nvme: add csi, ms and nuse to sysfs

libnvme is using the sysfs for enumarating the nvme resources. Though
there are few missing attritbutes in the sysfs. For these libnvme issues
commands during discovering.

As the kernel already knows all these attributes and we would like to
avoid libnvme to issue commands all the time, expose these missing
attributes.

The nuse value is updated on request because the nuse is a volatile
value. Since any user can read the sysfs attribute, a very simple rate
limit is added (update once every 5 seconds). A more sophisticated
update strategy can be added later if there is actually a need for it.

Reviewed-by: Christoph Hellwig <[email protected]>
Reviewed-by: Sagi Grimberg <[email protected]>
Reviewed-by: Hannes Reinecke <[email protected]>
Signed-off-by: Daniel Wagner <[email protected]>
Signed-off-by: Keith Busch <[email protected]>

Author: igaw

drivers/nvme/host/core.c

@@ -20,6 +20,7 @@
 #include <linux/ptrace.h>
 #include <linux/nvme_ioctl.h>
 #include <linux/pm_qos.h>
+#include <linux/ratelimit.h>
 #include <asm/unaligned.h>
 
 #include "nvme.h"
@@ -1449,7 +1450,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl,
 	return status;
 }
 
-static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
+int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 			struct nvme_id_ns **id)
 {
 	struct nvme_command c = { };
@@ -2040,6 +2041,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	blk_mq_freeze_queue(ns->disk->queue);
 	lbaf = nvme_lbaf_index(id->flbas);
 	ns->head->lba_shift = id->lbaf[lbaf].ds;
+	ns->head->nuse = le64_to_cpu(id->nuse);
 	nvme_set_queue_limits(ns->ctrl, ns->queue);
 
 	ret = nvme_configure_metadata(ns->ctrl, ns->head, id);
@@ -3420,6 +3422,8 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 	head->ns_id = info->nsid;
 	head->ids = info->ids;
 	head->shared = info->is_shared;
+	ratelimit_state_init(&head->rs_nuse, 5 * HZ, 1);
+	ratelimit_set_flags(&head->rs_nuse, RATELIMIT_MSG_ON_RELEASE);
 	kref_init(&head->ref);
 
 	if (head->ids.csi) {

drivers/nvme/host/nvme.h

@@ -16,6 +16,7 @@
 #include <linux/rcupdate.h>
 #include <linux/wait.h>
 #include <linux/t10-pi.h>
+#include <linux/ratelimit_types.h>
 
 #include <trace/events/block.h>
 
@@ -451,13 +452,16 @@ struct nvme_ns_head {
 	u16			pi_size;
 	u16			sgs;
 	u32			sws;
+	u64			nuse;
 	u8			pi_type;
 	u8			guard_type;
 #ifdef CONFIG_BLK_DEV_ZONED
 	u64			zsze;
 #endif
 	unsigned long		features;
 
+	struct ratelimit_state	rs_nuse;
+
 	struct cdev		cdev;
 	struct device		cdev_device;
 
@@ -862,6 +866,8 @@ int nvme_ns_chr_uring_cmd(struct io_uring_cmd *ioucmd,
 		unsigned int issue_flags);
 int nvme_ns_head_chr_uring_cmd(struct io_uring_cmd *ioucmd,
 		unsigned int issue_flags);
+int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
+		struct nvme_id_ns **id);
 int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 int nvme_dev_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags);
 

drivers/nvme/host/sysfs.c

@@ -114,12 +114,97 @@ static ssize_t nsid_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(nsid);
 
+static ssize_t csi_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	return sysfs_emit(buf, "%u\n", dev_to_ns_head(dev)->ids.csi);
+}
+static DEVICE_ATTR_RO(csi);
+
+static ssize_t metadata_bytes_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%u\n", dev_to_ns_head(dev)->ms);
+}
+static DEVICE_ATTR_RO(metadata_bytes);
+
+static int ns_head_update_nuse(struct nvme_ns_head *head)
+{
+	struct nvme_id_ns *id;
+	struct nvme_ns *ns;
+	int srcu_idx, ret = -EWOULDBLOCK;
+
+	/* Avoid issuing commands too often by rate limiting the update */
+	if (!__ratelimit(&head->rs_nuse))
+		return 0;
+
+	srcu_idx = srcu_read_lock(&head->srcu);
+	ns = nvme_find_path(head);
+	if (!ns)
+		goto out_unlock;
+
+	ret = nvme_identify_ns(ns->ctrl, head->ns_id, &id);
+	if (ret)
+		goto out_unlock;
+
+	head->nuse = le64_to_cpu(id->nuse);
+	kfree(id);
+
+out_unlock:
+	srcu_read_unlock(&head->srcu, srcu_idx);
+	return ret;
+}
+
+static int ns_update_nuse(struct nvme_ns *ns)
+{
+	struct nvme_id_ns *id;
+	int ret;
+
+	/* Avoid issuing commands too often by rate limiting the update. */
+	if (!__ratelimit(&ns->head->rs_nuse))
+		return 0;
+
+	ret = nvme_identify_ns(ns->ctrl, ns->head->ns_id, &id);
+	if (ret)
+		goto out_free_id;
+
+	ns->head->nuse = le64_to_cpu(id->nuse);
+
+out_free_id:
+	kfree(id);
+
+	return ret;
+}
+
+static ssize_t nuse_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
+	struct gendisk *disk = dev_to_disk(dev);
+	struct block_device *bdev = disk->part0;
+	int ret;
+
+	if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
+	    bdev->bd_disk->fops == &nvme_ns_head_ops)
+		ret = ns_head_update_nuse(head);
+	else
+		ret = ns_update_nuse(bdev->bd_disk->private_data);
+	if (ret)
+		return ret;
+
+	return sysfs_emit(buf, "%llu\n", head->nuse);
+}
+static DEVICE_ATTR_RO(nuse);
+
 static struct attribute *nvme_ns_attrs[] = {
 	&dev_attr_wwid.attr,
 	&dev_attr_uuid.attr,
 	&dev_attr_nguid.attr,
 	&dev_attr_eui.attr,
+	&dev_attr_csi.attr,
 	&dev_attr_nsid.attr,
+	&dev_attr_metadata_bytes.attr,
+	&dev_attr_nuse.attr,
 #ifdef CONFIG_NVME_MULTIPATH
 	&dev_attr_ana_grpid.attr,
 	&dev_attr_ana_state.attr,