virtio,pc,pci: bug fixes, new test

Some small bug fixes, notably a fix for a regression
 in cpu hotplug after migration. I also included a
 new test, just to help make sure we don't regress cxl.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmdHJRIPHG1zdEByZWRo
 YXQuY29tAAoJECgfDbjSjVRpTkQIAJYFpFTPRnO8mA6gurfheB7Jt0ywAMrjKWfg
 uEkfZXXSQeCS8NBNPoZt7S8AE6xHE2a4b5lNWiS4a4coFmgTjtKPM8YsU01riyRk
 EasRxynGua2XGUWGK93r9L27v9zGz/vRC0Lujmw3VAUKGeL7a17KzmxwXLXe+DzS
 PgcI/H5hqoCDalT8aF6wOEDaWIHeo4dauDubYavW/+yaPtUvmy9MBkXbIV4iYqT5
 V6geeYIKW/yE/GHxxXOw/RE1FgpiZhebtQP26jPTSk0z/JaV5S0DNYs07joXmbaU
 fW5LSLgH3+oDI/GIhvsZ6hP87rVXBdaAogeJqT8SsuChBR55TpY=
 =B7KB
 -----END PGP SIGNATURE-----

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

virtio,pc,pci: bug fixes, new test

Some small bug fixes, notably a fix for a regression
in cpu hotplug after migration. I also included a
new test, just to help make sure we don't regress cxl.

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

# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmdHJRIPHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRpTkQIAJYFpFTPRnO8mA6gurfheB7Jt0ywAMrjKWfg
# uEkfZXXSQeCS8NBNPoZt7S8AE6xHE2a4b5lNWiS4a4coFmgTjtKPM8YsU01riyRk
# EasRxynGua2XGUWGK93r9L27v9zGz/vRC0Lujmw3VAUKGeL7a17KzmxwXLXe+DzS
# PgcI/H5hqoCDalT8aF6wOEDaWIHeo4dauDubYavW/+yaPtUvmy9MBkXbIV4iYqT5
# V6geeYIKW/yE/GHxxXOw/RE1FgpiZhebtQP26jPTSk0z/JaV5S0DNYs07joXmbaU
# fW5LSLgH3+oDI/GIhvsZ6hP87rVXBdaAogeJqT8SsuChBR55TpY=
# =B7KB
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 27 Nov 2024 13:56:34 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:
  vhost: fail device start if iotlb update fails
  bios-tables-test: Add data for complex numa test (GI, GP etc)
  bios-tables-test: Add complex SRAT / HMAT test for GI GP
  bios-tables-test: Allow for new acpihmat-generic-x test data.
  qapi/qom: Change Since entry for AcpiGenericPortProperties to 9.2
  hw/acpi: Fix size of HID in build_append_srat_acpi_device_handle()
  qapi: fix device-sync-config since-version
  hw/cxl: Check for zero length features in cmd_features_set_feature()
  tests/acpi: update expected blobs
  Revert "hw/acpi: Make CPUs ACPI `presence` conditional during vCPU hot-unplug"
  Revert "hw/acpi: Update ACPI `_STA` method with QOM vCPU ACPI Hotplug states"
  qtest: allow ACPI DSDT Table changes
  vhost_net: fix assertion triggered by batch of host notifiers processing

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

hw/acpi/aml-build.c

@@ -1960,7 +1960,7 @@ static void build_append_srat_acpi_device_handle(GArray *table_data,
 {
     assert(strlen(hid) == 8);
     /* Device Handle - ACPI */
-    for (int i = 0; i < sizeof(hid); i++) {
+    for (int i = 0; i < 8; i++) {
         build_append_int_noprefix(table_data, hid[i], 1);
     }
     build_append_int_noprefix(table_data, uid, 4);

hw/acpi/cpu.c

@@ -50,18 +50,6 @@ void acpi_cpu_ospm_status(CPUHotplugState *cpu_st, ACPIOSTInfoList ***list)
     }
 }
 
