15 files changed, 1308 insertions, 35 deletions

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 4e82c19cbbb..4ed17072ea8 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -139,6 +139,12 @@ OPTIONS
 
 --show-total-period:: Show a column with the sum of periods.
 
+-I::
+--show-info::
+	Display extended information about the perf.data file. This adds
+	information which may be very large and thus may clutter the display.
+	It currently includes: cpu and numa topology of the host system.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index db017867d9e..dec87ecb530 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -188,6 +188,13 @@ OPTIONS
 	CPUs are specified with -: 0-2. Default is to report samples on all
 	CPUs.
 
+-I::
+--show-info::
+	Display extended information about the perf.data file. This adds
+	information which may be very large and thus may clutter the display.
+	It currently includes: cpu and numa topology of the host system.
+	It can only be used with the perf script report mode.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 15130b50dfe..744e629797b 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -2,3 +2,4 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
new file mode 100644
index 00000000000..eba80c29294
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -0,0 +1,36 @@
+#include <sys/types.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "../../util/header.h"
+
+#define __stringify_1(x)        #x
+#define __stringify(x)          __stringify_1(x)
+
+#define mfspr(rn)       ({unsigned long rval; \
+			 asm volatile("mfspr %0," __stringify(rn) \
+				      : "=r" (rval)); rval; })
+
+#define SPRN_PVR        0x11F	/* Processor Version Register */
+#define PVR_VER(pvr)    (((pvr) >>  16) & 0xFFFF) /* Version field */
+#define PVR_REV(pvr)    (((pvr) >>   0) & 0xFFFF) /* Revison field */
+
+int
+get_cpuid(char *buffer, size_t sz)
+{
+	unsigned long pvr;
+	int nb;
+
+	pvr = mfspr(SPRN_PVR);
+
+	nb = snprintf(buffer, sz, "%lu,%lu$", PVR_VER(pvr), PVR_REV(pvr));
+
+	/* look for end marker to ensure the entire data fit */
+	if (strchr(buffer, '$')) {
+		buffer[nb-1] = '\0';
+		return 0;
+	}
+	return -1;
+}
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 15130b50dfe..744e629797b 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -2,3 +2,4 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
new file mode 100644
index 00000000000..f94006068d2
--- /dev/null
+++ b/tools/perf/arch/x86/util/header.c
@@ -0,0 +1,59 @@
+#include <sys/types.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "../../util/header.h"
+
+static inline void
+cpuid(unsigned int op, unsigned int *a, unsigned int *b, unsigned int *c,
+      unsigned int *d)
+{
+	__asm__ __volatile__ (".byte 0x53\n\tcpuid\n\t"
+			      "movl %%ebx, %%esi\n\t.byte 0x5b"
+			: "=a" (*a),
+			"=S" (*b),
+			"=c" (*c),
+			"=d" (*d)
+			: "a" (op));
+}
+
+int
+get_cpuid(char *buffer, size_t sz)
+{
+	unsigned int a, b, c, d, lvl;
+	int family = -1, model = -1, step = -1;
+	int nb;
+	char vendor[16];
+
+	cpuid(0, &lvl, &b, &c, &d);
+	strncpy(&vendor[0], (char *)(&b), 4);
+	strncpy(&vendor[4], (char *)(&d), 4);
+	strncpy(&vendor[8], (char *)(&c), 4);
+	vendor[12] = '\0';
+
+	if (lvl >= 1) {
+		cpuid(1, &a, &b, &c, &d);
+
+		family = (a >> 8) & 0xf;  /* bits 11 - 8 */
+		model  = (a >> 4) & 0xf;  /* Bits  7 - 4 */
+		step   = a & 0xf;
+
+		/* extended family */
+		if (family == 0xf)
+			family += (a >> 20) & 0xff;
+
+		/* extended model */
+		if (family >= 0x6)
+			model += ((a >> 16) & 0xf) << 4;
+	}
+	nb = snprintf(buffer, sz, "%s,%u,%u,%u$", vendor, family, model, step);
+
+	/* look for end marker to ensure the entire data fit */
+	if (strchr(buffer, '$')) {
+		buffer[nb-1] = '\0';
+		return 0;
+	}
+	return -1;
+}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index dd6467872f6..f82480fa7f2 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -529,6 +529,19 @@ static int __cmd_record(int argc, const char **argv)
 	if (have_tracepoints(&evsel_list->entries))
 		perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
 
