#define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
#define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
#define MSR_AMD64_SNP_VTOM_ENABLED BIT_ULL(3)
+#define MSR_AMD64_SEV_REFLECTVC_ENABLED BIT_ULL(MSR_AMD64_SEV_REFLECTVC_ENABLED_BIT)
+#define MSR_AMD64_SEV_RESTRICTED_INJECTION_ENABLED BIT_ULL(MSR_AMD64_SEV_RESTRICTED_INJECTION_ENABLED_BIT)
+#define MSR_AMD64_SEV_ALTERNATE_INJECTION_ENABLED BIT_ULL(MSR_AMD64_SEV_ALTERNATE_INJECTION_ENABLED_BIT
#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
/* AMD Collaborative Processor Performance Control MSRs */
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index f8b321a11ee4..911c991fec78 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -568,12 +568,12 @@ static inline void __unused_size_checks(void)
/* Check offsets of reserved fields */
- BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xa0);
- BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xcc);
- BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xd8);
- BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x180);
- BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x248);
- BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x298);
+// BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xa0);
+// BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xcc);
+// BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xd8);
+// BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x180);
+// BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x248);
+// BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x298);
BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xc8);
BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xcc);
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index f69c168391aa..85d6882262e7 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -115,6 +115,10 @@
#define SVM_VMGEXIT_AP_CREATE_ON_INIT 0
#define SVM_VMGEXIT_AP_CREATE 1
#define SVM_VMGEXIT_AP_DESTROY 2
+#define SVM_VMGEXIT_HV_DOORBELL_PAGE 0x80000014
+#define SVM_VMGEXIT_GET_PREFERRED_HV_DOORBELL_PAGE 0
+#define SVM_VMGEXIT_SET_HV_DOORBELL_PAGE 1
+#define SVM_VMGEXIT_QUERY_HV_DOORBELL_PAGE 2
#define SVM_VMGEXIT_HV_FEATURES 0x8000fffd
#define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index fe5e5e41433d..03d99fad9e76 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -122,6 +122,150 @@ struct sev_config {
static struct sev_config sev_cfg __read_mostly;
+static noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state);
+static noinstr void __sev_put_ghcb(struct ghcb_state *state);
+static int vmgexit_hv_doorbell_page(struct ghcb *ghcb, u64 op, u64 pa);
+static void sev_snp_setup_hv_doorbell_page(struct ghcb *ghcb);
+
+union hv_pending_events {
+ u16 events;
+ struct {
+ u8 vector;
+ u8 nmi : 1;
+ u8 mc : 1;
+ u8 reserved1 : 5;
+ u8 no_further_signal : 1;
+ };
+};
+
+struct sev_hv_doorbell_page {
+ union hv_pending_events pending_events;
+ u8 no_eoi_required;
+ u8 reserved2[61];
+ u8 padding[4032];
+};
+
+struct sev_snp_runtime_data {
+ struct sev_hv_doorbell_page hv_doorbell_page;
+};
+
+static DEFINE_PER_CPU(struct sev_snp_runtime_data*, snp_runtime_data);
+
+static inline u64 sev_es_rd_ghcb_msr(void)
+{
+ return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
+}
+
+static __always_inline void sev_es_wr_ghcb_msr(u64 val)
+{
+ u32 low, high;
+
+ low = (u32)(val);
+ high = (u32)(val >> 32);
+
+ native_wrmsr(MSR_AMD64_SEV_ES_GHCB, low, high);
+}
+
+struct sev_hv_doorbell_page *sev_snp_current_doorbell_page(void)
+{
+ return &this_cpu_read(snp_runtime_data)->hv_doorbell_page;
+}
+
+static u8 sev_hv_pending(void)
+{
+ return sev_snp_current_doorbell_page()->pending_events.events;
+}
+
+static void hv_doorbell_apic_eoi_write(u32 reg, u32 val)
+{
+ if (xchg(&sev_snp_current_doorbell_page()->no_eoi_required, 0) & 0x1)
+ return;
+
+ BUG_ON(reg != APIC_EOI);
+ apic->write(reg, val);
+}
+
+static void do_exc_hv(struct pt_regs *regs)
+{
+ union hv_pending_events pending_events;
+ u8 vector;
+
+ while (sev_hv_pending()) {
+ pending_events.events = xchg(
+ &sev_snp_current_doorbell_page()->pending_events.events,
+ 0);
+
+ if (pending_events.nmi)
+ exc_nmi(regs);
+
+#ifdef CONFIG_X86_MCE
+ if (pending_events.mc)
+ exc_machine_check(regs);
+#endif
+
+ if (!pending_events.vector)
+ return;
+
+ if (pending_events.vector < FIRST_EXTERNAL_VECTOR) {
+ /* Exception vectors */
