[PATCH 0/6] hw/block/nvme: support namespace attachment

[PATCH 0/6] hw/block/nvme: support namespace attachment

[Minwoo Im]

Hello,

This series supports namespace attachment: attach and detach.  It means
that this series also introduced a scheme for allocated namespace which
is detached, but allocated in a NVMe subsystem.  Given that now we have
nvme-subsys device to specify a NVMe subsystem, it can manage detached
namespaces from controllers in the subsystem itself.

Tested:

  -device nvme-subsys,id=subsys0 \                                                    
  -device nvme,serial=foo,id=nvme0,subsys=subsys0 \                                   
  -device nvme-ns,id=ns1,drive=drv0,nsid=1,subsys=subsys0,zoned=false \              
  -device nvme-ns,id=ns2,drive=drv1,nsid=2,subsys=subsys0,zoned=true \               
  -device nvme-ns,id=ns3,drive=drv2,nsid=3,subsys=subsys0,detached=true,zoned=false \
  -device nvme-ns,id=ns4,drive=drv3,nsid=4,subsys=subsys0,detached=true,zoned=true \ 

  root@vm:~# nvme list
  Node                  SN                   Model                                    Namespace Usage                      Format           FW Rev
  --------------------- -------------------- ---------------------------------------- --------- -------------------------- ---------------- --------
  /dev/nvme0n1          foo                  QEMU NVMe Ctrl                           1         268.44  MB / 268.44  MB    512   B +  0 B   1.0
  /dev/nvme0n2          foo                  QEMU NVMe Ctrl                           2         268.44  MB / 268.44  MB    512   B +  0 B   1.0

  root@vm:~# nvme attach-ns /dev/nvme0 --namespace-id=3 --controllers=0
  attach-ns: Success, nsid:3
  root@vm:~# nvme attach-ns /dev/nvme0 --namespace-id=4 --controllers=0
  attach-ns: Success, nsid:4
  root@vm:~# echo 1 > /sys/class/nvme/nvme0/rescan_controller

  root@vm:~# nvme list
  Node                  SN                   Model                                    Namespace Usage                      Format           FW Rev  
  --------------------- -------------------- ---------------------------------------- --------- -------------------------- ---------------- --------
  /dev/nvme0n1          foo                  QEMU NVMe Ctrl                           1         268.44  MB / 268.44  MB    512   B +  0 B   1.0     
  /dev/nvme0n2          foo                  QEMU NVMe Ctrl                           2         268.44  MB / 268.44  MB    512   B +  0 B   1.0     
  /dev/nvme0n3          foo                  QEMU NVMe Ctrl                           3         268.44  MB / 268.44  MB    512   B +  0 B   1.0     
  /dev/nvme0n4          foo                  QEMU NVMe Ctrl                           4         268.44  MB / 268.44  MB    512   B +  0 B   1.0     

  root@vm:~# nvme detach-ns /dev/nvme0 --namespace-id=3 --controllers=0
  detach-ns: Success, nsid:3
  root@vm:~# nvme detach-ns /dev/nvme0 --namespace-id=4 --controllers=0
  detach-ns: Success, nsid:4
  root@vm:~# echo 1 > /sys/class/nvme/nvme0/rescan_controller

  root@vm:~# nvme list
  Node                  SN                   Model                                    Namespace Usage                      Format           FW Rev  
  --------------------- -------------------- ---------------------------------------- --------- -------------------------- ---------------- --------
  /dev/nvme0n1          foo                  QEMU NVMe Ctrl                           1         268.44  MB / 268.44  MB    512   B +  0 B   1.0     
  /dev/nvme0n2          foo                  QEMU NVMe Ctrl                           2         268.44  MB / 268.44  MB    512   B +  0 B   1.0     

Thanks,

Minwoo Im (6):
  hw/block/nvme: support namespace detach
  hw/block/nvme: fix namespaces array to 1-based
  hw/block/nvme: fix allocated namespace list to 256
  hw/block/nvme: support allocated namespace type
  hw/block/nvme: refactor nvme_select_ns_iocs
  hw/block/nvme: support namespace attachment command

 hw/block/nvme-ns.c     |   1 +
 hw/block/nvme-ns.h     |   1 +
 hw/block/nvme-subsys.h |  28 +++++-
 hw/block/nvme.c        | 199 ++++++++++++++++++++++++++++++++++-------
 hw/block/nvme.h        |  33 +++++++
 hw/block/trace-events  |   2 +
 include/block/nvme.h   |   5 ++
 7 files changed, 234 insertions(+), 35 deletions(-)

