hw/block/nvme: support for shared namespace in subsystem

nvme-ns device is registered to a nvme controller device during the
initialization in nvme_register_namespace() in case that 'bus' property
is given which means it's mapped to a single controller.

This patch introduced a new property 'subsys' just like the controller
device instance did to map a namespace to a NVMe subsystem.

If 'subsys' property is given to the nvme-ns device, it will belong to
the specified subsystem and will be attached to all controllers in that
subsystem by enabling shared namespace capability in NMIC(Namespace
Multi-path I/O and Namespace Capabilities) in Identify Namespace.

Usage:

  -device nvme-subsys,id=subsys0
  -device nvme,serial=foo,id=nvme0,subsys=subsys0
  -device nvme,serial=bar,id=nvme1,subsys=subsys0
  -device nvme,serial=baz,id=nvme2,subsys=subsys0
  -device nvme-ns,id=ns1,drive=<drv>,nsid=1,subsys=subsys0  # Shared
  -device nvme-ns,id=ns2,drive=<drv>,nsid=2,bus=nvme2       # Non-shared

  In the above example, 'ns1' will be shared to 'nvme0' and 'nvme1' in
  the same subsystem.  On the other hand, 'ns2' will be attached to the
  'nvme2' only as a private namespace in that subsystem.

All the namespace with 'subsys' parameter will attach all controllers in
the subsystem to the namespace by default.

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
Tested-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>

5 files changed, 58 insertions, 4 deletions

diff --git a/hw/block/nvme-ns.c b/hw/block/nvme-ns.c
index 93ac6e107a..64b6a491ad 100644
--- a/hw/block/nvme-ns.c
+++ b/hw/block/nvme-ns.c
@@ -63,6 +63,10 @@ static int nvme_ns_init(NvmeNamespace *ns, Error **errp)
 
     id_ns->npda = id_ns->npdg = npdg - 1;
 
+    if (nvme_ns_shared(ns)) {
+        id_ns->nmic |= NVME_NMIC_NS_SHARED;
+    }
+
     return 0;
 }
 
@@ -363,14 +367,21 @@ static void nvme_ns_realize(DeviceState *dev, Error **errp)
         return;
     }
 
-    if (nvme_register_namespace(n, ns, errp)) {
-        return;
+    if (ns->subsys) {
+        if (nvme_subsys_register_ns(ns, errp)) {
+            return;
+        }
+    } else {
+        if (nvme_register_namespace(n, ns, errp)) {
+            return;
+        }
     }
-
 }
 
 static Property nvme_ns_props[] = {
     DEFINE_BLOCK_PROPERTIES(NvmeNamespace, blkconf),
+    DEFINE_PROP_LINK("subsys", NvmeNamespace, subsys, TYPE_NVME_SUBSYS,
+                     NvmeSubsystem *),
     DEFINE_PROP_UINT32("nsid", NvmeNamespace, params.nsid, 0),
     DEFINE_PROP_UUID("uuid", NvmeNamespace, params.uuid),
     DEFINE_PROP_BOOL("zoned", NvmeNamespace, params.zoned, false),
diff --git a/hw/block/nvme-ns.h b/hw/block/nvme-ns.h
index 293ac990e3..929e788619 100644
--- a/hw/block/nvme-ns.h
+++ b/hw/block/nvme-ns.h
@@ -47,6 +47,8 @@ typedef struct NvmeNamespace {
     const uint32_t *iocs;
     uint8_t      csi;
 
+    NvmeSubsystem   *subsys;
+
     NvmeIdNsZoned   *id_ns_zoned;
     NvmeZone        *zone_array;
     QTAILQ_HEAD(, NvmeZone) exp_open_zones;
@@ -77,6 +79,11 @@ static inline uint32_t nvme_nsid(NvmeNamespace *ns)
     return -1;
 }
 