+ WARN(1, "exception shouldn't happen\n");
+ } else if (pending_events.vector == FIRST_EXTERNAL_VECTOR) {
+ sysvec_irq_move_cleanup(regs);
+ } else if (pending_events.vector == IA32_SYSCALL_VECTOR) {
+ WARN(1, "syscall shouldn't happen\n");
+ } else if (pending_events.vector >= FIRST_SYSTEM_VECTOR) {
+ switch (pending_events.vector) {
+#if IS_ENABLED(CONFIG_HYPERV)
+ case HYPERV_STIMER0_VECTOR:
+ sysvec_hyperv_stimer0(regs);
+ break;
+ case HYPERVISOR_CALLBACK_VECTOR:
+ sysvec_hyperv_callback(regs);
+ break;
+#endif
+#ifdef CONFIG_SMP
+ case RESCHEDULE_VECTOR:
+ sysvec_reschedule_ipi(regs);
+ break;
+ case IRQ_MOVE_CLEANUP_VECTOR:
+ sysvec_irq_move_cleanup(regs);
+ break;
+ case REBOOT_VECTOR:
+ sysvec_reboot(regs);
+ break;
+ case CALL_FUNCTION_SINGLE_VECTOR:
+ sysvec_call_function_single(regs);
+ break;
+ case CALL_FUNCTION_VECTOR:
+ sysvec_call_function(regs);
+ break;
+#endif
+#ifdef CONFIG_X86_LOCAL_APIC
+ case ERROR_APIC_VECTOR:
+ sysvec_error_interrupt(regs);
+ break;
+ case SPURIOUS_APIC_VECTOR:
+ sysvec_spurious_apic_interrupt(regs);
+ break;
+ case LOCAL_TIMER_VECTOR:
+ sysvec_apic_timer_interrupt(regs);
+ break;
+ case X86_PLATFORM_IPI_VECTOR:
+ sysvec_x86_platform_ipi(regs);
+ break;
+#endif
+ case 0x0:
+ break;
+ default:
+ panic("Unexpected vector %d\n", vector);
+ unreachable();
+ }
+ } else {
+ common_interrupt(regs, pending_events.vector);
+ }
+ }
+}
+
static __always_inline bool on_vc_stack(struct pt_regs *regs)
{
unsigned long sp = regs->sp;
@@ -179,11 +323,6 @@ void noinstr __sev_es_ist_enter(struct pt_regs *regs)
this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], new_ist);
}
-static void do_exc_hv(struct pt_regs *regs)
-{
- /* Handle #HV exception. */
-}
-
void check_hv_pending(struct pt_regs *regs)
{
if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
@@ -232,68 +371,38 @@ void noinstr __sev_es_ist_exit(void)
this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist);
}
-/*
- * Nothing shall interrupt this code path while holding the per-CPU
- * GHCB. The backup GHCB is only for NMIs interrupting this path.
- *
- * Callers must disable local interrupts around it.
- */
-static noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
+static bool sev_restricted_injection_enabled(void)
+{
+ return sev_status & MSR_AMD64_SEV_RESTRICTED_INJECTION_ENABLED;
+}
+
+void __init sev_snp_init_hv_handling(void)
{
+ struct sev_snp_runtime_data *snp_data;
struct sev_es_runtime_data *data;
+ struct ghcb_state state;
struct ghcb *ghcb;
+ unsigned long flags;
+ int cpu;
+ int err;
WARN_ON(!irqs_disabled());
+ if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP) || !sev_restricted_injection_enabled())
+ return;
data = this_cpu_read(runtime_data);
- ghcb = &data->ghcb_page;
- if (unlikely(data->ghcb_active)) {
- /* GHCB is already in use - save its contents */
-
- if (unlikely(data->backup_ghcb_active)) {
- /*
- * Backup-GHCB is also already in use. There is no way
- * to continue here so just kill the machine. To make
- * panic() work, mark GHCBs inactive so that messages
- * can be printed out.
- */
- data->ghcb_active = false;
- data->backup_ghcb_active = false;
-
- instrumentation_begin();
- panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
- instrumentation_end();
- }
-
- /* Mark backup_ghcb active before writing to it */
- data->backup_ghcb_active = true;
-
- state->ghcb = &data->backup_ghcb;
+ local_irq_save(flags);
- /* Backup GHCB content */
- *state->ghcb = *ghcb;
- } else {
- state->ghcb = NULL;
- data->ghcb_active = true;
- }
+ ghcb = __sev_get_ghcb(&state);
- return ghcb;
-}
+ sev_snp_setup_hv_doorbell_page(ghcb);
-static inline u64 sev_es_rd_ghcb_msr(void)
-{
- return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
-}
-
-static __always_inline void sev_es_wr_ghcb_msr(u64 val)
-{
- u32 low, high;
+ __sev_put_ghcb(&state);
- low = (u32)(val);
- high = (u32)(val >> 32);
+ apic_set_eoi_write(hv_doorbell_apic_eoi_write);
- native_wrmsr(MSR_AMD64_SEV_ES_GHCB, low, high);
+ local_irq_restore(flags);
}
static int vc_fetch_insn_kernel(struct es_em_ctxt *ctxt,
@@ -554,6 +663,69 @@ static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt
/* Include code shared with pre-decompression boot stage */
#include "sev-shared.c"
+/*
+ * Nothing shall interrupt this code path while holding the per-CPU
+ * GHCB. The backup GHCB is only for NMIs interrupting this path.