+	perf_header__set_feat(&session->header, HEADER_HOSTNAME);
+	perf_header__set_feat(&session->header, HEADER_OSRELEASE);
+	perf_header__set_feat(&session->header, HEADER_ARCH);
+	perf_header__set_feat(&session->header, HEADER_CPUDESC);
+	perf_header__set_feat(&session->header, HEADER_NRCPUS);
+	perf_header__set_feat(&session->header, HEADER_EVENT_DESC);
+	perf_header__set_feat(&session->header, HEADER_CMDLINE);
+	perf_header__set_feat(&session->header, HEADER_VERSION);
+	perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
+	perf_header__set_feat(&session->header, HEADER_TOTAL_MEM);
+	perf_header__set_feat(&session->header, HEADER_NUMA_TOPOLOGY);
+	perf_header__set_feat(&session->header, HEADER_CPUID);
+
 	/* 512 kiB: default amount of unprivileged mlocked memory */
 	if (mmap_pages == UINT_MAX)
 		mmap_pages = (512 * 1024) / page_size;
@@ -800,6 +813,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	int err = -ENOMEM;
 	struct perf_evsel *pos;
 
+	perf_header__set_cmdline(argc, argv);
+
 	evsel_list = perf_evlist__new(NULL, NULL);
 	if (evsel_list == NULL)
 		return -ENOMEM;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index e7140c6289b..66fe822b181 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -40,6 +40,7 @@ static char		const *input_name = "perf.data";
 static bool		force, use_tui, use_stdio;
 static bool		hide_unresolved;
 static bool		dont_use_callchains;
+static bool		show_full_info;
 
 static bool		show_threads;
 static struct perf_read_values	show_threads_values;
@@ -273,6 +274,9 @@ static int __cmd_report(void)
 			goto out_delete;
 	}
 
+	if (use_browser <= 0)
+		perf_session__fprintf_info(session, stdout, show_full_info);
+
 	if (show_threads)
 		perf_read_values_init(&show_threads_values);
 
@@ -485,6 +489,8 @@ static const struct option options[] = {
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
 	OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
+	OPT_BOOLEAN('I', "show-info", &show_full_info,
+		    "Display extended information about perf.data file"),
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 09024ec2ab2..2f62a295226 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -22,6 +22,7 @@ static u64			last_timestamp;
 static u64			nr_unordered;
 extern const struct option	record_options[];
 static bool			no_callchain;
+static bool			show_full_info;
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 
@@ -1083,7 +1084,8 @@ static const struct option options[] = {
 		     "comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace,raw. Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr",
 		     parse_output_fields),
 	OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
-
+	OPT_BOOLEAN('I', "show-info", &show_full_info,
+		    "display extended information from perf.data file"),
 	OPT_END()
 };
 
@@ -1268,6 +1270,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
 			return -1;
 	}
 
+	perf_session__fprintf_info(session, stdout, show_full_info);
+
 	if (!no_callchain)
 		symbol_conf.use_callchain = true;
 	else
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 4702e2443a8..b382bd551aa 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -4,7 +4,6 @@
 #include "util/util.h"
 #include "util/strbuf.h"
 
-extern const char perf_version_string[];
 extern const char perf_usage_string[];
 extern const char perf_more_info_string[];
 
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index a5fc660c1f1..08b0b5e82a4 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -9,18 +9,21 @@ void get_term_dimensions(struct winsize *ws);
 #include "../../arch/x86/include/asm/unistd.h"
 #define rmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
+#define CPUINFO_PROC	"model name"
 #endif
 
