Merge tag 'perf-tools-for-v6.9-2024-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Namhyung Kim:
 "perf stat:

   - Support new 'cluster' aggregation mode for shared resources
     depending on the hardware configuration:

        $ sudo perf stat -a --per-cluster -e cycles,instructions sleep 1

         Performance counter stats for 'system wide':

        S0-D0-CLS0    2         85,051,822      cycles
        S0-D0-CLS0    2         73,909,908      instructions      #    0.87  insn per cycle
        S0-D0-CLS2    2         93,365,918      cycles
        S0-D0-CLS2    2         83,006,158      instructions      #    0.89  insn per cycle
        S0-D0-CLS4    2        104,157,523      cycles
        S0-D0-CLS4    2         53,234,396      instructions      #    0.51  insn per cycle
        S0-D0-CLS6    2         65,891,079      cycles
        S0-D0-CLS6    2         41,478,273      instructions      #    0.63  insn per cycle

               1.002407989 seconds time elapsed

   - Various fixes and cleanups for event metrics including NaN handling

  perf script:

   - Use libcapstone if available to disassemble the instructions. This
     enables 'perf script -F disasm' and 'perf script --insn-trace=disasm'
     (for Intel-PT):

        $ perf script -F event,ip,disasm
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffa9839d25             movq %rax, %r14
        cycles:P:  ffffffffa9cdcaf0             endbr64
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffaa401f86             iretq
        cycles:P:  ffffffffa99c4de5             movq 0x30(%rcx), %r8
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffaa401f86             iretq
        cycles:P:  ffffffffa9907983             movl 0x68(%rbx), %eax
        cycles:P:  ffffffffa988d428             wrmsr

   - Expose sample ID / stream ID to python scripts

  perf test:

   - Add more perf test cases from Redhat internal test suites. This
     time it adds the base infra and a few perf probe tests. More to
     come. :)

   - Add 'perf test -p' for parallel execution and fix some issues found
     by the parallel test

   - Support symbol test to print symbols in given (active) module:

        $ perf test -F -v Symbols --dso /lib/modules/$(uname -r)/kernel/fs/ext4/ext4.ko
        --- start ---
        Testing /lib/modules/6.5.13-1rodete2-amd64/kernel/fs/ext4/ext4.ko
        Overlapping symbols:
         7a990-7a9a0 l __pfx_ext4_exit_fs
         7a990-7a9a0 g __pfx_cleanup_module
        Overlapping symbols:
         7a9a0-7aa1c l ext4_exit_fs
         7a9a0-7aa1c g cleanup_module
        ...

  JSON metric updates:

   - A new round of Intel metric updates

   - Support Power11 PVR (compatible to Power10)

   - Fix cache latency events on Zen 4 to set SliceId properly

  Internal:

   - Fix reference counting for 'map' data structure, tireless work from
     Ian!

   - More memory optimization for struct thread and annotate histogram.
     Now, 'perf report' (TUI) and 'perf annotate' should be much
     lighter-weight in terms of memory footprint

   - Support cross-arch perf register access. Clean up the build
     configuration so that it can detect arch-register support at
     runtime. This can allow to parse register data in sample which was
     recorded in a different arch

  Others:

   - Sync task state in 'perf sched' to kernel using trace event fields.
     The task states have been changed so tools cannot assume a fixed
     encoding

   - Clean up 'perf mem' to generalize the arch-specific events

   - Add support for local and global variables to data type profiling.
     This would increase the success rate of type resolution with DWARF

   - Add short option -H for --hierarchy in 'perf report' and 'perf top'"

* tag 'perf-tools-for-v6.9-2024-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (154 commits)
  perf annotate: Add comments in the data structures
  perf annotate: Remove sym_hist.addr[] array
  perf annotate: Calculate instruction overhead using hashmap
  perf annotate: Add a hashmap for symbol histogram
  perf threads: Reduce table size from 256 to 8
  perf threads: Switch from rbtree to hashmap
  perf threads: Move threads to its own files
  perf machine: Move machine's threads into its own abstraction
  perf machine: Move fprintf to for_each loop and a callback
  perf trace: Ignore thread hashing in summary
  perf report: Sort child tasks by tid
  perf vendor events amd: Fix Zen 4 cache latency events
  perf version: Display availability of OpenCSD support
  perf vendor events intel: Add umasks/occ_sel to PCU events.
  perf map: Fix map reference count issues
  libperf evlist: Avoid out-of-bounds access
  perf lock contention: Account contending locks too
  perf metrics: Fix segv for metrics with no events
  perf metrics: Fix metric matching
  perf pmu: Fix a potential memory leak in perf_pmu__lookup()
  ...

