Merge tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/mst/qemu into staging

virtio,pc,pci: features, cleanups, fixes

more memslots support in libvhost-user
support PCIe Gen5/Gen6 link speeds in pcie
more traces in vdpa
network simulation devices support in vdpa
SMBIOS type 9 descriptor implementation
Bump max_cpus to 4096 vcpus in q35
aw-bits and granule options in VIRTIO-IOMMU
Support report NUMA nodes for device memory using GI in acpi
Beginning of shutdown event support in pvpanic

fixes, cleanups all over the place.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmXw0TMPHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRp8x4H+gLMoGwaGAX7gDGPgn2Ix4j/3kO77ZJ9X9k/
# 1KqZu/9eMS1j2Ei+vZqf05w7qRjxxhwDq3ilEXF/+UFqgAehLqpRRB8j5inqvzYt
# +jv0DbL11PBp/oFjWcytm5CbiVsvq8KlqCF29VNzc162XdtcduUOWagL96y8lJfZ
# uPrOoyeR7SMH9lp3LLLHWgu+9W4nOS03RroZ6Umj40y5B7yR0Rrppz8lMw5AoQtr
# 0gMRnFhYXeiW6CXdz+Tzcr7XfvkkYDi/j7ibiNSURLBfOpZa6Y8+kJGKxz5H1K1G
# 6ZY4PBcOpQzl+NMrktPHogczgJgOK10t+1i/R3bGZYw2Qn/93Eg=
# =C0UU
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 12 Mar 2024 22:03:31 GMT
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "mst@redhat.com"
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [full]
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>" [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: (68 commits)
  docs/specs/pvpanic: document shutdown event
  hw/cxl: Fix missing reserved data in CXL Device DVSEC
  hmat acpi: Fix out of bounds access due to missing use of indirection
  hmat acpi: Do not add Memory Proximity Domain Attributes Structure targetting non existent memory.
  qemu-options.hx: Document the virtio-iommu-pci aw-bits option
  hw/arm/virt: Set virtio-iommu aw-bits default value to 48
  hw/i386/q35: Set virtio-iommu aw-bits default value to 39
  virtio-iommu: Add an option to define the input range width
  virtio-iommu: Trace domain range limits as unsigned int
  qemu-options.hx: Document the virtio-iommu-pci granule option
  virtio-iommu: Change the default granule to the host page size
  virtio-iommu: Add a granule property
  hw/i386/acpi-build: Add support for SRAT Generic Initiator structures
  hw/acpi: Implement the SRAT GI affinity structure
  qom: new object to associate device to NUMA node
  hw/i386/pc: Inline pc_cmos_init() into pc_cmos_init_late() and remove it
  hw/i386/pc: Set "normal" boot device order in pc_basic_device_init()
  hw/i386/pc: Avoid one use of the current_machine global
  hw/i386/pc: Remove "rtc_state" link again
  Revert "hw/i386/pc: Confine system flash handling to pc_sysfw"
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

# Conflicts:
#	hw/core/machine.c

1 files changed, 186 insertions, 3 deletions

diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index cb6940fc0e..eaaf86402c 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -1442,6 +1442,155 @@ int virtio_pci_add_shm_cap(VirtIOPCIProxy *proxy,
     return virtio_pci_add_mem_cap(proxy, &cap.cap);
 }
 