-- 
2.17.1

[PATCH 1/6] hw/block/nvme: support namespace detach

[Minwoo Im]

Given that now we have nvme-subsys device supported, we can manage
namespace allocated, but not attached: detached.  This patch introduced
a parameter for nvme-ns device named 'detached'.  This parameter
indicates whether the given namespace device is detached from
a entire NVMe subsystem('subsys' given case, shared namespace) or a
controller('bus' given case, private namespace).

- Allocated namespace

  1) Shared ns in the subsystem 'subsys0':

     -device nvme-ns,id=ns1,drive=blknvme0,nsid=1,subsys=subsys0,detached=true

  2) Private ns for the controller 'nvme0' of the subsystem 'subsys0':

     -device nvme-subsys,id=subsys0
     -device nvme,serial=foo,id=nvme0,subsys=subsys0
     -device nvme-ns,id=ns1,drive=blknvme0,nsid=1,bus=nvme0,detached=true

  3) (Invalid case) Controller 'nvme0' has no subsystem to manage ns:

     -device nvme,serial=foo,id=nvme0
     -device nvme-ns,id=ns1,drive=blknvme0,nsid=1,bus=nvme0,detached=true

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
---
 hw/block/nvme-ns.c     |  1 +
 hw/block/nvme-ns.h     |  1 +
 hw/block/nvme-subsys.h |  1 +
 hw/block/nvme.c        | 41 +++++++++++++++++++++++++++++++++++++++--
 hw/block/nvme.h        | 22 ++++++++++++++++++++++
 5 files changed, 64 insertions(+), 2 deletions(-)

diff --git a/hw/block/nvme-ns.c b/hw/block/nvme-ns.c
index c3b513b0fc78..cdcb81319fb5 100644
--- a/hw/block/nvme-ns.c
+++ b/hw/block/nvme-ns.c
@@ -393,6 +393,7 @@ static Property nvme_ns_props[] = {
     DEFINE_BLOCK_PROPERTIES(NvmeNamespace, blkconf),
     DEFINE_PROP_LINK("subsys", NvmeNamespace, subsys, TYPE_NVME_SUBSYS,
                      NvmeSubsystem *),
+    DEFINE_PROP_BOOL("detached", NvmeNamespace, params.detached, false),
     DEFINE_PROP_UINT32("nsid", NvmeNamespace, params.nsid, 0),
     DEFINE_PROP_UUID("uuid", NvmeNamespace, params.uuid),
     DEFINE_PROP_UINT16("mssrl", NvmeNamespace, params.mssrl, 128),
diff --git a/hw/block/nvme-ns.h b/hw/block/nvme-ns.h
index 7af6884862b5..b0c00e115d81 100644
--- a/hw/block/nvme-ns.h
+++ b/hw/block/nvme-ns.h
@@ -26,6 +26,7 @@ typedef struct NvmeZone {
 } NvmeZone;
 
 typedef struct NvmeNamespaceParams {
+    bool     detached;
     uint32_t nsid;
     QemuUUID uuid;
 
diff --git a/hw/block/nvme-subsys.h b/hw/block/nvme-subsys.h
index ccf6a71398d3..890d118117dc 100644
--- a/hw/block/nvme-subsys.h
+++ b/hw/block/nvme-subsys.h
@@ -23,6 +23,7 @@ typedef struct NvmeSubsystem {
     uint8_t     subnqn[256];
 
     NvmeCtrl    *ctrls[NVME_SUBSYS_MAX_CTRLS];
+    /* Allocated namespaces for this subsystem */
     NvmeNamespace *namespaces[NVME_SUBSYS_MAX_NAMESPACES];
 } NvmeSubsystem;
 