+static inline bool nvme_ns_shared(NvmeNamespace *ns)
+{
+    return !!ns->subsys;
+}
+
 static inline NvmeLBAF *nvme_ns_lbaf(NvmeNamespace *ns)
 {
     NvmeIdNs *id_ns = &ns->id_ns;
diff --git a/hw/block/nvme-subsys.c b/hw/block/nvme-subsys.c
index 283a97b79d..af4804a819 100644
--- a/hw/block/nvme-subsys.c
+++ b/hw/block/nvme-subsys.c
@@ -43,6 +43,31 @@ int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp)
     return cntlid;
 }
 
+int nvme_subsys_register_ns(NvmeNamespace *ns, Error **errp)
+{
+    NvmeSubsystem *subsys = ns->subsys;
+    NvmeCtrl *n;
+    int i;
+
+    if (subsys->namespaces[nvme_nsid(ns)]) {
+        error_setg(errp, "namespace %d already registerd to subsy %s",
+                   nvme_nsid(ns), subsys->parent_obj.id);
+        return -1;
+    }
+
+    subsys->namespaces[nvme_nsid(ns)] = ns;
+
+    for (i = 0; i < ARRAY_SIZE(subsys->ctrls); i++) {
+        n = subsys->ctrls[i];
+
+        if (n && nvme_register_namespace(n, ns, errp)) {
+            return -1;
+        }
+    }
+
+    return 0;
+}
+
 static void nvme_subsys_setup(NvmeSubsystem *subsys)
 {
     const char *nqn = subsys->params.nqn ?
diff --git a/hw/block/nvme-subsys.h b/hw/block/nvme-subsys.h
index 55411eccfb..7a54a85120 100644
--- a/hw/block/nvme-subsys.h
+++ b/hw/block/nvme-subsys.h
@@ -14,6 +14,7 @@
     OBJECT_CHECK(NvmeSubsystem, (obj), TYPE_NVME_SUBSYS)
 
 #define NVME_SUBSYS_MAX_CTRLS   32
+#define NVME_SUBSYS_MAX_NAMESPACES  32
 
 typedef struct NvmeCtrl NvmeCtrl;
 typedef struct NvmeNamespace NvmeNamespace;
@@ -22,6 +23,7 @@ typedef struct NvmeSubsystem {
     uint8_t     subnqn[256];
 
     NvmeCtrl    *ctrls[NVME_SUBSYS_MAX_CTRLS];
+    NvmeNamespace *namespaces[NVME_SUBSYS_MAX_NAMESPACES];
 
     struct {
         char *nqn;
@@ -29,5 +31,6 @@ typedef struct NvmeSubsystem {
 } NvmeSubsystem;
 
 int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp);
+int nvme_subsys_register_ns(NvmeNamespace *ns, Error **errp);
 
 #endif /* NVME_SUBSYS_H */
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 5a63c356ba..5e0819fd9e 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -26,7 +26,8 @@
  *              mdts=<N[optional]>,zoned.append_size_limit=<N[optional]>, \
  *              subsys=<subsys_id>
  *      -device nvme-ns,drive=<drive_id>,bus=<bus_name>,nsid=<nsid>,\
- *              zoned=<true|false[optional]>
+ *              zoned=<true|false[optional]>, \
+ *              subsys=<subsys_id>
  *
  * Note cmb_size_mb denotes size of CMB in MB. CMB is assumed to be at
  * offset 0 in BAR2 and supports only WDS, RDS and SQS for now. By default, the
@@ -79,6 +80,13 @@
  *   data size being in effect. By setting this property to 0, users can make
  *   ZASL to be equal to MDTS. This property only affects zoned namespaces.
  *
+ * nvme namespace device parameters
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * - `subsys`
+ *   If given, the namespace will be attached to all controllers in the
+ *   subsystem. Otherwise, `bus` must be given to attach this namespace to a
+ *   specific controller as a non-shared namespace.
+ *
  * Setting `zoned` to true selects Zoned Command Set at the namespace.
  * In this case, the following namespace properties are available to configure
  * zoned operation: