Merge tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/m…

…st/qemu into staging

virtio,pc,pci: features, cleanups, fixes

vhost-scsi support for worker ioctls

fixes, cleanups all over the place.

Signed-off-by: Michael S. Tsirkin <[email protected]>

# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmWKohIPHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRpG2YH/1rJGV8TQm4V8kcGP9wOknPAMFADnEFdFmrB
# V+JEDnyKrdcEZLPRh0b846peWRJhC13iL7Ks3VNjeVsfE9TyzNyNDpUzCJPfYFjR
# 3m8ChLDvE9tKBA5/hXMIcgDXaYcPIrPvHyl4HG8EQn7oaeMpS2uecKqDpDDvNXGq
# oNamNvqimFSqA+3ChzA+0Qt07Ts7xFEw4OEXSwfRXlsam/dhQG0SI+crRheHuvFb
# HR8EwmNydA1D/M51AuBNuvX36u3SnPWm7Anp5711SZ1b59unshI0ztIqIJnGkvYe
# qpUJSmxR6ulwWe4nQfb+GhBsuJ2j2ORC7YfXyAT7mw8rds8loaI=
# =cNy2
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 26 Dec 2023 04:51:14 EST
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "[email protected]"
# gpg: Good signature from "Michael S. Tsirkin <[email protected]>" [full]
# gpg:                 aka "Michael S. Tsirkin <[email protected]>" [full]
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/mst/qemu: (21 commits)
  vdpa: move memory listener to vhost_vdpa_shared
  vdpa: use dev_shared in vdpa_iommu
  vdpa: use VhostVDPAShared in vdpa_dma_map and unmap
  vdpa: move iommu_list to vhost_vdpa_shared
  vdpa: remove msg type of vhost_vdpa
  vdpa: move backend_cap to vhost_vdpa_shared
  vdpa: move iotlb_batch_begin_sent to vhost_vdpa_shared
  vdpa: move file descriptor to vhost_vdpa_shared
  vdpa: use vdpa shared for tracing
  vdpa: move shadow_data to vhost_vdpa_shared
  vdpa: move iova_range to vhost_vdpa_shared
  vdpa: move iova tree to the shared struct
  vdpa: add VhostVDPAShared
  vdpa: do not set virtio status bits if unneeded
  Fix bugs when VM shutdown with virtio-gpu unplugged
  vhost-scsi: fix usage of error_reportf_err()
  hw/acpi: propagate vcpu hotplug after switch to modern interface
  vhost-scsi: Add support for a worker thread per virtqueue
  vhost: Add worker backend callouts
  tests: bios-tables-test: Rename smbios type 4 related test functions
  ...

Signed-off-by: Stefan Hajnoczi <[email protected]>

hw/acpi/cpu_hotplug.c

@@ -59,7 +59,8 @@ static const MemoryRegionOps AcpiCpuHotplug_ops = {
     },
 };
 
-static void acpi_set_cpu_present_bit(AcpiCpuHotplug *g, CPUState *cpu)
+static void acpi_set_cpu_present_bit(AcpiCpuHotplug *g, CPUState *cpu,
+                                     bool *swtchd_to_modern)
 {
     CPUClass *k = CPU_GET_CLASS(cpu);
     int64_t cpu_id;
@@ -68,31 +69,42 @@ static void acpi_set_cpu_present_bit(AcpiCpuHotplug *g, CPUState *cpu)
     if ((cpu_id / 8) >= ACPI_GPE_PROC_LEN) {
         object_property_set_bool(g->device, "cpu-hotplug-legacy", false,
                                  &error_abort);
+        *swtchd_to_modern = true;
         return;
     }
 
+    *swtchd_to_modern = false;
     g->sts[cpu_id / 8] |= (1 << (cpu_id % 8));
 }
 
 void legacy_acpi_cpu_plug_cb(HotplugHandler *hotplug_dev,
                              AcpiCpuHotplug *g, DeviceState *dev, Error **errp)
 {
-    acpi_set_cpu_present_bit(g, CPU(dev));
-    acpi_send_event(DEVICE(hotplug_dev), ACPI_CPU_HOTPLUG_STATUS);
+    bool swtchd_to_modern;
+    Error *local_err = NULL;
+
+    acpi_set_cpu_present_bit(g, CPU(dev), &swtchd_to_modern);
+    if (swtchd_to_modern) {
+        /* propagate the hotplug to the modern interface */
+        hotplug_handler_plug(hotplug_dev, dev, &local_err);
+    } else {
+        acpi_send_event(DEVICE(hotplug_dev), ACPI_CPU_HOTPLUG_STATUS);
+    }
 }
 
 void legacy_acpi_cpu_hotplug_init(MemoryRegion *parent, Object *owner,
                                   AcpiCpuHotplug *gpe_cpu, uint16_t base)
 {
     CPUState *cpu;
+    bool swtchd_to_modern;
 
     memory_region_init_io(&gpe_cpu->io, owner, &AcpiCpuHotplug_ops,
                           gpe_cpu, "acpi-cpu-hotplug", ACPI_GPE_PROC_LEN);
     memory_region_add_subregion(parent, base, &gpe_cpu->io);
     gpe_cpu->device = owner;
 
     CPU_FOREACH(cpu) {
-        acpi_set_cpu_present_bit(gpe_cpu, cpu);
+        acpi_set_cpu_present_bit(gpe_cpu, cpu, &swtchd_to_modern);
     }
 }
 

hw/display/virtio-gpu-base.c

@@ -251,7 +251,11 @@ void
 virtio_gpu_base_device_unrealize(DeviceState *qdev)
 {
     VirtIOGPUBase *g = VIRTIO_GPU_BASE(qdev);
+    VirtIODevice *vdev = VIRTIO_DEVICE(qdev);
 
+    virtio_del_queue(vdev, 0);
+    virtio_del_queue(vdev, 1);
+    virtio_cleanup(vdev);
     migrate_del_blocker(&g->migration_blocker);
 }
 

hw/scsi/vhost-scsi.c

@@ -91,13 +91,13 @@ static int vhost_scsi_start(VHostSCSI *s)
 
     ret = vhost_scsi_common_start(vsc, &local_err);
     if (ret < 0) {
-        error_reportf_err(local_err, "Error starting vhost-scsi");
+        error_reportf_err(local_err, "Error starting vhost-scsi: ");
         return ret;
     }
 
     ret = vhost_scsi_set_endpoint(s);
     if (ret < 0) {
-        error_reportf_err(local_err, "Error setting vhost-scsi endpoint");
+        error_report("Error setting vhost-scsi endpoint");
         vhost_scsi_common_stop(vsc);
     }
 
@@ -165,6 +165,59 @@ static const VMStateDescription vmstate_virtio_vhost_scsi = {
     .pre_save = vhost_scsi_pre_save,
 };
 
+static int vhost_scsi_set_workers(VHostSCSICommon *vsc, bool per_virtqueue)
+{
+    struct vhost_dev *dev = &vsc->dev;
+    struct vhost_vring_worker vq_worker;
+    struct vhost_worker_state worker;
+    int i, ret;
+
+    /* Use default worker */
+    if (!per_virtqueue || dev->nvqs == VHOST_SCSI_VQ_NUM_FIXED + 1) {
+        return 0;
+    }
+
+    /*
+     * ctl/evt share the first worker since it will be rare for them
+     * to send cmds while IO is running.
+     */
+    for (i = VHOST_SCSI_VQ_NUM_FIXED + 1; i < dev->nvqs; i++) {
+        memset(&worker, 0, sizeof(worker));
+
+        ret = dev->vhost_ops->vhost_new_worker(dev, &worker);
+        if (ret == -ENOTTY) {
+            /*
+             * worker ioctls are not implemented so just ignore and
+             * and continue device setup.
+             */
+            warn_report("vhost-scsi: Backend supports a single worker. "
+                        "Ignoring worker_per_virtqueue=true setting.");
+            ret = 0;
+            break;
+        } else if (ret) {
+            break;
+        }
+
+        memset(&vq_worker, 0, sizeof(vq_worker));
+        vq_worker.worker_id = worker.worker_id;
+        vq_worker.index = i;
+
+        ret = dev->vhost_ops->vhost_attach_vring_worker(dev, &vq_worker);
+        if (ret == -ENOTTY) {
+            /*
+             * It's a bug for the kernel to have supported the worker creation
+             * ioctl but not attach.
+             */
+            dev->vhost_ops->vhost_free_worker(dev, &worker);
+            break;
+        } else if (ret) {
+            break;
+        }
+    }
+
+    return ret;
+}
+
 static void vhost_scsi_realize(DeviceState *dev, Error **errp)
 {
     VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev);
@@ -232,6 +285,13 @@ static void vhost_scsi_realize(DeviceState *dev, Error **errp)
         goto free_vqs;
     }
 
