Merge remote-tracking branch 'remotes/bonzini-gitlab/tags/for-upstream' into staging

* SGX implementation for x86 * Miscellaneous bugfixes * Fix dependencies from ROMs to qtests # gpg: Signature made Thu 30 Sep 2021 14:30:35 BST # gpg: using RSA key F13338574B662389866C7682BFFBD25F78C7AE83 # gpg: issuer "pbonzini@redhat.com" # gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full] # gpg: aka "Paolo Bonzini <pbonzini@redhat.com>" [full] # Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4 E2F7 7E15 100C CD36 69B1 # Subkey fingerprint: F133 3857 4B66 2389 866C 7682 BFFB D25F 78C7 AE83 * remotes/bonzini-gitlab/tags/for-upstream: (33 commits) meson_options.txt: Switch the default value for the vnc option to 'auto' build-sys: add HAVE_IPPROTO_MPTCP memory: Add tracepoint for dirty sync memory: Name all the memory listeners target/i386: Fix memory leak in sev_read_file_base64() tests: qtest: bios-tables-test depends on the unpacked edk2 ROMs meson: unpack edk2 firmware even if --disable-blobs target/i386: Add the query-sgx-capabilities QMP command target/i386: Add HMP and QMP interfaces for SGX docs/system: Add SGX documentation to the system manual sgx-epc: Add the fill_device_info() callback support i440fx: Add support for SGX EPC q35: Add support for SGX EPC i386: acpi: Add SGX EPC entry to ACPI tables i386/pc: Add e820 entry for SGX EPC section(s) hw/i386/pc: Account for SGX EPC sections when calculating device memory hw/i386/fw_cfg: Set SGX bits in feature control fw_cfg accordingly Adjust min CPUID level to 0x12 when SGX is enabled i386: Propagate SGX CPUID sub-leafs to KVM i386: kvm: Add support for exposing PROVISIONKEY to guest ... Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2026-07-06 00:20:22 -07:00 · 2021-09-30 17:38:31 +01:00
parent fce8f7735f c1de5858bd
commit 0021c4765a
64 changed files with 1397 additions and 38 deletions
@@ -295,6 +295,7 @@ static void hvf_region_del(MemoryListener *listener,
 }

 static MemoryListener hvf_memory_listener = {
+    .name = "hvf",
    .priority = 10,
    .region_add = hvf_region_add,
    .region_del = hvf_region_del,
@@ -1129,6 +1129,7 @@ static void kvm_coalesce_pio_del(MemoryListener *listener,
 }

 static MemoryListener kvm_coalesced_pio_listener = {
+    .name = "kvm-coalesced-pio",
    .coalesced_io_add = kvm_coalesce_pio_add,
    .coalesced_io_del = kvm_coalesce_pio_del,
 };
@@ -1633,7 +1634,7 @@ static void kvm_io_ioeventfd_del(MemoryListener *listener,
 }

 void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
-                                  AddressSpace *as, int as_id)
+                                  AddressSpace *as, int as_id, const char *name)
 {
    int i;

@@ -1649,6 +1650,7 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
    kml->listener.log_start = kvm_log_start;
    kml->listener.log_stop = kvm_log_stop;
    kml->listener.priority = 10;
+    kml->listener.name = name;

    if (s->kvm_dirty_ring_size) {
        kml->listener.log_sync_global = kvm_log_sync_global;
@@ -1669,6 +1671,7 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
 }

 static MemoryListener kvm_io_listener = {
+    .name = "kvm-io",
    .eventfd_add = kvm_io_ioeventfd_add,
    .eventfd_del = kvm_io_ioeventfd_del,
    .priority = 10,
@@ -2579,7 +2582,7 @@ static int kvm_init(MachineState *ms)
    s->memory_listener.listener.coalesced_io_del = kvm_uncoalesce_mmio_region;

