+static int nested_svm_check_permissions(struct vcpu_svm *svm)
+{
+ if (!(svm->vcpu.arch.shadow_efer & EFER_SVME)
+ || !is_paging(&svm->vcpu)) {
+ kvm_queue_exception(&svm->vcpu, UD_VECTOR);
+ return 1;
+ }
+
+ if (svm->vmcb->save.cpl) {
+ kvm_inject_gp(&svm->vcpu, 0);
+ return 1;
+ }
+
+ return 0;
+}
+
+static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
+ bool has_error_code, u32 error_code)
+{
+ if (is_nested(svm)) {
+ svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
+ svm->vmcb->control.exit_code_hi = 0;
+ svm->vmcb->control.exit_info_1 = error_code;
+ svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
+ if (nested_svm_exit_handled(svm, false)) {
+ nsvm_printk("VMexit -> EXCP 0x%x\n", nr);
+
+ nested_svm_vmexit(svm);
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
+static inline int nested_svm_intr(struct vcpu_svm *svm)
+{
+ if (is_nested(svm)) {
+ if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
+ return 0;
+
+ if (!(svm->vcpu.arch.hflags & HF_HIF_MASK))
+ return 0;
+
+ svm->vmcb->control.exit_code = SVM_EXIT_INTR;
+
+ if (nested_svm_exit_handled(svm, false)) {
+ nsvm_printk("VMexit -> INTR\n");
+ nested_svm_vmexit(svm);
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
+static struct page *nested_svm_get_page(struct vcpu_svm *svm, u64 gpa)
+{
+ struct page *page;
+
+ down_read(¤t->mm->mmap_sem);
+ page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT);
+ up_read(¤t->mm->mmap_sem);
+
+ if (is_error_page(page)) {
+ printk(KERN_INFO "%s: could not find page at 0x%llx\n",
+ __func__, gpa);
+ kvm_release_page_clean(page);
+ kvm_inject_gp(&svm->vcpu, 0);
+ return NULL;
+ }
+ return page;
+}
+
+static int nested_svm_do(struct vcpu_svm *svm,
+ u64 arg1_gpa, u64 arg2_gpa, void *opaque,
+ int (*handler)(struct vcpu_svm *svm,
+ void *arg1,
+ void *arg2,
+ void *opaque))
+{
+ struct page *arg1_page;
+ struct page *arg2_page = NULL;
+ void *arg1;
+ void *arg2 = NULL;
+ int retval;
+
+ arg1_page = nested_svm_get_page(svm, arg1_gpa);
+ if(arg1_page == NULL)
+ return 1;
+
+ if (arg2_gpa) {
+ arg2_page = nested_svm_get_page(svm, arg2_gpa);
+ if(arg2_page == NULL) {
+ kvm_release_page_clean(arg1_page);
+ return 1;
+ }
+ }
+
+ arg1 = kmap_atomic(arg1_page, KM_USER0);
+ if (arg2_gpa)
+ arg2 = kmap_atomic(arg2_page, KM_USER1);
+
+ retval = handler(svm, arg1, arg2, opaque);
+
+ kunmap_atomic(arg1, KM_USER0);
+ if (arg2_gpa)
+ kunmap_atomic(arg2, KM_USER1);
+
+ kvm_release_page_dirty(arg1_page);
+ if (arg2_gpa)
+ kvm_release_page_dirty(arg2_page);
+
+ return retval;
+}
+
+static int nested_svm_exit_handled_real(struct vcpu_svm *svm,
+ void *arg1,
+ void *arg2,
+ void *opaque)
+{
+ struct vmcb *nested_vmcb = (struct vmcb *)arg1;
+ bool kvm_overrides = *(bool *)opaque;
+ u32 exit_code = svm->vmcb->control.exit_code;
+
+ if (kvm_overrides) {
+ switch (exit_code) {
+ case SVM_EXIT_INTR:
+ case SVM_EXIT_NMI:
+ return 0;
+ /* For now we are always handling NPFs when using them */
+ case SVM_EXIT_NPF:
+ if (npt_enabled)
+ return 0;
+ break;
+ /* When we're shadowing, trap PFs */
+ case SVM_EXIT_EXCP_BASE + PF_VECTOR:
+ if (!npt_enabled)
+ return 0;
+ break;
+ default:
+ break;
+ }
+ }
+
+ switch (exit_code) {
+ case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: {