-static bool check_cpu_enabled_status(DeviceState *dev)
-{
-    CPUClass *k = dev ? CPU_GET_CLASS(dev) : NULL;
-    CPUState *cpu = CPU(dev);
-
-    if (cpu && (!k->cpu_enabled_status || k->cpu_enabled_status(cpu))) {
-        return true;
-    }
-
-    return false;
-}
-
 static uint64_t cpu_hotplug_rd(void *opaque, hwaddr addr, unsigned size)
 {
     uint64_t val = 0;
@@ -75,11 +63,10 @@ static uint64_t cpu_hotplug_rd(void *opaque, hwaddr addr, unsigned size)
     cdev = &cpu_st->devs[cpu_st->selector];
     switch (addr) {
     case ACPI_CPU_FLAGS_OFFSET_RW: /* pack and return is_* fields */
-        val |= check_cpu_enabled_status(DEVICE(cdev->cpu)) ? 1 : 0;
+        val |= cdev->cpu ? 1 : 0;
         val |= cdev->is_inserting ? 2 : 0;
         val |= cdev->is_removing  ? 4 : 0;
         val |= cdev->fw_remove  ? 16 : 0;
-        val |= cdev->cpu ? 32 : 0;
         trace_cpuhp_acpi_read_flags(cpu_st->selector, val);
         break;
     case ACPI_CPU_CMD_DATA_OFFSET_RW:
@@ -246,17 +233,6 @@ void cpu_hotplug_hw_init(MemoryRegion *as, Object *owner,
     memory_region_add_subregion(as, base_addr, &state->ctrl_reg);
 }
 
-static bool should_remain_acpi_present(DeviceState *dev)
-{
-    CPUClass *k = CPU_GET_CLASS(dev);
-    /*
-     * A system may contain CPUs that are always present on one die, NUMA node,
-     * or socket, yet may be non-present on another simultaneously. Check from
-     * architecture specific code.
-     */
-    return k->cpu_persistent_status && k->cpu_persistent_status(CPU(dev));
-}
-
 static AcpiCpuStatus *get_cpu_status(CPUHotplugState *cpu_st, DeviceState *dev)
 {
     CPUClass *k = CPU_GET_CLASS(dev);
@@ -313,9 +289,7 @@ void acpi_cpu_unplug_cb(CPUHotplugState *cpu_st,
         return;
     }
 
-    if (!should_remain_acpi_present(dev)) {
     cdev->cpu = NULL;
-    }
 }
 
 static const VMStateDescription vmstate_cpuhp_sts = {
@@ -362,7 +336,6 @@ const VMStateDescription vmstate_cpu_hotplug = {
 #define CPU_REMOVE_EVENT  "CRMV"
 #define CPU_EJECT_EVENT   "CEJ0"
 #define CPU_FW_EJECT_EVENT "CEJF"
-#define CPU_PRESENT       "CPRS"
 
 void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
                     build_madt_cpu_fn build_madt_cpu, hwaddr base_addr,
@@ -423,9 +396,7 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
         aml_append(field, aml_named_field(CPU_EJECT_EVENT, 1));
         /* tell firmware to do device eject, write only */
         aml_append(field, aml_named_field(CPU_FW_EJECT_EVENT, 1));
-        /* 1 if present, read only */
-        aml_append(field, aml_named_field(CPU_PRESENT, 1));
-        aml_append(field, aml_reserved_field(2));
+        aml_append(field, aml_reserved_field(3));
         aml_append(field, aml_named_field(CPU_COMMAND, 8));
         aml_append(cpu_ctrl_dev, field);
 
@@ -455,7 +426,6 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
         Aml *ctrl_lock = aml_name("%s.%s", cphp_res_path, CPU_LOCK);
         Aml *cpu_selector = aml_name("%s.%s", cphp_res_path, CPU_SELECTOR);
         Aml *is_enabled = aml_name("%s.%s", cphp_res_path, CPU_ENABLED);
-        Aml *is_present = aml_name("%s.%s", cphp_res_path, CPU_PRESENT);
         Aml *cpu_cmd = aml_name("%s.%s", cphp_res_path, CPU_COMMAND);
         Aml *cpu_data = aml_name("%s.%s", cphp_res_path, CPU_DATA);
         Aml *ins_evt = aml_name("%s.%s", cphp_res_path, CPU_INSERT_EVENT);
@@ -484,26 +454,13 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
         {
             Aml *idx = aml_arg(0);
             Aml *sta = aml_local(0);
-            Aml *ifctx2;
-            Aml *else_ctx;
 
