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>

3 files changed, 67 insertions, 34 deletions

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 64bf47a033..0f110cce3e 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -340,14 +340,71 @@ err:
     return ret;
 }
 
+void kvm_park_vcpu(CPUState *cpu)
+{
+    struct KVMParkedVcpu *vcpu;
+
+    trace_kvm_park_vcpu(cpu->cpu_index, kvm_arch_vcpu_id(cpu));
+
+    vcpu = g_malloc0(sizeof(*vcpu));
+    vcpu->vcpu_id = kvm_arch_vcpu_id(cpu);
+    vcpu->kvm_fd = cpu->kvm_fd;
+    QLIST_INSERT_HEAD(&kvm_state->kvm_parked_vcpus, vcpu, node);
+}
+
+int kvm_unpark_vcpu(KVMState *s, unsigned long vcpu_id)
+{
+    struct KVMParkedVcpu *cpu;
+    int kvm_fd = -ENOENT;
+
+    QLIST_FOREACH(cpu, &s->kvm_parked_vcpus, node) {
+        if (cpu->vcpu_id == vcpu_id) {
+            QLIST_REMOVE(cpu, node);
+            kvm_fd = cpu->kvm_fd;
+            g_free(cpu);
+        }
+    }
+
+    trace_kvm_unpark_vcpu(vcpu_id, kvm_fd > 0 ? "unparked" : "!found parked");
+
+    return kvm_fd;
+}
+
+int kvm_create_vcpu(CPUState *cpu)
+{
+    unsigned long vcpu_id = kvm_arch_vcpu_id(cpu);
+    KVMState *s = kvm_state;
+    int kvm_fd;
+
+    /* check if the KVM vCPU already exist but is parked */
+    kvm_fd = kvm_unpark_vcpu(s, vcpu_id);
+    if (kvm_fd < 0) {
+        /* vCPU not parked: create a new KVM vCPU */
+        kvm_fd = kvm_vm_ioctl(s, KVM_CREATE_VCPU, vcpu_id);
+        if (kvm_fd < 0) {
+            error_report("KVM_CREATE_VCPU IOCTL failed for vCPU %lu", vcpu_id);
+            return kvm_fd;
+        }
+    }
+
+    cpu->kvm_fd = kvm_fd;
+    cpu->kvm_state = s;
+    cpu->vcpu_dirty = true;
+    cpu->dirty_pages = 0;
+    cpu->throttle_us_per_full = 0;
+
+    trace_kvm_create_vcpu(cpu->cpu_index, vcpu_id, kvm_fd);
+
+    return 0;
+}
+
 static int do_kvm_destroy_vcpu(CPUState *cpu)
 {
     KVMState *s = kvm_state;
     long mmap_size;
-    struct KVMParkedVcpu *vcpu = NULL;
     int ret = 0;
 
-    trace_kvm_destroy_vcpu();
+    trace_kvm_destroy_vcpu(cpu->cpu_index, kvm_arch_vcpu_id(cpu));
 
     ret = kvm_arch_destroy_vcpu(cpu);
     if (ret < 0) {
@@ -373,10 +430,7 @@ static int do_kvm_destroy_vcpu(CPUState *cpu)
         }
     }
 
-    vcpu = g_malloc0(sizeof(*vcpu));
-    vcpu->vcpu_id = kvm_arch_vcpu_id(cpu);
-    vcpu->kvm_fd = cpu->kvm_fd;
-    QLIST_INSERT_HEAD(&kvm_state->kvm_parked_vcpus, vcpu, node);
+    kvm_park_vcpu(cpu);
 err:
     return ret;
 }
@@ -389,24 +443,6 @@ void kvm_destroy_vcpu(CPUState *cpu)
     }
 }
 