 #if defined(__x86_64__)
 #include "../../arch/x86/include/asm/unistd.h"
 #define rmb()		asm volatile("lfence" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
+#define CPUINFO_PROC	"model name"
 #endif
 
 #ifdef __powerpc__
 #include "../../arch/powerpc/include/asm/unistd.h"
 #define rmb()		asm volatile ("sync" ::: "memory")
 #define cpu_relax()	asm volatile ("" ::: "memory");
+#define CPUINFO_PROC	"cpu"
 #endif
 
 #ifdef __s390__
@@ -37,30 +40,35 @@ void get_term_dimensions(struct winsize *ws);
 # define rmb()		asm volatile("" ::: "memory")
 #endif
 #define cpu_relax()	asm volatile("" ::: "memory")
+#define CPUINFO_PROC	"cpu type"
 #endif
 
 #ifdef __hppa__
 #include "../../arch/parisc/include/asm/unistd.h"
 #define rmb()		asm volatile("" ::: "memory")
 #define cpu_relax()	asm volatile("" ::: "memory");
+#define CPUINFO_PROC	"cpu"
 #endif
 
 #ifdef __sparc__
 #include "../../arch/sparc/include/asm/unistd.h"
 #define rmb()		asm volatile("":::"memory")
 #define cpu_relax()	asm volatile("":::"memory")
+#define CPUINFO_PROC	"cpu"
 #endif
 
 #ifdef __alpha__
 #include "../../arch/alpha/include/asm/unistd.h"
 #define rmb()		asm volatile("mb" ::: "memory")
 #define cpu_relax()	asm volatile("" ::: "memory")
+#define CPUINFO_PROC	"cpu model"
 #endif
 
 #ifdef __ia64__
 #include "../../arch/ia64/include/asm/unistd.h"
 #define rmb()		asm volatile ("mf" ::: "memory")
 #define cpu_relax()	asm volatile ("hint @pause" ::: "memory")
+#define CPUINFO_PROC	"model name"
 #endif
 
 #ifdef __arm__
@@ -71,6 +79,7 @@ void get_term_dimensions(struct winsize *ws);
  */
 #define rmb()		((void(*)(void))0xffff0fa0)()
 #define cpu_relax()	asm volatile("":::"memory")
+#define CPUINFO_PROC	"Processor"
 #endif
 
 #ifdef __mips__
@@ -83,6 +92,7 @@ void get_term_dimensions(struct winsize *ws);
 				: /* no input */			\
 				: "memory")
 #define cpu_relax()	asm volatile("" ::: "memory")
+#define CPUINFO_PROC	"cpu model"
 #endif
 
 #include <time.h>
@@ -171,5 +181,6 @@ struct ip_callchain {
 };
 
 extern bool perf_host, perf_guest;
+extern const char perf_version_string[];
 
 #endif
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b6c1ad123ca..f2ceb0f7d66 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -7,6 +7,7 @@
 #include <stdlib.h>
 #include <linux/list.h>
 #include <linux/kernel.h>
+#include <sys/utsname.h>
 
 #include "evlist.h"
 #include "evsel.h"
@@ -17,12 +18,19 @@
 #include "session.h"
 #include "symbol.h"
 #include "debug.h"
+#include "cpumap.h"
 
 static bool no_buildid_cache = false;
 
 static int event_count;
 static struct perf_trace_event_type *events;
 
+static u32 header_argc;
+static const char **header_argv;
+
+static int dsos__write_buildid_table(struct perf_header *header, int fd);
+static int perf_session__cache_build_ids(struct perf_session *session);
+
 int perf_header__push_event(u64 id, const char *name)
 {
 	if (strlen(name) > MAX_EVENT_NAME)
@@ -110,6 +118,1020 @@ static int write_padded(int fd, const void *bf, size_t count,
 	return err;
 }
 