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 6b84e34843f5..a1e930f7c8e4 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -23,7 +23,7 @@
  *              max_ioqpairs=<N[optional]>, \
  *              aerl=<N[optional]>, aer_max_queued=<N[optional]>, \
  *              mdts=<N[optional]>,zoned.append_size_limit=<N[optional]>, \
- *              subsys=<subsys_id> \
+ *              subsys=<subsys_id>,detached=<true|false[optional]>
  *      -device nvme-ns,drive=<drive_id>,bus=<bus_name>,nsid=<nsid>,\
  *              zoned=<true|false[optional]>, \
  *              subsys=<subsys_id>
@@ -78,6 +78,13 @@
  *   controllers in the subsystem. Otherwise, `bus` must be given to attach
  *   this namespace to a specified single controller as a non-shared namespace.
  *
+ * - `detached`
+ *   Not to attach the namespace device to controllers in the NVMe subsystem
+ *   during boot-up. If not given, namespaces are all attahced to all
+ *   controllers in the subsystem by default.
+ *   It's mutual exclusive with 'bus' parameter. It's only valid in case
+ *   `subsys` is provided.
+ *
  * Setting `zoned` to true selects Zoned Command Set at the namespace.
  * In this case, the following namespace properties are available to configure
  * zoned operation:
@@ -4521,6 +4528,20 @@ static void nvme_init_state(NvmeCtrl *n)
     n->aer_reqs = g_new0(NvmeRequest *, n->params.aerl + 1);
 }
 
+static int nvme_attach_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
+{
+    if (nvme_ns_is_attached(n, ns)) {
+        error_setg(errp,
+                   "namespace %d is already attached to controller %d",
+                   nvme_nsid(ns), n->cntlid);
+        return -1;
+    }
+
+    nvme_ns_attach(n, ns);
+
+    return 0;
+}
+
 int nvme_register_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
 {
     uint32_t nsid = nvme_nsid(ns);
@@ -4552,7 +4573,23 @@ int nvme_register_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
 
     trace_pci_nvme_register_namespace(nsid);
 
-    n->namespaces[nsid - 1] = ns;
+    /*
+     * If subsys is not given, namespae is always attached to the controller
+     * because there's no subsystem to manage namespace allocation.
+     */
+    if (!n->subsys) {
+        if (ns->params.detached) {
+            error_setg(errp,
+                       "detached needs nvme-subsys specified nvme or nvme-ns");
+            return -1;
+        }
+
+        return nvme_attach_namespace(n, ns, errp);
+    } else {
+        if (!ns->params.detached) {
+            return nvme_attach_namespace(n, ns, errp);
+        }
+    }
 
     return 0;
 }
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index cb2b5175f1a1..bde0ed7c2679 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -176,6 +176,10 @@ typedef struct NvmeCtrl {
     NvmeSubsystem   *subsys;
 
     NvmeNamespace   namespace;
+    /*
+     * Attached namespaces to this controller.  If subsys is not given, all
+     * namespaces in this list will always be attached.
+     */
     NvmeNamespace   *namespaces[NVME_MAX_NAMESPACES];
     NvmeSQueue      **sq;
     NvmeCQueue      **cq;
@@ -194,6 +198,24 @@ static inline NvmeNamespace *nvme_ns(NvmeCtrl *n, uint32_t nsid)
     return n->namespaces[nsid - 1];
 }
 
+static inline bool nvme_ns_is_attached(NvmeCtrl *n, NvmeNamespace *ns)
+{
+    int nsid;
+
+    for (nsid = 1; nsid <= n->num_namespaces; nsid++) {
+        if (nvme_ns(n, nsid) == ns) {
+            return true;
+        }
+    }
+
+    return false;
+}
+
+static inline void nvme_ns_attach(NvmeCtrl *n, NvmeNamespace *ns)
+{
+    n->namespaces[nvme_nsid(ns) - 1] = ns;
+}
+
 static inline NvmeCQueue *nvme_cq(NvmeRequest *req)
 {
     NvmeSQueue *sq = req->sq;
-- 
2.17.1

[PATCH 2/6] hw/block/nvme: fix namespaces array to 1-based

[Minwoo Im]

subsys->namespaces array used to be sized to NVME_SUBSYS_MAX_NAMESPACES.
But subsys->namespaces are being accessed with 1-based namespace id
which means the very first array entry will always be empty(NULL).

