Commit acae8b36 authored by Kan Liang's avatar Kan Liang Committed by Arnaldo Carvalho de Melo
Browse files

perf header: Add die information in CPU topology 



With the new CPUID.1F, a new level type of CPU topology, 'die', is
introduced. The 'die' information in CPU topology should be added in
perf header.

To be compatible with old perf.data, the patch checks the section size
before reading the die information. The new info is added at the end of
the cpu_topology section, the old perf tool ignores the extra data.  It
never reads data crossing the section boundary.

The new perf tool with the patch can be used on legacy kernel. Add a new
function has_die_topology() to check if die topology information is
supported by kernel. The function only check X86 and CPU 0. Assuming
other CPUs have same topology.

Use similar method for core and socket to support die id and sibling
dies string.

Signed-off-by: default avatarKan Liang <kan.liang@linux.intel.com>
Reviewed-by: default avatarJiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1559688644-106558-2-git-send-email-kan.liang@linux.intel.com


Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
parent b74d8686

tools/perf/Documentation/perf.data-file-format.txt

+7 −2
Original line number Diff line number Diff line
@@ -153,7 +153,7 @@ struct { 


String lists defining the core and CPU threads topology.

The string lists are followed by a variable length array

which contains core_id and socket_id of each cpu.

which contains core_id, die_id (for x86) and socket_id of each cpu.

The number of entries can be determined by the size of the

section minus the sizes of both string lists.
@@ -162,14 +162,19 @@ struct { 
       struct perf_header_string_list threads; /* Variable length */

       struct {

	      uint32_t core_id;

	      uint32_t die_id;

	      uint32_t socket_id;

       } cpus[nr]; /* Variable length records */

};



Example:

	sibling cores   : 0-3

	sibling cores   : 0-8

	sibling dies	: 0-3

	sibling dies	: 4-7

	sibling threads : 0-1

	sibling threads : 2-3

	sibling threads : 4-5

	sibling threads : 6-7



	HEADER_NUMA_TOPOLOGY = 14,

tools/perf/util/cputopo.c

+71 −5
Original line number Diff line number Diff line 
// SPDX-License-Identifier: GPL-2.0

#include <sys/param.h>

#include <sys/utsname.h>

#include <inttypes.h>

#include <api/fs/fs.h>
@@ -8,9 +9,10 @@ 
#include "util.h"

#include "env.h"





#define CORE_SIB_FMT \

	"%s/devices/system/cpu/cpu%d/topology/core_siblings_list"

#define DIE_SIB_FMT \

	"%s/devices/system/cpu/cpu%d/topology/die_cpus_list"

#define THRD_SIB_FMT \

	"%s/devices/system/cpu/cpu%d/topology/thread_siblings_list"

#define NODE_ONLINE_FMT \
@@ -34,12 +36,12 @@ static int build_cpu_topology(struct cpu_topology *tp, int cpu) 
		  sysfs__mountpoint(), cpu);

	fp = fopen(filename, "r");

	if (!fp)

		goto try_threads;

		goto try_dies;



	sret = getline(&buf, &len, fp);

	fclose(fp);

	if (sret <= 0)

		goto try_threads;

		goto try_dies;



	p = strchr(buf, '\n');

	if (p)
@@ -57,6 +59,37 @@ static int build_cpu_topology(struct cpu_topology *tp, int cpu) 
	}

	ret = 0;



try_dies:

	if (!tp->die_siblings)

		goto try_threads;



	scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT,

		  sysfs__mountpoint(), cpu);

	fp = fopen(filename, "r");

	if (!fp)

		goto try_threads;



	sret = getline(&buf, &len, fp);

	fclose(fp);

	if (sret <= 0)

		goto try_threads;



	p = strchr(buf, '\n');

	if (p)

		*p = '\0';



	for (i = 0; i < tp->die_sib; i++) {

		if (!strcmp(buf, tp->die_siblings[i]))

			break;

	}

	if (i == tp->die_sib) {

		tp->die_siblings[i] = buf;

		tp->die_sib++;

		buf = NULL;

		len = 0;