             aml_append(method, aml_acquire(ctrl_lock, 0xFFFF));
             aml_append(method, aml_store(idx, cpu_selector));
             aml_append(method, aml_store(zero, sta));
-            ifctx = aml_if(aml_equal(is_present, one));
+            ifctx = aml_if(aml_equal(is_enabled, one));
             {
-                ifctx2 = aml_if(aml_equal(is_enabled, one));
-                {
-                    /* cpu is present and enabled */
-                    aml_append(ifctx2, aml_store(aml_int(0xF), sta));
-                }
-                aml_append(ifctx, ifctx2);
-                else_ctx = aml_else();
-                {
-                    /* cpu is present but disabled */
-                    aml_append(else_ctx, aml_store(aml_int(0xD), sta));
-                }
-                aml_append(ifctx, else_ctx);
+                aml_append(ifctx, aml_store(aml_int(0xF), sta));
             }
             aml_append(method, ifctx);
             aml_append(method, aml_release(ctrl_lock));

hw/cxl/cxl-mailbox-utils.c

@@ -1288,6 +1288,10 @@ static CXLRetCode cmd_features_set_feature(const struct cxl_cmd *cmd,
     set_feat_info->data_offset = hdr->offset;
     bytes_to_copy = len_in - sizeof(CXLSetFeatureInHeader);
 
+    if (bytes_to_copy == 0) {
+        return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+    }
+
     if (qemu_uuid_is_equal(&hdr->uuid, &patrol_scrub_uuid)) {
         if (hdr->version != CXL_MEMDEV_PS_SET_FEATURE_VERSION) {
             return CXL_MBOX_UNSUPPORTED;

hw/net/vhost_net.c

@@ -229,9 +229,24 @@ static int vhost_net_enable_notifiers(VirtIODevice *dev,
     int nvhosts = data_queue_pairs + cvq;
     struct vhost_net *net;
     struct vhost_dev *hdev;
-    int r, i, j;
+    int r, i, j, k;
     NetClientState *peer;
 
+    /*
+     * We will pass the notifiers to the kernel, make sure that QEMU
+     * doesn't interfere.
+     */
+    for (i = 0; i < nvhosts; i++) {
+        r = virtio_device_grab_ioeventfd(dev);
+        if (r < 0) {
+            error_report("vhost %d binding does not support host notifiers", i);
+            for (k = 0; k < i; k++) {
+                virtio_device_release_ioeventfd(dev);
+            }
+            return r;
+        }
+    }
+
     /*
      * Batch all the host notifiers in a single transaction to avoid
      * quadratic time complexity in address_space_update_ioeventfds().
@@ -247,16 +262,6 @@ static int vhost_net_enable_notifiers(VirtIODevice *dev,
 
         net = get_vhost_net(peer);
         hdev = &net->dev;
-        /*
-         * We will pass the notifiers to the kernel, make sure that QEMU
-         * doesn't interfere.
-         */
-        r = virtio_device_grab_ioeventfd(dev);
-        if (r < 0) {
-            error_report("binding does not support host notifiers");
-            memory_region_transaction_commit();
-            goto fail_nvhosts;
-        }
 
         for (j = 0; j < hdev->nvqs; j++) {
             r = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus),
@@ -277,6 +282,14 @@ static int vhost_net_enable_notifiers(VirtIODevice *dev,
     return 0;
 fail_nvhosts:
     vhost_net_disable_notifiers_nvhosts(dev, ncs, data_queue_pairs, i);
+    /*
+     * This for loop starts from i+1, not i, because the i-th ioeventfd
+     * has already been released in vhost_dev_disable_notifiers_nvqs().
+     */
+    for (k = i + 1; k < nvhosts; k++) {
+        virtio_device_release_ioeventfd(dev);
+    }
+
     return r;
 }
 