+static int do_write_string(int fd, const char *str)
+{
+	u32 len, olen;
+	int ret;
+
+	olen = strlen(str) + 1;
+	len = ALIGN(olen, NAME_ALIGN);
+
+	/* write len, incl. \0 */
+	ret = do_write(fd, &len, sizeof(len));
+	if (ret < 0)
+		return ret;
+
+	return write_padded(fd, str, olen, len);
+}
+
+static char *do_read_string(int fd, struct perf_header *ph)
+{
+	ssize_t sz, ret;
+	u32 len;
+	char *buf;
+
+	sz = read(fd, &len, sizeof(len));
+	if (sz < (ssize_t)sizeof(len))
+		return NULL;
+
+	if (ph->needs_swap)
+		len = bswap_32(len);
+
+	buf = malloc(len);
+	if (!buf)
+		return NULL;
+
+	ret = read(fd, buf, len);
+	if (ret == (ssize_t)len) {
+		/*
+		 * strings are padded by zeroes
+		 * thus the actual strlen of buf
+		 * may be less than len
+		 */
+		return buf;
+	}
+
+	free(buf);
+	return NULL;
+}
+
+int
+perf_header__set_cmdline(int argc, const char **argv)
+{
+	int i;
+
+	header_argc = (u32)argc;
+
+	/* do not include NULL termination */
+	header_argv = calloc(argc, sizeof(char *));
+	if (!header_argv)
+		return -ENOMEM;
+
+	/*
+	 * must copy argv contents because it gets moved
+	 * around during option parsing
+	 */
+	for (i = 0; i < argc ; i++)
+		header_argv[i] = argv[i];
+
+	return 0;
+}
+
+static int write_trace_info(int fd, struct perf_header *h __used,
+			    struct perf_evlist *evlist)
+{
+	return read_tracing_data(fd, &evlist->entries);
+}
+
+
+static int write_build_id(int fd, struct perf_header *h,
+			  struct perf_evlist *evlist __used)
+{
+	struct perf_session *session;
+	int err;
+
+	session = container_of(h, struct perf_session, header);
+
+	err = dsos__write_buildid_table(h, fd);
+	if (err < 0) {
+		pr_debug("failed to write buildid table\n");
+		return err;
+	}
+	if (!no_buildid_cache)
+		perf_session__cache_build_ids(session);
+
+	return 0;
+}
+
+static int write_hostname(int fd, struct perf_header *h __used,
+			  struct perf_evlist *evlist __used)
+{
+	struct utsname uts;
+	int ret;
+
+	ret = uname(&uts);
+	if (ret < 0)
+		return -1;
+
+	return do_write_string(fd, uts.nodename);
+}
+
+static int write_osrelease(int fd, struct perf_header *h __used,
+			   struct perf_evlist *evlist __used)
+{
+	struct utsname uts;
+	int ret;
+
+	ret = uname(&uts);
+	if (ret < 0)
+		return -1;
+
+	return do_write_string(fd, uts.release);
+}
+
+static int write_arch(int fd, struct perf_header *h __used,
+		      struct perf_evlist *evlist __used)
+{
+	struct utsname uts;
+	int ret;
+
+	ret = uname(&uts);
+	if (ret < 0)
+		return -1;
+
+	return do_write_string(fd, uts.machine);
+}
+
+static int write_version(int fd, struct perf_header *h __used,
+			 struct perf_evlist *evlist __used)
+{
+	return do_write_string(fd, perf_version_string);
+}
+
+static int write_cpudesc(int fd, struct perf_header *h __used,
+		       struct perf_evlist *evlist __used)
+{
+#ifndef CPUINFO_PROC
+#define CPUINFO_PROC NULL
+#endif
+	FILE *file;
+	char *buf = NULL;
+	char *s, *p;
+	const char *search = CPUINFO_PROC;
+	size_t len = 0;
