Qemu SEV-ES guest support

From: Tom Lendacky <[email protected]>

Provide initial support for SEV-ES. This includes creating a function to indicate the guest is an SEV-ES guest (which will return false until all support is in place), performing the proper SEV initialization and ensuring that the guest CPU state is measured as part of the launch.

Cc Paolo Bonzini <[email protected]>

Cc Richard Henderson <[email protected]>

Cc Eduardo Habkost <[email protected]>

Reviewed-by Dr. David Alan Gilbert <[email protected]>

Co-developed-by Jiri Slaby <[email protected]>

Signed-off-by Jiri Slaby <[email protected]>

Signed-off-by Tom Lendacky <[email protected]>

---
 target/i386/cpu.c      |  1 +
 target/i386/sev-stub.c |  6 ++++++
 target/i386/sev.c      | 44 ++++++++++++++++++++++++++++++++++++++++--
 target/i386/sev_i386.h |  1 +
 4 files changed, 50 insertions(+), 2 deletions(-)

target/i386/cpu.c +1 -0

index 72a79e6019..0415d8a99c 100644
@@ -5987,6 +5987,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
         break;
     case 0x8000001F:
         *eax = sev_enabled() ? 0x2 : 0;
+        *eax |= sev_es_enabled() ? 0x8 : 0;
         *ebx = sev_get_cbit_position();
         *ebx |= sev_get_reduced_phys_bits() << 6;
         *ecx = 0;

target/i386/sev-stub.c +6 -0

index c1fecc2101..229a2ee77b 100644
@@ -49,8 +49,14 @@ SevCapability *sev_get_capabilities(Error **errp)
     error_setg(errp, "SEV is not available in this QEMU");
     return NULL;
 }
+
 int sev_inject_launch_secret(const char *hdr, const char *secret,
                              uint64_t gpa, Error **errp)
 {
     return 1;
 }
+
+bool sev_es_enabled(void)
+{
+    return false;
+}

target/i386/sev.c +42 -2

index 1546606811..fce2128c07 100644
@@ -360,6 +360,12 @@ sev_enabled(void)
     return !!sev_guest;
 }
 
+bool
+sev_es_enabled(void)
+{
+    return false;
+}
+
 uint64_t
 sev_get_me_mask(void)
 {

@@ -580,6 +586,20 @@ sev_launch_update_data(SevGuestState *sev, uint8_t *addr, uint64_t len)
     return ret;
 }
 
+static int
+sev_launch_update_vmsa(SevGuestState *sev)
+{
+    int ret, fw_error;
+
+    ret = sev_ioctl(sev->sev_fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL, &fw_error);
+    if (ret) {
+        error_report("%s: LAUNCH_UPDATE_VMSA ret=%d fw_error=%d '%s'",
+                __func__, ret, fw_error, fw_error_to_str(fw_error));
+    }
+
+    return ret;
+}
+
 static void
 sev_launch_get_measure(Notifier *notifier, void *unused)
 {

@@ -592,6 +612,14 @@ sev_launch_get_measure(Notifier *notifier, void *unused)
         return;
     }
 
+    if (sev_es_enabled()) {
+        /* measure all the VM save areas before getting launch_measure */
+        ret = sev_launch_update_vmsa(sev);
+        if (ret) {
+            exit(1);
+        }
+    }
+
     measurement = g_new0(struct kvm_sev_launch_measure, 1);
 
     /* query the measurement blob length */

@@ -686,7 +714,7 @@ sev_guest_init(const char *id)
 {
     SevGuestState *sev;
     char *devname;
-    int ret, fw_error;
+    int ret, fw_error, cmd;
     uint32_t ebx;
     uint32_t host_cbitpos;
     struct sev_user_data_status status = {};

@@ -747,8 +775,20 @@ sev_guest_init(const char *id)
     sev->api_major = status.api_major;
     sev->api_minor = status.api_minor;
 