    kvm_memory_listener_register(s, &s->memory_listener,
-                                 &address_space_memory, 0);
+                                 &address_space_memory, 0, "kvm-memory");
    if (kvm_eventfds_allowed) {
        memory_listener_register(&kvm_io_listener,
                                 &address_space_io);
@@ -0,0 +1,82 @@
+/*
+ * QEMU host SGX EPC memory backend
+ *
+ * Copyright (C) 2019 Intel Corporation
+ *
+ * Authors:
+ *   Sean Christopherson <sean.j.christopherson@intel.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#include <sys/ioctl.h>
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+#include "qom/object_interfaces.h"
+#include "qapi/error.h"
+#include "sysemu/hostmem.h"
+#include "hw/i386/hostmem-epc.h"
+
+static void
+sgx_epc_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
+{
+    uint32_t ram_flags;
+    char *name;
+    int fd;
+
+    if (!backend->size) {
+        error_setg(errp, "can't create backend with size 0");
+        return;
+    }
+
+    fd = qemu_open_old("/dev/sgx_vepc", O_RDWR);
+    if (fd < 0) {
+        error_setg_errno(errp, errno,
+                         "failed to open /dev/sgx_vepc to alloc SGX EPC");
+        return;
+    }
+
+    name = object_get_canonical_path(OBJECT(backend));
+    ram_flags = (backend->share ? RAM_SHARED : 0) | RAM_PROTECTED;
+    memory_region_init_ram_from_fd(&backend->mr, OBJECT(backend),
+                                   name, backend->size, ram_flags,
+                                   fd, 0, errp);
+    g_free(name);
+}
+
+static void sgx_epc_backend_instance_init(Object *obj)
+{
+    HostMemoryBackend *m = MEMORY_BACKEND(obj);
+
+    m->share = true;
+    m->merge = false;
+    m->dump = false;
+}
+
+static void sgx_epc_backend_class_init(ObjectClass *oc, void *data)
+{
+    HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc);
+
+    bc->alloc = sgx_epc_backend_memory_alloc;
+}
+
+static const TypeInfo sgx_epc_backed_info = {
+    .name = TYPE_MEMORY_BACKEND_EPC,
+    .parent = TYPE_MEMORY_BACKEND,
+    .instance_init = sgx_epc_backend_instance_init,
+    .class_init = sgx_epc_backend_class_init,
+    .instance_size = sizeof(HostMemoryBackendEpc),
+};
+
+static void register_types(void)
+{
+    int fd = qemu_open_old("/dev/sgx_vepc", O_RDWR);
+    if (fd >= 0) {
+        close(fd);
+
+        type_register_static(&sgx_epc_backed_info);
+    }
+}
+
+type_init(register_types);
@@ -16,5 +16,6 @@ softmmu_ss.add(when: ['CONFIG_VHOST_USER', 'CONFIG_VIRTIO'], if_true: files('vho
 softmmu_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('cryptodev-vhost.c'))
 softmmu_ss.add(when: ['CONFIG_VIRTIO_CRYPTO', 'CONFIG_VHOST_CRYPTO'], if_true: files('cryptodev-vhost-user.c'))
 softmmu_ss.add(when: 'CONFIG_GIO', if_true: [files('dbus-vmstate.c'), gio])
+softmmu_ss.add(when: 'CONFIG_SGX', if_true: files('hostmem-epc.c'))

 subdir('tpm')
@@ -22,6 +22,7 @@
 #CONFIG_TPM_CRB=n
 #CONFIG_TPM_TIS_ISA=n
 #CONFIG_VTD=n
+#CONFIG_SGX=n