+	int ret = -1;
+
+	if (!search)
+		return -1;
+
+	file = fopen("/proc/cpuinfo", "r");
+	if (!file)
+		return -1;
+
+	while (getline(&buf, &len, file) > 0) {
+		ret = strncmp(buf, search, strlen(search));
+		if (!ret)
+			break;
+	}
+
+	if (ret)
+		goto done;
+
+	s = buf;
+
+	p = strchr(buf, ':');
+	if (p && *(p+1) == ' ' && *(p+2))
+		s = p + 2;
+	p = strchr(s, '\n');
+	if (p)
+		*p = '\0';
+
+	/* squash extra space characters (branding string) */
+	p = s;
+	while (*p) {
+		if (isspace(*p)) {
+			char *r = p + 1;
+			char *q = r;
+			*p = ' ';
+			while (*q && isspace(*q))
+				q++;
+			if (q != (p+1))
+				while ((*r++ = *q++));
+		}
+		p++;
+	}
+	ret = do_write_string(fd, s);
+done:
+	free(buf);
+	fclose(file);
+	return ret;
+}
+
+static int write_nrcpus(int fd, struct perf_header *h __used,
+			struct perf_evlist *evlist __used)
+{
+	long nr;
+	u32 nrc, nra;
+	int ret;
+
+	nr = sysconf(_SC_NPROCESSORS_CONF);
+	if (nr < 0)
+		return -1;
+
+	nrc = (u32)(nr & UINT_MAX);
+
+	nr = sysconf(_SC_NPROCESSORS_ONLN);
+	if (nr < 0)
+		return -1;
+
+	nra = (u32)(nr & UINT_MAX);
+
+	ret = do_write(fd, &nrc, sizeof(nrc));
+	if (ret < 0)
+		return ret;
+
+	return do_write(fd, &nra, sizeof(nra));
+}
+
+static int write_event_desc(int fd, struct perf_header *h __used,
+			    struct perf_evlist *evlist)
+{
+	struct perf_evsel *attr;
+	u32 nre = 0, nri, sz;
+	int ret;
+
+	list_for_each_entry(attr, &evlist->entries, node)
+		nre++;
+
+	/*
+	 * write number of events
+	 */
+	ret = do_write(fd, &nre, sizeof(nre));
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * size of perf_event_attr struct
+	 */
+	sz = (u32)sizeof(attr->attr);
+	ret = do_write(fd, &sz, sizeof(sz));
+	if (ret < 0)
+		return ret;
+
+	list_for_each_entry(attr, &evlist->entries, node) {
+
+		ret = do_write(fd, &attr->attr, sz);
+		if (ret < 0)
+			return ret;
+		/*
+		 * write number of unique id per event
+		 * there is one id per instance of an event
+		 *
+		 * copy into an nri to be independent of the
+		 * type of ids,
+		 */
+		nri = attr->ids;
+		ret = do_write(fd, &nri, sizeof(nri));
+		if (ret < 0)
+			return ret;
+
+		/*
+		 * write event string as passed on cmdline
+		 */
+		ret = do_write_string(fd, attr->name);
+		if (ret < 0)
+			return ret;
+		/*
+		 * write unique ids for this event
+		 */
+		ret = do_write(fd, attr->id, attr->ids * sizeof(u64));
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+static int write_cmdline(int fd, struct perf_header *h __used,
+			 struct perf_evlist *evlist __used)
+{
+	char buf[MAXPATHLEN];
+	char proc[32];
+	u32 i, n;
+	int ret;
+
+	/*
+	 * actual atual path to perf binary
+	 */
+	sprintf(proc, "/proc/%d/exe", getpid());
+	ret = readlink(proc, buf, sizeof(buf));
+	if (ret <= 0)
+		return -1;
+
+	/* readlink() does not add null termination */
+	buf[ret] = '\0';
+
+	/* account for binary path */
+	n = header_argc + 1;
+
+	ret = do_write(fd, &n, sizeof(n));
+	if (ret < 0)
+		return ret;
+