+    if (sev_es_enabled()) {
+        if (!(status.flags & SEV_STATUS_FLAGS_CONFIG_ES)) {
+            error_report("%s: guest policy requires SEV-ES, but "
+                         "host SEV-ES support unavailable",
+                         __func__);
+            goto err;
+        }
+        cmd = KVM_SEV_ES_INIT;
+    } else {
+        cmd = KVM_SEV_INIT;
+    }
+
     trace_kvm_sev_init();
-    ret = sev_ioctl(sev->sev_fd, KVM_SEV_INIT, NULL, &fw_error);
+    ret = sev_ioctl(sev->sev_fd, cmd, NULL, &fw_error);
     if (ret) {
         error_report("%s: failed to initialize ret=%d fw_error=%d '%s'",
                      __func__, ret, fw_error, fw_error_to_str(fw_error));

target/i386/sev_i386.h +1 -0

index 4db6960f60..4f9a5e9b21 100644
@@ -29,6 +29,7 @@
 #define SEV_POLICY_SEV          0x20
 
 extern bool sev_enabled(void);
+extern bool sev_es_enabled(void);
 extern uint64_t sev_get_me_mask(void);
 extern SevInfo *sev_get_info(void);
 extern uint32_t sev_get_cbit_position(void);

Signature · 1 line

2.30.0

From: Tom Lendacky <[email protected]>

In prep for AP booting, require the use of in-kernel irqchip support. This lessens the Qemu support burden required to boot APs.

Cc Paolo Bonzini <[email protected]>

Cc Richard Henderson <[email protected]>

Cc Eduardo Habkost <[email protected]>

Reviewed-by Dr. David Alan Gilbert <[email protected]>

Signed-off-by Tom Lendacky <[email protected]>

---
 target/i386/sev.c | 6 ++++++
 1 file changed, 6 insertions(+)

target/i386/sev.c +6 -0

index fce2128c07..ddec7ebaa7 100644
@@ -776,6 +776,12 @@ sev_guest_init(const char *id)
     sev->api_minor = status.api_minor;
 
     if (sev_es_enabled()) {
+        if (!kvm_kernel_irqchip_allowed()) {
+            error_report("%s: SEV-ES guests require in-kernel irqchip support",
+                         __func__);
+            goto err;
+        }
+
         if (!(status.flags & SEV_STATUS_FLAGS_CONFIG_ES)) {
             error_report("%s: guest policy requires SEV-ES, but "
                          "host SEV-ES support unavailable",

Signature · 1 line

2.30.0

From: Tom Lendacky <[email protected]>

When SEV-ES is enabled, it is not possible modify the guests register state after it has been initially created, encrypted and measured.

Normally, an INIT-SIPI-SIPI request is used to boot the AP. However, the hypervisor cannot emulate this because it cannot update the AP register state. For the very first boot by an AP, the reset vector CS segment value and the EIP value must be programmed before the register has been encrypted and measured. Search the guest firmware for the guest for a specific GUID that tells Qemu the value of the reset vector to use.

Cc Paolo Bonzini <[email protected]>

Cc "Michael S. Tsirkin" <[email protected]>

Cc Marcel Apfelbaum <[email protected]>

Cc Richard Henderson <[email protected]>

Cc Eduardo Habkost <[email protected]>

Cc Marcelo Tosatti <[email protected]>

Signed-off-by Tom Lendacky <[email protected]>

---
 accel/kvm/kvm-all.c    | 64 ++++++++++++++++++++++++++++++++++++
 accel/stubs/kvm-stub.c |  5 +++
 hw/i386/pc_sysfw.c     | 10 +++++-
 include/sysemu/kvm.h   | 16 +++++++++
 include/sysemu/sev.h   |  3 ++
 target/i386/kvm/kvm.c  |  2 ++
 target/i386/sev.c      | 74 ++++++++++++++++++++++++++++++++++++++++++
 7 files changed, 173 insertions(+), 1 deletion(-)

accel/kvm/kvm-all.c +64 -0

index 3feb17d965..410879cf94 100644
@@ -39,6 +39,7 @@
 #include "qemu/main-loop.h"
 #include "trace.h"
 #include "hw/irq.h"
+#include "sysemu/kvm.h"
 #include "sysemu/sev.h"
 #include "qapi/visitor.h"
 #include "qapi/qapi-types-common.h"

@@ -126,6 +127,12 @@ struct KVMState
     /* memory encryption */
     void *memcrypt_handle;
     int (*memcrypt_encrypt_data)(void *handle, uint8_t *ptr, uint64_t len);
+    int (*memcrypt_save_reset_vector)(void *handle, void *flash_ptr,
+                                      uint64_t flash_size, uint32_t *addr);
+
+    uint32_t reset_cs;
+    uint32_t reset_ip;
+    bool reset_data_valid;
 
     /* For "info mtree -f" to tell if an MR is registered in KVM */
     int nr_as;

@@ -245,6 +252,62 @@ int kvm_memcrypt_encrypt_data(uint8_t *ptr, uint64_t len)
     return 1;
 }
 