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
---
 hw/block/nvme-subsys.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/hw/block/nvme-subsys.h b/hw/block/nvme-subsys.h
index 890d118117dc..574774390c4c 100644
--- a/hw/block/nvme-subsys.h
+++ b/hw/block/nvme-subsys.h
@@ -24,7 +24,7 @@ typedef struct NvmeSubsystem {
 
     NvmeCtrl    *ctrls[NVME_SUBSYS_MAX_CTRLS];
     /* Allocated namespaces for this subsystem */
-    NvmeNamespace *namespaces[NVME_SUBSYS_MAX_NAMESPACES];
+    NvmeNamespace *namespaces[NVME_SUBSYS_MAX_NAMESPACES + 1];
 } NvmeSubsystem;
 
 int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp);
-- 
2.17.1

[PATCH 3/6] hw/block/nvme: fix allocated namespace list to 256

[Minwoo Im]

Expand allocated namespace list (subsys->namespaces) to have 256 entries
which is a value lager than at least NVME_MAX_NAMESPACES which is for
attached namespace list in a controller.

Allocated namespace list should at least larger than attached namespace
list.

	n->num_namespaces = NVME_MAX_NAMESPACES;

The above line will set the NN field by id->nn so that the subsystem
should also prepare at least this number of namespace list entries.

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
---
 hw/block/nvme-subsys.h | 2 +-
 hw/block/nvme.h        | 6 ++++++
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/hw/block/nvme-subsys.h b/hw/block/nvme-subsys.h
index 574774390c4c..8a0732b22316 100644
--- a/hw/block/nvme-subsys.h
+++ b/hw/block/nvme-subsys.h
@@ -14,7 +14,7 @@
     OBJECT_CHECK(NvmeSubsystem, (obj), TYPE_NVME_SUBSYS)
 
 #define NVME_SUBSYS_MAX_CTRLS   32
-#define NVME_SUBSYS_MAX_NAMESPACES  32
+#define NVME_SUBSYS_MAX_NAMESPACES  256
 
 typedef struct NvmeCtrl NvmeCtrl;
 typedef struct NvmeNamespace NvmeNamespace;
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index bde0ed7c2679..1c7796b20996 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -10,6 +10,12 @@
 #define NVME_DEFAULT_ZONE_SIZE   (128 * MiB)
 #define NVME_DEFAULT_MAX_ZA_SIZE (128 * KiB)
 
+/*
+ * Subsystem namespace list for allocated namespaces should be larger than
+ * attached namespace list in a controller.
+ */
+QEMU_BUILD_BUG_ON(NVME_MAX_NAMESPACES > NVME_SUBSYS_MAX_NAMESPACES);
+
 typedef struct NvmeParams {
     char     *serial;
     uint32_t num_queues; /* deprecated since 5.1 */
-- 
2.17.1

[PATCH 4/6] hw/block/nvme: support allocated namespace type

[Minwoo Im]

From NVMe spec 1.4b "6.1.5. NSID and Namespace Relationships" defines
valid namespace types:

	- Unallocated: Not exists in the NVMe subsystem
	- Allocated: Exists in the NVMe subsystem
	- Inactive: Not attached to the controller
	- Active: Attached to the controller

This patch added support for allocated, but not attached namespace type:

	!nvme_ns(n, nsid) && nvme_subsys_ns(n->subsys, nsid)

nvme_ns() returns attached namespace instance of the given controller
and nvme_subsys_ns() returns allocated namespace instance in the
subsystem.

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
---
 hw/block/nvme-subsys.h | 13 +++++++++
 hw/block/nvme.c        | 63 +++++++++++++++++++++++++++++++-----------
 2 files changed, 60 insertions(+), 16 deletions(-)

diff --git a/hw/block/nvme-subsys.h b/hw/block/nvme-subsys.h
index 8a0732b22316..14627f9ccb41 100644
--- a/hw/block/nvme-subsys.h
+++ b/hw/block/nvme-subsys.h
@@ -30,4 +30,17 @@ typedef struct NvmeSubsystem {
 int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp);
 int nvme_subsys_register_ns(NvmeNamespace *ns, Error **errp);
 
+/*
+ * Return allocated namespace of the specified nsid in the subsystem.
+ */
+static inline NvmeNamespace *nvme_subsys_ns(NvmeSubsystem *subsys,
+        uint32_t nsid)
+{
+    if (!subsys) {
+        return NULL;
+    }
+
+    return subsys->namespaces[nsid];
+}
+
 #endif /* NVME_SUBSYS_H */
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index a1e930f7c8e4..d1761a82731f 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -3124,7 +3124,7 @@ static uint16_t nvme_identify_ctrl_csi(NvmeCtrl *n, NvmeRequest *req)
     return NVME_INVALID_FIELD | NVME_DNR;
 }
 