+	ret = do_write_string(fd, buf);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0 ; i < header_argc; i++) {
+		ret = do_write_string(fd, header_argv[i]);
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+#define CORE_SIB_FMT \
+	"/sys/devices/system/cpu/cpu%d/topology/core_siblings_list"
+#define THRD_SIB_FMT \
+	"/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list"
+
+struct cpu_topo {
+	u32 core_sib;
+	u32 thread_sib;
+	char **core_siblings;
+	char **thread_siblings;
+};
+
+static int build_cpu_topo(struct cpu_topo *tp, int cpu)
+{
+	FILE *fp;
+	char filename[MAXPATHLEN];
+	char *buf = NULL, *p;
+	size_t len = 0;
+	u32 i = 0;
+	int ret = -1;
+
+	sprintf(filename, CORE_SIB_FMT, cpu);
+	fp = fopen(filename, "r");
+	if (!fp)
+		return -1;
+
+	if (getline(&buf, &len, fp) <= 0)
+		goto done;
+
+	fclose(fp);
+
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	for (i = 0; i < tp->core_sib; i++) {
+		if (!strcmp(buf, tp->core_siblings[i]))
+			break;
+	}
+	if (i == tp->core_sib) {
+		tp->core_siblings[i] = buf;
+		tp->core_sib++;
+		buf = NULL;
+		len = 0;
+	}
+
+	sprintf(filename, THRD_SIB_FMT, cpu);
+	fp = fopen(filename, "r");
+	if (!fp)
+		goto done;
+
+	if (getline(&buf, &len, fp) <= 0)
+		goto done;
+
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	for (i = 0; i < tp->thread_sib; i++) {
+		if (!strcmp(buf, tp->thread_siblings[i]))
+			break;
+	}
+	if (i == tp->thread_sib) {
+		tp->thread_siblings[i] = buf;
+		tp->thread_sib++;
+		buf = NULL;
+	}
+	ret = 0;
+done:
+	if(fp)
+		fclose(fp);
+	free(buf);
+	return ret;
+}
+
+static void free_cpu_topo(struct cpu_topo *tp)
+{
+	u32 i;
+
+	if (!tp)
+		return;
+
+	for (i = 0 ; i < tp->core_sib; i++)
+		free(tp->core_siblings[i]);
+
+	for (i = 0 ; i < tp->thread_sib; i++)
+		free(tp->thread_siblings[i]);
+
+	free(tp);
+}
+
+static struct cpu_topo *build_cpu_topology(void)
+{
+	struct cpu_topo *tp;
+	void *addr;
+	u32 nr, i;
+	size_t sz;
+	long ncpus;
+	int ret = -1;
+
+	ncpus = sysconf(_SC_NPROCESSORS_CONF);
+	if (ncpus < 0)
+		return NULL;
+
+	nr = (u32)(ncpus & UINT_MAX);
+
+	sz = nr * sizeof(char *);
+
+	addr = calloc(1, sizeof(*tp) + 2 * sz);
+	if (!addr)
+		return NULL;
+
+	tp = addr;
+
+	addr += sizeof(*tp);
+	tp->core_siblings = addr;
+	addr += sz;
+	tp->thread_siblings = addr;
+
+	for (i = 0; i < nr; i++) {
+		ret = build_cpu_topo(tp, i);
+		if (ret < 0)
+			break;
+	}
+	if (ret) {
+		free_cpu_topo(tp);
+		tp = NULL;
+	}
+	return tp;
+}
+
+static int write_cpu_topology(int fd, struct perf_header *h __used,
+			  struct perf_evlist *evlist __used)
+{
+	struct cpu_topo *tp;
+	u32 i;
+	int ret;
+
+	tp = build_cpu_topology();
+	if (!tp)
+		return -1;
+
+	ret = do_write(fd, &tp->core_sib, sizeof(tp->core_sib));
+	if (ret < 0)
+		goto done;
+
+	for (i = 0; i < tp->core_sib; i++) {
+		ret = do_write_string(fd, tp->core_siblings[i]);
+		if (ret < 0)
+			goto done;
+	}
+	ret = do_write(fd, &tp->thread_sib, sizeof(tp->thread_sib));
+	if (ret < 0)
+		goto done;
+
+	for (i = 0; i < tp->thread_sib; i++) {
