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

virtio,pci,pc: features,fixes

pci: Initial support for SPDM Responders
cxl: Add support for scan media, feature commands, device patrol scrub
    control, DDR5 ECS control, firmware updates
virtio: in-order support
virtio-net: support for SR-IOV emulation (note: known issues on s390,
                                          might get reverted if not fixed)
smbios: memory device size is now configurable per Machine
cpu: architecture agnostic code to support vCPU Hotplug

Fixes, cleanups all over the place.

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

# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmae9l8PHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRp8fYH/impBH9nViO/WK48io4mLSkl0EUL8Y/xrMvH
# zKFCKaXq8D96VTt1Z4EGKYgwG0voBKZaCEKYU/0ARGnSlSwxINQ8ROCnBWMfn2sx
# yQt08EXVMznNLtXjc6U5zCoCi6SaV85GH40No3MUFXBQt29ZSlFqO/fuHGZHYBwS
# wuVKvTjjNF4EsGt3rS4Qsv6BwZWMM+dE6yXpKWk68kR8IGp+6QGxkMbWt9uEX2Md
# VuemKVnFYw0XGCGy5K+ZkvoA2DGpEw0QxVSOMs8CI55Oc9SkTKz5fUSzXXGo1if+
# M1CTjOPJu6pMym6gy6XpFa8/QioDA/jE2vBQvfJ64TwhJDV159s=
# =k8e9
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 23 Jul 2024 10:16:31 AM AEST
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "mst@redhat.com"
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [undefined]
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>" [undefined]
# gpg: WARNING: The key's User ID is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# 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: (61 commits)
  hw/nvme: Add SPDM over DOE support
  backends: Initial support for SPDM socket support
  hw/pci: Add all Data Object Types defined in PCIe r6.0
  tests/acpi: Add expected ACPI AML files for RISC-V
  tests/qtest/bios-tables-test.c: Enable basic testing for RISC-V
  tests/acpi: Add empty ACPI data files for RISC-V
  tests/qtest/bios-tables-test.c: Remove the fall back path
  tests/acpi: update expected DSDT blob for aarch64 and microvm
  acpi/gpex: Create PCI link devices outside PCI root bridge
  tests/acpi: Allow DSDT acpi table changes for aarch64
  hw/riscv/virt-acpi-build.c: Update the HID of RISC-V UART
  hw/riscv/virt-acpi-build.c: Add namespace devices for PLIC and APLIC
  virtio-iommu: Add trace point on virtio_iommu_detach_endpoint_from_domain
  hw/vfio/common: Add vfio_listener_region_del_iommu trace event
  virtio-iommu: Remove the end point on detach
  virtio-iommu: Free [host_]resv_ranges on unset_iommu_devices
  virtio-iommu: Remove probe_done
  Revert "virtio-iommu: Clear IOMMUDevice when VFIO device is unplugged"
  gdbstub: Add helper function to unregister GDB register space
  physmem: Add helper function to destroy CPU AddressSpace
  ...

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 128 insertions, 3 deletions

diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
index 583a224163..397c261c3c 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -872,6 +872,46 @@ static void virtqueue_packed_fill(VirtQueue *vq, const VirtQueueElement *elem,
     vq->used_elems[idx].ndescs = elem->ndescs;
 }
 
+static void virtqueue_ordered_fill(VirtQueue *vq, const VirtQueueElement *elem,
+                                   unsigned int len)
+{
+    unsigned int i, steps, max_steps;
+
+    i = vq->used_idx % vq->vring.num;
+    steps = 0;
+    /*
+     * We shouldn't need to increase 'i' by more than the distance
+     * between used_idx and last_avail_idx.
+     */
+    max_steps = (vq->last_avail_idx - vq->used_idx) % vq->vring.num;
+
+    /* Search for element in vq->used_elems */
+    while (steps <= max_steps) {
+        /* Found element, set length and mark as filled */
+        if (vq->used_elems[i].index == elem->index) {
+            vq->used_elems[i].len = len;
+            vq->used_elems[i].in_order_filled = true;
+            break;
+        }
+
+        i += vq->used_elems[i].ndescs;
+        steps += vq->used_elems[i].ndescs;
+
+        if (i >= vq->vring.num) {
+            i -= vq->vring.num;
+        }
+    }
+
+    /*
+     * We should be able to find a matching VirtQueueElement in
+     * used_elems. If we don't, this is an error.
+     */
+    if (steps >= max_steps) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: %s cannot fill buffer id %u\n",
+                      __func__, vq->vdev->name, elem->index);
+    }
+}
+
 static void virtqueue_packed_fill_desc(VirtQueue *vq,
                                        const VirtQueueElement *elem,
                                        unsigned int idx,
@@ -922,7 +962,9 @@ void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem,
         return;
     }
 