+/* Called within call_rcu().  */
+static void bitmap_free_region_cache(BitmapMemoryRegionCaches *caches)
+{
+    assert(caches != NULL);
+    address_space_cache_destroy(&caches->bitmap);
+    g_free(caches);
+}
+
+static void lm_disable(VirtIODevice *vdev)
+{
+    BitmapMemoryRegionCaches *caches;
+    caches = qatomic_read(&vdev->caches);
+    qatomic_rcu_set(&vdev->caches, NULL);
+    if (caches) {
+        call_rcu(caches, bitmap_free_region_cache, rcu);
+    }
+}
+
+static void lm_enable(VirtIODevice *vdev)
+{
+    BitmapMemoryRegionCaches *old = vdev->caches;
+    BitmapMemoryRegionCaches *new = NULL;
+    hwaddr addr, end, size;
+    int64_t len;
+
+    addr = vdev->lm_base_addr_low | ((hwaddr)(vdev->lm_base_addr_high) << 32);
+    end = vdev->lm_end_addr_low | ((hwaddr)(vdev->lm_end_addr_high) << 32);
+    size = end - addr;
+    if (size <= 0) {
+        error_report("Invalid lm size.");
+        return;
+    }
+
+    new = g_new0(BitmapMemoryRegionCaches, 1);
+    len = address_space_cache_init(&new->bitmap, vdev->dma_as, addr, size,
+                                   true);
+    if (len < size) {
+        virtio_error(vdev, "Cannot map bitmap");
+        goto err_bitmap;
+    }
+    qatomic_rcu_set(&vdev->caches, new);
+
+    if (old) {
+        call_rcu(old, bitmap_free_region_cache, rcu);
+    }
+
+    return;
+
+err_bitmap:
+    address_space_cache_destroy(&new->bitmap);
+    g_free(new);
+}
+
+static uint64_t virtio_pci_lm_read(void *opaque, hwaddr addr,
+                                       unsigned size)
+{
+    VirtIOPCIProxy *proxy = opaque;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+    hwaddr offset_end = LM_VRING_STATE_OFFSET +
+                        virtio_pci_queue_mem_mult(proxy) * VIRTIO_QUEUE_MAX;
+    uint32_t val;
+    int qid;
+
+    if (vdev == NULL) {
+        return UINT64_MAX;
+    }
+    switch (addr) {
+    case LM_LOGGING_CTRL:
+        val = vdev->lm_logging_ctrl;
+        break;
+    case LM_BASE_ADDR_LOW:
+        val = vdev->lm_base_addr_low;
+        break;
+    case LM_BASE_ADDR_HIGH:
+        val = vdev->lm_base_addr_high;
+        break;
+    case LM_END_ADDR_LOW:
+        val = vdev->lm_end_addr_low;
+        break;
+    case LM_END_ADDR_HIGH:
+        val = vdev->lm_end_addr_high;
+        break;
+    default:
+        if (addr >= LM_VRING_STATE_OFFSET && addr <= offset_end) {
+            qid = (addr - LM_VRING_STATE_OFFSET) /
+                  virtio_pci_queue_mem_mult(proxy);
+            val = virtio_queue_get_vring_states(vdev, qid);
+        } else
+            val = 0;
+
+        break;
+    }
+
+    return val;
+}
+
+static void virtio_pci_lm_write(void *opaque, hwaddr addr,
+                                    uint64_t val, unsigned size)
+{
+    VirtIOPCIProxy *proxy = opaque;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+    hwaddr offset_end = LM_VRING_STATE_OFFSET +
+                        virtio_pci_queue_mem_mult(proxy) * VIRTIO_QUEUE_MAX;
+    int qid;
+
+    if (vdev == NULL) {
+        return;
+    }
+
+    switch (addr) {
+    case LM_LOGGING_CTRL:
+        vdev->lm_logging_ctrl = val;
+        switch (val) {
+        case LM_DISABLE:
+            lm_disable(vdev);
+            break;
+        case LM_ENABLE:
+            lm_enable(vdev);
+            break;
+        default:
+            virtio_error(vdev, "Unsupport LM_LOGGING_CTRL value: %"PRIx64,
+                         val);
+                break;
+        };
+
+        break;
+    case LM_BASE_ADDR_LOW:
+        vdev->lm_base_addr_low = val;
+        break;
+    case LM_BASE_ADDR_HIGH:
+        vdev->lm_base_addr_high = val;
+        break;
+    case LM_END_ADDR_LOW:
+        vdev->lm_end_addr_low = val;
+        break;
+    case LM_END_ADDR_HIGH:
+        vdev->lm_end_addr_high = val;
+        break;
+    default:
+        if (addr >= LM_VRING_STATE_OFFSET && addr <= offset_end) {
+            qid = (addr - LM_VRING_STATE_OFFSET) /
+                  virtio_pci_queue_mem_mult(proxy);
+            virtio_queue_set_vring_states(vdev, qid, val);
+        } else
+            virtio_error(vdev, "Unsupport addr: %"PRIx64, addr);
+        break;
+    }
+}
+
 static uint64_t virtio_pci_common_read(void *opaque, hwaddr addr,
                                        unsigned size)
 {
@@ -1823,6 +1972,15 @@ static void virtio_pci_modern_regions_init(VirtIOPCIProxy *proxy,
         },
         .endianness = DEVICE_LITTLE_ENDIAN,
     };
+    static const MemoryRegionOps lm_ops = {
+        .read = virtio_pci_lm_read,
+        .write = virtio_pci_lm_write,
+        .impl = {
+            .min_access_size = 1,
+            .max_access_size = 4,
+        },
+        .endianness = DEVICE_LITTLE_ENDIAN,
+    };
     g_autoptr(GString) name = g_string_new(NULL);
 