+void kvm_memcrypt_set_reset_vector(CPUState *cpu)
+{
+    X86CPU *x86;
+    CPUX86State *env;
+
+    /* Only update if we have valid reset information */
+    if (!kvm_state->reset_data_valid) {
+        return;
+    }
+
+    /* Do not update the BSP reset state */
+    if (cpu->cpu_index == 0) {
+        return;
+    }
+
+    x86 = X86_CPU(cpu);
+    env = &x86->env;
+
+    cpu_x86_load_seg_cache(env, R_CS, 0xf000, kvm_state->reset_cs, 0xffff,
+                           DESC_P_MASK | DESC_S_MASK | DESC_CS_MASK |
+                           DESC_R_MASK | DESC_A_MASK);
+
+    env->eip = kvm_state->reset_ip;
+}
+
+int kvm_memcrypt_save_reset_vector(void *flash_ptr, uint64_t flash_size)
+{
+    CPUState *cpu;
+    uint32_t addr;
+    int ret;
+
+    if (kvm_memcrypt_enabled() &&
+        kvm_state->memcrypt_save_reset_vector) {
+
+        addr = 0;
+        ret = kvm_state->memcrypt_save_reset_vector(kvm_state->memcrypt_handle,
+                                                    flash_ptr, flash_size,
+                                                    &addr);
+        if (ret) {
+            return ret;
+        }
+
+        if (addr) {
+            kvm_state->reset_cs = addr & 0xffff0000;
+            kvm_state->reset_ip = addr & 0x0000ffff;
+            kvm_state->reset_data_valid = true;
+
+            CPU_FOREACH(cpu) {
+                kvm_memcrypt_set_reset_vector(cpu);
+            }
+        }
+    }
+
+    return 0;
+}
+
 /* Called with KVMMemoryListener.slots_lock held */
 static KVMSlot *kvm_get_free_slot(KVMMemoryListener *kml)
 {

@@ -2216,6 +2279,7 @@ static int kvm_init(MachineState *ms)
         }
 
         kvm_state->memcrypt_encrypt_data = sev_encrypt_data;
+        kvm_state->memcrypt_save_reset_vector = sev_es_save_reset_vector;
     }
 
     ret = kvm_arch_init(ms, s);

accel/stubs/kvm-stub.c +5 -0

index 680e099463..162c28429e 100644
@@ -91,6 +91,11 @@ int kvm_memcrypt_encrypt_data(uint8_t *ptr, uint64_t len)
   return 1;
 }
 
+int kvm_memcrypt_save_reset_vector(void *flash_ptr, uint64_t flash_size)
+{
+    return -ENOSYS;
+}
+
 #ifndef CONFIG_USER_ONLY
 int kvm_irqchip_add_msi_route(KVMState *s, int vector, PCIDevice *dev)
 {

hw/i386/pc_sysfw.c +9 -1

index 436b78c587..edec28842d 100644
@@ -248,7 +248,8 @@ static void pc_system_flash_map(PCMachineState *pcms,
     PFlashCFI01 *system_flash;
     MemoryRegion *flash_mem;
     void *flash_ptr;
-    int ret, flash_size;
+    uint64_t flash_size;
+    int ret;
 
     assert(PC_MACHINE_GET_CLASS(pcms)->pci_enabled);
 

@@ -301,6 +302,13 @@ static void pc_system_flash_map(PCMachineState *pcms,
                  * search for them
                  */
                 pc_system_parse_ovmf_flash(flash_ptr, flash_size);
+
+                ret = kvm_memcrypt_save_reset_vector(flash_ptr, flash_size);
+                if (ret) {
+                    error_report("failed to locate and/or save reset vector");
+                    exit(1);
+                }
+
                 ret = kvm_memcrypt_encrypt_data(flash_ptr, flash_size);
                 if (ret) {
                     error_report("failed to encrypt pflash rom");

include/sysemu/kvm.h +16 -0

index bb5d5cf497..875ca101e3 100644
@@ -249,6 +249,22 @@ bool kvm_memcrypt_enabled(void);
  */
 int kvm_memcrypt_encrypt_data(uint8_t *ptr, uint64_t len);
 