-static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeRequest *req)
+static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeRequest *req, bool active)
 {
     NvmeNamespace *ns;
     NvmeIdentify *c = (NvmeIdentify *)&req->cmd;
@@ -3138,7 +3138,14 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeRequest *req)
 
     ns = nvme_ns(n, nsid);
     if (unlikely(!ns)) {
-        return nvme_rpt_empty_id_struct(n, req);
+        if (!active) {
+            ns = nvme_subsys_ns(n->subsys, nsid);
+            if (!ns) {
+                return nvme_rpt_empty_id_struct(n, req);
+            }
+        } else {
+            return nvme_rpt_empty_id_struct(n, req);
+        }
     }
 
     if (c->csi == NVME_CSI_NVM && nvme_csi_has_nvm_support(ns)) {
@@ -3149,7 +3156,8 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeRequest *req)
     return NVME_INVALID_CMD_SET | NVME_DNR;
 }
 
-static uint16_t nvme_identify_ns_csi(NvmeCtrl *n, NvmeRequest *req)
+static uint16_t nvme_identify_ns_csi(NvmeCtrl *n, NvmeRequest *req,
+        bool active)
 {
     NvmeNamespace *ns;
     NvmeIdentify *c = (NvmeIdentify *)&req->cmd;
@@ -3163,7 +3171,14 @@ static uint16_t nvme_identify_ns_csi(NvmeCtrl *n, NvmeRequest *req)
 
     ns = nvme_ns(n, nsid);
     if (unlikely(!ns)) {
-        return nvme_rpt_empty_id_struct(n, req);
+        if (!active) {
+            ns = nvme_subsys_ns(n->subsys, nsid);
+            if (!ns) {
+                return nvme_rpt_empty_id_struct(n, req);
+            }
+        } else {
+            return nvme_rpt_empty_id_struct(n, req);
+        }
     }
 
     if (c->csi == NVME_CSI_NVM && nvme_csi_has_nvm_support(ns)) {
@@ -3176,7 +3191,8 @@ static uint16_t nvme_identify_ns_csi(NvmeCtrl *n, NvmeRequest *req)
     return NVME_INVALID_FIELD | NVME_DNR;
 }
 
-static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeRequest *req)
+static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeRequest *req,
+        bool active)
 {
     NvmeNamespace *ns;
     NvmeIdentify *c = (NvmeIdentify *)&req->cmd;
@@ -3201,7 +3217,14 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeRequest *req)
     for (i = 1; i <= n->num_namespaces; i++) {
         ns = nvme_ns(n, i);
         if (!ns) {
-            continue;
+            if (!active) {
+                ns = nvme_subsys_ns(n->subsys, i);
+                if (!ns) {
+                    continue;
+                }
+            } else {
+                continue;
+            }
         }
         if (ns->params.nsid <= min_nsid) {
             continue;
@@ -3215,7 +3238,8 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeRequest *req)
     return nvme_dma(n, list, data_len, DMA_DIRECTION_FROM_DEVICE, req);
 }
 
-static uint16_t nvme_identify_nslist_csi(NvmeCtrl *n, NvmeRequest *req)
+static uint16_t nvme_identify_nslist_csi(NvmeCtrl *n, NvmeRequest *req,
+        bool active)
 {
     NvmeNamespace *ns;
     NvmeIdentify *c = (NvmeIdentify *)&req->cmd;
@@ -3241,7 +3265,14 @@ static uint16_t nvme_identify_nslist_csi(NvmeCtrl *n, NvmeRequest *req)
     for (i = 1; i <= n->num_namespaces; i++) {
         ns = nvme_ns(n, i);
         if (!ns) {
-            continue;
+            if (!active) {
+                ns = nvme_subsys_ns(n->subsys, i);
+                if (!ns) {
+                    continue;
+                }
+            } else {
+                continue;
+            }
         }
         if (ns->params.nsid <= min_nsid || c->csi != ns->csi) {
             continue;
@@ -3321,25 +3352,25 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeRequest *req)
 