	}

	ret = 0;



try_threads:

	scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT,

		  sysfs__mountpoint(), cpu);
@@ -98,21 +131,46 @@ void cpu_topology__delete(struct cpu_topology *tp) 
	for (i = 0 ; i < tp->core_sib; i++)

		zfree(&tp->core_siblings[i]);



	if (tp->die_sib) {

		for (i = 0 ; i < tp->die_sib; i++)

			zfree(&tp->die_siblings[i]);

	}



	for (i = 0 ; i < tp->thread_sib; i++)

		zfree(&tp->thread_siblings[i]);



	free(tp);

}



static bool has_die_topology(void)

{

	char filename[MAXPATHLEN];

	struct utsname uts;



	if (uname(&uts) < 0)

		return false;



	if (strncmp(uts.machine, "x86_64", 6))

		return false;



	scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT,

		  sysfs__mountpoint(), 0);

	if (access(filename, F_OK) == -1)

		return false;



	return true;

}



struct cpu_topology *cpu_topology__new(void)

{

	struct cpu_topology *tp = NULL;

	void *addr;

	u32 nr, i;

	u32 nr, i, nr_addr;

	size_t sz;

	long ncpus;

	int ret = -1;

	struct cpu_map *map;

	bool has_die = has_die_topology();



	ncpus = cpu__max_present_cpu();
@@ -126,7 +184,11 @@ struct cpu_topology *cpu_topology__new(void) 
	nr = (u32)(ncpus & UINT_MAX);



	sz = nr * sizeof(char *);

	addr = calloc(1, sizeof(*tp) + 2 * sz);

	if (has_die)

		nr_addr = 3;

	else

		nr_addr = 2;

	addr = calloc(1, sizeof(*tp) + nr_addr * sz);

	if (!addr)

		goto out_free;
@@ -134,6 +196,10 @@ struct cpu_topology *cpu_topology__new(void) 
	addr += sizeof(*tp);

	tp->core_siblings = addr;

	addr += sz;

	if (has_die) {

		tp->die_siblings = addr;

		addr += sz;

	}

	tp->thread_siblings = addr;



	for (i = 0; i < nr; i++) {

tools/perf/util/cputopo.h

+2 −0
Original line number Diff line number Diff line
@@ -7,8 +7,10 @@ 


struct cpu_topology {

	u32	  core_sib;

	u32	  die_sib;

	u32	  thread_sib;

	char	**core_siblings;

	char	**die_siblings;

	char	**thread_siblings;

};

tools/perf/util/env.c

+1 −0
Original line number Diff line number Diff line
@@ -246,6 +246,7 @@ int perf_env__read_cpu_topology_map(struct perf_env *env) 
	for (cpu = 0; cpu < nr_cpus; ++cpu) {

		env->cpu[cpu].core_id	= cpu_map__get_core_id(cpu);

		env->cpu[cpu].socket_id	= cpu_map__get_socket_id(cpu);

		env->cpu[cpu].die_id	= cpu_map__get_die_id(cpu);

	}



	env->nr_cpus_avail = nr_cpus;

tools/perf/util/env.h

+3 −0
Original line number Diff line number Diff line
@@ -9,6 +9,7 @@ 


struct cpu_topology_map {

	int	socket_id;

	int	die_id;

	int	core_id;

};
@@ -49,6 +50,7 @@ struct perf_env { 


	int			nr_cmdline;

	int			nr_sibling_cores;

	int			nr_sibling_dies;

	int			nr_sibling_threads;

	int			nr_numa_nodes;

	int			nr_memory_nodes;
@@ -57,6 +59,7 @@ struct perf_env { 
	char			*cmdline;

	const char		**cmdline_argv;

	char			*sibling_cores;

	char			*sibling_dies;

	char			*sibling_threads;

	char			*pmu_mappings;

	struct cpu_topology_map	*cpu;

CRA Git | Maintained and supported by SUSTech CRA and CCSE