     g_string_printf(name, "virtio-pci-common-%s", vdev_name);
@@ -1859,6 +2017,14 @@ static void virtio_pci_modern_regions_init(VirtIOPCIProxy *proxy,
                           proxy,
                           name->str,
                           proxy->notify_pio.size);
+    if (proxy->flags & VIRTIO_PCI_FLAG_VDPA) {
+        g_string_printf(name, "virtio-pci-lm-%s", vdev_name);
+        memory_region_init_io(&proxy->lm.mr, OBJECT(proxy),
+                          &lm_ops,
+                          proxy,
+                          name->str,
+                          proxy->lm.size);
+    }
 }
 
 static void virtio_pci_modern_region_map(VirtIOPCIProxy *proxy,
@@ -2021,6 +2187,10 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
         virtio_pci_modern_mem_region_map(proxy, &proxy->isr, &cap);
         virtio_pci_modern_mem_region_map(proxy, &proxy->device, &cap);
         virtio_pci_modern_mem_region_map(proxy, &proxy->notify, &notify.cap);
+        if (proxy->flags & VIRTIO_PCI_FLAG_VDPA) {
+            memory_region_add_subregion(&proxy->modern_bar,
+                                        proxy->lm.offset, &proxy->lm.mr);
+        }
 
         if (modern_pio) {
             memory_region_init(&proxy->io_bar, OBJECT(proxy),
@@ -2090,6 +2260,9 @@ static void virtio_pci_device_unplugged(DeviceState *d)
         virtio_pci_modern_mem_region_unmap(proxy, &proxy->isr);
         virtio_pci_modern_mem_region_unmap(proxy, &proxy->device);
         virtio_pci_modern_mem_region_unmap(proxy, &proxy->notify);
+        if (proxy->flags & VIRTIO_PCI_FLAG_VDPA) {
+            memory_region_del_subregion(&proxy->modern_bar, &proxy->lm.mr);
+        }
         if (modern_pio) {
             virtio_pci_modern_io_region_unmap(proxy, &proxy->notify_pio);
         }
@@ -2144,9 +2317,17 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
     proxy->notify_pio.type = VIRTIO_PCI_CAP_NOTIFY_CFG;
 
     /* subclasses can enforce modern, so do this unconditionally */
-    memory_region_init(&proxy->modern_bar, OBJECT(proxy), "virtio-pci",
-                       /* PCI BAR regions must be powers of 2 */
-                       pow2ceil(proxy->notify.offset + proxy->notify.size));
+    if (!(proxy->flags & VIRTIO_PCI_FLAG_VDPA)) {
+        memory_region_init(&proxy->modern_bar, OBJECT(proxy), "virtio-pci",
+                           /* PCI BAR regions must be powers of 2 */
+                           pow2ceil(proxy->notify.offset + proxy->notify.size));
+    } else {
+        proxy->lm.offset = proxy->notify.offset + proxy->notify.size;
+        proxy->lm.size = 0x20 + VIRTIO_QUEUE_MAX * 4;
+        memory_region_init(&proxy->modern_bar, OBJECT(proxy), "virtio-pci",
+                           /* PCI BAR regions must be powers of 2 */
+                           pow2ceil(proxy->lm.offset + proxy->lm.size));
+    }
 
     if (proxy->disable_legacy == ON_OFF_AUTO_AUTO) {
         proxy->disable_legacy = pcie_port ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF;
@@ -2301,6 +2482,8 @@ static Property virtio_pci_properties[] = {
                     VIRTIO_PCI_FLAG_INIT_FLR_BIT, true),
     DEFINE_PROP_BIT("aer", VirtIOPCIProxy, flags,
                     VIRTIO_PCI_FLAG_AER_BIT, false),
+    DEFINE_PROP_BIT("vdpa", VirtIOPCIProxy, flags,
+                    VIRTIO_PCI_FLAG_VDPA_BIT, false),
     DEFINE_PROP_END_OF_LIST(),
 };