[PATCH v2 18/27] nvdimm/ocxl: Add an IOCTL to report controller statistics

["Alastair D'Silva" <alastair@au1.ibm.com>]

From: Alastair D'Silva <alastair@d-silva.org>

The controller can report a number of statistics that are useful
in evaluating the performance and reliability of the card.

This patch exposes this information via an IOCTL.

Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
 drivers/nvdimm/ocxl/scm.c      | 185 +++++++++++++++++++++++++++++++++
 include/uapi/nvdimm/ocxl-scm.h |  17 +++
 2 files changed, 202 insertions(+)

diff --git a/drivers/nvdimm/ocxl/scm.c b/drivers/nvdimm/ocxl/scm.c
index a520f209d626..54a2bac1cab7 100644
--- a/drivers/nvdimm/ocxl/scm.c
+++ b/drivers/nvdimm/ocxl/scm.c
@@ -806,6 +806,186 @@ static int scm_ioctl_controller_dump_complete(struct scm_data *scm_data)
 				    GLOBAL_MMIO_HCI_CONTROLLER_DUMP_COLLECTED);
 }
 
+/**
+ * scm_controller_stats_header_parse() - Parse the first 64 bits of the controller stats admin command response
+ * @scm_data: the SCM metadata
+ * @length: out, returns the number of bytes in the response (excluding the 64 bit header)
+ */
+static int scm_controller_stats_header_parse(struct scm_data *scm_data,
+	u32 *length)
+{
+	int rc;
+	u64 val;
+
+	u16 data_identifier;
+	u32 data_length;
+
+	rc = ocxl_global_mmio_read64(scm_data->ocxl_afu,
+				     scm_data->admin_command.data_offset,
+				     OCXL_LITTLE_ENDIAN, &val);
+	if (rc)
+		return rc;
+
+	data_identifier = val >> 48;
+	data_length = val & 0xFFFFFFFF;
+
+	if (data_identifier != 0x4353) {
+		dev_err(&scm_data->dev,
+			"Bad data identifier for controller stats, expected 'CS', got '%-.*s'\n",
+			2, (char *)&data_identifier);
+		return -EINVAL;
+	}
+
+	*length = data_length;
+	return 0;
+}
+
+static int scm_ioctl_controller_stats(struct scm_data *scm_data,
+				      struct scm_ioctl_controller_stats __user *uarg)
+{
+	struct scm_ioctl_controller_stats args;
+	u32 length;
+	int rc;
+	u64 val;
+
+	memset(&args, '\0', sizeof(args));
+
+	mutex_lock(&scm_data->admin_command.lock);
+
+	rc = scm_admin_command_request(scm_data, ADMIN_COMMAND_CONTROLLER_STATS);
+	if (rc)
+		goto out;
+
+	rc = ocxl_global_mmio_write64(scm_data->ocxl_afu,
+				      scm_data->admin_command.request_offset + 0x08,
+				      OCXL_LITTLE_ENDIAN, 0);
+	if (rc)
+		goto out;
+
+	rc = scm_admin_command_execute(scm_data);
+	if (rc)
+		goto out;
+
+
+	rc = scm_admin_command_complete_timeout(scm_data,
+						ADMIN_COMMAND_CONTROLLER_STATS);
+	if (rc < 0) {
+		dev_warn(&scm_data->dev, "Controller stats timed out\n");
+		goto out;
+	}
+
+	rc = scm_admin_response(scm_data);
+	if (rc < 0)
+		goto out;
+	if (rc != STATUS_SUCCESS) {
+		scm_warn_status(scm_data,
+				"Unexpected status from controller stats", rc);
+		goto out;
+	}
+
+	rc = scm_controller_stats_header_parse(scm_data, &length);
+	if (rc)
+		goto out;
+
+	if (length != 0x140)
+		scm_warn_status(scm_data,
+				"Unexpected length for controller stats data, expected 0x140, got 0x%x",
+				length);
+
+	rc = ocxl_global_mmio_read64(scm_data->ocxl_afu,
+				     scm_data->admin_command.data_offset + 0x08 + 0x08,
+				     OCXL_LITTLE_ENDIAN, &val);
+	if (rc)
+		goto out;
+
+	args.reset_count = val >> 32;
+	args.reset_uptime = val & 0xFFFFFFFF;
+
+	rc = ocxl_global_mmio_read64(scm_data->ocxl_afu,
+				     scm_data->admin_command.data_offset + 0x08 + 0x10,
+				     OCXL_LITTLE_ENDIAN, &val);
+	if (rc)
+		goto out;
+
+	args.power_on_uptime = val >> 32;
+
+	rc = ocxl_global_mmio_read64(scm_data->ocxl_afu,
+				     scm_data->admin_command.data_offset + 0x08 + 0x40 + 0x08,
+				     OCXL_LITTLE_ENDIAN, &args.host_load_count);
+	if (rc)
+		goto out;
+
+	rc = ocxl_global_mmio_read64(scm_data->ocxl_afu,
+				     scm_data->admin_command.data_offset + 0x08 + 0x40 + 0x10,
+				     OCXL_LITTLE_ENDIAN, &args.host_store_count);
+	if (rc)
+		goto out;
+
+	rc = ocxl_global_mmio_read64(scm_data->ocxl_afu,
+				     scm_data->admin_command.data_offset + 0x08 + 0x40 + 0x18,
+				     OCXL_LITTLE_ENDIAN, &args.media_read_count);
+	if (rc)
+		goto out;
+
+	rc = ocxl_global_mmio_read64(scm_data->ocxl_afu,
+				     scm_data->admin_command.data_offset + 0x08 + 0x40 + 0x20,
+				     OCXL_LITTLE_ENDIAN, &args.media_write_count);
+	if (rc)
+		goto out;
+
+	rc = ocxl_global_mmio_read64(scm_data->ocxl_afu,
+				     scm_data->admin_command.data_offset + 0x08 + 0x40 + 0x28,
+				     OCXL_LITTLE_ENDIAN, &args.cache_hit_count);
+	if (rc)
+		goto out;
+
+	rc = ocxl_global_mmio_read64(scm_data->ocxl_afu,
+				     scm_data->admin_command.data_offset + 0x08 + 0x40 + 0x30,
+				     OCXL_LITTLE_ENDIAN, &args.cache_miss_count);
+	if (rc)
+		goto out;
+
+	rc = ocxl_global_mmio_read64(scm_data->ocxl_afu,
+				     scm_data->admin_command.data_offset + 0x08 + 0x40 + 0x38,
+				     OCXL_LITTLE_ENDIAN, &args.media_read_latency);
+	if (rc)
+		goto out;
+
+	rc = ocxl_global_mmio_read64(scm_data->ocxl_afu,
+				     scm_data->admin_command.data_offset + 0x08 + 0x40 + 0x40,
+				     OCXL_LITTLE_ENDIAN, &args.media_write_latency);
+	if (rc)
+		goto out;
+
+	rc = ocxl_global_mmio_read64(scm_data->ocxl_afu,
+				     scm_data->admin_command.data_offset + 0x08 + 0x40 + 0x48,
+				     OCXL_LITTLE_ENDIAN, &args.cache_read_latency);
+	if (rc)
+		goto out;
+
+	rc = ocxl_global_mmio_read64(scm_data->ocxl_afu,
+				     scm_data->admin_command.data_offset + 0x08 + 0x40 + 0x50,
+				     OCXL_LITTLE_ENDIAN, &args.cache_write_latency);
+	if (rc)
+		goto out;
+
+	if (copy_to_user(uarg, &args, sizeof(args))) {
+		rc = -EFAULT;
+		goto out;
+	}
+
+	rc = scm_admin_response_handled(scm_data);
+	if (rc)
+		goto out;
+
+	rc = 0;
+	goto out;
+
+out:
+	mutex_unlock(&scm_data->admin_command.lock);
+	return rc;
+}
+
 static long scm_file_ioctl(struct file *file, unsigned int cmd,
 			   unsigned long args)
 {
@@ -830,6 +1010,11 @@ static long scm_file_ioctl(struct file *file, unsigned int cmd,
 	case SCM_IOCTL_CONTROLLER_DUMP_COMPLETE:
 		rc = scm_ioctl_controller_dump_complete(scm_data);
 		break;
+
+	case SCM_IOCTL_CONTROLLER_STATS:
+		rc = scm_ioctl_controller_stats(scm_data,
+						(struct scm_ioctl_controller_stats __user *)args);
+		break;
 	}
 
