tools/perf: Fix out of bound access to cpu mask array

The cpu mask init code in "record__mmap_cpu_mask_init" function access
"bits" array part of "struct mmap_cpu_mask".  The size of this array is
the value from cpu__max_cpu().cpu.  This array is used to contain the
cpumask value for each cpu. While setting bit for each cpu, it calls
"set_bit" function which access index in "bits" array.

If we provide a command line option to -C which is greater than the
number of CPU's present in the system, the set_bit could access an array
member which is out-of the array size. This is because currently, there
is no boundary check for the CPU. This will result in seg fault:

<<>>
  ./perf record -C 12341234 ls
  Perf can support 2048 CPUs. Consider raising MAX_NR_CPUS
  Segmentation fault (core dumped)
<<>>

Debugging with gdb, points to function flow as below:

<<>>
  set_bit
  record__mmap_cpu_mask_init
  record__init_thread_default_masks
  record__init_thread_masks
  cmd_record
<<>>

Fix this by adding boundary check for the array.

After the patch:

<<>>
./perf record -C 12341234 ls
  Perf can support 2048 CPUs. Consider raising MAX_NR_CPUS
  Failed to initialize parallel data streaming masks
<<>>

With this fix, if -C is given a non-exsiting CPU, perf
record will fail with:

<<>>
  ./perf record -C 50 ls
  Failed to initialize parallel data streaming masks
<<>>
Reported-by: Nageswara R Sastry <rnsastry@linux.ibm.com>
Signed-off-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Nageswara R Sastry <rnsastry@linux.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20220905141929.7171-2-atrajeev@linux.vnet.ibm.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-record.c

@@ -3358,16 +3358,22 @@ static struct option __record_options[] = {
 
 struct option *record_options = __record_options;
 
-static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cpu_map *cpus)
+static int record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cpu_map *cpus)
 {
 	struct perf_cpu cpu;
 	int idx;
 
 	if (cpu_map__is_dummy(cpus))
-		return;
+		return 0;
 
-	perf_cpu_map__for_each_cpu(cpu, idx, cpus)
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+		/* Return ENODEV is input cpu is greater than max cpu */
+		if ((unsigned long)cpu.cpu > mask->nbits)
+			return -ENODEV;
 		set_bit(cpu.cpu, mask->bits);
+	}
+
+	return 0;
 }
 
 static int record__mmap_cpu_mask_init_spec(struct mmap_cpu_mask *mask, const char *mask_spec)
@@ -3379,7 +3385,9 @@ static int record__mmap_cpu_mask_init_spec(struct mmap_cpu_mask *mask, const cha
 		return -ENOMEM;
 
 	bitmap_zero(mask->bits, mask->nbits);
-	record__mmap_cpu_mask_init(mask, cpus);
+	if (record__mmap_cpu_mask_init(mask, cpus))
+		return -ENODEV;
+
 	perf_cpu_map__put(cpus);
 
 	return 0;
@@ -3461,7 +3469,12 @@ static int record__init_thread_masks_spec(struct record *rec, struct perf_cpu_ma
 		pr_err("Failed to allocate CPUs mask\n");
 		return ret;
 	}
-	record__mmap_cpu_mask_init(&cpus_mask, cpus);
+
+	ret = record__mmap_cpu_mask_init(&cpus_mask, cpus);
+	if (ret) {
+		pr_err("Failed to init cpu mask\n");
+		goto out_free_cpu_mask;
+	}
 
 	ret = record__thread_mask_alloc(&full_mask, cpu__max_cpu().cpu);
 	if (ret) {
@@ -3702,7 +3715,8 @@ static int record__init_thread_default_masks(struct record *rec, struct perf_cpu
 	if (ret)
 		return ret;
 
-	record__mmap_cpu_mask_init(&rec->thread_masks->maps, cpus);
+	if (record__mmap_cpu_mask_init(&rec->thread_masks->maps, cpus))
+		return -ENODEV;
 
 	rec->nr_threads = 1;