     switch (le32_to_cpu(c->cns)) {
     case NVME_ID_CNS_NS:
-         /* fall through */
+        return nvme_identify_ns(n, req, true);
     case NVME_ID_CNS_NS_PRESENT:
-        return nvme_identify_ns(n, req);
+        return nvme_identify_ns(n, req, false);
     case NVME_ID_CNS_CS_NS:
-         /* fall through */
+        return nvme_identify_ns_csi(n, req, true);
     case NVME_ID_CNS_CS_NS_PRESENT:
-        return nvme_identify_ns_csi(n, req);
+        return nvme_identify_ns_csi(n, req, false);
     case NVME_ID_CNS_CTRL:
         return nvme_identify_ctrl(n, req);
     case NVME_ID_CNS_CS_CTRL:
         return nvme_identify_ctrl_csi(n, req);
     case NVME_ID_CNS_NS_ACTIVE_LIST:
-         /* fall through */
+        return nvme_identify_nslist(n, req, true);
     case NVME_ID_CNS_NS_PRESENT_LIST:
-        return nvme_identify_nslist(n, req);
+        return nvme_identify_nslist(n, req, false);
     case NVME_ID_CNS_CS_NS_ACTIVE_LIST:
-         /* fall through */
+        return nvme_identify_nslist_csi(n, req, true);
     case NVME_ID_CNS_CS_NS_PRESENT_LIST:
-        return nvme_identify_nslist_csi(n, req);
+        return nvme_identify_nslist_csi(n, req, false);
     case NVME_ID_CNS_NS_DESCR_LIST:
         return nvme_identify_ns_descr_list(n, req);
     case NVME_ID_CNS_IO_COMMAND_SET:
-- 
2.17.1

[PATCH 5/6] hw/block/nvme: refactor nvme_select_ns_iocs

[Minwoo Im]

This patch has no functional changes.  This patch just refactored
nvme_select_ns_iocs() to iterate the attached namespaces of the
controlller and make it invoke __nvme_select_ns_iocs().

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
---
 hw/block/nvme.c | 36 +++++++++++++++++++++---------------
 1 file changed, 21 insertions(+), 15 deletions(-)

diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index d1761a82731f..697368a6ae0c 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -3896,6 +3896,25 @@ static void nvme_ctrl_shutdown(NvmeCtrl *n)
     }
 }
 
+static void __nvme_select_ns_iocs(NvmeCtrl *n, NvmeNamespace *ns)
+{
+    ns->iocs = nvme_cse_iocs_none;
+    switch (ns->csi) {
+    case NVME_CSI_NVM:
+        if (NVME_CC_CSS(n->bar.cc) != NVME_CC_CSS_ADMIN_ONLY) {
+            ns->iocs = nvme_cse_iocs_nvm;
+        }
+        break;
+    case NVME_CSI_ZONED:
+        if (NVME_CC_CSS(n->bar.cc) == NVME_CC_CSS_CSI) {
+            ns->iocs = nvme_cse_iocs_zoned;
+        } else if (NVME_CC_CSS(n->bar.cc) == NVME_CC_CSS_NVM) {
+            ns->iocs = nvme_cse_iocs_nvm;
+        }
+        break;
+    }
+}
+
 static void nvme_select_ns_iocs(NvmeCtrl *n)
 {
     NvmeNamespace *ns;
@@ -3906,21 +3925,8 @@ static void nvme_select_ns_iocs(NvmeCtrl *n)
         if (!ns) {
             continue;
         }
-        ns->iocs = nvme_cse_iocs_none;
-        switch (ns->csi) {
-        case NVME_CSI_NVM:
-            if (NVME_CC_CSS(n->bar.cc) != NVME_CC_CSS_ADMIN_ONLY) {
-                ns->iocs = nvme_cse_iocs_nvm;
-            }
-            break;
-        case NVME_CSI_ZONED:
-            if (NVME_CC_CSS(n->bar.cc) == NVME_CC_CSS_CSI) {
-                ns->iocs = nvme_cse_iocs_zoned;
-            } else if (NVME_CC_CSS(n->bar.cc) == NVME_CC_CSS_NVM) {
-                ns->iocs = nvme_cse_iocs_nvm;
-            }
-            break;
-        }
+
+        __nvme_select_ns_iocs(n, ns);
     }
 }
 
-- 
2.17.1

[PATCH 6/6] hw/block/nvme: support namespace attachment command

[Minwoo Im]

This patch supports Namespace Attachment command for the pre-defined
nvme-ns device nodes.  Of course, attach/detach namespace should only be
supported in case 'subsys' is given.  This is because if we detach a
namespace from a controller, somebody needs to manage the detached, but
allocated namespace in the NVMe subsystem.