+/**
+ * kvm_memcrypt_set_reset_vector - sets the CS/IP value for the AP if SEV-ES
+ *                                 is active.
+ */
+void kvm_memcrypt_set_reset_vector(CPUState *cpu);
+
+/**
+ * kvm_memcrypt_save_reset_vector - locates and saves the reset vector to be
+ *                                  used as the initial CS/IP value for APs
+ *                                  if SEV-ES is active.
+ *
+ * Return: 1 SEV-ES is active and failed to locate a valid reset vector
+ *         0 SEV-ES is not active or successfully located and saved the
+ *           reset vector address
+ */
+int kvm_memcrypt_save_reset_vector(void *flash_prt, uint64_t flash_size);
 
 #ifdef NEED_CPU_H
 #include "cpu.h"

include/sysemu/sev.h +3 -0

index 7ab6e3e31d..6f5ad3fd03 100644
@@ -20,4 +20,7 @@ void *sev_guest_init(const char *id);
 int sev_encrypt_data(void *handle, uint8_t *ptr, uint64_t len);
 int sev_inject_launch_secret(const char *hdr, const char *secret,
                              uint64_t gpa, Error **errp);
+int sev_es_save_reset_vector(void *handle, void *flash_ptr,
+                             uint64_t flash_size, uint32_t *addr);
+
 #endif

target/i386/kvm/kvm.c +2 -0

index 6dc1ee052d..aaae79557d 100644
@@ -1920,6 +1920,8 @@ void kvm_arch_reset_vcpu(X86CPU *cpu)
     }
     /* enabled by default */
     env->poll_control_msr = 1;
+
+    kvm_memcrypt_set_reset_vector(CPU(cpu));
 }
 
 void kvm_arch_do_init_vcpu(X86CPU *cpu)

target/i386/sev.c +48 -0

index ddec7ebaa7..badc141554 100644
@@ -22,6 +22,7 @@
 #include "qom/object_interfaces.h"
 #include "qemu/base64.h"
 #include "qemu/module.h"
+#include "qemu/uuid.h"
 #include "sysemu/kvm.h"
 #include "sev_i386.h"
 #include "sysemu/sysemu.h"

@@ -31,6 +32,7 @@
 #include "qom/object.h"
 #include "exec/address-spaces.h"
 #include "monitor/monitor.h"
+#include "hw/i386/pc.h"
 
 #define TYPE_SEV_GUEST "sev-guest"
 OBJECT_DECLARE_SIMPLE_TYPE(SevGuestState, SEV_GUEST)

@@ -71,6 +73,12 @@ struct SevGuestState {
 #define DEFAULT_GUEST_POLICY    0x1 /* disable debug */
 #define DEFAULT_SEV_DEVICE      "/dev/sev"
 
+#define SEV_INFO_BLOCK_GUID     "00f771de-1a7e-4fcb-890e-68c77e2fb44e"
+typedef struct __attribute__((__packed__)) SevInfoBlock {
+    /* SEV-ES Reset Vector Address */
+    uint32_t reset_addr;
+} SevInfoBlock;
+
 static SevGuestState *sev_guest;
 static Error *sev_mig_blocker;
 

@@ -896,6 +904,72 @@ int sev_inject_launch_secret(const char *packet_hdr, const char *secret,
     return 0;
 }
 
+static int
+sev_es_parse_reset_block(SevInfoBlock *info, uint32_t *addr)
+{
+    if (!info->reset_addr) {
+        error_report("SEV-ES reset address is zero");
+        return 1;
+    }
+
+    *addr = info->reset_addr;
+
+    return 0;
+}
+
+int
+sev_es_save_reset_vector(void *handle, void *flash_ptr, uint64_t flash_size,
+                         uint32_t *addr)
+{
+    QemuUUID info_guid, *guid;
+    SevInfoBlock *info;
+    uint8_t *data;
+    uint16_t *len;
+
+    assert(handle);
+
+    /*
+     * Initialize the address to zero. An address of zero with a successful
+     * return code indicates that SEV-ES is not active.
+     */
+    *addr = 0;
+    if (!sev_es_enabled()) {
+        return 0;
+    }
+
+    /*
+     * Extract the AP reset vector for SEV-ES guests by locating the SEV GUID.
+     * The SEV GUID is located on its own (original implementation) or within
+     * the Firmware GUID Table (new implementation), either of which are
+     * located 32 bytes from the end of the flash.
+     *
+     * Check the Firmware GUID Table first.