+ *
+ * Callers must disable local interrupts around it.
+ */
+static noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
+{
+ struct sev_es_runtime_data *data;
+ struct ghcb *ghcb;
+
+ WARN_ON(!irqs_disabled());
+
+ data = this_cpu_read(runtime_data);
+ ghcb = &data->ghcb_page;
+
+ if (unlikely(data->ghcb_active)) {
+ /* GHCB is already in use - save its contents */
+
+ if (unlikely(data->backup_ghcb_active)) {
+ /*
+ * Backup-GHCB is also already in use. There is no way
+ * to continue here so just kill the machine. To make
+ * panic() work, mark GHCBs inactive so that messages
+ * can be printed out.
+ */
+ data->ghcb_active = false;
+ data->backup_ghcb_active = false;
+
+ instrumentation_begin();
+ panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
+ instrumentation_end();
+ }
+
+ /* Mark backup_ghcb active before writing to it */
+ data->backup_ghcb_active = true;
+
+ state->ghcb = &data->backup_ghcb;
+
+ /* Backup GHCB content */
+ *state->ghcb = *ghcb;
+ } else {
+ state->ghcb = NULL;
+ data->ghcb_active = true;
+ }
+
+ return ghcb;
+}
+
+static void sev_snp_setup_hv_doorbell_page(struct ghcb *ghcb)
+{
+ u64 pa;
+ enum es_result ret;
+
+ pa = __pa(sev_snp_current_doorbell_page());
+ vc_ghcb_invalidate(ghcb);
+ ret = vmgexit_hv_doorbell_page(ghcb,
+ SVM_VMGEXIT_SET_HV_DOORBELL_PAGE,
+ pa);
+ if (ret != ES_OK)
+ panic("SEV-SNP: failed to set up #HV doorbell page");
+}
+
static noinstr void __sev_put_ghcb(struct ghcb_state *state)
{
struct sev_es_runtime_data *data;
@@ -1282,6 +1454,7 @@ static void snp_register_per_cpu_ghcb(void)
ghcb = &data->ghcb_page;
snp_register_ghcb_early(__pa(ghcb));
+ sev_snp_setup_hv_doorbell_page(ghcb);
}
void setup_ghcb(void)
@@ -1321,6 +1494,11 @@ void setup_ghcb(void)
snp_register_ghcb_early(__pa(&boot_ghcb_page));
}
+int vmgexit_hv_doorbell_page(struct ghcb *ghcb, u64 op, u64 pa)
+{
+ return sev_es_ghcb_hv_call(ghcb, NULL, SVM_VMGEXIT_HV_DOORBELL_PAGE, op, pa);
+}
+
#ifdef CONFIG_HOTPLUG_CPU
static void sev_es_ap_hlt_loop(void)
{
@@ -1394,6 +1572,7 @@ static void __init alloc_runtime_data(int cpu)
static void __init init_ghcb(int cpu)
{
struct sev_es_runtime_data *data;
+ struct sev_snp_runtime_data *snp_data;
int err;
data = per_cpu(runtime_data, cpu);
@@ -1405,6 +1584,19 @@ static void __init init_ghcb(int cpu)
memset(&data->ghcb_page, 0, sizeof(data->ghcb_page));
+ snp_data = memblock_alloc(sizeof(*snp_data), PAGE_SIZE);
+ if (!snp_data)
+ panic("Can't allocate SEV-SNP runtime data");
+
+ err = early_set_memory_decrypted((unsigned long)&snp_data->hv_doorbell_page,
+ sizeof(snp_data->hv_doorbell_page));
+ if (err)
+ panic("Can't map #HV doorbell pages unencrypted");
+
+ memset(&snp_data->hv_doorbell_page, 0, sizeof(snp_data->hv_doorbell_page));
+
+ per_cpu(snp_runtime_data, cpu) = snp_data;
+
data->ghcb_active = false;
data->backup_ghcb_active = false;
}
@@ -2045,7 +2237,12 @@ DEFINE_IDTENTRY_VC_USER(exc_vmm_communication)
static bool hv_raw_handle_exception(struct pt_regs *regs)
{
- return false;
+ /* Clear the no_further_signal bit */
+ sev_snp_current_doorbell_page()->pending_events.events &= 0x7fff;
+
+ check_hv_pending(regs);
+
+ return true;
}
static __always_inline bool on_hv_fallback_stack(struct pt_regs *regs)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d29debec8134..1aa6cab2394b 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -1503,5 +1503,7 @@ void __init trap_init(void)
cpu_init_exception_handling();
/* Setup traps as cpu_init() might #GP */
idt_setup_traps();
+ sev_snp_init_hv_handling();
+
cpu_init();
}
