Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - Improved kbprobes robustness

   - Intel PEBS support for PT hardware tracing

   - Other Intel PT improvements: high order pages memory footprint
     reduction and various related cleanups

   - Misc cleanups

  The perf tooling side has been very busy in this cycle, with over 300
  commits. This is an incomplete high-level summary of the many
  improvements done by over 30 developers:

   - Lots of updates to the following tools:

      'perf c2c'
      'perf config'
      'perf record'
      'perf report'
      'perf script'
      'perf test'
      'perf top'
      'perf trace'

   - Updates to libperf and libtraceevent, and a consolidation of the
     proliferation of x86 instruction decoder libraries.

   - Vendor event updates for Intel and PowerPC CPUs,

   - Updates to hardware tracing tooling for ARM and Intel CPUs,

   - ... and lots of other changes and cleanups - see the shortlog and
     Git log for details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (322 commits)
  kprobes: Prohibit probing on BUG() and WARN() address
  perf/x86: Make more stuff static
  x86, perf: Fix the dependency of the x86 insn decoder selftest
  objtool: Ignore intentional differences for the x86 insn decoder
  objtool: Update sync-check.sh from perf's check-headers.sh
  perf build: Ignore intentional differences for the x86 insn decoder
  perf intel-pt: Use shared x86 insn decoder
  perf intel-pt: Remove inat.c from build dependency list
  perf: Update .gitignore file
  objtool: Move x86 insn decoder to a common location
  perf metricgroup: Support multiple events for metricgroup
  perf metricgroup: Scale the metric result
  perf pmu: Change convert_scale from static to global
  perf symbols: Move mem_info and branch_info out of symbol.h
  perf auxtrace: Uninline functions that touch perf_session
  perf tools: Remove needless evlist.h include directives
  perf tools: Remove needless evlist.h include directives
  perf tools: Remove needless thread_map.h include directives
  perf tools: Remove needless thread.h include directives
  perf tools: Remove needless map.h include directives
  ...

1 files changed, 34 insertions, 21 deletions

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 83b2fbbeeb90..b4749d3eed08 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -3,17 +3,26 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <regex.h>
+#include <stdlib.h>
 #include "callchain.h"
 #include "debug.h"
+#include "dso.h"
+#include "env.h"
 #include "event.h"
 #include "evsel.h"
 #include "hist.h"
 #include "machine.h"
 #include "map.h"
+#include "map_symbol.h"
+#include "branch.h"
+#include "mem-events.h"
+#include "srcline.h"
 #include "symbol.h"
 #include "sort.h"
 #include "strlist.h"
+#include "target.h"
 #include "thread.h"
+#include "util.h"
 #include "vdso.h"
 #include <stdbool.h>
 #include <sys/types.h>
@@ -27,6 +36,7 @@
 #include <linux/ctype.h>
 #include <symbol/kallsyms.h>
 #include <linux/mman.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
@@ -642,7 +652,7 @@ int machine__process_namespaces_event(struct machine *machine __maybe_unused,
 int machine__process_lost_event(struct machine *machine __maybe_unused,
 				union perf_event *event, struct perf_sample *sample __maybe_unused)
 {
-	dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
+	dump_printf(": id:%" PRI_lu64 ": lost:%" PRI_lu64 "\n",
 		    event->lost.id, event->lost.lost);
 	return 0;
 }
@@ -650,7 +660,7 @@ int machine__process_lost_event(struct machine *machine __maybe_unused,
 int machine__process_lost_samples_event(struct machine *machine __maybe_unused,
 					union perf_event *event, struct perf_sample *sample)
 {
-	dump_printf(": id:%" PRIu64 ": lost samples :%" PRIu64 "\n",
+	dump_printf(": id:%" PRIu64 ": lost samples :%" PRI_lu64 "\n",
 		    sample->id, event->lost_samples.lost);
 	return 0;
 }
@@ -710,20 +720,20 @@ static int machine__process_ksymbol_register(struct machine *machine,
 	struct symbol *sym;
 	struct map *map;
 
-	map = map_groups__find(&machine->kmaps, event->ksymbol_event.addr);
+	map = map_groups__find(&machine->kmaps, event->ksymbol.addr);
 	if (!map) {
-		map = dso__new_map(event->ksymbol_event.name);
+		map = dso__new_map(event->ksymbol.name);
 		if (!map)
 			return -ENOMEM;
 