hw/virtio/vhost.c

@@ -2095,11 +2095,22 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings)
          * vhost-kernel code requires for this.*/
         for (i = 0; i < hdev->nvqs; ++i) {
             struct vhost_virtqueue *vq = hdev->vqs + i;
-            vhost_device_iotlb_miss(hdev, vq->used_phys, true);
+            r = vhost_device_iotlb_miss(hdev, vq->used_phys, true);
+            if (r) {
+                goto fail_iotlb;
+            }
         }
     }
     vhost_start_config_intr(hdev);
     return 0;
+fail_iotlb:
+    if (vhost_dev_has_iommu(hdev) &&
+        hdev->vhost_ops->vhost_set_iotlb_callback) {
+        hdev->vhost_ops->vhost_set_iotlb_callback(hdev, false);
+    }
+    if (hdev->vhost_ops->vhost_dev_start) {
+        hdev->vhost_ops->vhost_dev_start(hdev, false);
+    }
 fail_start:
     if (vrings) {
         vhost_dev_set_vring_enable(hdev, false);

include/hw/core/cpu.h

@@ -158,8 +158,6 @@ struct CPUClass {
     void (*dump_state)(CPUState *cpu, FILE *, int flags);
     void (*query_cpu_fast)(CPUState *cpu, CpuInfoFast *value);
     int64_t (*get_arch_id)(CPUState *cpu);
-    bool (*cpu_persistent_status)(CPUState *cpu);
-    bool (*cpu_enabled_status)(CPUState *cpu);
     void (*set_pc)(CPUState *cpu, vaddr value);
     vaddr (*get_pc)(CPUState *cpu);
     int (*gdb_read_register)(CPUState *cpu, GByteArray *buf, int reg);

qapi/qdev.json

@@ -182,7 +182,7 @@
 #
 # @unstable: The command is experimental.
 #
-# Since: 9.1
+# Since: 9.2
 ##
 { 'command': 'device-sync-config',
   'features': [ 'unstable' ],

qapi/qom.json

@@ -877,7 +877,7 @@
 #     complex as there may be interleaving across multiple devices
 #     and shared links in the path.
 #
-# Since: 9.1
+# Since: 9.2
 ##
 { 'struct': 'AcpiGenericPortProperties',
   'data': { 'pci-bus': 'str',

tests/qtest/bios-tables-test.c

@@ -1936,6 +1936,101 @@ static void test_acpi_q35_tcg_acpi_hmat_noinitiator(void)
     free_test_data(&data);
 }
 