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
---
 hw/block/nvme-subsys.h | 10 +++++++
 hw/block/nvme.c        | 59 ++++++++++++++++++++++++++++++++++++++++++
 hw/block/nvme.h        |  5 ++++
 hw/block/trace-events  |  2 ++
 include/block/nvme.h   |  5 ++++
 5 files changed, 81 insertions(+)

diff --git a/hw/block/nvme-subsys.h b/hw/block/nvme-subsys.h
index 14627f9ccb41..ef4bec928eae 100644
--- a/hw/block/nvme-subsys.h
+++ b/hw/block/nvme-subsys.h
@@ -30,6 +30,16 @@ typedef struct NvmeSubsystem {
 int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp);
 int nvme_subsys_register_ns(NvmeNamespace *ns, Error **errp);
 
+static inline NvmeCtrl *nvme_subsys_ctrl(NvmeSubsystem *subsys,
+        uint32_t cntlid)
+{
+    if (!subsys) {
+        return NULL;
+    }
+
+    return subsys->ctrls[cntlid];
+}
+
 /*
  * Return allocated namespace of the specified nsid in the subsystem.
  */
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 697368a6ae0c..769436722c7e 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -183,6 +183,7 @@ static const uint32_t nvme_cse_acs[256] = {
     [NVME_ADM_CMD_SET_FEATURES]     = NVME_CMD_EFF_CSUPP,
     [NVME_ADM_CMD_GET_FEATURES]     = NVME_CMD_EFF_CSUPP,
     [NVME_ADM_CMD_ASYNC_EV_REQ]     = NVME_CMD_EFF_CSUPP,
+    [NVME_ADM_CMD_NS_ATTACHMENT]    = NVME_CMD_EFF_CSUPP,
 };
 
 static const uint32_t nvme_cse_iocs_none[256];
@@ -3766,6 +3767,62 @@ static uint16_t nvme_aer(NvmeCtrl *n, NvmeRequest *req)
     return NVME_NO_COMPLETE;
 }
 
+static void __nvme_select_ns_iocs(NvmeCtrl *n, NvmeNamespace *ns);
+static uint16_t nvme_ns_attachment(NvmeCtrl *n, NvmeRequest *req)
+{
+    NvmeNamespace *ns;
+    NvmeCtrl *ctrl;
+    uint16_t list[NVME_CONTROLLER_LIST_SIZE] = {};
+    uint32_t nsid = le32_to_cpu(req->cmd.nsid);
+    uint32_t dw10 = le32_to_cpu(req->cmd.cdw10);
+    bool attach = !(dw10 & 0xf);
+    uint16_t *nr_ids = &list[0];
+    uint16_t *ids = &list[1];
+    uint16_t ret;
+    int i;
+
+    trace_pci_nvme_ns_attachment(nvme_cid(req), dw10 & 0xf);
+
+    ns = nvme_subsys_ns(n->subsys, nsid);
+    if (!ns) {
+        return NVME_INVALID_FIELD | NVME_DNR;
+    }
+
+    ret = nvme_dma(n, (uint8_t *)list, 4096,
+                   DMA_DIRECTION_TO_DEVICE, req);
+    if (ret) {
+        return ret;
+    }
+
+    if (!*nr_ids) {
+        return NVME_NS_CTRL_LIST_INVALID | NVME_DNR;
+    }
+
+    for (i = 0; i < *nr_ids; i++) {
+        ctrl = nvme_subsys_ctrl(n->subsys, ids[i]);
+        if (!ctrl) {
+            return NVME_NS_CTRL_LIST_INVALID | NVME_DNR;
+        }
+
+        if (attach) {
+            if (nvme_ns_is_attached(ctrl, ns)) {
+                return NVME_NS_ALREADY_ATTACHED | NVME_DNR;
+            }
+
+            nvme_ns_attach(n, ns);
+            __nvme_select_ns_iocs(n, ns);
+        } else {
+            if (!nvme_ns_is_attached(ctrl, ns)) {
+                return NVME_NS_NOT_ATTACHED | NVME_DNR;
+            }
+
+            nvme_ns_detach(n, ns);
+        }
+    }
+
+    return NVME_SUCCESS;
+}
+
 static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeRequest *req)
 {
     trace_pci_nvme_admin_cmd(nvme_cid(req), nvme_sqid(req), req->cmd.opcode,
@@ -3797,6 +3854,8 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeRequest *req)
         return nvme_get_feature(n, req);
     case NVME_ADM_CMD_ASYNC_EV_REQ:
         return nvme_aer(n, req);
+    case NVME_ADM_CMD_NS_ATTACHMENT:
+        return nvme_ns_attachment(n, req);
     default:
         assert(false);
     }
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 1c7796b20996..5a1ab857d166 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -222,6 +222,11 @@ static inline void nvme_ns_attach(NvmeCtrl *n, NvmeNamespace *ns)
     n->namespaces[nvme_nsid(ns) - 1] = ns;
 }
 
