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
  ...

8 files changed, 93 insertions, 103 deletions

diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index 5c13438c7bd4..b53294d74b01 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -1,6 +1,7 @@
 perf-y += header.o
 perf-y += machine.o
 perf-y += perf_regs.o
+perf-y += tsc.o
 perf-$(CONFIG_DWARF)     += dwarf-regs.o
 perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/arm64/util/tsc.c b/tools/perf/arch/arm64/util/tsc.c
new file mode 100644
index 000000000000..cc85bd9e73f1
--- /dev/null
+++ b/tools/perf/arch/arm64/util/tsc.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/types.h>
+
+#include "../../../util/tsc.h"
+
+u64 rdtsc(void)
+{
+	u64 val;
+
+	/*
+	 * According to ARM DDI 0487F.c, from Armv8.0 to Armv8.5 inclusive, the
+	 * system counter is at least 56 bits wide; from Armv8.6, the counter
+	 * must be 64 bits wide.  So the system counter could be less than 64
+	 * bits wide and it is attributed with the flag 'cap_user_time_short'
+	 * is true.
+	 */
+	asm volatile("mrs %0, cntvct_el0" : "=r" (val));
+
+	return val;
+}
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 1a950171a66f..58b2d610aadb 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -40,8 +40,11 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 	return bufp;
 }
 
-int arch_get_runtimeparam(void)
+int arch_get_runtimeparam(struct pmu_event *pe)
 {
 	int count;
-	return sysfs__read_int("/devices/hv_24x7/interface/sockets", &count) < 0 ? 1 : count;
+	char path[PATH_MAX] = "/devices/hv_24x7/interface/";
+
+	atoi(pe->aggr_mode) == PerChip ? strcat(path, "sockets") : strcat(path, "coresperchip");
+	return sysfs__read_int(path, &count) < 0 ? 1 : count;
 }
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 7eb5621c021d..24ea12ec7e02 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -110,6 +110,7 @@ static struct ins x86__instructions[] = {
 	{ .name = "por",	.ops = &mov_ops,  },
 	{ .name = "rclb",	.ops = &mov_ops,  },
 	{ .name = "rcll",	.ops = &mov_ops,  },
+	{ .name = "ret",	.ops = &ret_ops,  },
 	{ .name = "retq",	.ops = &ret_ops,  },
 	{ .name = "sbb",	.ops = &mov_ops,  },
 	{ .name = "sbbl",	.ops = &mov_ops,  },
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 47f9c56e744f..347c39b960eb 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -3,7 +3,7 @@ perf-y += tsc.o
 perf-y += pmu.o
 perf-y += kvm-stat.o
 perf-y += perf_regs.o
-perf-y += group.o
+perf-y += topdown.o
 perf-y += machine.o
 perf-y += event.o
 
diff --git a/tools/perf/arch/x86/util/group.c b/tools/perf/arch/x86/util/group.c
deleted file mode 100644
index e2f8034b8973..000000000000
--- a/tools/perf/arch/x86/util/group.c
+++ /dev/null
@@ -1,28 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <stdio.h>
-#include "api/fs/fs.h"
-#include "util/group.h"
-
-/*
- * Check whether we can use a group for top down.
- * Without a group may get bad results due to multiplexing.
- */
-bool arch_topdown_check_group(bool *warn)
-{
-	int n;
-
-	if (sysctl__read_int("kernel/nmi_watchdog", &n) < 0)
-		return false;
-	if (n > 0) {
-		*warn = true;
-		return false;
-	}
-	return true;
-}
-
-void arch_topdown_group_warn(void)
-{
-	fprintf(stderr,
-		"nmi_watchdog enabled with topdown. May give wrong results.\n"
-		"Disable with echo 0 > /proc/sys/kernel/nmi_watchdog\n");
-}
diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c
new file mode 100644
index 000000000000..2f3d96aa92a5
--- /dev/null
+++ b/tools/perf/arch/x86/util/topdown.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include "api/fs/fs.h"
+#include "util/pmu.h"
+#include "util/topdown.h"
+
+/*
+ * Check whether we can use a group for top down.
+ * Without a group may get bad results due to multiplexing.
+ */
+bool arch_topdown_check_group(bool *warn)
+{
+	int n;
+
+	if (sysctl__read_int("kernel/nmi_watchdog", &n) < 0)
+		return false;
+	if (n > 0) {
+		*warn = true;
+		return false;
+	}
+	return true;
+}
+
+void arch_topdown_group_warn(void)
+{
+	fprintf(stderr,
+		"nmi_watchdog enabled with topdown. May give wrong results.\n"
+		"Disable with echo 0 > /proc/sys/kernel/nmi_watchdog\n");
+}
+
+#define TOPDOWN_SLOTS		0x0400
+
+static bool is_topdown_slots_event(struct evsel *counter)
+{
+	if (!counter->pmu_name)
+		return false;
+
+	if (strcmp(counter->pmu_name, "cpu"))
+		return false;
+
+	if (counter->core.attr.config == TOPDOWN_SLOTS)
+		return true;
+
+	return false;
+}
+
+/*
+ * Check whether a topdown group supports sample-read.
+ *
+ * Only Topdown metic supports sample-read. The slots
+ * event must be the leader of the topdown group.
+ */
+
+bool arch_topdown_sample_read(struct evsel *leader)
+{
+	if (!pmu_have_event("cpu", "slots"))
+		return false;
+
+	if (is_topdown_slots_event(leader))
+		return true;
+
+	return false;
+}
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 2f55afb14e1f..559365f8fe52 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -1,45 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <stdbool.h>
-#include <errno.h>
-
-#include <linux/stddef.h>
-#include <linux/perf_event.h>
-
 #include <linux/types.h>
-#include <asm/barrier.h>
-#include "../../../util/debug.h"
-#include "../../../util/event.h"
-#include "../../../util/synthetic-events.h"
-#include "../../../util/tsc.h"
-
-int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
-			     struct perf_tsc_conversion *tc)
-{
-	bool cap_user_time_zero;
-	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;
-		cap_user_time_zero = pc->cap_user_time_zero;
-		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 (!cap_user_time_zero)
-		return -EOPNOTSUPP;
-
-	return 0;
-}
+#include "../../../util/tsc.h"
 
 u64 rdtsc(void)
 {
@@ -49,36 +11,3 @@ u64 rdtsc(void)
 
 	return low | ((u64)high) << 32;
 }
-
-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;
-
-	return process(tool, &event, NULL, machine);
-}