[PATCH 1/2] hw/nvme: add namespace hotplug support

mr-083 posted 2 patches 2 days, 10 hours ago
Maintainers: Kevin Wolf <kwolf@redhat.com>, Hanna Reitz <hreitz@redhat.com>, "Dr. David Alan Gilbert" <dave@treblig.org>, Keith Busch <kbusch@kernel.org>, Klaus Jensen <its@irrelevant.dk>, Jesper Devantier <foss@defmacro.it>
[PATCH 1/2] hw/nvme: add namespace hotplug support
Posted by mr-083 2 days, 10 hours ago
Add hotplug support for nvme-ns devices on the NvmeBus. This enables
namespace-level hot-swap without removing the NVMe controller, which
is how physical NVMe drives behave when hot-swapped in the same PCIe
slot.

Mark nvme-ns devices as hotpluggable and register the NvmeBus as a
hotplug handler with proper plug and unplug callbacks:

- plug: attach namespace to all started controllers and send an
  Asynchronous Event Notification (AEN) with NS_ATTR_CHANGED so
  the guest kernel rescans namespaces
- unplug: detach from all controllers, send AEN, remove from
  subsystem, then unrealize the device

The plug handler skips controllers that haven't started yet
(qs_created == false) to avoid interfering with boot-time namespace
attachment in nvme_start_ctrl().

Both the controller bus and subsystem bus are configured as hotplug
handlers via qbus_set_bus_hotplug_handler() since nvme-ns devices
may reparent to the subsystem bus during realize.

Signed-off-by: Matthieu Receveur <matthieu@min.io>
---
 hw/nvme/ctrl.c   | 85 ++++++++++++++++++++++++++++++++++++++++++++++++
 hw/nvme/ns.c     |  1 +
 hw/nvme/subsys.c |  2 ++
 3 files changed, 88 insertions(+)

diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c
index be6c7028cb..5502e4ea2b 100644
--- a/hw/nvme/ctrl.c
+++ b/hw/nvme/ctrl.c
@@ -206,6 +206,7 @@
 #include "system/hostmem.h"
 #include "hw/pci/msix.h"
 #include "hw/pci/pcie_sriov.h"
+#include "hw/core/qdev.h"
 #include "system/spdm-socket.h"
 #include "migration/vmstate.h"
 
@@ -9293,6 +9294,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     }
 
     qbus_init(&n->bus, sizeof(NvmeBus), TYPE_NVME_BUS, dev, dev->id);
+    qbus_set_bus_hotplug_handler(BUS(&n->bus));
 
     if (nvme_init_subsys(n, errp)) {
         return;
@@ -9553,10 +9555,93 @@ static const TypeInfo nvme_info = {
     },
 };
 