+    ret = vhost_scsi_set_workers(vsc, vs->conf.worker_per_virtqueue);
+    if (ret < 0) {
+        error_setg(errp, "vhost-scsi: vhost worker setup failed: %s",
+                   strerror(-ret));
+        goto free_vqs;
+    }
+
     /* At present, channel and lun both are 0 for bootable vhost-scsi disk */
     vsc->channel = 0;
     vsc->lun = 0;
@@ -297,6 +357,8 @@ static Property vhost_scsi_properties[] = {
                                                  VIRTIO_SCSI_F_T10_PI,
                                                  false),
     DEFINE_PROP_BOOL("migratable", VHostSCSICommon, migratable, false),
+    DEFINE_PROP_BOOL("worker_per_virtqueue", VirtIOSCSICommon,
+                     conf.worker_per_virtqueue, false),
     DEFINE_PROP_END_OF_LIST(),
 };
 

hw/scsi/vhost-user-scsi.c

@@ -83,7 +83,8 @@ static void vhost_user_scsi_set_status(VirtIODevice *vdev, uint8_t status)
     if (should_start) {
         ret = vhost_user_scsi_start(s, &local_err);
         if (ret < 0) {
-            error_reportf_err(local_err, "unable to start vhost-user-scsi: %s",
+            error_reportf_err(local_err,
+                              "unable to start vhost-user-scsi: %s: ",
                               strerror(-ret));
             qemu_chr_fe_disconnect(&vs->conf.chardev);
         }

hw/virtio/trace-events

@@ -30,16 +30,16 @@ vhost_user_write(uint32_t req, uint32_t flags) "req:%d flags:0x%"PRIx32""
 vhost_user_create_notifier(int idx, void *n) "idx:%d n:%p"
 