+static inline void nvme_ns_detach(NvmeCtrl *n, NvmeNamespace *ns)
+{
+    n->namespaces[nvme_nsid(ns) - 1] = NULL;
+}
+
 static inline NvmeCQueue *nvme_cq(NvmeRequest *req)
 {
     NvmeSQueue *sq = req->sq;
diff --git a/hw/block/trace-events b/hw/block/trace-events
index b6e972d733a6..bf67fe7873d2 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -80,6 +80,8 @@ pci_nvme_aer(uint16_t cid) "cid %"PRIu16""
 pci_nvme_aer_aerl_exceeded(void) "aerl exceeded"
 pci_nvme_aer_masked(uint8_t type, uint8_t mask) "type 0x%"PRIx8" mask 0x%"PRIx8""
 pci_nvme_aer_post_cqe(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
+pci_nvme_ns_attachment(uint16_t cid, uint8_t sel) "cid %"PRIu16", sel=0x%"PRIx8""
+pci_nvme_ns_attachment_attach(uint16_t cntlid, uint32_t nsid) "cntlid=0x%"PRIx16", nsid=0x%"PRIx32""
 pci_nvme_enqueue_event(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
 pci_nvme_enqueue_event_noqueue(int queued) "queued %d"
 pci_nvme_enqueue_event_masked(uint8_t typ) "type 0x%"PRIx8""
diff --git a/include/block/nvme.h b/include/block/nvme.h
index f82b5ffc2c1d..4b016f954fee 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -566,6 +566,7 @@ enum NvmeAdminCommands {
     NVME_ADM_CMD_ASYNC_EV_REQ   = 0x0c,
     NVME_ADM_CMD_ACTIVATE_FW    = 0x10,
     NVME_ADM_CMD_DOWNLOAD_FW    = 0x11,
+    NVME_ADM_CMD_NS_ATTACHMENT  = 0x15,
     NVME_ADM_CMD_FORMAT_NVM     = 0x80,
     NVME_ADM_CMD_SECURITY_SEND  = 0x81,
     NVME_ADM_CMD_SECURITY_RECV  = 0x82,
@@ -836,6 +837,9 @@ enum NvmeStatusCodes {
     NVME_FEAT_NOT_CHANGEABLE    = 0x010e,
     NVME_FEAT_NOT_NS_SPEC       = 0x010f,
     NVME_FW_REQ_SUSYSTEM_RESET  = 0x0110,
+    NVME_NS_ALREADY_ATTACHED    = 0x0118,
+    NVME_NS_NOT_ATTACHED        = 0x011A,
+    NVME_NS_CTRL_LIST_INVALID   = 0x011C,
     NVME_CONFLICTING_ATTRS      = 0x0180,
     NVME_INVALID_PROT_INFO      = 0x0181,
     NVME_WRITE_TO_RO            = 0x0182,
@@ -951,6 +955,7 @@ typedef struct QEMU_PACKED NvmePSD {
     uint8_t     resv[16];
 } NvmePSD;
 
+#define NVME_CONTROLLER_LIST_SIZE 2048
 #define NVME_IDENTIFY_DATA_SIZE 4096
 
 enum NvmeIdCns {
-- 
2.17.1