Merge tag 'perf-tools-for-v5.13-2021-04-29' of git://git.kernel.org/p…

…ub/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 bb42b3d ("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
  ...

MAINTAINERS

@@ -14290,8 +14290,10 @@ R:	Mark Rutland <[email protected]>
 R:	Alexander Shishkin <[email protected]>
 R:	Jiri Olsa <[email protected]>
 R:	Namhyung Kim <[email protected]>
+L:	[email protected]
 L:	[email protected]
 S:	Supported
+W:	https://perf.wiki.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
 F:	arch/*/events/*
 F:	arch/*/events/*/*

tools/build/Makefile.feature

@@ -52,6 +52,7 @@ FEATURE_TESTS_BASIC :=                  \
         libpython-version               \
         libslang                        \
         libslang-include-subdir         \
+        libtraceevent                   \
         libcrypto                       \
         libunwind                       \
         pthread-attr-setaffinity-np     \
@@ -239,17 +240,24 @@ ifeq ($(VF),1)
   feature_verbose := 1
 endif
 
-ifeq ($(feature_display),1)
-  $(info )
-  $(info Auto-detecting system features:)
-  $(foreach feat,$(FEATURE_DISPLAY),$(call feature_print_status,$(feat),))
-  ifneq ($(feature_verbose),1)
+feature_display_entries = $(eval $(feature_display_entries_code))
+define feature_display_entries_code
+  ifeq ($(feature_display),1)
     $(info )
+    $(info Auto-detecting system features:)
+    $(foreach feat,$(FEATURE_DISPLAY),$(call feature_print_status,$(feat),))
+    ifneq ($(feature_verbose),1)
+      $(info )
+    endif
   endif
-endif
 
-ifeq ($(feature_verbose),1)
-  TMP := $(filter-out $(FEATURE_DISPLAY),$(FEATURE_TESTS))
-  $(foreach feat,$(TMP),$(call feature_print_status,$(feat),))
-  $(info )
+  ifeq ($(feature_verbose),1)
+    TMP := $(filter-out $(FEATURE_DISPLAY),$(FEATURE_TESTS))
+    $(foreach feat,$(TMP),$(call feature_print_status,$(feat),))
+    $(info )
+  endif
+endef
+
+ifeq ($(FEATURE_DISPLAY_DEFERRED),)
+  $(call feature_display_entries)
 endif

tools/build/feature/Makefile

@@ -36,6 +36,7 @@ FILES=                                          \
          test-libpython-version.bin             \
          test-libslang.bin                      \
          test-libslang-include-subdir.bin       \
+         test-libtraceevent.bin                 \
          test-libcrypto.bin                     \
          test-libunwind.bin                     \
          test-libunwind-debug-frame.bin         \
@@ -196,6 +197,9 @@ $(OUTPUT)test-libslang.bin:
 $(OUTPUT)test-libslang-include-subdir.bin:
 	$(BUILD) -lslang
 
+$(OUTPUT)test-libtraceevent.bin:
+	$(BUILD) -ltraceevent
+
 $(OUTPUT)test-libcrypto.bin:
 	$(BUILD) -lcrypto
 

tools/build/feature/test-libtraceevent.c

@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <traceevent/trace-seq.h>
+
+int main(void)
+{
+	int rv = 0;
+	struct trace_seq s;
+	trace_seq_init(&s);
+	rv += !(s.state == TRACE_SEQ__GOOD);
+	trace_seq_destroy(&s);
+	return rv;
+}

