selftests/resctrl: Exclude shareable bits from schemata in CAT test

CAT test doesn't take shareable bits into account, i.e., the test might
be sharing cache with some devices (e.g., graphics).

Introduce get_mask_no_shareable() and use it to provision an
environment for CAT test where the allocated LLC is isolated better.
Excluding shareable_bits may create hole(s) into the cbm_mask, thus add
a new helper count_contiguous_bits() to find the longest contiguous set
of CBM bits.

create_bit_mask() is needed by an upcoming CAT test rewrite so make it
available in resctrl.h right away.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>

tools/testing/selftests/resctrl/cat_test.c

@@ -89,15 +89,19 @@ void cat_test_cleanup(void)
 
 int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 {
+	unsigned long full_cache_mask, long_mask;
 	unsigned long l_mask, l_mask_1;
 	int ret, pipefd[2], sibling_cpu_no;
 	unsigned long cache_total_size = 0;
-	unsigned long long_mask;
 	int count_of_bits;
 	char pipe_message;
 	size_t span;
 
-	ret = get_full_cbm(cache_type, &long_mask);
+	ret = get_full_cbm(cache_type, &full_cache_mask);
+	if (ret)
+		return ret;
+	/* Get the largest contiguous exclusive portion of the cache */
+	ret = get_mask_no_shareable(cache_type, &long_mask);
 	if (ret)
 		return ret;
 
@@ -136,7 +140,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 	/* Set param values for parent thread which will be allocated bitmask
 	 * with (max_bits - n) bits
 	 */
-	span = cache_portion_size(cache_total_size, l_mask, long_mask);
+	span = cache_portion_size(cache_total_size, l_mask, full_cache_mask);
 	strcpy(param.ctrlgrp, "c2");
 	strcpy(param.mongrp, "m2");
 	strcpy(param.filename, RESULT_FILE_NAME2);
@@ -158,7 +162,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 		param.mask = l_mask_1;
 		strcpy(param.ctrlgrp, "c1");
 		strcpy(param.mongrp, "m1");
-		span = cache_portion_size(cache_total_size, l_mask_1, long_mask);
+		span = cache_portion_size(cache_total_size, l_mask_1, full_cache_mask);
 		strcpy(param.filename, RESULT_FILE_NAME1);
 		param.num_of_runs = 0;
 		param.cpu_no = sibling_cpu_no;

tools/testing/selftests/resctrl/resctrl.h

@@ -98,7 +98,9 @@ void tests_cleanup(void);
 void mbm_test_cleanup(void);
 int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd);
 void mba_test_cleanup(void);
+unsigned long create_bit_mask(unsigned int start, unsigned int len);
 int get_full_cbm(const char *cache_type, unsigned long *mask);
+int get_mask_no_shareable(const char *cache_type, unsigned long *mask);
 int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size);
 void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
 int signal_handler_register(void);

tools/testing/selftests/resctrl/resctrlfs.c

@@ -228,6 +228,44 @@ static int get_bit_mask(const char *filename, unsigned long *mask)
 	return 0;
 }
 
+/*
+ * create_bit_mask- Create bit mask from start, len pair
+ * @start:	LSB of the mask
+ * @len		Number of bits in the mask
+ */
+unsigned long create_bit_mask(unsigned int start, unsigned int len)
+{
+	return ((1UL << len) - 1UL) << start;
+}
+
+/*
+ * count_contiguous_bits - Returns the longest train of bits in a bit mask
+ * @val		A bit mask
+ * @start	The location of the least-significant bit of the longest train
+ *
+ * Return:	The length of the contiguous bits in the longest train of bits
+ */
+static unsigned int count_contiguous_bits(unsigned long val, unsigned int *start)
+{
+	unsigned long last_val;
+	unsigned int count = 0;
+
+	while (val) {
+		last_val = val;
+		val &= (val >> 1);
+		count++;
+	}
+
+	if (start) {
+		if (count)
+			*start = ffsl(last_val) - 1;
+		else
+			*start = 0;
+	}
+
+	return count;
+}
+
 /*
  * get_full_cbm - Get full Cache Bit Mask (CBM)
  * @cache_type:	Cache type as "L2" or "L3"
@@ -254,6 +292,57 @@ int get_full_cbm(const char *cache_type, unsigned long *mask)
 	return 0;
 }
 
+/*
+ * get_shareable_mask - Get shareable mask from shareable_bits
+ * @cache_type:		Cache type as "L2" or "L3"
+ * @shareable_mask:	Shareable mask returned as unsigned long
+ *
+ * Return: = 0 on success, < 0 on failure.
+ */
+static int get_shareable_mask(const char *cache_type, unsigned long *shareable_mask)
+{
+	char mask_path[PATH_MAX];
+
+	if (!cache_type)
+		return -1;
+
+	snprintf(mask_path, sizeof(mask_path), "%s/%s/shareable_bits",
+		 INFO_PATH, cache_type);
+
+	return get_bit_mask(mask_path, shareable_mask);
+}
+
+/*
+ * get_mask_no_shareable - Get Cache Bit Mask (CBM) without shareable bits
+ * @cache_type:		Cache type as "L2" or "L3"
+ * @mask:		The largest exclusive portion of the cache out of the
+ *			full CBM, returned as unsigned long
+ *
+ * Parts of a cache may be shared with other devices such as GPU. This function
+ * calculates the largest exclusive portion of the cache where no other devices
+ * besides CPU have access to the cache portion.
+ *
+ * Return: = 0 on success, < 0 on failure.
+ */
+int get_mask_no_shareable(const char *cache_type, unsigned long *mask)
+{
+	unsigned long full_mask, shareable_mask;
+	unsigned int start, len;
+
+	if (get_full_cbm(cache_type, &full_mask) < 0)
+		return -1;
+	if (get_shareable_mask(cache_type, &shareable_mask) < 0)
+		return -1;
+
+	len = count_contiguous_bits(full_mask & ~shareable_mask, &start);
+	if (!len)
+		return -1;
+
+	*mask = create_bit_mask(start, len);
+
+	return 0;
+}
+
 /*
  * get_core_sibling - Get sibling core id from the same socket for given CPU
  * @cpu_no:	CPU number