| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Wed, 20 Nov 2019 12:38:57 +0300
From: Alexey Budankov <alexey.budankov@...ux.intel.com>
To: Arnaldo Carvalho de Melo <acme@...nel.org>
Cc: Jiri Olsa <jolsa@...hat.com>, Namhyung Kim <namhyung@...nel.org>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Andi Kleen <ak@...ux.intel.com>,
linux-kernel <linux-kernel@...r.kernel.org>
Subject: [PATCH v1 3/3] perf record: adapt affinity to machines with #CPUs >
1K
Use struct mmap_cpu_mask type for tool's thread and mmap data
buffers to overcome current 1024 CPUs mask size limitation of
cpu_set_t type.
Currently glibc cpu_set_t type has internal mask size limit
of 1024 CPUs. Moving to struct mmap_cpu_mask type allows
overcoming that limit. tools bitmap API is used to manipulate
objects of struct mmap_cpu_mask type.
Reported-by: Andi Kleen <ak@...ux.intel.com>
Signed-off-by: Alexey Budankov <alexey.budankov@...ux.intel.com>
---
tools/perf/builtin-record.c | 28 ++++++++++++++++++++++------
tools/perf/util/mmap.c | 28 ++++++++++++++++++++++------
tools/perf/util/mmap.h | 2 +-
3 files changed, 45 insertions(+), 13 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index b95c000c1ed9..238688516bc8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -62,6 +62,7 @@
#include <linux/string.h>
#include <linux/time64.h>
#include <linux/zalloc.h>
+#include <linux/bitmap.h>
struct switch_output {
bool enabled;
@@ -93,7 +94,7 @@ struct record {
bool timestamp_boundary;
struct switch_output switch_output;
unsigned long long samples;
- cpu_set_t affinity_mask;
+ struct mmap_cpu_mask affinity_mask;
unsigned long output_max_size; /* = 0: unlimited */
};
@@ -951,13 +952,21 @@ static struct perf_event_header finished_round_event = {
.type = PERF_RECORD_FINISHED_ROUND,
};
+#define MASK_SIZE 1023
static void record__adjust_affinity(struct record *rec, struct mmap *map)
{
+ char mask[MASK_SIZE + 1] = {0};
+
if (rec->opts.affinity != PERF_AFFINITY_SYS &&
- !CPU_EQUAL(&rec->affinity_mask, &map->affinity_mask)) {
- CPU_ZERO(&rec->affinity_mask);
- CPU_OR(&rec->affinity_mask, &rec->affinity_mask, &map->affinity_mask);
- sched_setaffinity(0, sizeof(rec->affinity_mask), &rec->affinity_mask);
+ !bitmap_equal(rec->affinity_mask.bits, map->affinity_mask.bits,
+ rec->affinity_mask.nbits)) {
+ bitmap_zero(rec->affinity_mask.bits, rec->affinity_mask.nbits);
+ bitmap_or(rec->affinity_mask.bits, rec->affinity_mask.bits,
+ map->affinity_mask.bits, rec->affinity_mask.nbits);
+ sched_setaffinity(0, mmap_cpu_mask_bytes(&rec->affinity_mask),
+ (cpu_set_t *)rec->affinity_mask.bits);
+ bitmap_scnprintf(rec->affinity_mask.bits, rec->affinity_mask.nbits, mask, MASK_SIZE);
+ pr_debug("thread mask[%ld]: %s\n", rec->affinity_mask.nbits, mask);
}
}
@@ -2389,7 +2398,6 @@ int cmd_record(int argc, const char **argv)
# undef REASON
#endif
- CPU_ZERO(&rec->affinity_mask);
rec->opts.affinity = PERF_AFFINITY_SYS;
rec->evlist = evlist__new();
@@ -2405,6 +2413,14 @@ int cmd_record(int argc, const char **argv)
if (quiet)
perf_quiet_option();
+ rec->affinity_mask.nbits = cpu__max_cpu();
+ rec->affinity_mask.bits = bitmap_alloc(rec->affinity_mask.nbits);
+ if (!rec->affinity_mask.bits) {
+ pr_err("Failed to allocate thread mask for %ld cpus\n", rec->affinity_mask.nbits);
+ return -ENOMEM;
+ }
+ pr_debug("thread mask[%ld]: empty\n", rec->affinity_mask.nbits);
+
/* Make system wide (-a) the default target. */
if (!argc && target__none(&rec->opts.target))
rec->opts.target.system_wide = true;
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 063d1b93c53d..070b1873cd45 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -23,6 +23,7 @@
#include "mmap.h"
#include "../perf.h"
#include <internal/lib.h> /* page_size */
+#include <linux/bitmap.h>
size_t mmap__mmap_len(struct mmap *map)
{
@@ -215,7 +216,7 @@ void mmap__munmap(struct mmap *map)
auxtrace_mmap__munmap(&map->auxtrace_mmap);
}
-static void build_node_mask(int node, cpu_set_t *mask)
+static void build_node_mask(int node, struct mmap_cpu_mask *mask)
{
int c, cpu, nr_cpus;
const struct perf_cpu_map *cpu_map = NULL;
@@ -228,28 +229,43 @@ static void build_node_mask(int node, cpu_set_t *mask)
for (c = 0; c < nr_cpus; c++) {
cpu = cpu_map->map[c]; /* map c index to online cpu index */
if (cpu__get_node(cpu) == node)
- CPU_SET(cpu, mask);
+ set_bit(cpu, mask->bits);
}
}
-static void perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp)
+static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp)
{
- CPU_ZERO(&map->affinity_mask);
+ map->affinity_mask.nbits = cpu__max_cpu();
+ map->affinity_mask.bits = bitmap_alloc(map->affinity_mask.nbits);
+ if (!map->affinity_mask.bits)
+ return 1;
+
if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1)
build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask);
else if (mp->affinity == PERF_AFFINITY_CPU)
- CPU_SET(map->core.cpu, &map->affinity_mask);
+ set_bit(map->core.cpu, map->affinity_mask.bits);
+
+ return 0;
}
+#define MASK_SIZE 1023
int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu)
{
+ char mask[MASK_SIZE + 1] = {0};
+
if (perf_mmap__mmap(&map->core, &mp->core, fd, cpu)) {
pr_debug2("failed to mmap perf event ring buffer, error %d\n",
errno);
return -1;
}
- perf_mmap__setup_affinity_mask(map, mp);
+ if (perf_mmap__setup_affinity_mask(map, mp)) {
+ pr_debug2("failed to alloc mmap affinity mask, error %d\n",
+ errno);
+ return -1;
+ }
+ bitmap_scnprintf(map->affinity_mask.bits, map->affinity_mask.nbits, mask, MASK_SIZE);
+ pr_debug("%p: mmap mask[%ld]: %s\n", map, map->affinity_mask.nbits, mask);
map->core.flush = mp->flush;
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index a218a0eb1466..0a644e112ac6 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -40,7 +40,7 @@ struct mmap {
int nr_cblocks;
} aio;
#endif
- cpu_set_t affinity_mask;
+ struct mmap_cpu_mask affinity_mask;
void *data;
int comp_level;
};
--
2.20.1
Powered by blists - more mailing lists