 # Boards:
 #
@@ -0,0 +1,165 @@
+Software Guard eXtensions (SGX)
+===============================
+
+Overview
+--------
+
+Intel Software Guard eXtensions (SGX) is a set of instructions and mechanisms
+for memory accesses in order to provide security accesses for sensitive
+applications and data. SGX allows an application to use it's pariticular
+address space as an *enclave*, which is a protected area provides confidentiality
+and integrity even in the presence of privileged malware. Accesses to the
+enclave memory area from any software not resident in the enclave are prevented,
+including those from privileged software.
+
+Virtual SGX
+-----------
+
+SGX feature is exposed to guest via SGX CPUID. Looking at SGX CPUID, we can
+report the same CPUID info to guest as on host for most of SGX CPUID. With
+reporting the same CPUID guest is able to use full capacity of SGX, and KVM
+doesn't need to emulate those info.
+
+The guest's EPC base and size are determined by Qemu, and KVM needs Qemu to
+notify such info to it before it can initialize SGX for guest.
+
+Virtual EPC
+~~~~~~~~~~~
+
+By default, Qemu does not assign EPC to a VM, i.e. fully enabling SGX in a VM
+requires explicit allocation of EPC to the VM. Similar to other specialized
+memory types, e.g. hugetlbfs, EPC is exposed as a memory backend.
+
+SGX EPC is enumerated through CPUID, i.e. EPC "devices" need to be realized
+prior to realizing the vCPUs themselves, which occurs long before generic
+devices are parsed and realized.  This limitation means that EPC does not
+require -maxmem as EPC is not treated as {cold,hot}plugged memory.
+
+Qemu does not artificially restrict the number of EPC sections exposed to a
+guest, e.g. Qemu will happily allow you to create 64 1M EPC sections. Be aware
+that some kernels may not recognize all EPC sections, e.g. the Linux SGX driver
+is hardwired to support only 8 EPC sections.
+
+The following Qemu snippet creates two EPC sections, with 64M pre-allocated
+to the VM and an additional 28M mapped but not allocated::
+
+ -object memory-backend-epc,id=mem1,size=64M,prealloc=on \
+ -object memory-backend-epc,id=mem2,size=28M \
+ -M sgx-epc.0.memdev=mem1,sgx-epc.1.memdev=mem2
+
+Note:
+
+The size and location of the virtual EPC are far less restricted compared
+to physical EPC. Because physical EPC is protected via range registers,
+the size of the physical EPC must be a power of two (though software sees
+a subset of the full EPC, e.g. 92M or 128M) and the EPC must be naturally
+aligned.  KVM SGX's virtual EPC is purely a software construct and only
+requires the size and location to be page aligned. Qemu enforces the EPC
+size is a multiple of 4k and will ensure the base of the EPC is 4k aligned.
+To simplify the implementation, EPC is always located above 4g in the guest
+physical address space.
+
+Migration
+~~~~~~~~~
+
+Qemu/KVM doesn't prevent live migrating SGX VMs, although from hardware's
+perspective, SGX doesn't support live migration, since both EPC and the SGX
+key hierarchy are bound to the physical platform. However live migration
+can be supported in the sense if guest software stack can support recreating
+enclaves when it suffers sudden lose of EPC; and if guest enclaves can detect
+SGX keys being changed, and handle gracefully. For instance, when ERESUME fails
+with #PF.SGX, guest software can gracefully detect it and recreate enclaves;
+and when enclave fails to unseal sensitive information from outside, it can
+detect such error and sensitive information can be provisioned to it again.
+
+CPUID
+~~~~~
+
+Due to its myriad dependencies, SGX is currently not listed as supported
+in any of Qemu's built-in CPU configuration. To expose SGX (and SGX Launch
+Control) to a guest, you must either use `-cpu host` to pass-through the
+host CPU model, or explicitly enable SGX when using a built-in CPU model,
+e.g. via `-cpu <model>,+sgx` or `-cpu <model>,+sgx,+sgxlc`.
+
+All SGX sub-features enumerated through CPUID, e.g. SGX2, MISCSELECT,
+ATTRIBUTES, etc... can be restricted via CPUID flags. Be aware that enforcing
+restriction of MISCSELECT, ATTRIBUTES and XFRM requires intercepting ECREATE,
+i.e. may marginally reduce SGX performance in the guest. All SGX sub-features
+controlled via -cpu are prefixed with "sgx", e.g.::
+
+  $ qemu-system-x86_64 -cpu help | xargs printf "%s\n" | grep sgx
+  sgx
+  sgx-debug
+  sgx-encls-c
+  sgx-enclv
+  sgx-exinfo
+  sgx-kss
+  sgx-mode64
+  sgx-provisionkey
+  sgx-tokenkey
+  sgx1
+  sgx2
+  sgxlc
+
+The following Qemu snippet passes through the host CPU but restricts access to
+the provision and EINIT token keys::
+
+ -cpu host,-sgx-provisionkey,-sgx-tokenkey
+
+SGX sub-features cannot be emulated, i.e. sub-features that are not present
+in hardware cannot be forced on via '-cpu'.
+
+Virtualize SGX Launch Control
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Qemu SGX support for Launch Control (LC) is passive, in the sense that it
+does not actively change the LC configuration.  Qemu SGX provides the user
+the ability to set/clear the CPUID flag (and by extension the associated
+IA32_FEATURE_CONTROL MSR bit in fw_cfg) and saves/restores the LE Hash MSRs
+when getting/putting guest state, but Qemu does not add new controls to
+directly modify the LC configuration.  Similar to hardware behavior, locking
+the LC configuration to a non-Intel value is left to guest firmware.  Unlike
+host bios setting for SGX launch control(LC), there is no special bios setting
+for SGX guest by our design. If host is in locked mode, we can still allow
+creating VM with SGX.
+
+Feature Control
+~~~~~~~~~~~~~~~
+
+Qemu SGX updates the `etc/msr_feature_control` fw_cfg entry to set the SGX
+(bit 18) and SGX LC (bit 17) flags based on their respective CPUID support,
+i.e. existing guest firmware will automatically set SGX and SGX LC accordingly,
+assuming said firmware supports fw_cfg.msr_feature_control.
+
+Launching a guest
+-----------------
+
+To launch a SGX guest:
+
+.. parsed-literal::
+
+  |qemu_system_x86| \\
+   -cpu host,+sgx-provisionkey \\
+   -object memory-backend-epc,id=mem1,size=64M,prealloc=on \\
+   -object memory-backend-epc,id=mem2,size=28M \\
+   -M sgx-epc.0.memdev=mem1,sgx-epc.1.memdev=mem2
+
+Utilizing SGX in the guest requires a kernel/OS with SGX support.
+The support can be determined in guest by::
+
+  $ grep sgx /proc/cpuinfo
+
+and SGX epc info by::
+
+  $ dmesg | grep sgx
+  [    1.242142] sgx: EPC section 0x180000000-0x181bfffff
+  [    1.242319] sgx: EPC section 0x181c00000-0x1837fffff
+
+References
+----------
+
+- `SGX Homepage <https://software.intel.com/sgx>`__
+
+- `SGX SDK <https://github.com/intel/linux-sgx.git>`__
+
+- SGX specification: Intel SDM Volume 3
@@ -26,6 +26,7 @@ Architectural features
   :maxdepth: 1

   i386/cpu
+   i386/sgx

 .. _pcsys_005freq:

