perf record: Adapt affinity to machines with #CPUs > 1K

Use struct mmap_cpu_mask type for the tool's thread and mmap data
buffers to overcome current 1024 CPUs mask size limitation of cpu_set_t
type.

Currently glibc's cpu_set_t type has an internal mask size limit of 1024
CPUs.

Moving to the 'struct mmap_cpu_mask' type allows overcoming that limit.

The tools bitmap API is used to manipulate objects of 'struct mmap_cpu_mask'
type.

Committer notes:

To print the 'nbits' struct member we must use %zd, since it is a
size_t, this fixes the build in some toolchains/arches.

Reported-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/96d7e2ff-ce8b-c1e0-d52c-aa59ea96f0ea@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 22 insertions, 6 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index fb19ef63cc35..4c301466101b 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 */
 };
 
@@ -961,10 +962,15 @@ static struct perf_event_header finished_round_event = {
 static void record__adjust_affinity(struct record *rec, struct mmap *map)
 {
 	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);
+		if (verbose == 2)
+			mmap_cpu_mask__scnprintf(&rec->affinity_mask, "thread");
 	}
 }
 
@@ -2433,7 +2439,6 @@ 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();
@@ -2499,6 +2504,16 @@ int cmd_record(int argc, const char **argv)
 
 	symbol__init(NULL);
 
+	if (rec->opts.affinity != PERF_AFFINITY_SYS) {
+		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 %zd cpus\n", rec->affinity_mask.nbits);
+			return -ENOMEM;
+		}
+		pr_debug2("thread mask[%zd]: empty\n", rec->affinity_mask.nbits);
+	}
+
 	err = record__auxtrace_init(rec);
 	if (err)
 		goto out;
@@ -2613,6 +2628,7 @@ int cmd_record(int argc, const char **argv)
 
 	err = __cmd_record(&record, argc, argv);
 out:
+	bitmap_free(rec->affinity_mask.bits);
 	evlist__delete(rec->evlist);
 	symbol__exit();
 	auxtrace_record__free(rec->itr);