drm/amdkfd: Add number of watch points to topology

This patch adds the number of watch points to the node capabilities in the
topology module
Signed-off-by: Alexey Skidanov <Alexey.Skidanov@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@amd.com>

drivers/gpu/drm/amd/amdkfd/kfd_device.c

@@ -32,6 +32,7 @@
 static const struct kfd_device_info kaveri_device_info = {
 	.max_pasid_bits = 16,
 	.ih_ring_entry_size = 4 * sizeof(uint32_t),
+	.num_of_watch_points = 4,
 	.mqd_size_aligned = MQD_SIZE_ALIGNED
 };
 

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -107,6 +107,7 @@ enum cache_policy {
 struct kfd_device_info {
 	unsigned int max_pasid_bits;
 	size_t ih_ring_entry_size;
+	uint8_t num_of_watch_points;
 	uint16_t mqd_size_aligned;
 };
 

drivers/gpu/drm/amd/amdkfd/kfd_topology.c

@@ -27,6 +27,7 @@
 #include <linux/acpi.h>
 #include <linux/hash.h>
 #include <linux/cpufreq.h>
+#include <linux/log2.h>
 
 #include "kfd_priv.h"
 #include "kfd_crat.h"
@@ -630,10 +631,10 @@ static struct kobj_type cache_type = {
 static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 		char *buffer)
 {
-	ssize_t ret;
 	struct kfd_topology_device *dev;
 	char public_name[KFD_TOPOLOGY_PUBLIC_NAME_SIZE];
 	uint32_t i;
+	uint32_t log_max_watch_addr;
 
 	/* Making sure that the buffer is an empty string */
 	buffer[0] = 0;
@@ -641,8 +642,10 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 	if (strcmp(attr->name, "gpu_id") == 0) {
 		dev = container_of(attr, struct kfd_topology_device,
 				attr_gpuid);
-		ret = sysfs_show_32bit_val(buffer, dev->gpu_id);
-	} else if (strcmp(attr->name, "name") == 0) {
+		return sysfs_show_32bit_val(buffer, dev->gpu_id);
+	}
+
+	if (strcmp(attr->name, "name") == 0) {
 		dev = container_of(attr, struct kfd_topology_device,
 				attr_name);
 		for (i = 0; i < KFD_TOPOLOGY_PUBLIC_NAME_SIZE; i++) {
@@ -652,8 +655,9 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 				break;
 		}
 		public_name[KFD_TOPOLOGY_PUBLIC_NAME_SIZE-1] = 0x0;
-		ret = sysfs_show_str_val(buffer, public_name);
-	} else {
+		return sysfs_show_str_val(buffer, public_name);
+	}
+
 	dev = container_of(attr, struct kfd_topology_device,
 			attr_props);
 	sysfs_show_32bit_prop(buffer, "cpu_cores_count",
@@ -708,6 +712,19 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 			dev->node_props.location_id);
 
 	if (dev->gpu) {
+		log_max_watch_addr =
+			__ilog2_u32(dev->gpu->device_info->num_of_watch_points);
+
+		if (log_max_watch_addr) {
+			dev->node_props.capability |=
+					HSA_CAP_WATCH_POINTS_SUPPORTED;
+
+			dev->node_props.capability |=
+				((log_max_watch_addr <<
+					HSA_CAP_WATCH_POINTS_TOTALBITS_SHIFT) &
+				HSA_CAP_WATCH_POINTS_TOTALBITS_MASK);
+		}
+
 		sysfs_show_32bit_prop(buffer, "max_engine_clk_fcompute",
 				kfd2kgd->get_max_engine_clock_in_mhz(
 					dev->gpu->kgd));
@@ -718,14 +735,10 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 				kfd2kgd->get_fw_version(
 						dev->gpu->kgd,
 						KGD_ENGINE_MEC1));
-
 	}
 
-		ret = sysfs_show_32bit_prop(buffer, "max_engine_clk_ccompute",
+	return sysfs_show_32bit_prop(buffer, "max_engine_clk_ccompute",
 					cpufreq_quick_get_max(0)/1000);
-	}
-
-	return ret;
 }
 
 static const struct sysfs_ops node_ops = {