@@ -877,3 +877,18 @@ SRST
  ``info dirty_rate``
    Display the vcpu dirty rate information.
 ERST
+
+#if defined(TARGET_I386)
+    {
+        .name       = "sgx",
+        .args_type  = "",
+        .params     = "",
+        .help       = "show intel SGX information",
+        .cmd        = hmp_info_sgx,
+    },
+#endif
+
+SRST
+  ``info sgx``
+    Show intel SGX information.
+ERST
@@ -6,6 +6,10 @@ config SEV
    select X86_FW_OVMF
    depends on KVM

+config SGX
+    bool
+    depends on KVM
+
 config PC
    bool
    imply APPLESMC
@@ -21,6 +25,7 @@ config PC
    imply PVPANIC_ISA
    imply QXL
    imply SEV
+    imply SGX
    imply SGA
    imply TEST_DEVICES
    imply TPM_CRB
@@ -1841,6 +1841,28 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
    }
 #endif

+    if (pcms->sgx_epc.size != 0) {
+        uint64_t epc_base = pcms->sgx_epc.base;
+        uint64_t epc_size = pcms->sgx_epc.size;
+
+        dev = aml_device("EPC");
+        aml_append(dev, aml_name_decl("_HID", aml_eisaid("INT0E0C")));
+        aml_append(dev, aml_name_decl("_STR",
+                                      aml_unicode("Enclave Page Cache 1.0")));
+        crs = aml_resource_template();
+        aml_append(crs,
+                   aml_qword_memory(AML_POS_DECODE, AML_MIN_FIXED,
+                                    AML_MAX_FIXED, AML_NON_CACHEABLE,
+                                    AML_READ_WRITE, 0, epc_base,
+                                    epc_base + epc_size - 1, 0, epc_size));
+        aml_append(dev, aml_name_decl("_CRS", crs));
+
+        method = aml_method("_STA", 0, AML_NOTSERIALIZED);
+        aml_append(method, aml_return(aml_int(0x0f)));
+        aml_append(dev, method);
+
+        aml_append(sb_scope, dev);
+    }
    aml_append(dsdt, sb_scope);

    /* copy AML table into ACPI tables blob and patch header there */
@@ -159,7 +159,7 @@ void fw_cfg_build_feature_control(MachineState *ms, FWCfgState *fw_cfg)
 {
    X86CPU *cpu = X86_CPU(ms->possible_cpus->cpus[0].cpu);
    CPUX86State *env = &cpu->env;
-    uint32_t unused, ecx, edx;
+    uint32_t unused, ebx, ecx, edx;
    uint64_t feature_control_bits = 0;
    uint64_t *val;

@@ -174,6 +174,16 @@ void fw_cfg_build_feature_control(MachineState *ms, FWCfgState *fw_cfg)
        feature_control_bits |= FEATURE_CONTROL_LMCE;
    }

+    if (env->cpuid_level >= 7) {
+        cpu_x86_cpuid(env, 0x7, 0, &unused, &ebx, &ecx, &unused);
+        if (ebx & CPUID_7_0_EBX_SGX) {
+            feature_control_bits |= FEATURE_CONTROL_SGX;
+        }
+        if (ecx & CPUID_7_0_ECX_SGX_LC) {
+            feature_control_bits |= FEATURE_CONTROL_SGX_LC;
+        }
+    }
+
    if (!feature_control_bits) {
        return;
    }
@@ -16,6 +16,8 @@ i386_ss.add(when: 'CONFIG_Q35', if_true: files('pc_q35.c'))
 i386_ss.add(when: 'CONFIG_VMMOUSE', if_true: files('vmmouse.c'))
 i386_ss.add(when: 'CONFIG_VMPORT', if_true: files('vmport.c'))
 i386_ss.add(when: 'CONFIG_VTD', if_true: files('intel_iommu.c'))
+i386_ss.add(when: 'CONFIG_SGX', if_true: files('sgx-epc.c','sgx.c'),
+                                if_false: files('sgx-stub.c'))

 i386_ss.add(when: 'CONFIG_ACPI', if_true: files('acpi-common.c'))
 i386_ss.add(when: 'CONFIG_ACPI_HW_REDUCED', if_true: files('generic_event_device_x86.c'))
@@ -889,6 +889,10 @@ void pc_memory_init(PCMachineState *pcms,
        e820_add_entry(0x100000000ULL, x86ms->above_4g_mem_size, E820_RAM);
    }