tools/include/linux/math64.h

@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_MATH64_H
+#define _LINUX_MATH64_H
+
+#include <linux/types.h>
+
+#ifdef __x86_64__
+static inline u64 mul_u64_u64_div64(u64 a, u64 b, u64 c)
+{
+	u64 q;
+
+	asm ("mulq %2; divq %3" : "=a" (q)
+				: "a" (a), "rm" (b), "rm" (c)
+				: "rdx");
+
+	return q;
+}
+#define mul_u64_u64_div64 mul_u64_u64_div64
+#endif
+
+#ifdef __SIZEOF_INT128__
+static inline u64 mul_u64_u32_shr(u64 a, u32 b, unsigned int shift)
+{
+	return (u64)(((unsigned __int128)a * b) >> shift);
+}
+
+#else
+
+#ifdef __i386__
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+	u32 high, low;
+
+	asm ("mull %[b]" : "=a" (low), "=d" (high)
+			 : [a] "a" (a), [b] "rm" (b) );
+
+	return low | ((u64)high) << 32;
+}
+#else
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+	return (u64)a * b;
+}
+#endif
+
+static inline u64 mul_u64_u32_shr(u64 a, u32 b, unsigned int shift)
+{
+	u32 ah, al;
+	u64 ret;
+
+	al = a;
+	ah = a >> 32;
+
+	ret = mul_u32_u32(al, b) >> shift;
+	if (ah)
+		ret += mul_u32_u32(ah, b) << (32 - shift);
+
+	return ret;
+}
+
+#endif	/* __SIZEOF_INT128__ */
+
+#ifndef mul_u64_u64_div64
+static inline u64 mul_u64_u64_div64(u64 a, u64 b, u64 c)
+{
+	u64 quot, rem;
+
+	quot = a / c;
+	rem = a % c;
+
+	return quot * b + (rem * b) / c;
+}
+#endif
+
+#endif /* _LINUX_MATH64_H */

tools/include/linux/types.h

@@ -61,6 +61,9 @@ typedef __u32 __bitwise __be32;
 typedef __u64 __bitwise __le64;
 typedef __u64 __bitwise __be64;
 
+typedef __u16 __bitwise __sum16;
+typedef __u32 __bitwise __wsum;
+
 typedef struct {
 	int counter;
 } atomic_t;

tools/include/uapi/linux/perf_event.h

@@ -37,6 +37,21 @@ enum perf_type_id {
 	PERF_TYPE_MAX,				/* non-ABI */
 };
 
+/*
+ * attr.config layout for type PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE
+ * PERF_TYPE_HARDWARE:			0xEEEEEEEE000000AA
+ *					AA: hardware event ID
+ *					EEEEEEEE: PMU type ID
+ * PERF_TYPE_HW_CACHE:			0xEEEEEEEE00DDCCBB
+ *					BB: hardware cache ID
+ *					CC: hardware cache op ID
+ *					DD: hardware cache op result ID
+ *					EEEEEEEE: PMU type ID
+ * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied.
+ */
+#define PERF_PMU_TYPE_SHIFT		32
+#define PERF_HW_EVENT_MASK		0xffffffff
+
 /*
  * Generalized performance event event_id types, used by the
  * attr.event_id parameter of the sys_perf_event_open()

tools/lib/perf/Documentation/libperf.txt

@@ -136,6 +136,9 @@ SYNOPSIS
                        struct perf_thread_map *threads);
   void perf_evsel__close(struct perf_evsel *evsel);
   void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
+  int perf_evsel__mmap(struct perf_evsel *evsel, int pages);
+  void perf_evsel__munmap(struct perf_evsel *evsel);
+  void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread);
   int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
                        struct perf_counts_values *count);
   int perf_evsel__enable(struct perf_evsel *evsel);

tools/lib/perf/evsel.c

@@ -11,10 +11,12 @@
 #include <stdlib.h>
 #include <internal/xyarray.h>
 #include <internal/cpumap.h>
+#include <internal/mmap.h>
 #include <internal/threadmap.h>
 #include <internal/lib.h>
 #include <linux/string.h>
 #include <sys/ioctl.h>
+#include <sys/mman.h>
 
 void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr)
 {
@@ -38,6 +40,7 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 }
 
 #define FD(e, x, y) (*(int *) xyarray__entry(e->fd, x, y))
+#define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL)
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
@@ -55,6 +58,13 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 	return evsel->fd != NULL ? 0 : -ENOMEM;
 }
 
+static int perf_evsel__alloc_mmap(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	evsel->mmap = xyarray__new(ncpus, nthreads, sizeof(struct perf_mmap));
+
+	return evsel->mmap != NULL ? 0 : -ENOMEM;
+}
+
 static int
 sys_perf_event_open(struct perf_event_attr *attr,
 		    pid_t pid, int cpu, int group_fd,
@@ -156,6 +166,72 @@ void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu)
 	perf_evsel__close_fd_cpu(evsel, cpu);
 }
 