+/* Test intended to hit corner cases of SRAT and HMAT */
+static void test_acpi_q35_tcg_acpi_hmat_generic_x(void)
+{
+    test_data data = {};
+
+    data.machine = MACHINE_Q35;
+    data.arch    = "x86";
+    data.variant = ".acpihmat-generic-x";
+    test_acpi_one(" -machine hmat=on,cxl=on"
+                  " -smp 3,sockets=3"
+                  " -m 128M,maxmem=384M,slots=2"
+                  " -device pcie-root-port,chassis=1,id=pci.1"
+                  " -device pci-testdev,bus=pci.1,"
+                  "multifunction=on,addr=00.0"
+                  " -device pci-testdev,bus=pci.1,addr=00.1"
+                  " -device pci-testdev,bus=pci.1,id=gidev,addr=00.2"
+                  " -device pxb-cxl,bus_nr=64,bus=pcie.0,id=cxl.1"
+                  " -object memory-backend-ram,size=64M,id=ram0"
+                  " -object memory-backend-ram,size=64M,id=ram1"
+                  " -numa node,nodeid=0,cpus=0,memdev=ram0"
+                  " -numa node,nodeid=1"
+                  " -object acpi-generic-initiator,id=gi0,pci-dev=gidev,node=1"
+                  " -numa node,nodeid=2"
+                  " -object acpi-generic-port,id=gp0,pci-bus=cxl.1,node=2"
+                  " -numa node,nodeid=3,cpus=1"
+                  " -numa node,nodeid=4,memdev=ram1"
+                  " -numa node,nodeid=5,cpus=2"
+                  " -numa hmat-lb,initiator=0,target=0,hierarchy=memory,"
+                  "data-type=access-latency,latency=10"
+                  " -numa hmat-lb,initiator=0,target=0,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=800M"
+                  " -numa hmat-lb,initiator=0,target=2,hierarchy=memory,"
+                  "data-type=access-latency,latency=100"
+                  " -numa hmat-lb,initiator=0,target=2,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=200M"
+                  " -numa hmat-lb,initiator=0,target=4,hierarchy=memory,"
+                  "data-type=access-latency,latency=100"
+                  " -numa hmat-lb,initiator=0,target=4,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=200M"
+                  " -numa hmat-lb,initiator=0,target=5,hierarchy=memory,"
+                  "data-type=access-latency,latency=200"
+                  " -numa hmat-lb,initiator=0,target=5,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=400M"
+                  " -numa hmat-lb,initiator=1,target=0,hierarchy=memory,"
+                  "data-type=access-latency,latency=500"
+                  " -numa hmat-lb,initiator=1,target=0,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=100M"
+                  " -numa hmat-lb,initiator=1,target=2,hierarchy=memory,"
+                  "data-type=access-latency,latency=50"
+                  " -numa hmat-lb,initiator=1,target=2,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=400M"
+                  " -numa hmat-lb,initiator=1,target=4,hierarchy=memory,"
+                  "data-type=access-latency,latency=50"
+                  " -numa hmat-lb,initiator=1,target=4,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=800M"
+                  " -numa hmat-lb,initiator=1,target=5,hierarchy=memory,"
+                  "data-type=access-latency,latency=500"
+                  " -numa hmat-lb,initiator=1,target=5,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=100M"
+                  " -numa hmat-lb,initiator=3,target=0,hierarchy=memory,"
+                  "data-type=access-latency,latency=20"
+                  " -numa hmat-lb,initiator=3,target=0,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=400M"
+                  " -numa hmat-lb,initiator=3,target=2,hierarchy=memory,"
+                  "data-type=access-latency,latency=80"
+                  " -numa hmat-lb,initiator=3,target=2,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=200M"
+                  " -numa hmat-lb,initiator=3,target=4,hierarchy=memory,"
+                  "data-type=access-latency,latency=80"
+                  " -numa hmat-lb,initiator=3,target=4,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=200M"
+                  " -numa hmat-lb,initiator=3,target=5,hierarchy=memory,"
+                  "data-type=access-latency,latency=20"
+                  " -numa hmat-lb,initiator=3,target=5,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=400M"
+                  " -numa hmat-lb,initiator=5,target=0,hierarchy=memory,"
+                  "data-type=access-latency,latency=20"
+                  " -numa hmat-lb,initiator=5,target=0,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=400M"
+                  " -numa hmat-lb,initiator=5,target=2,hierarchy=memory,"
+                  "data-type=access-latency,latency=80"
+                  " -numa hmat-lb,initiator=5,target=4,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=200M"
+                  " -numa hmat-lb,initiator=5,target=4,hierarchy=memory,"
+                  "data-type=access-latency,latency=80"
+                  " -numa hmat-lb,initiator=5,target=2,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=200M"
+                  " -numa hmat-lb,initiator=5,target=5,hierarchy=memory,"
+                  "data-type=access-latency,latency=10"
+                  " -numa hmat-lb,initiator=5,target=5,hierarchy=memory,"
+                  "data-type=access-bandwidth,bandwidth=800M",
+                  &data);
+    free_test_data(&data);
+}
+
 #ifdef CONFIG_POSIX
 static void test_acpi_erst(const char *machine, const char *arch)
 {
@@ -2414,6 +2509,8 @@ int main(int argc, char *argv[])
             qtest_add_func("acpi/q35/nohpet", test_acpi_q35_tcg_nohpet);
             qtest_add_func("acpi/q35/acpihmat-noinitiator",
                            test_acpi_q35_tcg_acpi_hmat_noinitiator);
+            qtest_add_func("acpi/q35/acpihmat-genericx",
+                           test_acpi_q35_tcg_acpi_hmat_generic_x);
 
             /* i386 does not support memory hotplug */
             if (strcmp(arch, "i386")) {