5 files changed, 45 insertions, 94 deletions

diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
index 191b372f9a2d..62df03e91c7e 100644
--- a/tools/perf/arch/x86/util/mem-events.c
+++ b/tools/perf/arch/x86/util/mem-events.c
@@ -1,93 +1,28 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "util/pmu.h"
-#include "util/pmus.h"
-#include "util/env.h"
-#include "map_symbol.h"
-#include "mem-events.h"
 #include "linux/string.h"
-#include "env.h"
+#include "util/map_symbol.h"
+#include "util/mem-events.h"
+#include "mem-events.h"
 
-static char mem_loads_name[100];
-static bool mem_loads_name__init;
-static char mem_stores_name[100];
 
 #define MEM_LOADS_AUX		0x8203
-#define MEM_LOADS_AUX_NAME     "{%s/mem-loads-aux/,%s/mem-loads,ldlat=%u/}:P"
 
-#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
+#define E(t, n, s, l, a) { .tag = t, .name = n, .event_name = s, .ldlat = l, .aux_event = a }
 
-static struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX] = {
-	E("ldlat-loads",	"%s/mem-loads,ldlat=%u/P",	"%s/events/mem-loads"),
-	E("ldlat-stores",	"%s/mem-stores/P",		"%s/events/mem-stores"),
-	E(NULL,			NULL,				NULL),
+struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"%s/mem-loads,ldlat=%u/P",	"mem-loads",	true,	0),
+	E("ldlat-stores",	"%s/mem-stores/P",		"mem-stores",	false,	0),
+	E(NULL,			NULL,				NULL,		false,	0),
 };
 
-static struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
-	E(NULL,		NULL,		NULL),
-	E(NULL,		NULL,		NULL),
-	E("mem-ldst",	"ibs_op//",	"ibs_op"),
+struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"{%s/mem-loads-aux/,%s/mem-loads,ldlat=%u/}:P",	"mem-loads",	true,	MEM_LOADS_AUX),
+	E("ldlat-stores",	"%s/mem-stores/P",		"mem-stores",	false,	0),
+	E(NULL,			NULL,				NULL,		false,	0),
 };
 