+    if (pcms->sgx_epc.size != 0) {
+        e820_add_entry(pcms->sgx_epc.base, pcms->sgx_epc.size, E820_RESERVED);
+    }
+
    if (!pcmc->has_reserved_memory &&
        (machine->ram_slots ||
         (machine->maxram_size > machine->ram_size))) {
@@ -919,8 +923,15 @@ void pc_memory_init(PCMachineState *pcms,
            exit(EXIT_FAILURE);
        }

+        if (pcms->sgx_epc.size != 0) {
+            machine->device_memory->base = sgx_epc_above_4g_end(&pcms->sgx_epc);
+        } else {
+            machine->device_memory->base =
+                0x100000000ULL + x86ms->above_4g_mem_size;
+        }
+
        machine->device_memory->base =
-            ROUND_UP(0x100000000ULL + x86ms->above_4g_mem_size, 1 * GiB);
+            ROUND_UP(machine->device_memory->base, 1 * GiB);

        if (pcmc->enforce_aligned_dimm) {
            /* size device region assuming 1G page max alignment per slot */
@@ -1005,6 +1016,8 @@ uint64_t pc_pci_hole64_start(void)
        if (!pcmc->broken_reserved_end) {
            hole64_start += memory_region_size(&ms->device_memory->mr);
        }
+    } else if (pcms->sgx_epc.size != 0) {
+            hole64_start = sgx_epc_above_4g_end(&pcms->sgx_epc);
    } else {
        hole64_start = 0x100000000ULL + x86ms->above_4g_mem_size;
    }
@@ -153,6 +153,7 @@ static void pc_init1(MachineState *machine,
        }
    }

+    pc_machine_init_sgx_epc(pcms);
    x86_cpus_init(x86ms, pcmc->default_cpu_version);

    if (pcmc->kvmclock_enabled) {
@@ -177,6 +177,7 @@ static void pc_q35_init(MachineState *machine)
        x86ms->below_4g_mem_size = machine->ram_size;
    }

+    pc_machine_init_sgx_epc(pcms);
    x86_cpus_init(x86ms, pcmc->default_cpu_version);