-		map->start = event->ksymbol_event.addr;
-		map->end = map->start + event->ksymbol_event.len;
+		map->start = event->ksymbol.addr;
+		map->end = map->start + event->ksymbol.len;
 		map_groups__insert(&machine->kmaps, map);
 	}
 
 	sym = symbol__new(map->map_ip(map, map->start),
-			  event->ksymbol_event.len,
-			  0, 0, event->ksymbol_event.name);
+			  event->ksymbol.len,
+			  0, 0, event->ksymbol.name);
 	if (!sym)
 		return -ENOMEM;
 	dso__insert_symbol(map->dso, sym);
@@ -736,7 +746,7 @@ static int machine__process_ksymbol_unregister(struct machine *machine,
 {
 	struct map *map;
 
-	map = map_groups__find(&machine->kmaps, event->ksymbol_event.addr);
+	map = map_groups__find(&machine->kmaps, event->ksymbol.addr);
 	if (map)
 		map_groups__remove(&machine->kmaps, map);
 
@@ -750,7 +760,7 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused,
 	if (dump_trace)
 		perf_event__fprintf_ksymbol(event, stdout);
 
-	if (event->ksymbol_event.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER)
+	if (event->ksymbol.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER)
 		return machine__process_ksymbol_unregister(machine, event,
 							   sample);
 	return machine__process_ksymbol_register(machine, event, sample);
@@ -1919,7 +1929,7 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 	case PERF_RECORD_KSYMBOL:
 		ret = machine__process_ksymbol(machine, event, sample); break;
 	case PERF_RECORD_BPF_EVENT:
-		ret = machine__process_bpf_event(machine, event, sample); break;
+		ret = machine__process_bpf(machine, event, sample); break;
 	default:
 		ret = -1;
 		break;
@@ -2288,7 +2298,7 @@ static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
 
 static int thread__resolve_callchain_sample(struct thread *thread,
 					    struct callchain_cursor *cursor,
-					    struct perf_evsel *evsel,
+					    struct evsel *evsel,
 					    struct perf_sample *sample,
 					    struct symbol **parent,
 					    struct addr_location *root_al,
@@ -2494,13 +2504,13 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 
 static int thread__resolve_callchain_unwind(struct thread *thread,
 					    struct callchain_cursor *cursor,
-					    struct perf_evsel *evsel,
+					    struct evsel *evsel,
 					    struct perf_sample *sample,
 					    int max_stack)
 {
 	/* Can we do dwarf post unwind? */
-	if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
-	      (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
+	if (!((evsel->core.attr.sample_type & PERF_SAMPLE_REGS_USER) &&
+	      (evsel->core.attr.sample_type & PERF_SAMPLE_STACK_USER)))
 		return 0;
 
 	/* Bail out if nothing was captured. */
@@ -2514,7 +2524,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread,
 
 int thread__resolve_callchain(struct thread *thread,
 			      struct callchain_cursor *cursor,
-			      struct perf_evsel *evsel,
+			      struct evsel *evsel,
 			      struct perf_sample *sample,
 			      struct symbol **parent,
 			      struct addr_location *root_al,
@@ -2600,7 +2610,7 @@ int machines__for_each_thread(struct machines *machines,
 }
 
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
-				  struct target *target, struct thread_map *threads,
+				  struct target *target, struct perf_thread_map *threads,
 				  perf_event__handler_t process, bool data_mmap,
 				  unsigned int nr_threads_synthesize)
 {
@@ -2616,7 +2626,9 @@ int __machine__synthesize_threads(struct machine *machine, struct perf_tool *too
 
 pid_t machine__get_current_tid(struct machine *machine, int cpu)
 {
-	if (cpu < 0 || cpu >= MAX_NR_CPUS || !machine->current_tid)
+	int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
+
+	if (cpu < 0 || cpu >= nr_cpus || !machine->current_tid)
 		return -1;
 
 	return machine->current_tid[cpu];
@@ -2626,6 +2638,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 			     pid_t tid)
 {
 	struct thread *thread;
+	int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
 
 	if (cpu < 0)
 		return -EINVAL;
@@ -2633,14 +2646,14 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 	if (!machine->current_tid) {
 		int i;
 
-		machine->current_tid = calloc(MAX_NR_CPUS, sizeof(pid_t));
+		machine->current_tid = calloc(nr_cpus, sizeof(pid_t));
 		if (!machine->current_tid)
 			return -ENOMEM;
-		for (i = 0; i < MAX_NR_CPUS; i++)
+		for (i = 0; i < nr_cpus; i++)
 			machine->current_tid[i] = -1;
 	}
 
-	if (cpu >= MAX_NR_CPUS) {
+	if (cpu >= nr_cpus) {
 		pr_err("Requested CPU %d too large. ", cpu);
 		pr_err("Consider raising MAX_NR_CPUS\n");
 		return -EINVAL;