+		ret = do_write_string(fd, tp->thread_siblings[i]);
+		if (ret < 0)
+			break;
+	}
+done:
+	free_cpu_topo(tp);
+	return ret;
+}
+
+
+
+static int write_total_mem(int fd, struct perf_header *h __used,
+			  struct perf_evlist *evlist __used)
+{
+	char *buf = NULL;
+	FILE *fp;
+	size_t len = 0;
+	int ret = -1, n;
+	uint64_t mem;
+
+	fp = fopen("/proc/meminfo", "r");
+	if (!fp)
+		return -1;
+
+	while (getline(&buf, &len, fp) > 0) {
+		ret = strncmp(buf, "MemTotal:", 9);
+		if (!ret)
+			break;
+	}
+	if (!ret) {
+		n = sscanf(buf, "%*s %"PRIu64, &mem);
+		if (n == 1)
+			ret = do_write(fd, &mem, sizeof(mem));
+	}
+	free(buf);
+	fclose(fp);
+	return ret;
+}
+
+static int write_topo_node(int fd, int node)
+{
+	char str[MAXPATHLEN];
+	char field[32];
+	char *buf = NULL, *p;
+	size_t len = 0;
+	FILE *fp;
+	u64 mem_total, mem_free, mem;
+	int ret = -1;
+
+	sprintf(str, "/sys/devices/system/node/node%d/meminfo", node);
+	fp = fopen(str, "r");
+	if (!fp)
+		return -1;
+
+	while (getline(&buf, &len, fp) > 0) {
+		/* skip over invalid lines */
+		if (!strchr(buf, ':'))
+			continue;
+		if (sscanf(buf, "%*s %*d %s %"PRIu64, field, &mem) != 2)
+			goto done;
+		if (!strcmp(field, "MemTotal:"))
+			mem_total = mem;
+		if (!strcmp(field, "MemFree:"))
+			mem_free = mem;
+	}
+
+	fclose(fp);
+
+	ret = do_write(fd, &mem_total, sizeof(u64));
+	if (ret)
+		goto done;
+
+	ret = do_write(fd, &mem_free, sizeof(u64));
+	if (ret)
+		goto done;
+
+	ret = -1;
+	sprintf(str, "/sys/devices/system/node/node%d/cpulist", node);
+
+	fp = fopen(str, "r");
+	if (!fp)
+		goto done;
+
+	if (getline(&buf, &len, fp) <= 0)
+		goto done;
+
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	ret = do_write_string(fd, buf);
+done:
+	free(buf);
+	fclose(fp);
+	return ret;
+}
+
+static int write_numa_topology(int fd, struct perf_header *h __used,
+			  struct perf_evlist *evlist __used)
+{
+	char *buf = NULL;
+	size_t len = 0;
+	FILE *fp;
+	struct cpu_map *node_map = NULL;
+	char *c;
+	u32 nr, i, j;
+	int ret = -1;
+
+	fp = fopen("/sys/devices/system/node/online", "r");
+	if (!fp)
+		return -1;
+
+	if (getline(&buf, &len, fp) <= 0)
+		goto done;
+
+	c = strchr(buf, '\n');
+	if (c)
+		*c = '\0';
+
+	node_map = cpu_map__new(buf);
+	if (!node_map)
+		goto done;
+
+	nr = (u32)node_map->nr;
+
+	ret = do_write(fd, &nr, sizeof(nr));
+	if (ret < 0)
+		goto done;
+
+	for (i = 0; i < nr; i++) {
+		j = (u32)node_map->map[i];
+		ret = do_write(fd, &j, sizeof(j));
+		if (ret < 0)
+			break;
+
+		ret = write_topo_node(fd, i);
+		if (ret < 0)
+			break;
+	}
+done:
+	free(buf);
+	fclose(fp);
+	free(node_map);
+	return ret;
+}
+
+/*
+ * default get_cpuid(): nothing gets recorded
+ * actual implementation must be in arch/$(ARCH)/util/header.c
+ */
+int __attribute__((weak)) get_cpuid(char *buffer __used, size_t sz __used)
+{
+	return -1;
+}
+
+static int write_cpuid(int fd, struct perf_header *h __used,
+		       struct perf_evlist *evlist __used)
+{
+	char buffer[64];
+	int ret;