+ u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0);
+ if (nested_vmcb->control.intercept_cr_read & cr_bits)
+ return 1;
+ break;
+ }
+ case SVM_EXIT_WRITE_CR0 ... SVM_EXIT_WRITE_CR8: {
+ u32 cr_bits = 1 << (exit_code - SVM_EXIT_WRITE_CR0);
+ if (nested_vmcb->control.intercept_cr_write & cr_bits)
+ return 1;
+ break;
+ }
+ case SVM_EXIT_READ_DR0 ... SVM_EXIT_READ_DR7: {
+ u32 dr_bits = 1 << (exit_code - SVM_EXIT_READ_DR0);
+ if (nested_vmcb->control.intercept_dr_read & dr_bits)
+ return 1;
+ break;
+ }
+ case SVM_EXIT_WRITE_DR0 ... SVM_EXIT_WRITE_DR7: {
+ u32 dr_bits = 1 << (exit_code - SVM_EXIT_WRITE_DR0);
+ if (nested_vmcb->control.intercept_dr_write & dr_bits)
+ return 1;
+ break;
+ }
+ case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: {
+ u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE);
+ if (nested_vmcb->control.intercept_exceptions & excp_bits)
+ return 1;
+ break;
+ }
+ default: {
+ u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR);
+ nsvm_printk("exit code: 0x%x\n", exit_code);
+ if (nested_vmcb->control.intercept & exit_bits)
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
+static int nested_svm_exit_handled_msr(struct vcpu_svm *svm,
+ void *arg1, void *arg2,
+ void *opaque)
+{
+ struct vmcb *nested_vmcb = (struct vmcb *)arg1;
+ u8 *msrpm = (u8 *)arg2;
+ u32 t0, t1;
+ u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
+ u32 param = svm->vmcb->control.exit_info_1 & 1;
+
+ if (!(nested_vmcb->control.intercept & (1ULL << INTERCEPT_MSR_PROT)))
+ return 0;
+
+ switch(msr) {
+ case 0 ... 0x1fff:
+ t0 = (msr * 2) % 8;
+ t1 = msr / 8;
+ break;
+ case 0xc0000000 ... 0xc0001fff:
+ t0 = (8192 + msr - 0xc0000000) * 2;
+ t1 = (t0 / 8);
+ t0 %= 8;
+ break;
+ case 0xc0010000 ... 0xc0011fff:
+ t0 = (16384 + msr - 0xc0010000) * 2;
+ t1 = (t0 / 8);
+ t0 %= 8;
+ break;
+ default:
+ return 1;
+ break;
+ }
+ if (msrpm[t1] & ((1 << param) << t0))
+ return 1;
+
+ return 0;
+}
+
+static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override)
+{
+ bool k = kvm_override;
+
+ switch (svm->vmcb->control.exit_code) {
+ case SVM_EXIT_MSR:
+ return nested_svm_do(svm, svm->nested_vmcb,
+ svm->nested_vmcb_msrpm, NULL,
+ nested_svm_exit_handled_msr);
+ default: break;
+ }
+
+ return nested_svm_do(svm, svm->nested_vmcb, 0, &k,
+ nested_svm_exit_handled_real);
+}
+
+static int nested_svm_vmexit_real(struct vcpu_svm *svm, void *arg1,
+ void *arg2, void *opaque)
+{
+ struct vmcb *nested_vmcb = (struct vmcb *)arg1;
+ struct vmcb *hsave = svm->hsave;
+ u64 nested_save[] = { nested_vmcb->save.cr0,
+ nested_vmcb->save.cr3,
+ nested_vmcb->save.cr4,
+ nested_vmcb->save.efer,
+ nested_vmcb->control.intercept_cr_read,
+ nested_vmcb->control.intercept_cr_write,
+ nested_vmcb->control.intercept_dr_read,
+ nested_vmcb->control.intercept_dr_write,
+ nested_vmcb->control.intercept_exceptions,
+ nested_vmcb->control.intercept,
+ nested_vmcb->control.msrpm_base_pa,
+ nested_vmcb->control.iopm_base_pa,
+ nested_vmcb->control.tsc_offset };
+
+ /* Give the current vmcb to the guest */
+ memcpy(nested_vmcb, svm->vmcb, sizeof(struct vmcb));
+ nested_vmcb->save.cr0 = nested_save[0];
+ if (!npt_enabled)
+ nested_vmcb->save.cr3 = nested_save[1];
+ nested_vmcb->save.cr4 = nested_save[2];
