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

Pull perf updates from Ingo Molnar:
 "The main changes in this cycle on the kernel side were:

   - CPU PMU and uncore driver updates to Intel Snow Ridge, IceLake,
     KabyLake, AmberLake and WhiskeyLake CPUs.

   - Rework the MSR probing infrastructure to make it more robust, make
     it work better on virtualized systems and to better expose it on
     sysfs.

   - Rework PMU attributes group support based on the feedback from
     Greg. The core sysfs patch that adds sysfs_update_groups() was
     acked by Greg.

  There's a lot of perf tooling changes as well, all around the place:

   - vendor updates to Intel, cs-etm (ARM), ARM64, s390,

   - various enhancements to Intel PT tooling support:
      - Improve CBR (Core to Bus Ratio) packets support.
      - Export power and ptwrite events to sqlite and postgresql.
      - Add support for decoding PEBS via PT packets.
      - Add support for samples to contain IPC ratio, collecting cycles
        information from CYC packets, showing the IPC info periodically
      - Allow using time ranges

   - lots of updates to perf pmu, perf stat, perf trace, eBPF support,
     perf record, perf diff, etc. - please see the shortlog and Git log
     for details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (252 commits)
  tools arch x86: Sync asm/cpufeatures.h with the with the kernel
  tools build: Check if gettid() is available before providing helper
  perf jvmti: Address gcc string overflow warning for strncpy()
  perf python: Remove -fstack-protector-strong if clang doesn't have it
  perf annotate TUI browser: Do not use member from variable within its own initialization
  perf tests: Fix record+probe_libc_inet_pton.sh for powerpc64
  perf evsel: Do not rely on errno values for precise_ip fallback
  perf thread: Allow references to thread objects after machine__exit()
  perf header: Assign proper ff->ph in perf_event__synthesize_features()
  tools arch kvm: Sync kvm headers with the kernel sources
  perf script: Allow specifying the files to process guest samples
  perf tools metric: Don't include duration_time in group
  perf list: Avoid extra : for --raw metrics
  perf vendor events intel: Metric fixes for SKX/CLX
  perf tools: Fix typos / broken sentences
  perf jevents: Add support for Hisi hip08 L3C PMU aliasing
  perf jevents: Add support for Hisi hip08 HHA PMU aliasing
  perf jevents: Add support for Hisi hip08 DDRC PMU aliasing
  perf pmu: Support more complex PMU event aliasing
  perf diff: Documentation -c cycles option
  ...

1 files changed, 82 insertions, 7 deletions

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1ae66f09dc7d..e5e19b461061 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -82,7 +82,7 @@
 #include <sys/time.h>
 #include <sys/resource.h>
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
 
 #define DEFAULT_SEPARATOR	" "
 #define FREEZE_ON_SMI_PATH	"devices/cpu/freeze_on_smi"
@@ -776,6 +776,8 @@ static struct option stat_options[] = {
 		    "stop workload and print counts after a timeout period in ms (>= 10ms)"),
 	OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
 		     "aggregate counts per processor socket", AGGR_SOCKET),
+	OPT_SET_UINT(0, "per-die", &stat_config.aggr_mode,
+		     "aggregate counts per processor die", AGGR_DIE),
 	OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode,
 		     "aggregate counts per physical processor core", AGGR_CORE),
 	OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
@@ -800,6 +802,12 @@ static int perf_stat__get_socket(struct perf_stat_config *config __maybe_unused,
 	return cpu_map__get_socket(map, cpu, NULL);
 }
 
+static int perf_stat__get_die(struct perf_stat_config *config __maybe_unused,
+			      struct cpu_map *map, int cpu)
+{
+	return cpu_map__get_die(map, cpu, NULL);
+}
+
 static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
 			       struct cpu_map *map, int cpu)
 {
@@ -840,6 +848,12 @@ static int perf_stat__get_socket_cached(struct perf_stat_config *config,
 	return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx);
 }
 