+static void nvme_ns_hot_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
+                              Error **errp)
+{
+    NvmeNamespace *ns = NVME_NS(dev);
+    NvmeSubsystem *subsys = ns->subsys;
+    uint32_t nsid = ns->params.nsid;
+    int i;
+
+    /*
+     * Attach to all started controllers and notify via AEN.
+     * Skip controllers that haven't started yet (boot-time realize) —
+     * nvme_start_ctrl() will attach namespaces during controller init.
+     */
+    for (i = 0; i < NVME_MAX_CONTROLLERS; i++) {
+        NvmeCtrl *ctrl = nvme_subsys_ctrl(subsys, i);
+        if (!ctrl || !ctrl->qs_created) {
+            continue;
+        }
+
+        if (nvme_csi_supported(ctrl, ns->csi) && !ns->params.detached) {
+            nvme_attach_ns(ctrl, ns);
+            nvme_update_dsm_limits(ctrl, ns);
+
+            if (!test_and_set_bit(nsid, ctrl->changed_nsids)) {
+                nvme_enqueue_event(ctrl, NVME_AER_TYPE_NOTICE,
+                                   NVME_AER_INFO_NOTICE_NS_ATTR_CHANGED,
+                                   NVME_LOG_CHANGED_NSLIST);
+            }
+        }
+    }
+}
+
+static void nvme_ns_hot_unplug(HotplugHandler *hotplug_dev, DeviceState *dev,
+                               Error **errp)
+{
+    NvmeNamespace *ns = NVME_NS(dev);
+    NvmeSubsystem *subsys = ns->subsys;
+    uint32_t nsid = ns->params.nsid;
+    int i;
+
+    /*
+     * Detach from all controllers and notify the guest via AEN.
+     * Must happen before unrealize to avoid use-after-free when the
+     * guest sends I/O to a freed namespace.
+     */
+    for (i = 0; i < NVME_MAX_CONTROLLERS; i++) {
+        NvmeCtrl *ctrl = nvme_subsys_ctrl(subsys, i);
+        if (!ctrl || !nvme_ns(ctrl, nsid)) {
+            continue;
+        }
+
+        nvme_detach_ns(ctrl, ns);
+        nvme_update_dsm_limits(ctrl, NULL);
+
+        if (!test_and_set_bit(nsid, ctrl->changed_nsids)) {
+            nvme_enqueue_event(ctrl, NVME_AER_TYPE_NOTICE,
+                               NVME_AER_INFO_NOTICE_NS_ATTR_CHANGED,
+                               NVME_LOG_CHANGED_NSLIST);
+        }
+    }
+
+    /* Remove from subsystem namespace list. */
+    subsys->namespaces[nsid] = NULL;
+
+    /*
+     * Unrealize: drain I/O, flush, cleanup structures, remove from QOM.
+     * nvme_ns_unrealize() handles drain/shutdown/cleanup internally.
+     */
+    qdev_unrealize(dev);
+}
+
+static void nvme_bus_class_init(ObjectClass *klass, const void *data)
+{
+    HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(klass);
+    hc->plug = nvme_ns_hot_plug;
+    hc->unplug = nvme_ns_hot_unplug;
+}
+
 static const TypeInfo nvme_bus_info = {
     .name = TYPE_NVME_BUS,
     .parent = TYPE_BUS,
     .instance_size = sizeof(NvmeBus),
+    .class_init = nvme_bus_class_init,
+    .interfaces = (const InterfaceInfo[]) {
+        { TYPE_HOTPLUG_HANDLER },
+        { }
+    },
 };
 
 static void nvme_register_types(void)
diff --git a/hw/nvme/ns.c b/hw/nvme/ns.c
index b0106eaa5c..eb628c0734 100644
--- a/hw/nvme/ns.c
+++ b/hw/nvme/ns.c
@@ -937,6 +937,7 @@ static void nvme_ns_class_init(ObjectClass *oc, const void *data)
     dc->bus_type = TYPE_NVME_BUS;
     dc->realize = nvme_ns_realize;
     dc->unrealize = nvme_ns_unrealize;
+    dc->hotpluggable = true;
     device_class_set_props(dc, nvme_ns_props);
     dc->desc = "Virtual NVMe namespace";
 }
diff --git a/hw/nvme/subsys.c b/hw/nvme/subsys.c
index 777e1c620f..fa35055d3c 100644
--- a/hw/nvme/subsys.c
+++ b/hw/nvme/subsys.c
@@ -9,6 +9,7 @@
 #include "qemu/osdep.h"
 #include "qemu/units.h"
 #include "qapi/error.h"
+#include "hw/core/qdev.h"
 
 #include "nvme.h"
 
@@ -205,6 +206,7 @@ static void nvme_subsys_realize(DeviceState *dev, Error **errp)
     NvmeSubsystem *subsys = NVME_SUBSYS(dev);
 
     qbus_init(&subsys->bus, sizeof(NvmeBus), TYPE_NVME_BUS, dev, dev->id);
+    qbus_set_bus_hotplug_handler(BUS(&subsys->bus));
 
     nvme_subsys_setup(subsys, errp);
 }
-- 
2.50.1 (Apple Git-155)