+
+	ret = get_cpuid(buffer, sizeof(buffer));
+	if (!ret)
+		goto write_it;
+
+	return -1;
+write_it:
+	return do_write_string(fd, buffer);
+}
+
+static void print_hostname(struct perf_header *ph, int fd, FILE *fp)
+{
+	char *str = do_read_string(fd, ph);
+	fprintf(fp, "# hostname : %s\n", str);
+	free(str);
+}
+
+static void print_osrelease(struct perf_header *ph, int fd, FILE *fp)
+{
+	char *str = do_read_string(fd, ph);
+	fprintf(fp, "# os release : %s\n", str);
+	free(str);
+}
+
+static void print_arch(struct perf_header *ph, int fd, FILE *fp)
+{
+	char *str = do_read_string(fd, ph);
+	fprintf(fp, "# arch : %s\n", str);
+	free(str);
+}
+
+static void print_cpudesc(struct perf_header *ph, int fd, FILE *fp)
+{
+	char *str = do_read_string(fd, ph);
+	fprintf(fp, "# cpudesc : %s\n", str);
+	free(str);
+}
+
+static void print_nrcpus(struct perf_header *ph, int fd, FILE *fp)
+{
+	ssize_t ret;
+	u32 nr;
+
+	ret = read(fd, &nr, sizeof(nr));
+	if (ret != (ssize_t)sizeof(nr))
+		nr = -1; /* interpreted as error */
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	fprintf(fp, "# nrcpus online : %u\n", nr);
+
+	ret = read(fd, &nr, sizeof(nr));
+	if (ret != (ssize_t)sizeof(nr))
+		nr = -1; /* interpreted as error */
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	fprintf(fp, "# nrcpus avail : %u\n", nr);
+}
+
+static void print_version(struct perf_header *ph, int fd, FILE *fp)
+{
+	char *str = do_read_string(fd, ph);
+	fprintf(fp, "# perf version : %s\n", str);
+	free(str);
+}
+
+static void print_cmdline(struct perf_header *ph, int fd, FILE *fp)
+{
+	ssize_t ret;
+	char *str;
+	u32 nr, i;
+
+	ret = read(fd, &nr, sizeof(nr));
+	if (ret != (ssize_t)sizeof(nr))
+		return;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	fprintf(fp, "# cmdline : ");
+
+	for (i = 0; i < nr; i++) {
+		str = do_read_string(fd, ph);
+		fprintf(fp, "%s ", str);
+		free(str);
+	}
+	fputc('\n', fp);
+}
+
+static void print_cpu_topology(struct perf_header *ph, int fd, FILE *fp)
+{
+	ssize_t ret;
+	u32 nr, i;
+	char *str;
+
+	ret = read(fd, &nr, sizeof(nr));
+	if (ret != (ssize_t)sizeof(nr))
+		return;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	for (i = 0; i < nr; i++) {
+		str = do_read_string(fd, ph);
+		fprintf(fp, "# sibling cores   : %s\n", str);
+		free(str);
+	}
+
+	ret = read(fd, &nr, sizeof(nr));
+	if (ret != (ssize_t)sizeof(nr))
+		return;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	for (i = 0; i < nr; i++) {
+		str = do_read_string(fd, ph);
+		fprintf(fp, "# sibling threads : %s\n", str);
+		free(str);
+	}
+}
+
+static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
+{
+	struct perf_event_attr attr;
+	uint64_t id;
+	void *buf = NULL;
+	char *str;
+	u32 nre, sz, nr, i, j, msz;
+	int ret;
+
+	/* number of events */
+	ret = read(fd, &nre, sizeof(nre));
+	if (ret != (ssize_t)sizeof(nre))
+		goto error;
+
+	if (ph->needs_swap)
+		nre = bswap_32(nre);
+
+	ret = read(fd, &sz, sizeof(sz));
+	if (ret != (ssize_t)sizeof(sz))