target/i386/sev.c +16 -0

+
+    qemu_uuid_parse(SEV_INFO_BLOCK_GUID, &info_guid);
+    info_guid = qemu_uuid_bswap(info_guid); /* GUIDs are LE */
+
+    guid = (QemuUUID *)(data - sizeof(info_guid));
+    if (!qemu_uuid_is_equal(guid, &info_guid)) {
+        error_report("SEV information block/Firmware GUID Table block not found in pflash rom");
+        return 1;
+    }
+
+    len = (uint16_t *)((uint8_t *)guid - sizeof(*len));
+    info = (SevInfoBlock *)(data - le16_to_cpu(*len));
+
+    return sev_es_parse_reset_block(info, addr);
+}
+
 static void
 sev_register_types(void)
 {

Signature · 1 line

2.30.0

Quoted 20 lines · Tom Lendacky

From: Tom Lendacky <[email protected]>

When SEV-ES is enabled, it is not possible modify the guests register state after it has been initially created, encrypted and measured.

Normally, an INIT-SIPI-SIPI request is used to boot the AP. However, the hypervisor cannot emulate this because it cannot update the AP register state. For the very first boot by an AP, the reset vector CS segment value and the EIP value must be programmed before the register has been encrypted and measured. Search the guest firmware for the guest for a specific GUID that tells Qemu the value of the reset vector to use.

Cc Paolo Bonzini <[email protected]>

Cc "Michael S. Tsirkin" <[email protected]>

Cc Marcel Apfelbaum <[email protected]>

Cc Richard Henderson <[email protected]>

Cc Eduardo Habkost <[email protected]>

Cc Marcelo Tosatti <[email protected]>

Signed-off-by Tom Lendacky <[email protected]>

---

target/i386/sev.c int sev_inject_launch_secret(const char *packet_hdr, const char *secret, · line 956

Quoted 6 lines

target/i386/sev.c +6 -0

+
+    /*
+     * SEV info block not found in the Firmware GUID Table (or there isn't
+     * a Firmware GUID Table), fall back to the original implementation.
+     */
+    data = flash_ptr + flash_size - 0x20;

Even if the SEV_INFO_BLOCK_GUID is always located at 32 bytes from the end of the flash, isn't it better to define a constant with a value of 0x20?

Quoted 2 lines

+

From: Tom Lendacky <[email protected]>

An SEV-ES guest does not allow register state to be altered once it has been measured. When an SEV-ES guest issues a reboot command, Qemu will reset the vCPU state and resume the guest. This will cause failures under SEV-ES. Prevent that from occuring by introducing an arch-specific callback that returns a boolean indicating whether vCPUs are resettable.

Cc Peter Maydell <[email protected]>

Cc Aurelien Jarno <[email protected]>

Cc Jiaxun Yang <[email protected]>

Cc Aleksandar Rikalo <[email protected]>

Cc David Gibson <[email protected]>

Cc David Hildenbrand <[email protected]>

Reviewed-by Dr. David Alan Gilbert <[email protected]>

Signed-off-by Tom Lendacky <[email protected]>

---
 accel/kvm/kvm-all.c       |  5 +++++
 include/sysemu/cpus.h     |  2 ++
 include/sysemu/hw_accel.h |  5 +++++
 include/sysemu/kvm.h      | 10 ++++++++++
 softmmu/cpus.c            |  5 +++++
 softmmu/runstate.c        |  3 +++
 target/arm/kvm.c          |  5 +++++
 target/i386/kvm/kvm.c     |  6 ++++++
 target/mips/kvm.c         |  5 +++++
 target/ppc/kvm.c          |  5 +++++
 target/s390x/kvm.c        |  5 +++++
 11 files changed, 56 insertions(+)

accel/kvm/kvm-all.c +5 -0

index 410879cf94..6c099a3869 100644
@@ -2414,6 +2414,11 @@ void kvm_flush_coalesced_mmio_buffer(void)
     s->coalesced_flush_in_progress = false;
 }
 
+bool kvm_cpu_check_are_resettable(void)
+{
+    return kvm_arch_cpu_check_are_resettable();
+}
+
 static void do_kvm_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg)
 {
     if (!cpu->vcpu_dirty) {

include/sysemu/cpus.h +2 -0

index e8156728c6..1cb4f9dbeb 100644
@@ -57,6 +57,8 @@ extern int icount_align_option;
 /* Unblock cpu */
 void qemu_cpu_kick_self(void);
 
+bool cpus_are_resettable(void);
+
 void cpu_synchronize_all_states(void);
 void cpu_synchronize_all_post_reset(void);
 void cpu_synchronize_all_post_init(void);

include/sysemu/hw_accel.h +5 -0

index ffed6192a3..61672f9b32 100644
@@ -22,4 +22,9 @@ void cpu_synchronize_post_reset(CPUState *cpu);
 void cpu_synchronize_post_init(CPUState *cpu);
 void cpu_synchronize_pre_loadvm(CPUState *cpu);
 