    kvmclock_create(pcmc->kvmclock_create_always);
@@ -0,0 +1,184 @@
+/*
+ * SGX EPC device
+ *
+ * Copyright (C) 2019 Intel Corporation
+ *
+ * Authors:
+ *   Sean Christopherson <sean.j.christopherson@intel.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#include "qemu/osdep.h"
+#include "hw/i386/pc.h"
+#include "hw/i386/sgx-epc.h"
+#include "hw/mem/memory-device.h"
+#include "hw/qdev-properties.h"
+#include "qapi/error.h"
+#include "qapi/visitor.h"
+#include "target/i386/cpu.h"
+#include "exec/address-spaces.h"
+
+static Property sgx_epc_properties[] = {
+    DEFINE_PROP_UINT64(SGX_EPC_ADDR_PROP, SGXEPCDevice, addr, 0),
+    DEFINE_PROP_LINK(SGX_EPC_MEMDEV_PROP, SGXEPCDevice, hostmem,
+                     TYPE_MEMORY_BACKEND_EPC, HostMemoryBackendEpc *),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void sgx_epc_get_size(Object *obj, Visitor *v, const char *name,
+                             void *opaque, Error **errp)
+{
+    Error *local_err = NULL;
+    uint64_t value;
+
+    value = memory_device_get_region_size(MEMORY_DEVICE(obj), &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    visit_type_uint64(v, name, &value, errp);
+}
+
+static void sgx_epc_init(Object *obj)
+{
+    object_property_add(obj, SGX_EPC_SIZE_PROP, "uint64", sgx_epc_get_size,
+                        NULL, NULL, NULL);
+}
+
+static void sgx_epc_realize(DeviceState *dev, Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(qdev_get_machine());
+    X86MachineState *x86ms = X86_MACHINE(pcms);
+    MemoryDeviceState *md = MEMORY_DEVICE(dev);
+    SGXEPCState *sgx_epc = &pcms->sgx_epc;
+    SGXEPCDevice *epc = SGX_EPC(dev);
+    HostMemoryBackend *hostmem;
+    const char *path;
+
+    if (x86ms->boot_cpus != 0) {
+        error_setg(errp, "'" TYPE_SGX_EPC "' can't be created after vCPUs,"
+                         "e.g. via -device");
+        return;
+    }
+
+    if (!epc->hostmem) {
+        error_setg(errp, "'" SGX_EPC_MEMDEV_PROP "' property is not set");
+        return;
+    }
+    hostmem = MEMORY_BACKEND(epc->hostmem);
+    if (host_memory_backend_is_mapped(hostmem)) {
+        path = object_get_canonical_path_component(OBJECT(hostmem));
+        error_setg(errp, "can't use already busy memdev: %s", path);
+        return;
+    }
+
+    epc->addr = sgx_epc->base + sgx_epc->size;
+
+    memory_region_add_subregion(&sgx_epc->mr, epc->addr - sgx_epc->base,
+                                host_memory_backend_get_memory(hostmem));
+
+    host_memory_backend_set_mapped(hostmem, true);
+
+    sgx_epc->sections = g_renew(SGXEPCDevice *, sgx_epc->sections,
+                                sgx_epc->nr_sections + 1);
+    sgx_epc->sections[sgx_epc->nr_sections++] = epc;
+
+    sgx_epc->size += memory_device_get_region_size(md, errp);
+}
+
+static void sgx_epc_unrealize(DeviceState *dev)
+{
+    SGXEPCDevice *epc = SGX_EPC(dev);
+    HostMemoryBackend *hostmem = MEMORY_BACKEND(epc->hostmem);
+
+    host_memory_backend_set_mapped(hostmem, false);
+}
+
+static uint64_t sgx_epc_md_get_addr(const MemoryDeviceState *md)
+{
+    const SGXEPCDevice *epc = SGX_EPC(md);
+
+    return epc->addr;
+}
+
+static void sgx_epc_md_set_addr(MemoryDeviceState *md, uint64_t addr,
+                                Error **errp)
+{
+    object_property_set_uint(OBJECT(md), SGX_EPC_ADDR_PROP, addr, errp);
+}
+
+static uint64_t sgx_epc_md_get_plugged_size(const MemoryDeviceState *md,
+                                            Error **errp)
+{
+    return 0;
+}
+
+static MemoryRegion *sgx_epc_md_get_memory_region(MemoryDeviceState *md,
+                                                  Error **errp)
+{
+    SGXEPCDevice *epc = SGX_EPC(md);
+    HostMemoryBackend *hostmem;
+
+    if (!epc->hostmem) {
+        error_setg(errp, "'" SGX_EPC_MEMDEV_PROP "' property must be set");
+        return NULL;
+    }
+
+    hostmem = MEMORY_BACKEND(epc->hostmem);
+    return host_memory_backend_get_memory(hostmem);
+}
+
+static void sgx_epc_md_fill_device_info(const MemoryDeviceState *md,
+                                        MemoryDeviceInfo *info)
+{
+    SgxEPCDeviceInfo *se = g_new0(SgxEPCDeviceInfo, 1);
+    SGXEPCDevice *epc = SGX_EPC(md);
+
+    se->memaddr = epc->addr;
+    se->size = object_property_get_uint(OBJECT(epc), SGX_EPC_SIZE_PROP,
+                                        NULL);
+    se->memdev = object_get_canonical_path(OBJECT(epc->hostmem));
+
+    info->u.sgx_epc.data = se;
+    info->type = MEMORY_DEVICE_INFO_KIND_SGX_EPC;
+}
+
+static void sgx_epc_class_init(ObjectClass *oc, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+    MemoryDeviceClass *mdc = MEMORY_DEVICE_CLASS(oc);
+
+    dc->hotpluggable = false;
+    dc->realize = sgx_epc_realize;
+    dc->unrealize = sgx_epc_unrealize;
+    dc->desc = "SGX EPC section";
+    device_class_set_props(dc, sgx_epc_properties);
+
+    mdc->get_addr = sgx_epc_md_get_addr;
+    mdc->set_addr = sgx_epc_md_set_addr;
+    mdc->get_plugged_size = sgx_epc_md_get_plugged_size;
+    mdc->get_memory_region = sgx_epc_md_get_memory_region;
+    mdc->fill_device_info = sgx_epc_md_fill_device_info;
+}
+
+static TypeInfo sgx_epc_info = {
+    .name          = TYPE_SGX_EPC,
+    .parent        = TYPE_DEVICE,
+    .instance_size = sizeof(SGXEPCDevice),
+    .instance_init = sgx_epc_init,
+    .class_init    = sgx_epc_class_init,
+    .class_size    = sizeof(DeviceClass),
+    .interfaces = (InterfaceInfo[]) {
+        { TYPE_MEMORY_DEVICE },
+        { }
+    },
+};
+
+static void sgx_epc_register_types(void)
+{
+    type_register_static(&sgx_epc_info);
+}
+
+type_init(sgx_epc_register_types)