-static int kvm_get_vcpu(KVMState *s, unsigned long vcpu_id)
-{
-    struct KVMParkedVcpu *cpu;
-
-    QLIST_FOREACH(cpu, &s->kvm_parked_vcpus, node) {
-        if (cpu->vcpu_id == vcpu_id) {
-            int kvm_fd;
-
-            QLIST_REMOVE(cpu, node);
-            kvm_fd = cpu->kvm_fd;
-            g_free(cpu);
-            return kvm_fd;
-        }
-    }
-
-    return kvm_vm_ioctl(s, KVM_CREATE_VCPU, (void *)vcpu_id);
-}
-
 int kvm_init_vcpu(CPUState *cpu, Error **errp)
 {
     KVMState *s = kvm_state;
@@ -415,19 +451,14 @@ int kvm_init_vcpu(CPUState *cpu, Error **errp)
 
     trace_kvm_init_vcpu(cpu->cpu_index, kvm_arch_vcpu_id(cpu));
 
-    ret = kvm_get_vcpu(s, kvm_arch_vcpu_id(cpu));
+    ret = kvm_create_vcpu(cpu);
     if (ret < 0) {
-        error_setg_errno(errp, -ret, "kvm_init_vcpu: kvm_get_vcpu failed (%lu)",
+        error_setg_errno(errp, -ret,
+                         "kvm_init_vcpu: kvm_create_vcpu failed (%lu)",
                          kvm_arch_vcpu_id(cpu));
         goto err;
     }
 
-    cpu->kvm_fd = ret;
-    cpu->kvm_state = s;
-    cpu->vcpu_dirty = true;
-    cpu->dirty_pages = 0;
-    cpu->throttle_us_per_full = 0;
-
     mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
     if (mmap_size < 0) {
         ret = mmap_size;
diff --git a/accel/kvm/kvm-cpus.h b/accel/kvm/kvm-cpus.h
index ca40add32c..171b22fd29 100644
--- a/accel/kvm/kvm-cpus.h
+++ b/accel/kvm/kvm-cpus.h
@@ -22,5 +22,4 @@ bool kvm_supports_guest_debug(void);
 int kvm_insert_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len);
 int kvm_remove_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len);
 void kvm_remove_all_breakpoints(CPUState *cpu);
-
 #endif /* KVM_CPUS_H */
diff --git a/accel/kvm/trace-events b/accel/kvm/trace-events
index 681ccb667d..37626c1ac5 100644
--- a/accel/kvm/trace-events
+++ b/accel/kvm/trace-events
@@ -9,6 +9,10 @@ kvm_device_ioctl(int fd, int type, void *arg) "dev fd %d, type 0x%x, arg %p"
 kvm_failed_reg_get(uint64_t id, const char *msg) "Warning: Unable to retrieve ONEREG %" PRIu64 " from KVM: %s"
 kvm_failed_reg_set(uint64_t id, const char *msg) "Warning: Unable to set ONEREG %" PRIu64 " to KVM: %s"
 kvm_init_vcpu(int cpu_index, unsigned long arch_cpu_id) "index: %d id: %lu"
+kvm_create_vcpu(int cpu_index, unsigned long arch_cpu_id, int kvm_fd) "index: %d, id: %lu, kvm fd: %d"
+kvm_destroy_vcpu(int cpu_index, unsigned long arch_cpu_id) "index: %d id: %lu"
+kvm_park_vcpu(int cpu_index, unsigned long arch_cpu_id) "index: %d id: %lu"
+kvm_unpark_vcpu(unsigned long arch_cpu_id, const char *msg) "id: %lu %s"
 kvm_irqchip_commit_routes(void) ""
 kvm_irqchip_add_msi_route(char *name, int vector, int virq) "dev %s vector %d virq %d"
 kvm_irqchip_update_msi_route(int virq) "Updating MSI route virq=%d"
@@ -25,7 +29,6 @@ kvm_dirty_ring_reaper(const char *s) "%s"
 kvm_dirty_ring_reap(uint64_t count, int64_t t) "reaped %"PRIu64" pages (took %"PRIi64" us)"
 kvm_dirty_ring_reaper_kick(const char *reason) "%s"
 kvm_dirty_ring_flush(int finished) "%d"
-kvm_destroy_vcpu(void) ""
 kvm_failed_get_vcpu_mmap_size(void) ""
 kvm_cpu_exec(void) ""
 kvm_interrupt_exit_request(void) ""