+static inline bool cpu_check_are_resettable(void)
+{
+    return kvm_enabled() ? kvm_cpu_check_are_resettable() : true;
+}
+
 #endif /* QEMU_HW_ACCEL_H */

include/sysemu/kvm.h +10 -0

index 875ca101e3..3e265cea3d 100644
@@ -573,4 +573,14 @@ int kvm_get_max_memslots(void);
 /* Notify resamplefd for EOI of specific interrupts. */
 void kvm_resample_fd_notify(int gsi);
 
+/**
+ * kvm_cpu_check_are_resettable - return whether CPUs can be reset
+ *
+ * Returns: true: CPUs are resettable
+ *          false: CPUs are not resettable
+ */
+bool kvm_cpu_check_are_resettable(void);
+
+bool kvm_arch_cpu_check_are_resettable(void);
+
 #endif

softmmu/cpus.c +5 -0

index 1dc20b9dc3..89de46eae0 100644
@@ -194,6 +194,11 @@ void cpu_synchronize_pre_loadvm(CPUState *cpu)
     }
 }
 
+bool cpus_are_resettable(void)
+{
+    return cpu_check_are_resettable();
+}
+
 int64_t cpus_get_virtual_clock(void)
 {
     /*

softmmu/runstate.c +3 -0

index beee050815..1813691898 100644
@@ -527,6 +527,9 @@ void qemu_system_reset_request(ShutdownCause reason)
     if (reboot_action == REBOOT_ACTION_SHUTDOWN &&
         reason != SHUTDOWN_CAUSE_SUBSYSTEM_RESET) {
         shutdown_requested = reason;
+    } else if (!cpus_are_resettable()) {
+        error_report("cpus are not resettable, terminating");
+        shutdown_requested = reason;
     } else {
         reset_requested = reason;
     }

target/arm/kvm.c +5 -0

index ffe186de8d..00e124c812 100644
@@ -1045,3 +1045,8 @@ int kvm_arch_msi_data_to_gsi(uint32_t data)
 {
     return (data - 32) & 0xffff;
 }
+
+bool kvm_arch_cpu_check_are_resettable(void)
+{
+    return true;
+}

target/i386/kvm/kvm.c +6 -0

index aaae79557d..bb6bfc19de 100644
@@ -27,6 +27,7 @@
 #include "sysemu/kvm_int.h"
 #include "sysemu/runstate.h"
 #include "kvm_i386.h"
+#include "sev_i386.h"
 #include "hyperv.h"
 #include "hyperv-proto.h"
 

@@ -4788,3 +4789,8 @@ bool kvm_has_waitpkg(void)
 {
     return has_msr_umwait;
 }
+
+bool kvm_arch_cpu_check_are_resettable(void)
+{
+    return !sev_es_enabled();
+}

target/mips/kvm.c +5 -0

index 84fb10ea35..123ec1be7e 100644
@@ -1290,3 +1290,8 @@ int mips_kvm_type(MachineState *machine, const char *vm_type)
 
     return -1;
 }
+
+bool kvm_arch_cpu_check_are_resettable(void)
+{
+    return true;
+}

target/ppc/kvm.c +5 -0

index daf690a678..f45ed11058 100644
@@ -2947,3 +2947,8 @@ void kvmppc_svm_off(Error **errp)
         error_setg_errno(errp, -rc, "KVM_PPC_SVM_OFF ioctl failed");
     }
 }
+
+bool kvm_arch_cpu_check_are_resettable(void)
+{
+    return true;
+}

target/s390x/kvm.c +5 -0

index dc27fa36c9..7a892d663d 100644
@@ -2599,3 +2599,8 @@ void kvm_s390_stop_interrupt(S390CPU *cpu)
 
     kvm_s390_vcpu_interrupt(cpu, &irq);
 }
+
+bool kvm_arch_cpu_check_are_resettable(void)
+{
+    return true;
+}

Signature · 1 line

2.30.0

From: Tom Lendacky <[email protected]>

SMM is not currently supported for an SEV-ES guest by KVM. Change the SMM capability check from a KVM-wide check to a per-VM check in order to have a finer-grained SMM capability check.