 	return rc;
diff --git a/include/uapi/nvdimm/ocxl-scm.h b/include/uapi/nvdimm/ocxl-scm.h
index abd2dc9ea112..0a5de46c5acd 100644
--- a/include/uapi/nvdimm/ocxl-scm.h
+++ b/include/uapi/nvdimm/ocxl-scm.h
@@ -50,6 +50,22 @@ struct scm_ioctl_controller_dump_data {
 	__u64 reserved[8];
 };
 
+struct scm_ioctl_controller_stats {
+	__u32 reset_count;
+	__u32 reset_uptime; // seconds
+	__u32 power_on_uptime; // seconds
+	__u64 host_load_count;
+	__u64 host_store_count;
+	__u64 media_read_count;
+	__u64 media_write_count;
+	__u64 cache_hit_count;
+	__u64 cache_miss_count;
+	__u64 media_read_latency; // nanoseconds
+	__u64 media_write_latency; // nanoseconds
+	__u64 cache_read_latency; // nanoseconds
+	__u64 cache_write_latency; // nanoseconds
+};
+
 /* ioctl numbers */
 #define SCM_MAGIC 0x5C
 /* SCM devices */
@@ -57,5 +73,6 @@ struct scm_ioctl_controller_dump_data {
 #define SCM_IOCTL_CONTROLLER_DUMP _IO(SCM_MAGIC, 0x02)
 #define SCM_IOCTL_CONTROLLER_DUMP_DATA _IOWR(SCM_MAGIC, 0x03, struct scm_ioctl_controller_dump_data)
 #define SCM_IOCTL_CONTROLLER_DUMP_COMPLETE _IO(SCM_MAGIC, 0x04)
+#define SCM_IOCTL_CONTROLLER_STATS _IO(SCM_MAGIC, 0x05)
 
 #endif /* _UAPI_OCXL_SCM_H */
-- 
2.23.0
_______________________________________________
Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org
To unsubscribe send an email to linux-nvdimm-leave@lists.01.org