use cases: Assess raw overhead of 'perf stat' or
     measure just wall clock time.

   - Improve readability of shadow stats.

  perf record:

   - Change the COMM when starting tha workload so that --exclude-perf
     doesn't seem to be not honoured.

   - Improve 'Workload failed' message printing events + what was
     exec'ed.

   - Fix cross-arch support for TIME_CONV.

  perf report:

   - Add option to disable raw event ordering.

   - Dump the contents of PERF_RECORD_TIME_CONV in 'perf report -D'.

   - Improvements to --stat output, that shows information about
     PERF_RECORD_ events.

   - Preserve identifier id in OCaml demangler.

  perf annotate:

   - Show full source location with 'l' hotkey in the 'perf annotate'
     TUI.

   - Add line number like in TUI and source location at EOL to the 'perf
     annotate' --stdio mode.

   - Add --demangle and --demangle-kernel to 'perf annotate'.

   - Allow configuring annotate.demangle{,_kernel} in 'perf config'.

   - Fix sample events lost in stdio mode.

  perf data:

   - Allow converting a perf.data file to JSON.

  libperf:

   - Add support for user space counter access.

   - Update topdown documentation to permit rdpmc calls.

  perf test:

   - Add 'perf test' for 'perf stat' CSV output.

   - Add 'perf test' entries to test the hybrid PMU support.

   - Cleanup 'perf test daemon' if its 'perf test' is interrupted.

   - Handle metric reuse in pmu-events parsing 'perf test' entry.

   - Add test for PE executable support.

   - Add timeout for wait for daemon start in its 'perf test' entries.

  Build:

   - Enable libtraceevent dynamic linking.

   - Improve feature detection output.

   - Fix caching of feature checks caching.

   - First round of updates for tools copies of kernel headers.

   - Enable warnings when compiling BPF programs.

  Vendor specific events:

   - Intel:
      - Add missing skylake & icelake model numbers.

   - arm64:
      - Add Hisi hip08 L1, L2 and L3 metrics.
      - Add Fujitsu A64FX PMU events.

   - PowerPC:
      - Initial JSON/events list for power10 platform.
      - Remove unsupported power9 metrics.

   - AMD:
      - Add Zen3 events.
      - Fix broken L2 Cache Hits from L2 HWPF metric.
      - Use lowercases for all the eventcodes and umasks.

  Hardware tracing:

   - arm64:
      - Update CoreSight ETM metadata format.
      - Fix bitmap for CS-ETM option.
      - Support PID tracing in config.
      - Detect pid in VMID for kernel running at EL2.

  Arch specific updates:

   - MIPS:
      - Support MIPS unwinding and dwarf-regs.
      - Generate mips syscalls_n64.c syscall table.

   - PowerPC:
      - Add support for PERF_SAMPLE_WEIGH_STRUCT on PowerPC.
      - Support pipeline stage cycles for powerpc.

  libbeauty:

   - Fix fsconfig generator"

* tag 'perf-tools-for-v5.13-2021-04-29' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (132 commits)
  perf build: Defer printing detected features to the end of all feature checks
  tools build: Allow deferring printing the results of feature detection
  perf build: Regenerate the FEATURE_DUMP file after extra feature checks
  perf session: Dump PERF_RECORD_TIME_CONV event
  perf session: Add swap operation for event TIME_CONV
  perf jit: Let convert_timestamp() to be backwards-compatible
  perf tools: Change fields type in perf_record_time_conv
  perf tools: Enable libtraceevent dynamic linking
  perf Documentation: Document intel-hybrid support
  perf tests: Skip 'perf stat metrics (shadow stat) test' for hybrid
  perf tests: Support 'Convert perf time to TSC' test for hybrid
  perf tests: Support 'Session topology' test for hybrid
  perf tests: Support 'Parse and process metrics' test for hybrid
  perf tests: Support 'Track with sched_switch' test for hybrid
  perf tests: Skip 'Setup struct perf_event_attr' test for hybrid
  perf tests: Add hybrid cases for 'Roundtrip evsel->name' test
  perf tests: Add hybrid cases for 'Parse event definition strings' test
  perf record: Uniquify hybrid event name
  perf stat: Warn group events from different hybrid PMU
  perf stat: Filter out unmatched aggregation for hybrid event
  ...

1 files changed, 88 insertions, 0 deletions

diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index 79d5ed6c38cc..c89dfa5f67b3 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -8,9 +8,11 @@
 #include <linux/perf_event.h>
 #include <perf/mmap.h>
 #include <perf/event.h>
+#include <perf/evsel.h>
 #include <internal/mmap.h>
 #include <internal/lib.h>
 #include <linux/kernel.h>
+#include <linux/math64.h>
 #include "internal.h"
 
 void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
@@ -273,3 +275,89 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map)
 
 	return event;
 }
+
+#if defined(__i386__) || defined(__x86_64__)
+static u64 read_perf_counter(unsigned int counter)
+{
+	unsigned int low, high;
+
+	asm volatile("rdpmc" : "=a" (low), "=d" (high) : "c" (counter));
+
+	return low | ((u64)high) << 32;
+}
+
+static u64 read_timestamp(void)
+{
+	unsigned int low, high;
+
+	asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+	return low | ((u64)high) << 32;
+}
+#else
+static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; }
+static u64 read_timestamp(void) { return 0; }
+#endif
+
+int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count)
+{
+	struct perf_event_mmap_page *pc = map->base;
+	u32 seq, idx, time_mult = 0, time_shift = 0;
+	u64 cnt, cyc = 0, time_offset = 0, time_cycles = 0, time_mask = ~0ULL;
+
+	if (!pc || !pc->cap_user_rdpmc)
+		return -1;
+
+	do {
+		seq = READ_ONCE(pc->lock);
+		barrier();
+
+		count->ena = READ_ONCE(pc->time_enabled);
+		count->run = READ_ONCE(pc->time_running);
+
+		if (pc->cap_user_time && count->ena != count->run) {
+			cyc = read_timestamp();
+			time_mult = READ_ONCE(pc->time_mult);
+			time_shift = READ_ONCE(pc->time_shift);
+			time_offset = READ_ONCE(pc->time_offset);
+
+			if (pc->cap_user_time_short) {
+				time_cycles = READ_ONCE(pc->time_cycles);
+				time_mask = READ_ONCE(pc->time_mask);
+			}
+		}
+
+		idx = READ_ONCE(pc->index);
+		cnt = READ_ONCE(pc->offset);
+		if (pc->cap_user_rdpmc && idx) {
+			s64 evcnt = read_perf_counter(idx - 1);
+			u16 width = READ_ONCE(pc->pmc_width);
+
+			evcnt <<= 64 - width;
+			evcnt >>= 64 - width;
+			cnt += evcnt;
+		} else
+			return -1;
+
+		barrier();
+	} while (READ_ONCE(pc->lock) != seq);
+
+	if (count->ena != count->run) {
+		u64 delta;
+
+		/* Adjust for cap_usr_time_short, a nop if not */
+		cyc = time_cycles + ((cyc - time_cycles) & time_mask);
+
+		delta = time_offset + mul_u64_u32_shr(cyc, time_mult, time_shift);
+
+		count->ena += delta;
+		if (idx)
+			count->run += delta;
+
+		cnt = mul_u64_u64_div64(cnt, count->ena, count->run);
+	}
+
+	count->val = cnt;
+
+	return 0;
+}