Cc Paolo Bonzini <[email protected]>

Cc Richard Henderson <[email protected]>

Cc Eduardo Habkost <[email protected]>

Suggested-by Sean Christopherson <[email protected]>

Signed-off-by Tom Lendacky <[email protected]>

---
 target/i386/kvm/kvm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

target/i386/kvm/kvm.c +1 -1

index bb6bfc19de..37fca43cd9 100644
@@ -135,7 +135,7 @@ int kvm_has_pit_state2(void)
 
 bool kvm_has_smm(void)
 {
-    return kvm_check_extension(kvm_state, KVM_CAP_X86_SMM);
+    return kvm_vm_check_extension(kvm_state, KVM_CAP_X86_SMM);
 }
 
 bool kvm_has_adjust_clock_stable(void)

Signature · 1 line

2.30.0

From: Tom Lendacky <[email protected]>

Update the sev_es_enabled() function return value to be based on the SEV policy that has been specified. SEV-ES is enabled if SEV is enabled and the SEV-ES policy bit is set in the policy object.

Cc Paolo Bonzini <[email protected]>

Cc Richard Henderson <[email protected]>

Cc Eduardo Habkost <[email protected]>

Reviewed-by Dr. David Alan Gilbert <[email protected]>

Signed-off-by Tom Lendacky <[email protected]>

---
 target/i386/sev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

target/i386/sev.c +1 -1

index badc141554..62ecc28cf6 100644
@@ -371,7 +371,7 @@ sev_enabled(void)
 bool
 sev_es_enabled(void)
 {
-    return false;
+    return sev_enabled() && (sev_guest->policy & SEV_POLICY_ES);
 }
 
 uint64_t

Signature · 1 line

2.30.0

From: Tom Lendacky <[email protected]>

This patch series provides support for launching an SEV-ES guest.

Secure Encrypted Virtualization - Encrypted State (SEV-ES) expands on the SEV support to protect the guest register state from the hypervisor. See "AMD64 Architecture Programmer's Manual Volume 2: System Programming", section "15.35 Encrypted State (SEV-ES)" [1].

In order to allow a hypervisor to perform functions on behalf of a guest, there is architectural support for notifying a guest's operating system when certain types of VMEXITs are about to occur. This allows the guest to selectively share information with the hypervisor to satisfy the requested function. The notification is performed using a new exception, the VMM Communication exception (#VC). The information is shared through the Guest-Hypervisor Communication Block (GHCB) using the VMGEXIT instruction. The GHCB format and the protocol for using it is documented in "SEV-ES Guest-Hypervisor Communication Block Standardization" [2].

The main areas of the Qemu code that are updated to support SEV-ES are around the SEV guest launch process and AP booting in order to support booting multiple vCPUs.

There are no new command line switches required. Instead, the desire for SEV-ES is presented using the SEV policy object. Bit 2 of the SEV policy object indicates that SEV-ES is required.

The SEV launch process is updated in two ways. The first is that a the KVM_SEV_ES_INIT ioctl is used to initialize the guest instead of the standard KVM_SEV_INIT ioctl. The second is that before the SEV launch measurement is calculated, the LAUNCH_UPDATE_VMSA SEV API is invoked for each vCPU that Qemu has created. Once the LAUNCH_UPDATE_VMSA API has been invoked, no direct changes to the guest register state can be made.

AP booting poses some interesting challenges. The INIT-SIPI-SIPI sequence is typically used to boot the APs. However, the hypervisor is not allowed to update the guest registers. For the APs, the reset vector must be known in advance. An OVMF method to provide a known reset vector address exists by providing an SEV information block, identified by UUID, near the end of the firmware [3]. OVMF will program the jump to the actual reset vector in this area of memory. Since the memory location is known in advance, an AP can be created with the known reset vector address as its starting CS:IP. The GHCB document [2] talks about how SMP booting under SEV-ES is performed. SEV-ES also requires the use of the in-kernel irqchip support in order to minimize the changes required to Qemu to support AP booting.

