nvme: track shared namespaces

Introduce a new struct nvme_ns_head that holds information about an actual
namespace, unlike struct nvme_ns, which only holds the per-controller
namespace information.  For private namespaces there is a 1:1 relation of
the two, but for shared namespaces this lets us discover all the paths to
it.  For now only the identifiers are moved to the new structure, but most
of the information in struct nvme_ns should eventually move over.

To allow lockless path lookup the list of nvme_ns structures per
nvme_ns_head is protected by SRCU, which requires freeing the nvme_ns
structure through call_srcu.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Javier González <javier@cnexlabs.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

drivers/nvme/host/lightnvm.c

@@ -305,7 +305,7 @@ static int nvme_nvm_identity(struct nvm_dev *nvmdev, struct nvm_id *nvm_id)
 	int ret;
 
 	c.identity.opcode = nvme_nvm_admin_identity;
-	c.identity.nsid = cpu_to_le32(ns->ns_id);
+	c.identity.nsid = cpu_to_le32(ns->head->ns_id);
 	c.identity.chnl_off = 0;
 
 	nvme_nvm_id = kmalloc(sizeof(struct nvme_nvm_id), GFP_KERNEL);
@@ -344,7 +344,7 @@ static int nvme_nvm_get_l2p_tbl(struct nvm_dev *nvmdev, u64 slba, u32 nlb,
 	int ret = 0;
 
 	c.l2p.opcode = nvme_nvm_admin_get_l2p_tbl;
-	c.l2p.nsid = cpu_to_le32(ns->ns_id);
+	c.l2p.nsid = cpu_to_le32(ns->head->ns_id);
 	entries = kmalloc(len, GFP_KERNEL);
 	if (!entries)
 		return -ENOMEM;
@@ -402,7 +402,7 @@ static int nvme_nvm_get_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr ppa,
 	int ret = 0;
 
 	c.get_bb.opcode = nvme_nvm_admin_get_bb_tbl;
-	c.get_bb.nsid = cpu_to_le32(ns->ns_id);
+	c.get_bb.nsid = cpu_to_le32(ns->head->ns_id);
 	c.get_bb.spba = cpu_to_le64(ppa.ppa);
 
 	bb_tbl = kzalloc(tblsz, GFP_KERNEL);
@@ -452,7 +452,7 @@ static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr *ppas,
 	int ret = 0;
 
 	c.set_bb.opcode = nvme_nvm_admin_set_bb_tbl;
-	c.set_bb.nsid = cpu_to_le32(ns->ns_id);
+	c.set_bb.nsid = cpu_to_le32(ns->head->ns_id);
 	c.set_bb.spba = cpu_to_le64(ppas->ppa);
 	c.set_bb.nlb = cpu_to_le16(nr_ppas - 1);
 	c.set_bb.value = type;
@@ -469,7 +469,7 @@ static inline void nvme_nvm_rqtocmd(struct nvm_rq *rqd, struct nvme_ns *ns,
 				    struct nvme_nvm_command *c)
 {
 	c->ph_rw.opcode = rqd->opcode;
-	c->ph_rw.nsid = cpu_to_le32(ns->ns_id);
+	c->ph_rw.nsid = cpu_to_le32(ns->head->ns_id);
 	c->ph_rw.spba = cpu_to_le64(rqd->ppa_addr.ppa);
 	c->ph_rw.metadata = cpu_to_le64(rqd->dma_meta_list);
 	c->ph_rw.control = cpu_to_le16(rqd->flags);
@@ -731,7 +731,7 @@ static int nvme_nvm_submit_vio(struct nvme_ns *ns,
 
 	memset(&c, 0, sizeof(c));
 	c.ph_rw.opcode = vio.opcode;
-	c.ph_rw.nsid = cpu_to_le32(ns->ns_id);
+	c.ph_rw.nsid = cpu_to_le32(ns->head->ns_id);
 	c.ph_rw.control = cpu_to_le16(vio.control);
 	c.ph_rw.length = cpu_to_le16(vio.nppas);
 
@@ -768,7 +768,7 @@ static int nvme_nvm_user_vcmd(struct nvme_ns *ns, int admin,
 
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = vcmd.opcode;
-	c.common.nsid = cpu_to_le32(ns->ns_id);
+	c.common.nsid = cpu_to_le32(ns->head->ns_id);
 	c.common.cdw2[0] = cpu_to_le32(vcmd.cdw2);
 	c.common.cdw2[1] = cpu_to_le32(vcmd.cdw3);
 	/* cdw11-12 */

drivers/nvme/host/nvme.h

@@ -136,7 +136,6 @@ struct nvme_ctrl {
 	struct device ctrl_device;
 	struct device *device;	/* char device */
 	struct cdev cdev;
-	struct ida ns_ida;
 	struct work_struct reset_work;
 	struct work_struct delete_work;
 
@@ -209,12 +208,14 @@ struct nvme_subsystem {
 	struct list_head	entry;
 	struct mutex		lock;
 	struct list_head	ctrls;
+	struct list_head	nsheads;
 	char			subnqn[NVMF_NQN_SIZE];
 	char			serial[20];
 	char			model[40];
 	char			firmware_rev[8];
 	u8			cmic;
 	u16			vendor_id;
+	struct ida		ns_ida;
 };
 
 /*
@@ -226,18 +227,35 @@ struct nvme_ns_ids {
 	uuid_t	uuid;
 };
 
+/*
+ * Anchor structure for namespaces.  There is one for each namespace in a
+ * NVMe subsystem that any of our controllers can see, and the namespace
+ * structure for each controller is chained of it.  For private namespaces
+ * there is a 1:1 relation to our namespace structures, that is ->list
+ * only ever has a single entry for private namespaces.
+ */
+struct nvme_ns_head {
+	struct list_head	list;
+	struct srcu_struct      srcu;
+	struct nvme_subsystem	*subsys;
+	unsigned		ns_id;
+	struct nvme_ns_ids	ids;
+	struct list_head	entry;
+	struct kref		ref;
+	int			instance;
+};
+
 struct nvme_ns {
 	struct list_head list;
 
 	struct nvme_ctrl *ctrl;
 	struct request_queue *queue;
 	struct gendisk *disk;
+	struct list_head siblings;
 	struct nvm_dev *ndev;
 	struct kref kref;
-	int instance;
+	struct nvme_ns_head *head;
 
-	unsigned ns_id;
-	struct nvme_ns_ids ids;
 	int lba_shift;
 	u16 ms;
 	u16 sgs;