+static int perf_stat__get_die_cached(struct perf_stat_config *config,
+					struct cpu_map *map, int idx)
+{
+	return perf_stat__get_aggr(config, perf_stat__get_die, map, idx);
+}
+
 static int perf_stat__get_core_cached(struct perf_stat_config *config,
 				      struct cpu_map *map, int idx)
 {
@@ -870,6 +884,13 @@ static int perf_stat_init_aggr_mode(void)
 		}
 		stat_config.aggr_get_id = perf_stat__get_socket_cached;
 		break;
+	case AGGR_DIE:
+		if (cpu_map__build_die_map(evsel_list->cpus, &stat_config.aggr_map)) {
+			perror("cannot build die map");
+			return -1;
+		}
+		stat_config.aggr_get_id = perf_stat__get_die_cached;
+		break;
 	case AGGR_CORE:
 		if (cpu_map__build_core_map(evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build core map");
@@ -935,21 +956,55 @@ static int perf_env__get_socket(struct cpu_map *map, int idx, void *data)
 	return cpu == -1 ? -1 : env->cpu[cpu].socket_id;
 }
 
+static int perf_env__get_die(struct cpu_map *map, int idx, void *data)
+{
+	struct perf_env *env = data;
+	int die_id = -1, cpu = perf_env__get_cpu(env, map, idx);
+
+	if (cpu != -1) {
+		/*
+		 * Encode socket in bit range 15:8
+		 * die_id is relative to socket,
+		 * we need a global id. So we combine
+		 * socket + die id
+		 */
+		if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n"))
+			return -1;
+
+		if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n"))
+			return -1;
+
+		die_id = (env->cpu[cpu].socket_id << 8) | (env->cpu[cpu].die_id & 0xff);
+	}
+
+	return die_id;
+}
+
 static int perf_env__get_core(struct cpu_map *map, int idx, void *data)
 {
 	struct perf_env *env = data;
 	int core = -1, cpu = perf_env__get_cpu(env, map, idx);
 
 	if (cpu != -1) {
-		int socket_id = env->cpu[cpu].socket_id;
-
 		/*
-		 * Encode socket in upper 16 bits
-		 * core_id is relative to socket, and
+		 * Encode socket in bit range 31:24
+		 * encode die id in bit range 23:16
+		 * core_id is relative to socket and die,
 		 * we need a global id. So we combine
-		 * socket + core id.
+		 * socket + die id + core id
 		 */
-		core = (socket_id << 16) | (env->cpu[cpu].core_id & 0xffff);
+		if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n"))
+			return -1;
+
+		if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n"))
+			return -1;
+
+		if (WARN_ONCE(env->cpu[cpu].core_id >> 16, "The core id number is too big.\n"))
+			return -1;
+
+		core = (env->cpu[cpu].socket_id << 24) |
+		       (env->cpu[cpu].die_id << 16) |
+		       (env->cpu[cpu].core_id & 0xffff);
 	}
 
 	return core;
@@ -961,6 +1016,12 @@ static int perf_env__build_socket_map(struct perf_env *env, struct cpu_map *cpus
 	return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env);
 }
 
+static int perf_env__build_die_map(struct perf_env *env, struct cpu_map *cpus,
+				   struct cpu_map **diep)
+{
+	return cpu_map__build_map(cpus, diep, perf_env__get_die, env);
+}
+
 static int perf_env__build_core_map(struct perf_env *env, struct cpu_map *cpus,
 				    struct cpu_map **corep)
 {
@@ -972,6 +1033,11 @@ static int perf_stat__get_socket_file(struct perf_stat_config *config __maybe_un
 {
 	return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
 }
+static int perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused,
+				   struct cpu_map *map, int idx)
+{
+	return perf_env__get_die(map, idx, &perf_stat.session->header.env);
+}
 
 static int perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused,
 				    struct cpu_map *map, int idx)
@@ -991,6 +1057,13 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
 		}
 		stat_config.aggr_get_id = perf_stat__get_socket_file;
 		break;
+	case AGGR_DIE:
+		if (perf_env__build_die_map(env, evsel_list->cpus, &stat_config.aggr_map)) {
+			perror("cannot build die map");
+			return -1;
+		}
+		stat_config.aggr_get_id = perf_stat__get_die_file;
+		break;
 	case AGGR_CORE:
 		if (perf_env__build_core_map(env, evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build core map");
@@ -1541,6 +1614,8 @@ static int __cmd_report(int argc, const char **argv)
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
 	OPT_SET_UINT(0, "per-socket", &perf_stat.aggr_mode,
 		     "aggregate counts per processor socket", AGGR_SOCKET),
+	OPT_SET_UINT(0, "per-die", &perf_stat.aggr_mode,
+		     "aggregate counts per processor die", AGGR_DIE),
 	OPT_SET_UINT(0, "per-core", &perf_stat.aggr_mode,
 		     "aggregate counts per physical processor core", AGGR_CORE),
 	OPT_SET_UINT('A', "no-aggr", &perf_stat.aggr_mode,