[1] https://www.amd.com/system/files/TechDocs/24593.pdf
[2] https://developer.amd.com/wp-content/resources/56421.pdf
[3] 30937f2f98c4 ("OvmfPkg: Use the SEV-ES work area for the SEV-ES AP reset vector")

     https://github.com/tianocore/edk2/commit/30937f2f98c42496f2f143fe8374ae7f7e684847

Cc Aleksandar Rikalo <[email protected]>

Cc Aurelien Jarno <[email protected]>

Cc David Gibson <[email protected]>

Cc David Hildenbrand <[email protected]>

Cc Eduardo Habkost <[email protected]>

Cc Jiaxun Yang <[email protected]>

Cc Marcel Apfelbaum <[email protected]>

Cc Marcelo Tosatti <[email protected]>

Cc "Michael S. Tsirkin" <[email protected]>

Cc Paolo Bonzini <[email protected]>

Cc Peter Maydell <[email protected]>

Cc Richard Henderson <[email protected]>

---

These patches are based on commit:
9cd69f1a27 ("Merge remote-tracking branch 'remotes/stefanberger/tags/pull-tpm-2021-01-25-1' into staging")

Additionally, these patches pre-req the following patch series that has not yet been accepted into the Qemu tree:

[PATCH v2 0/2] sev: enable secret injection to a self described area in OVMF
https://lore.kernel.org/qemu-devel/[email protected]/

A version of the tree can be found at:
https://github.com/AMDESE/qemu/tree/sev-es-v14

Changes since v5:
- Rework the reset prevention patch to not issue the error message if the --no-reboot option has been specified for SEV-ES guests.

Changes since v4:
- Add support for an updated Firmware GUID table implementation, that is now present in OVMF SEV-ES firmware, when searching for the reset vector information. The code will check for the new implementation first, followed by the original implementation to maintain backward compatibility.

Changes since v3:
- Use the QemuUUID structure for GUID definitions
- Use SEV-ES policy bit definition from target/i386/sev_i386.h
- Update SMM support to a per-VM check in order to check SMM capability at the VM level since SEV-ES guests don't currently support SMM
- Make the CPU resettable check an arch-specific check

Changes since v2:
- Add in-kernel irqchip requirement for SEV-ES guests

Changes since v1:
- Fixed checkpatch.pl errors/warnings

Tom Lendacky (6):
sev/i386: Add initial support for SEV-ES
sev/i386: Require in-kernel irqchip support for SEV-ES guests sev/i386: Allow AP booting under SEV-ES
sev/i386: Don't allow a system reset under an SEV-ES guest kvm/i386: Use a per-VM check for SMM capability sev/i386: Enable an SEV-ES guest based on SEV policy

  accel/kvm/kvm-all.c       |  69 +++++++++++++++++++++
  accel/stubs/kvm-stub.c    |   5 ++
  hw/i386/pc_sysfw.c        |  10 ++-
  include/sysemu/cpus.h     |   2 +
  include/sysemu/hw_accel.h |   5 ++
  include/sysemu/kvm.h      |  26 ++++++++
  include/sysemu/sev.h      |   3 +
  softmmu/cpus.c            |   5 ++
  softmmu/runstate.c        |   3 +
  target/arm/kvm.c          |   5 ++
  target/i386/cpu.c         |   1 +

  target/i386/kvm/kvm.c     |  10 ++-
  target/i386/sev-stub.c    |   6 ++
  target/i386/sev.c         | 124 +++++++++++++++++++++++++++++++++++++-
  target/i386/sev_i386.h    |   1 +
  target/mips/kvm.c         |   5 ++
  target/ppc/kvm.c          |   5 ++
  target/s390x/kvm.c        |   5 ++
  18 files changed, 286 insertions(+), 4 deletions(-)

Quoted 4 lines · Tom Lendacky

From: Tom Lendacky <[email protected]>

This patch series provides support for launching an SEV-ES guest.

Quoted 1 line

Queued, thanks.

Paolo

Quoted 3 lines

Quoted 1 line

Queued, thanks.

It looks like David Gibson's patches for the memory encryption rework went into the main tree before mine. So, I think I'm going to have to rework my patches. Let me look into it.

Quoted 5 lines · Tom Lendacky

Quoted 3 lines

Quoted 1 line

Queued, thanks.

It looks like David Gibson's patches for the memory encryption rework went into the main tree before mine. So, I think I'm going to have to rework my patches. Let me look into it.

I was going to ask you to check out my own rebase, but it hadn't finished CI yet.  Please take a look at branch sev-next at https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgitlab.com%2Fbonzini%2Fqemu&amp;data=04%7C01%7Cthomas.lendacky%40amd.com%7C0fd806ab779a47c04fb508d8cc4eef45%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637483986711396809%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=kxzVD%2FwGNrU0zIhZjxyA0XCDtyycPW%2FROsvs3BrlkJE%3D&amp;reserved=0 (commit 15acccb1b769aa3854bfd875d3d17945703e3f2a, ignore the PPC failure).

Paolo