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, 97 insertions, 15 deletions

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 847ae51a524b..6a93ff5d8db5 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -13,6 +13,7 @@
 #include <linux/list.h>
 #include <linux/kernel.h>
 #include <linux/bitops.h>
+#include <linux/string.h>
 #include <linux/stringify.h>
 #include <sys/stat.h>
 #include <sys/utsname.h>
@@ -43,7 +44,7 @@
 #include "cputopo.h"
 #include "bpf-event.h"
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
 
 /*
  * magic2 = "PERFILE2"
@@ -416,10 +417,8 @@ static int __write_cpudesc(struct feat_fd *ff, const char *cpuinfo_proc)
 	while (*p) {
 		if (isspace(*p)) {
 			char *r = p + 1;
-			char *q = r;
+			char *q = skip_spaces(r);
 			*p = ' ';
-			while (*q && isspace(*q))
-				q++;
 			if (q != (p+1))
 				while ((*r++ = *q++));
 		}
@@ -599,6 +598,27 @@ static int write_cpu_topology(struct feat_fd *ff,
 		if (ret < 0)
 			return ret;
 	}
+
+	if (!tp->die_sib)
+		goto done;
+
+	ret = do_write(ff, &tp->die_sib, sizeof(tp->die_sib));
+	if (ret < 0)
+		goto done;
+
+	for (i = 0; i < tp->die_sib; i++) {
+		ret = do_write_string(ff, tp->die_siblings[i]);
+		if (ret < 0)
+			goto done;
+	}
+
+	for (j = 0; j < perf_env.nr_cpus_avail; j++) {
+		ret = do_write(ff, &perf_env.cpu[j].die_id,
+			       sizeof(perf_env.cpu[j].die_id));
+		if (ret < 0)
+			return ret;
+	}
+
 done:
 	cpu_topology__delete(tp);
 	return ret;
@@ -1028,7 +1048,7 @@ static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 lev
 		return -1;
 
 	cache->type[len] = 0;
-	cache->type = rtrim(cache->type);
+	cache->type = strim(cache->type);
 
 	scnprintf(file, PATH_MAX, "%s/size", path);
 	if (sysfs__read_str(file, &cache->size, &len)) {
@@ -1037,7 +1057,7 @@ static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 lev
 	}
 
 	cache->size[len] = 0;
-	cache->size = rtrim(cache->size);
+	cache->size = strim(cache->size);
 
 	scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path);
 	if (sysfs__read_str(file, &cache->map, &len)) {
@@ -1047,7 +1067,7 @@ static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 lev
 	}
 
 	cache->map[len] = 0;
-	cache->map = rtrim(cache->map);
+	cache->map = strim(cache->map);
 	return 0;
 }
 
@@ -1100,7 +1120,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
 	return 0;
 }
 
-#define MAX_CACHES 2000
+#define MAX_CACHES (MAX_NR_CPUS * 4)
 
 static int write_cache(struct feat_fd *ff,
 		       struct perf_evlist *evlist __maybe_unused)
@@ -1439,10 +1459,20 @@ static void print_cpu_topology(struct feat_fd *ff, FILE *fp)
 	str = ph->env.sibling_cores;
 
 	for (i = 0; i < nr; i++) {
-		fprintf(fp, "# sibling cores   : %s\n", str);
+		fprintf(fp, "# sibling sockets : %s\n", str);
 		str += strlen(str) + 1;
 	}
 
+	if (ph->env.nr_sibling_dies) {
+		nr = ph->env.nr_sibling_dies;
+		str = ph->env.sibling_dies;
+
+		for (i = 0; i < nr; i++) {
+			fprintf(fp, "# sibling dies    : %s\n", str);
+			str += strlen(str) + 1;
+		}
+	}
+
 	nr = ph->env.nr_sibling_threads;
 	str = ph->env.sibling_threads;
 
@@ -1451,12 +1481,28 @@ static void print_cpu_topology(struct feat_fd *ff, FILE *fp)
 		str += strlen(str) + 1;
 	}
 
-	if (ph->env.cpu != NULL) {
-		for (i = 0; i < cpu_nr; i++)
-			fprintf(fp, "# CPU %d: Core ID %d, Socket ID %d\n", i,
-				ph->env.cpu[i].core_id, ph->env.cpu[i].socket_id);
-	} else
-		fprintf(fp, "# Core ID and Socket ID information is not available\n");
+	if (ph->env.nr_sibling_dies) {
+		if (ph->env.cpu != NULL) {
+			for (i = 0; i < cpu_nr; i++)
+				fprintf(fp, "# CPU %d: Core ID %d, "
+					    "Die ID %d, Socket ID %d\n",
+					    i, ph->env.cpu[i].core_id,
+					    ph->env.cpu[i].die_id,
+					    ph->env.cpu[i].socket_id);
+		} else
+			fprintf(fp, "# Core ID, Die ID and Socket ID "
+				    "information is not available\n");
+	} else {
+		if (ph->env.cpu != NULL) {
+			for (i = 0; i < cpu_nr; i++)
+				fprintf(fp, "# CPU %d: Core ID %d, "
+					    "Socket ID %d\n",
+					    i, ph->env.cpu[i].core_id,
+					    ph->env.cpu[i].socket_id);
+		} else
+			fprintf(fp, "# Core ID and Socket ID "
+				    "information is not available\n");
+	}
 }
 
 static void print_clockid(struct feat_fd *ff, FILE *fp)
@@ -2214,6 +2260,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 			goto free_cpu;
 
 		ph->env.cpu[i].core_id = nr;
+		size += sizeof(u32);
 
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
@@ -2225,6 +2272,40 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		}
 
 		ph->env.cpu[i].socket_id = nr;
+		size += sizeof(u32);
+	}
+
+	/*
+	 * The header may be from old perf,
+	 * which doesn't include die information.
+	 */
+	if (ff->size <= size)
+		return 0;
+
+	if (do_read_u32(ff, &nr))
+		return -1;
+
+	ph->env.nr_sibling_dies = nr;
+	size += sizeof(u32);
+
+	for (i = 0; i < nr; i++) {
+		str = do_read_string(ff);
+		if (!str)
+			goto error;
+
+		/* include a NULL character at the end */
+		if (strbuf_add(&sb, str, strlen(str) + 1) < 0)
+			goto error;
+		size += string_size(str);
+		free(str);
+	}
+	ph->env.sibling_dies = strbuf_detach(&sb, NULL);
+
+	for (i = 0; i < (u32)cpu_nr; i++) {
+		if (do_read_u32(ff, &nr))
+			goto free_cpu;
+
+		ph->env.cpu[i].die_id = nr;
 	}
 
 	return 0;
@@ -3602,6 +3683,7 @@ int perf_event__synthesize_features(struct perf_tool *tool,
 		return -ENOMEM;
 
 	ff.size = sz - sz_hdr;
+	ff.ph = &session->header;
 
 	for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
 		if (!feat_ops[feat].synthesize) {