 # vhost-vdpa.c
-vhost_vdpa_dma_map(void *vdpa, int fd, uint32_t msg_type, uint32_t asid, uint64_t iova, uint64_t size, uint64_t uaddr, uint8_t perm, uint8_t type) "vdpa:%p fd: %d msg_type: %"PRIu32" asid: %"PRIu32" iova: 0x%"PRIx64" size: 0x%"PRIx64" uaddr: 0x%"PRIx64" perm: 0x%"PRIx8" type: %"PRIu8
-vhost_vdpa_dma_unmap(void *vdpa, int fd, uint32_t msg_type, uint32_t asid, uint64_t iova, uint64_t size, uint8_t type) "vdpa:%p fd: %d msg_type: %"PRIu32" asid: %"PRIu32" iova: 0x%"PRIx64" size: 0x%"PRIx64" type: %"PRIu8
-vhost_vdpa_listener_begin_batch(void *v, int fd, uint32_t msg_type, uint8_t type)  "vdpa:%p fd: %d msg_type: %"PRIu32" type: %"PRIu8
-vhost_vdpa_listener_commit(void *v, int fd, uint32_t msg_type, uint8_t type)  "vdpa:%p fd: %d msg_type: %"PRIu32" type: %"PRIu8
-vhost_vdpa_listener_region_add_unaligned(void *v, const char *name, uint64_t offset_as, uint64_t offset_page) "vdpa: %p region %s offset_within_address_space %"PRIu64" offset_within_region %"PRIu64
+vhost_vdpa_dma_map(void *vdpa, int fd, uint32_t msg_type, uint32_t asid, uint64_t iova, uint64_t size, uint64_t uaddr, uint8_t perm, uint8_t type) "vdpa_shared:%p fd: %d msg_type: %"PRIu32" asid: %"PRIu32" iova: 0x%"PRIx64" size: 0x%"PRIx64" uaddr: 0x%"PRIx64" perm: 0x%"PRIx8" type: %"PRIu8
+vhost_vdpa_dma_unmap(void *vdpa, int fd, uint32_t msg_type, uint32_t asid, uint64_t iova, uint64_t size, uint8_t type) "vdpa_shared:%p fd: %d msg_type: %"PRIu32" asid: %"PRIu32" iova: 0x%"PRIx64" size: 0x%"PRIx64" type: %"PRIu8
+vhost_vdpa_listener_begin_batch(void *v, int fd, uint32_t msg_type, uint8_t type)  "vdpa_shared:%p fd: %d msg_type: %"PRIu32" type: %"PRIu8
+vhost_vdpa_listener_commit(void *v, int fd, uint32_t msg_type, uint8_t type)  "vdpa_shared:%p fd: %d msg_type: %"PRIu32" type: %"PRIu8
+vhost_vdpa_listener_region_add_unaligned(void *v, const char *name, uint64_t offset_as, uint64_t offset_page) "vdpa_shared: %p region %s offset_within_address_space %"PRIu64" offset_within_region %"PRIu64
 vhost_vdpa_listener_region_add(void *vdpa, uint64_t iova, uint64_t llend, void *vaddr, bool readonly) "vdpa: %p iova 0x%"PRIx64" llend 0x%"PRIx64" vaddr: %p read-only: %d"
-vhost_vdpa_listener_region_del_unaligned(void *v, const char *name, uint64_t offset_as, uint64_t offset_page) "vdpa: %p region %s offset_within_address_space %"PRIu64" offset_within_region %"PRIu64
+vhost_vdpa_listener_region_del_unaligned(void *v, const char *name, uint64_t offset_as, uint64_t offset_page) "vdpa_shared: %p region %s offset_within_address_space %"PRIu64" offset_within_region %"PRIu64
 vhost_vdpa_listener_region_del(void *vdpa, uint64_t iova, uint64_t llend) "vdpa: %p iova 0x%"PRIx64" llend 0x%"PRIx64
 vhost_vdpa_add_status(void *dev, uint8_t status) "dev: %p status: 0x%"PRIx8
-vhost_vdpa_init(void *dev, void *vdpa) "dev: %p vdpa: %p"
+vhost_vdpa_init(void *dev, void *s, void *vdpa) "dev: %p, common dev: %p vdpa: %p"
 vhost_vdpa_cleanup(void *dev, void *vdpa) "dev: %p vdpa: %p"
 vhost_vdpa_memslots_limit(void *dev, int ret) "dev: %p = 0x%x"
 vhost_vdpa_set_mem_table(void *dev, uint32_t nregions, uint32_t padding) "dev: %p nregions: %"PRIu32" padding: 0x%"PRIx32

hw/virtio/vdpa-dev.c

@@ -66,7 +66,6 @@ static void vhost_vdpa_device_realize(DeviceState *dev, Error **errp)
     if (*errp) {
         return;
     }
-    v->vdpa.device_fd = v->vhostfd;
 
     v->vdev_id = vhost_vdpa_device_get_u32(v->vhostfd,
                                            VHOST_VDPA_GET_DEVICE_ID, errp);
@@ -114,7 +113,9 @@ static void vhost_vdpa_device_realize(DeviceState *dev, Error **errp)
                    strerror(-ret));
         goto free_vqs;
     }
-    v->vdpa.iova_range = iova_range;
+    v->vdpa.shared = g_new0(VhostVDPAShared, 1);
+    v->vdpa.shared->device_fd = v->vhostfd;
+    v->vdpa.shared->iova_range = iova_range;
 