+ nested_vmcb->save.efer = nested_save[3];
+ nested_vmcb->control.intercept_cr_read = nested_save[4];
+ nested_vmcb->control.intercept_cr_write = nested_save[5];
+ nested_vmcb->control.intercept_dr_read = nested_save[6];
+ nested_vmcb->control.intercept_dr_write = nested_save[7];
+ nested_vmcb->control.intercept_exceptions = nested_save[8];
+ nested_vmcb->control.intercept = nested_save[9];
+ nested_vmcb->control.msrpm_base_pa = nested_save[10];
+ nested_vmcb->control.iopm_base_pa = nested_save[11];
+ nested_vmcb->control.tsc_offset = nested_save[12];
+
+ /* We always set V_INTR_MASKING and remember the old value in hflags */
+ if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
+ nested_vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK;
+
+ if ((nested_vmcb->control.int_ctl & V_IRQ_MASK) &&
+ (nested_vmcb->control.int_vector)) {
+ nsvm_printk("WARNING: IRQ 0x%x still enabled on #VMEXIT\n",
+ nested_vmcb->control.int_vector);
+ }
+
+ /* Restore the original control entries */
+ svm->vmcb->control = hsave->control;
+
+ /* Kill any pending exceptions */
+ if (svm->vcpu.arch.exception.pending == true)
+ nsvm_printk("WARNING: Pending Exception\n");
+ svm->vcpu.arch.exception.pending = false;
+
+ /* Restore selected save entries */
+ svm->vmcb->save.es = hsave->save.es;
+ svm->vmcb->save.cs = hsave->save.cs;
+ svm->vmcb->save.ss = hsave->save.ss;
+ svm->vmcb->save.ds = hsave->save.ds;
+ svm->vmcb->save.gdtr = hsave->save.gdtr;
+ svm->vmcb->save.idtr = hsave->save.idtr;
+ svm->vmcb->save.rflags = hsave->save.rflags;
+ svm_set_efer(&svm->vcpu, hsave->save.efer);
+ svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE);
+ svm_set_cr4(&svm->vcpu, hsave->save.cr4);
+ if (npt_enabled) {
+ svm->vmcb->save.cr3 = hsave->save.cr3;
+ svm->vcpu.arch.cr3 = hsave->save.cr3;
+ } else {
+ kvm_set_cr3(&svm->vcpu, hsave->save.cr3);
+ }
+ kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, hsave->save.rax);
+ kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, hsave->save.rsp);
+ kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, hsave->save.rip);
+ svm->vmcb->save.dr7 = 0;
+ svm->vmcb->save.cpl = 0;
+ svm->vmcb->control.exit_int_info = 0;
+
+ svm->vcpu.arch.hflags &= ~HF_GIF_MASK;
+ /* Exit nested SVM mode */
+ svm->nested_vmcb = 0;
+
+ return 0;
+}
+
+static int nested_svm_vmexit(struct vcpu_svm *svm)
+{
+ nsvm_printk("VMexit\n");
+ if (nested_svm_do(svm, svm->nested_vmcb, 0,
+ NULL, nested_svm_vmexit_real))
+ return 1;
+
+ kvm_mmu_reset_context(&svm->vcpu);
+ kvm_mmu_load(&svm->vcpu);
+
+ return 0;
+}
+
+static int nested_svm_vmrun_msrpm(struct vcpu_svm *svm, void *arg1,
+ void *arg2, void *opaque)
+{
+ int i;
+ u32 *nested_msrpm = (u32*)arg1;
+ for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++)
+ svm->nested_msrpm[i] = svm->msrpm[i] | nested_msrpm[i];
+ svm->vmcb->control.msrpm_base_pa = __pa(svm->nested_msrpm);
+
+ return 0;
+}
+
+static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1,
+ void *arg2, void *opaque)
+{
+ struct vmcb *nested_vmcb = (struct vmcb *)arg1;
+ struct vmcb *hsave = svm->hsave;
+
+ /* nested_vmcb is our indicator if nested SVM is activated */
+ svm->nested_vmcb = svm->vmcb->save.rax;
+
+ /* Clear internal status */