+void perf_evsel__munmap(struct perf_evsel *evsel)
+{
+	int cpu, thread;
+
+	if (evsel->fd == NULL || evsel->mmap == NULL)
+		return;
+
+	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
+			int fd = FD(evsel, cpu, thread);
+			struct perf_mmap *map = MMAP(evsel, cpu, thread);
+
+			if (fd < 0)
+				continue;
+
+			perf_mmap__munmap(map);
+		}
+	}
+
+	xyarray__delete(evsel->mmap);
+	evsel->mmap = NULL;
+}
+
+int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
+{
+	int ret, cpu, thread;
+	struct perf_mmap_param mp = {
+		.prot = PROT_READ | PROT_WRITE,
+		.mask = (pages * page_size) - 1,
+	};
+
+	if (evsel->fd == NULL || evsel->mmap)
+		return -EINVAL;
+
+	if (perf_evsel__alloc_mmap(evsel, xyarray__max_x(evsel->fd), xyarray__max_y(evsel->fd)) < 0)
+		return -ENOMEM;
+
+	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
+			int fd = FD(evsel, cpu, thread);
+			struct perf_mmap *map = MMAP(evsel, cpu, thread);
+
+			if (fd < 0)
+				continue;
+
+			perf_mmap__init(map, NULL, false, NULL);
+
+			ret = perf_mmap__mmap(map, &mp, fd, cpu);
+			if (ret) {
+				perf_evsel__munmap(evsel);
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread)
+{
+	if (FD(evsel, cpu, thread) < 0 || MMAP(evsel, cpu, thread) == NULL)
+		return NULL;
+
+	return MMAP(evsel, cpu, thread)->base;
+}
+
 int perf_evsel__read_size(struct perf_evsel *evsel)
 {
 	u64 read_format = evsel->attr.read_format;
@@ -191,6 +267,10 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 	if (FD(evsel, cpu, thread) < 0)
 		return -EINVAL;
 
+	if (MMAP(evsel, cpu, thread) &&
+	    !perf_mmap__read_self(MMAP(evsel, cpu, thread), count))
+		return 0;
+
 	if (readn(FD(evsel, cpu, thread), count->values, size) <= 0)
 		return -errno;
 

tools/lib/perf/include/internal/evsel.h

@@ -41,6 +41,7 @@ struct perf_evsel {
 	struct perf_cpu_map	*own_cpus;
 	struct perf_thread_map	*threads;
 	struct xyarray		*fd;
+	struct xyarray		*mmap;
 	struct xyarray		*sample_id;
 	u64			*id;
 	u32			 ids;

tools/lib/perf/include/internal/mmap.h

@@ -11,6 +11,7 @@
 #define PERF_SAMPLE_MAX_SIZE (1 << 16)
 
 struct perf_mmap;
+struct perf_counts_values;
 
 typedef void (*libperf_unmap_cb_t)(struct perf_mmap *map);
 
@@ -52,4 +53,6 @@ void perf_mmap__put(struct perf_mmap *map);
 
 u64 perf_mmap__read_head(struct perf_mmap *map);
 
+int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count);
+
 #endif /* __LIBPERF_INTERNAL_MMAP_H */

tools/lib/perf/include/internal/tests.h

@@ -3,11 +3,32 @@
 #define __LIBPERF_INTERNAL_TESTS_H
 
 #include <stdio.h>
+#include <unistd.h>
 
 int tests_failed;
+int tests_verbose;
+
+static inline int get_verbose(char **argv, int argc)
+{
+	int c;
+	int verbose = 0;
+
+	while ((c = getopt(argc, argv, "v")) != -1) {
+		switch (c)
+		{
+		case 'v':
+			verbose = 1;
+			break;
+		default:
+			break;
+		}
+	}
+	return verbose;
+}
 
 #define __T_START					\
 do {							\
+	tests_verbose = get_verbose(argv, argc);	\
 	fprintf(stdout, "- running %s...", __FILE__);	\
 	fflush(NULL);					\
 	tests_failed = 0;				\
@@ -30,4 +51,15 @@ do {
 	}                                                                        \
 } while (0)
 
+#define __T_VERBOSE(...)						\
+do {									\
+	if (tests_verbose) {						\
+		if (tests_verbose == 1) {				\
+			fputc('\n', stderr);				\
+			tests_verbose++;				\
+		}							\
+		fprintf(stderr, ##__VA_ARGS__);				\
+	}								\
+} while (0)
+
 #endif /* __LIBPERF_INTERNAL_TESTS_H */