@@ -0,0 +1,26 @@
+#include "qemu/osdep.h"
+#include "hw/i386/pc.h"
+#include "hw/i386/sgx-epc.h"
+#include "hw/i386/sgx.h"
+
+SGXInfo *sgx_get_info(Error **errp)
+{
+    error_setg(errp, "SGX support is not compiled in");
+    return NULL;
+}
+
+SGXInfo *sgx_get_capabilities(Error **errp)
+{
+    error_setg(errp, "SGX support is not compiled in");
+    return NULL;
+}
+
+void pc_machine_init_sgx_epc(PCMachineState *pcms)
+{
+    memset(&pcms->sgx_epc, 0, sizeof(SGXEPCState));
+}
+
+int sgx_epc_get_section(int section_nr, uint64_t *addr, uint64_t *size)
+{
+    g_assert_not_reached();
+}
@@ -0,0 +1,170 @@
+/*
+ * SGX common code
+ *
+ * Copyright (C) 2021 Intel Corporation
+ *
+ * Authors:
+ *   Yang Zhong<yang.zhong@intel.com>
+ *   Sean Christopherson <sean.j.christopherson@intel.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#include "qemu/osdep.h"
+#include "hw/i386/pc.h"
+#include "hw/i386/sgx-epc.h"
+#include "hw/mem/memory-device.h"
+#include "monitor/qdev.h"
+#include "qapi/error.h"
+#include "exec/address-spaces.h"
+#include "hw/i386/sgx.h"
+#include "sysemu/hw_accel.h"
+
+#define SGX_MAX_EPC_SECTIONS            8
+#define SGX_CPUID_EPC_INVALID           0x0
+
+/* A valid EPC section. */
+#define SGX_CPUID_EPC_SECTION           0x1
+#define SGX_CPUID_EPC_MASK              0xF
+
+static uint64_t sgx_calc_section_metric(uint64_t low, uint64_t high)
+{
+    return (low & MAKE_64BIT_MASK(12, 20)) +
+           ((high & MAKE_64BIT_MASK(0, 20)) << 32);
+}
+
+static uint64_t sgx_calc_host_epc_section_size(void)
+{
+    uint32_t i, type;
+    uint32_t eax, ebx, ecx, edx;
+    uint64_t size = 0;
+
+    for (i = 0; i < SGX_MAX_EPC_SECTIONS; i++) {
+        host_cpuid(0x12, i + 2, &eax, &ebx, &ecx, &edx);
+
+        type = eax & SGX_CPUID_EPC_MASK;
+        if (type == SGX_CPUID_EPC_INVALID) {
+            break;
+        }
+
+        if (type != SGX_CPUID_EPC_SECTION) {
+            break;
+        }
+
+        size += sgx_calc_section_metric(ecx, edx);
+    }
+
+    return size;
+}
+
+SGXInfo *sgx_get_capabilities(Error **errp)
+{
+    SGXInfo *info = NULL;
+    uint32_t eax, ebx, ecx, edx;
+
+    int fd = qemu_open_old("/dev/sgx_vepc", O_RDWR);
+    if (fd < 0) {
+        error_setg(errp, "SGX is not enabled in KVM");
+        return NULL;
+    }
+
+    info = g_new0(SGXInfo, 1);
+    host_cpuid(0x7, 0, &eax, &ebx, &ecx, &edx);
+
+    info->sgx = ebx & (1U << 2) ? true : false;
+    info->flc = ecx & (1U << 30) ? true : false;
+
+    host_cpuid(0x12, 0, &eax, &ebx, &ecx, &edx);
+    info->sgx1 = eax & (1U << 0) ? true : false;
+    info->sgx2 = eax & (1U << 1) ? true : false;
+
+    info->section_size = sgx_calc_host_epc_section_size();
+
+    close(fd);
+
+    return info;
+}
+
+SGXInfo *sgx_get_info(Error **errp)
+{
+    SGXInfo *info = NULL;
+    X86MachineState *x86ms;
+    PCMachineState *pcms =
+        (PCMachineState *)object_dynamic_cast(qdev_get_machine(),
+                                              TYPE_PC_MACHINE);
+    if (!pcms) {
+        error_setg(errp, "SGX is only supported on PC machines");
+        return NULL;
+    }
+
+    x86ms = X86_MACHINE(pcms);
+    if (!x86ms->sgx_epc_list) {
+        error_setg(errp, "No EPC regions defined, SGX not available");
+        return NULL;
+    }
+
+    SGXEPCState *sgx_epc = &pcms->sgx_epc;
+    info = g_new0(SGXInfo, 1);
+
+    info->sgx = true;
+    info->sgx1 = true;
+    info->sgx2 = true;
+    info->flc = true;
+    info->section_size = sgx_epc->size;
+
+    return info;
+}
+
+int sgx_epc_get_section(int section_nr, uint64_t *addr, uint64_t *size)
+{
+    PCMachineState *pcms = PC_MACHINE(qdev_get_machine());
+    SGXEPCDevice *epc;
+
+    if (pcms->sgx_epc.size == 0 || pcms->sgx_epc.nr_sections <= section_nr) {
+        return 1;
+    }
+
+    epc = pcms->sgx_epc.sections[section_nr];
+
+    *addr = epc->addr;
+    *size = memory_device_get_region_size(MEMORY_DEVICE(epc), &error_fatal);
+
+    return 0;
+}
+
+void pc_machine_init_sgx_epc(PCMachineState *pcms)
+{
+    SGXEPCState *sgx_epc = &pcms->sgx_epc;
+    X86MachineState *x86ms = X86_MACHINE(pcms);
+    SgxEPCList *list = NULL;
+    Object *obj;
+
+    memset(sgx_epc, 0, sizeof(SGXEPCState));
+    if (!x86ms->sgx_epc_list) {
+        return;
+    }
+
+    sgx_epc->base = 0x100000000ULL + x86ms->above_4g_mem_size;
+
+    memory_region_init(&sgx_epc->mr, OBJECT(pcms), "sgx-epc", UINT64_MAX);
+    memory_region_add_subregion(get_system_memory(), sgx_epc->base,
+                                &sgx_epc->mr);
+
+    for (list = x86ms->sgx_epc_list; list; list = list->next) {
+        obj = object_new("sgx-epc");
+
+        /* set the memdev link with memory backend */
+        object_property_parse(obj, SGX_EPC_MEMDEV_PROP, list->value->memdev,
+                              &error_fatal);
+        object_property_set_bool(obj, "realized", true, &error_fatal);
+        object_unref(obj);
+    }
+
+    if ((sgx_epc->base + sgx_epc->size) < sgx_epc->base) {
+        error_report("Size of all 'sgx-epc' =0x%"PRIu64" causes EPC to wrap",
+                     sgx_epc->size);
+        exit(EXIT_FAILURE);
+    }
+
+    memory_region_set_size(&sgx_epc->mr, sgx_epc->size);
+}
@@ -30,6 +30,8 @@
 #include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qapi/qapi-visit-common.h"
+#include "qapi/clone-visitor.h"
+#include "qapi/qapi-visit-machine.h"
 #include "qapi/visitor.h"
 #include "sysemu/qtest.h"
 #include "sysemu/whpx.h"
@@ -1263,6 +1265,27 @@ static void x86_machine_set_bus_lock_ratelimit(Object *obj, Visitor *v,
    visit_type_uint64(v, name, &x86ms->bus_lock_ratelimit, errp);
 }