+ svm->vcpu.arch.exception.pending = false;
+
+ /* Save the old vmcb, so we don't need to pick what we save, but
+ can restore everything when a VMEXIT occurs */
+ memcpy(hsave, svm->vmcb, sizeof(struct vmcb));
+ /* We need to remember the original CR3 in the SPT case */
+ if (!npt_enabled)
+ hsave->save.cr3 = svm->vcpu.arch.cr3;
+ hsave->save.cr4 = svm->vcpu.arch.cr4;
+ hsave->save.rip = svm->next_rip;
+
+ if (svm->vmcb->save.rflags & X86_EFLAGS_IF)
+ svm->vcpu.arch.hflags |= HF_HIF_MASK;
+ else
+ svm->vcpu.arch.hflags &= ~HF_HIF_MASK;
+
+ /* Load the nested guest state */
+ svm->vmcb->save.es = nested_vmcb->save.es;
+ svm->vmcb->save.cs = nested_vmcb->save.cs;
+ svm->vmcb->save.ss = nested_vmcb->save.ss;
+ svm->vmcb->save.ds = nested_vmcb->save.ds;
+ svm->vmcb->save.gdtr = nested_vmcb->save.gdtr;
+ svm->vmcb->save.idtr = nested_vmcb->save.idtr;
+ svm->vmcb->save.rflags = nested_vmcb->save.rflags;
+ svm_set_efer(&svm->vcpu, nested_vmcb->save.efer);
+ svm_set_cr0(&svm->vcpu, nested_vmcb->save.cr0);
+ svm_set_cr4(&svm->vcpu, nested_vmcb->save.cr4);
+ if (npt_enabled) {
+ svm->vmcb->save.cr3 = nested_vmcb->save.cr3;
+ svm->vcpu.arch.cr3 = nested_vmcb->save.cr3;
+ } else {
+ kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3);
+ kvm_mmu_reset_context(&svm->vcpu);
+ }
+ svm->vmcb->save.cr2 = nested_vmcb->save.cr2;
+ kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax);
+ kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp);
+ kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip);
+ /* In case we don't even reach vcpu_run, the fields are not updated */
+ svm->vmcb->save.rax = nested_vmcb->save.rax;
+ svm->vmcb->save.rsp = nested_vmcb->save.rsp;
+ svm->vmcb->save.rip = nested_vmcb->save.rip;
+ svm->vmcb->save.dr7 = nested_vmcb->save.dr7;
+ svm->vmcb->save.dr6 = nested_vmcb->save.dr6;
+ svm->vmcb->save.cpl = nested_vmcb->save.cpl;
+
+ /* We don't want a nested guest to be more powerful than the guest,
+ so all intercepts are ORed */
+ svm->vmcb->control.intercept_cr_read |=
+ nested_vmcb->control.intercept_cr_read;
+ svm->vmcb->control.intercept_cr_write |=
+ nested_vmcb->control.intercept_cr_write;
+ svm->vmcb->control.intercept_dr_read |=
+ nested_vmcb->control.intercept_dr_read;
+ svm->vmcb->control.intercept_dr_write |=
+ nested_vmcb->control.intercept_dr_write;
+ svm->vmcb->control.intercept_exceptions |=
+ nested_vmcb->control.intercept_exceptions;
+
+ svm->vmcb->control.intercept |= nested_vmcb->control.intercept;
+
+ svm->nested_vmcb_msrpm = nested_vmcb->control.msrpm_base_pa;
+
+ force_new_asid(&svm->vcpu);
+ svm->vmcb->control.exit_int_info = nested_vmcb->control.exit_int_info;
+ svm->vmcb->control.exit_int_info_err = nested_vmcb->control.exit_int_info_err;
+ svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK;
+ if (nested_vmcb->control.int_ctl & V_IRQ_MASK) {
+ nsvm_printk("nSVM Injecting Interrupt: 0x%x\n",
+ nested_vmcb->control.int_ctl);
+ }
+ if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK)
+ svm->vcpu.arch.hflags |= HF_VINTR_MASK;
+ else
+ svm->vcpu.arch.hflags &= ~HF_VINTR_MASK;
+
+ nsvm_printk("nSVM exit_int_info: 0x%x | int_state: 0x%x\n",
+ nested_vmcb->control.exit_int_info,
+ nested_vmcb->control.int_state);
+
+ svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