     ret = vhost_dev_init(&v->dev, &v->vdpa, VHOST_BACKEND_TYPE_VDPA, 0, NULL);
     if (ret < 0) {
@@ -162,6 +163,7 @@ static void vhost_vdpa_device_realize(DeviceState *dev, Error **errp)
     vhost_dev_cleanup(&v->dev);
 free_vqs:
     g_free(vqs);
+    g_free(v->vdpa.shared);
 out:
     qemu_close(v->vhostfd);
     v->vhostfd = -1;
@@ -184,6 +186,7 @@ static void vhost_vdpa_device_unrealize(DeviceState *dev)
     g_free(s->config);
     g_free(s->dev.vqs);
     vhost_dev_cleanup(&s->dev);
+    g_free(s->vdpa.shared);
     qemu_close(s->vhostfd);
     s->vhostfd = -1;
 }

hw/virtio/vhost-backend.c

@@ -158,6 +158,30 @@ static int vhost_kernel_set_vring_busyloop_timeout(struct vhost_dev *dev,
     return vhost_kernel_call(dev, VHOST_SET_VRING_BUSYLOOP_TIMEOUT, s);
 }
 
+static int vhost_kernel_new_worker(struct vhost_dev *dev,
+                                   struct vhost_worker_state *worker)
+{
+    return vhost_kernel_call(dev, VHOST_NEW_WORKER, worker);
+}
+
+static int vhost_kernel_free_worker(struct vhost_dev *dev,
+                                    struct vhost_worker_state *worker)
+{
+    return vhost_kernel_call(dev, VHOST_FREE_WORKER, worker);
+}
+
+static int vhost_kernel_attach_vring_worker(struct vhost_dev *dev,
+                                            struct vhost_vring_worker *worker)
+{
+    return vhost_kernel_call(dev, VHOST_ATTACH_VRING_WORKER, worker);
+}
+
+static int vhost_kernel_get_vring_worker(struct vhost_dev *dev,
+                                         struct vhost_vring_worker *worker)
+{
+    return vhost_kernel_call(dev, VHOST_GET_VRING_WORKER, worker);
+}
+
 static int vhost_kernel_set_features(struct vhost_dev *dev,
                                      uint64_t features)
 {
@@ -313,6 +337,10 @@ const VhostOps kernel_ops = {
         .vhost_set_vring_err = vhost_kernel_set_vring_err,
         .vhost_set_vring_busyloop_timeout =
                                 vhost_kernel_set_vring_busyloop_timeout,
+        .vhost_get_vring_worker = vhost_kernel_get_vring_worker,
+        .vhost_attach_vring_worker = vhost_kernel_attach_vring_worker,
+        .vhost_new_worker = vhost_kernel_new_worker,
+        .vhost_free_worker = vhost_kernel_free_worker,
         .vhost_set_features = vhost_kernel_set_features,
         .vhost_get_features = vhost_kernel_get_features,
         .vhost_set_backend_cap = vhost_kernel_set_backend_cap,

hw/virtio/vhost-user-rng.c

@@ -129,13 +129,29 @@ static void vu_rng_guest_notifier_mask(VirtIODevice *vdev, int idx, bool mask)
 {
     VHostUserRNG *rng = VHOST_USER_RNG(vdev);
 
+    /*
+     * We don't support interrupts, return early if index is set to
+     * VIRTIO_CONFIG_IRQ_IDX.
+     */
+    if (idx == VIRTIO_CONFIG_IRQ_IDX) {
+        return;
+    }
+
     vhost_virtqueue_mask(&rng->vhost_dev, vdev, idx, mask);
 }
 
 static bool vu_rng_guest_notifier_pending(VirtIODevice *vdev, int idx)
 {
     VHostUserRNG *rng = VHOST_USER_RNG(vdev);
 
+    /*
+     * We don't support interrupts, return early if index is set to
+     * VIRTIO_CONFIG_IRQ_IDX.
+     */
+    if (idx == VIRTIO_CONFIG_IRQ_IDX) {
+        return false;
+    }
+
     return vhost_virtqueue_pending(&rng->vhost_dev, idx);
 }