+static void machine_get_sgx_epc(Object *obj, Visitor *v, const char *name,
+                                void *opaque, Error **errp)
+{
+    X86MachineState *x86ms = X86_MACHINE(obj);
+    SgxEPCList *list = x86ms->sgx_epc_list;
+
+    visit_type_SgxEPCList(v, name, &list, errp);
+}
+
+static void machine_set_sgx_epc(Object *obj, Visitor *v, const char *name,
+                                void *opaque, Error **errp)
+{
+    X86MachineState *x86ms = X86_MACHINE(obj);
+    SgxEPCList *list;
+
+    list = x86ms->sgx_epc_list;
+    visit_type_SgxEPCList(v, name, &x86ms->sgx_epc_list, errp);
+
+    qapi_free_SgxEPCList(list);
+}
+
 static void x86_machine_initfn(Object *obj)
 {
    X86MachineState *x86ms = X86_MACHINE(obj);
@@ -1322,6 +1345,12 @@ static void x86_machine_class_init(ObjectClass *oc, void *data)
                                x86_machine_set_bus_lock_ratelimit, NULL, NULL);
    object_class_property_set_description(oc, X86_MACHINE_BUS_LOCK_RATELIMIT,
            "Set the ratelimit for the bus locks acquired in VMs");
+
+    object_class_property_add(oc, "sgx-epc", "SgxEPC",
+        machine_get_sgx_epc, machine_set_sgx_epc,
+        NULL, NULL);
+    object_class_property_set_description(oc, "sgx-epc",
+        "SGX EPC device");
 }

 static const TypeInfo x86_machine_info = {
@@ -721,6 +721,7 @@ static void xen_log_global_stop(MemoryListener *listener)
 }

 static MemoryListener xen_memory_listener = {
+    .name = "xen-memory",
    .region_add = xen_region_add,
    .region_del = xen_region_del,
    .log_start = xen_log_start,
@@ -732,6 +733,7 @@ static MemoryListener xen_memory_listener = {
 };

 static MemoryListener xen_io_listener = {
+    .name = "xen-io",
    .region_add = xen_io_add,
    .region_del = xen_io_del,
    .priority = 10,
--- a/Show More
+++ b/Show More