+ svm->vmcb->control.int_state = nested_vmcb->control.int_state;
+ svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
+ if (nested_vmcb->control.event_inj & SVM_EVTINJ_VALID)
+ nsvm_printk("Injecting Event: 0x%x\n",
+ nested_vmcb->control.event_inj);
+ svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
+ svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
+
+ svm->vcpu.arch.hflags |= HF_GIF_MASK;
+
+ return 0;
+}
+
+static int nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
+{
+ to_vmcb->save.fs = from_vmcb->save.fs;
+ to_vmcb->save.gs = from_vmcb->save.gs;
+ to_vmcb->save.tr = from_vmcb->save.tr;
+ to_vmcb->save.ldtr = from_vmcb->save.ldtr;
+ to_vmcb->save.kernel_gs_base = from_vmcb->save.kernel_gs_base;
+ to_vmcb->save.star = from_vmcb->save.star;
+ to_vmcb->save.lstar = from_vmcb->save.lstar;
+ to_vmcb->save.cstar = from_vmcb->save.cstar;
+ to_vmcb->save.sfmask = from_vmcb->save.sfmask;
+ to_vmcb->save.sysenter_cs = from_vmcb->save.sysenter_cs;
+ to_vmcb->save.sysenter_esp = from_vmcb->save.sysenter_esp;
+ to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip;
+
+ return 1;
+}
+
+static int nested_svm_vmload(struct vcpu_svm *svm, void *nested_vmcb,
+ void *arg2, void *opaque)
+{
+ return nested_svm_vmloadsave((struct vmcb *)nested_vmcb, svm->vmcb);
+}
+
+static int nested_svm_vmsave(struct vcpu_svm *svm, void *nested_vmcb,
+ void *arg2, void *opaque)
+{
+ return nested_svm_vmloadsave(svm->vmcb, (struct vmcb *)nested_vmcb);
+}
+
+static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+ if (nested_svm_check_permissions(svm))
+ return 1;
+
+ svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+ skip_emulated_instruction(&svm->vcpu);
+
+ nested_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmload);
+
+ return 1;
+}
+
+static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+ if (nested_svm_check_permissions(svm))
+ return 1;
+
+ svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+ skip_emulated_instruction(&svm->vcpu);
+
+ nested_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmsave);
+
+ return 1;
+}
+
+static int vmrun_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+ nsvm_printk("VMrun\n");
+ if (nested_svm_check_permissions(svm))
+ return 1;
+
+ svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+ skip_emulated_instruction(&svm->vcpu);
+
+ if (nested_svm_do(svm, svm->vmcb->save.rax, 0,
+ NULL, nested_svm_vmrun))
+ return 1;
+
+ if (nested_svm_do(svm, svm->nested_vmcb_msrpm, 0,
+ NULL, nested_svm_vmrun_msrpm))
+ return 1;
+
+ return 1;
+}
+
+static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+ if (nested_svm_check_permissions(svm))
+ return 1;
+
+ svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+ skip_emulated_instruction(&svm->vcpu);
+
+ svm->vcpu.arch.hflags |= HF_GIF_MASK;
+
+ return 1;
+}
+
+static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+ if (nested_svm_check_permissions(svm))
+ return 1;
+
+ svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+ skip_emulated_instruction(&svm->vcpu);
+
+ svm->vcpu.arch.hflags &= ~HF_GIF_MASK;
+
+ /* After a CLGI no interrupts should come */
+ svm_clear_vintr(svm);
+ svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
+
+ return 1;
+}
+