-    if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) {
+    if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_IN_ORDER)) {
+        virtqueue_ordered_fill(vq, elem, len);
+    } else if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) {
         virtqueue_packed_fill(vq, elem, len, idx);
     } else {
         virtqueue_split_fill(vq, elem, len, idx);
@@ -981,6 +1023,73 @@ static void virtqueue_packed_flush(VirtQueue *vq, unsigned int count)
     }
 }
 
+static void virtqueue_ordered_flush(VirtQueue *vq)
+{
+    unsigned int i = vq->used_idx % vq->vring.num;
+    unsigned int ndescs = 0;
+    uint16_t old = vq->used_idx;
+    uint16_t new;
+    bool packed;
+    VRingUsedElem uelem;
+
+    packed = virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED);
+
+    if (packed) {
+        if (unlikely(!vq->vring.desc)) {
+            return;
+        }
+    } else if (unlikely(!vq->vring.used)) {
+        return;
+    }
+
+    /* First expected in-order element isn't ready, nothing to do */
+    if (!vq->used_elems[i].in_order_filled) {
+        return;
+    }
+
+    /* Search for filled elements in-order */
+    while (vq->used_elems[i].in_order_filled) {
+        /*
+         * First entry for packed VQs is written last so the guest
+         * doesn't see invalid descriptors.
+         */
+        if (packed && i != vq->used_idx) {
+            virtqueue_packed_fill_desc(vq, &vq->used_elems[i], ndescs, false);
+        } else if (!packed) {
+            uelem.id = vq->used_elems[i].index;
+            uelem.len = vq->used_elems[i].len;
+            vring_used_write(vq, &uelem, i);
+        }
+
+        vq->used_elems[i].in_order_filled = false;
+        ndescs += vq->used_elems[i].ndescs;
+        i += vq->used_elems[i].ndescs;
+        if (i >= vq->vring.num) {
+            i -= vq->vring.num;
+        }
+    }
+
+    if (packed) {
+        virtqueue_packed_fill_desc(vq, &vq->used_elems[vq->used_idx], 0, true);
+        vq->used_idx += ndescs;
+        if (vq->used_idx >= vq->vring.num) {
+            vq->used_idx -= vq->vring.num;
+            vq->used_wrap_counter ^= 1;
+            vq->signalled_used_valid = false;
+        }
+    } else {
+        /* Make sure buffer is written before we update index. */
+        smp_wmb();
+        new = old + ndescs;
+        vring_used_idx_set(vq, new);
+        if (unlikely((int16_t)(new - vq->signalled_used) <
+                     (uint16_t)(new - old))) {
+            vq->signalled_used_valid = false;
+        }
+    }
+    vq->inuse -= ndescs;
+}
+
 void virtqueue_flush(VirtQueue *vq, unsigned int count)
 {
     if (virtio_device_disabled(vq->vdev)) {
@@ -988,7 +1097,9 @@ void virtqueue_flush(VirtQueue *vq, unsigned int count)
         return;
     }
 
-    if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) {
+    if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_IN_ORDER)) {
+        virtqueue_ordered_flush(vq);
+    } else if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) {
         virtqueue_packed_flush(vq, count);
     } else {
         virtqueue_split_flush(vq, count);
@@ -1505,7 +1616,7 @@ static void *virtqueue_alloc_element(size_t sz, unsigned out_num, unsigned in_nu
 
 static void *virtqueue_split_pop(VirtQueue *vq, size_t sz)
 {
-    unsigned int i, head, max;
+    unsigned int i, head, max, idx;
     VRingMemoryRegionCaches *caches;
     MemoryRegionCache indirect_desc_cache;
     MemoryRegionCache *desc_cache;
@@ -1629,6 +1740,13 @@ static void *virtqueue_split_pop(VirtQueue *vq, size_t sz)
         elem->in_sg[i] = iov[out_num + i];
     }
 
+    if (virtio_vdev_has_feature(vdev, VIRTIO_F_IN_ORDER)) {
+        idx = (vq->last_avail_idx - 1) % vq->vring.num;
+        vq->used_elems[idx].index = elem->index;
+        vq->used_elems[idx].len = elem->len;
+        vq->used_elems[idx].ndescs = elem->ndescs;
+    }
+
     vq->inuse++;
 
     trace_virtqueue_pop(vq, elem, elem->in_num, elem->out_num);
@@ -1762,6 +1880,13 @@ static void *virtqueue_packed_pop(VirtQueue *vq, size_t sz)
 
     elem->index = id;
     elem->ndescs = (desc_cache == &indirect_desc_cache) ? 1 : elem_entries;
+
+    if (virtio_vdev_has_feature(vdev, VIRTIO_F_IN_ORDER)) {
+        vq->used_elems[vq->last_avail_idx].index = elem->index;
+        vq->used_elems[vq->last_avail_idx].len = elem->len;
+        vq->used_elems[vq->last_avail_idx].ndescs = elem->ndescs;
+    }
+
     vq->last_avail_idx += elem->ndescs;
     vq->inuse += elem->ndescs;