-struct perf_mem_event *perf_mem_events__ptr(int i)
-{
-	if (i >= PERF_MEM_EVENTS__MAX)
-		return NULL;
-
-	if (x86__is_amd_cpu())
-		return &perf_mem_events_amd[i];
-
-	return &perf_mem_events_intel[i];
-}
-
-bool is_mem_loads_aux_event(struct evsel *leader)
-{
-	struct perf_pmu *pmu = perf_pmus__find("cpu");
-
-	if (!pmu)
-		pmu = perf_pmus__find("cpu_core");
-
-	if (pmu && !perf_pmu__have_event(pmu, "mem-loads-aux"))
-		return false;
-
-	return leader->core.attr.config == MEM_LOADS_AUX;
-}
-
-const char *perf_mem_events__name(int i, const char *pmu_name)
-{
-	struct perf_mem_event *e = perf_mem_events__ptr(i);
-
-	if (!e)
-		return NULL;
-
-	if (i == PERF_MEM_EVENTS__LOAD) {
-		if (mem_loads_name__init && !pmu_name)
-			return mem_loads_name;
-
-		if (!pmu_name) {
-			mem_loads_name__init = true;
-			pmu_name = "cpu";
-		}
-
-		if (perf_pmus__have_event(pmu_name, "mem-loads-aux")) {
-			scnprintf(mem_loads_name, sizeof(mem_loads_name),
-				  MEM_LOADS_AUX_NAME, pmu_name, pmu_name,
-				  perf_mem_events__loads_ldlat);
-		} else {
-			scnprintf(mem_loads_name, sizeof(mem_loads_name),
-				  e->name, pmu_name,
-				  perf_mem_events__loads_ldlat);
-		}
-		return mem_loads_name;
-	}
-
-	if (i == PERF_MEM_EVENTS__STORE) {
-		if (!pmu_name)
-			pmu_name = "cpu";
-
-		scnprintf(mem_stores_name, sizeof(mem_stores_name),
-			  e->name, pmu_name);
-		return mem_stores_name;
-	}
-
-	return e->name;
-}
+struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
+	E(NULL,		NULL,		NULL,	false,	0),
+	E(NULL,		NULL,		NULL,	false,	0),
+	E("mem-ldst",	"%s//",		NULL,	false,	0),
+};
diff --git a/tools/perf/arch/x86/util/mem-events.h b/tools/perf/arch/x86/util/mem-events.h
new file mode 100644
index 000000000000..f55c8d3b7d59
--- /dev/null
+++ b/tools/perf/arch/x86/util/mem-events.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _X86_MEM_EVENTS_H
+#define _X86_MEM_EVENTS_H
+
+extern struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX];
+extern struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX];
+
+extern struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX];
+
+#endif /* _X86_MEM_EVENTS_H */
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index b813502a2727..12fd93f04802 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -13,7 +13,7 @@
 #include "../../../util/pmu.h"
 #include "../../../util/pmus.h"
 
-const struct sample_reg sample_reg_masks[] = {
+static const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(AX, PERF_REG_X86_AX),
 	SMPL_REG(BX, PERF_REG_X86_BX),
 	SMPL_REG(CX, PERF_REG_X86_CX),
@@ -276,6 +276,11 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
 	return SDT_ARG_VALID;
 }
 
+const struct sample_reg *arch__sample_reg_masks(void)
+{
+	return sample_reg_masks;
+}
+
 uint64_t arch__intr_reg_mask(void)
 {
 	struct perf_event_attr attr = {
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index 469555ae9b3c..c3d89d6ba1bf 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -15,6 +15,7 @@
 #include "../../../util/pmu.h"
 #include "../../../util/fncache.h"
 #include "../../../util/pmus.h"
+#include "mem-events.h"
 #include "env.h"
 
 void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused)
@@ -30,14 +31,14 @@ void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused)
 		pmu->selectable = true;
 	}
 #endif
-}
-
-int perf_pmus__num_mem_pmus(void)
-{
-	/* AMD uses IBS OP pmu and not a core PMU for perf mem/c2c */
-	if (x86__is_amd_cpu())
-		return 1;
 
-	/* Intel uses core pmus for perf mem/c2c */
-	return perf_pmus__num_core_pmus();
+	if (x86__is_amd_cpu()) {
+		if (!strcmp(pmu->name, "ibs_op"))
+			pmu->mem_events = perf_mem_events_amd;
+	} else if (pmu->is_core) {
+		if (perf_pmu__have_event(pmu, "mem-loads-aux"))
+			pmu->mem_events = perf_mem_events_intel_aux;
+		else
+			pmu->mem_events = perf_mem_events_intel;
+	}
 }
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 9b99f48b923c..e2d6cfe21057 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -33,7 +33,7 @@ static double cpuinfo_tsc_freq(void)
 
 	cpuinfo = fopen("/proc/cpuinfo", "r");
 	if (!cpuinfo) {
-		pr_err("Failed to read /proc/cpuinfo for TSC frequency");
+		pr_err("Failed to read /proc/cpuinfo for TSC frequency\n");
 		return NAN;
 	}
 	while (getline(&line, &len, cpuinfo) > 0) {
@@ -48,7 +48,7 @@ static double cpuinfo_tsc_freq(void)
 	}
 out:
 	if (fpclassify(result) == FP_ZERO)
-		pr_err("Failed to find TSC frequency in /proc/cpuinfo");
+		pr_err("Failed to find TSC frequency in /proc/cpuinfo\n");
 
 	free(line);
 	fclose(cpuinfo);