KVM: x86: fix CR8 handling

[deliverable/linux.git] / arch / x86 / kvm / svm.c

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 50387860a53ca261c8c73b35c10590a384beb0d5..3d4b88af50f9db230fbfb0ba2a5a93d9ada61bae 100644 (file)
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -185,6 +185,41 @@ static int nested_svm_vmexit(struct vcpu_svm *svm);
 static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
                                      bool has_error_code, u32 error_code);
 
+enum {
+       VMCB_INTERCEPTS, /* Intercept vectors, TSC offset,
+                           pause filter count */
+       VMCB_PERM_MAP,   /* IOPM Base and MSRPM Base */
+       VMCB_ASID,       /* ASID */
+       VMCB_INTR,       /* int_ctl, int_vector */
+       VMCB_NPT,        /* npt_en, nCR3, gPAT */
+       VMCB_CR,         /* CR0, CR3, CR4, EFER */
+       VMCB_DR,         /* DR6, DR7 */
+       VMCB_DT,         /* GDT, IDT */
+       VMCB_SEG,        /* CS, DS, SS, ES, CPL */
+       VMCB_CR2,        /* CR2 only */
+       VMCB_LBR,        /* DBGCTL, BR_FROM, BR_TO, LAST_EX_FROM, LAST_EX_TO */
+       VMCB_DIRTY_MAX,
+};
+
+/* TPR and CR2 are always written before VMRUN */
+#define VMCB_ALWAYS_DIRTY_MASK ((1U << VMCB_INTR) | (1U << VMCB_CR2))
+
+static inline void mark_all_dirty(struct vmcb *vmcb)
+{
+       vmcb->control.clean = 0;
+}
+
+static inline void mark_all_clean(struct vmcb *vmcb)
+{
+       vmcb->control.clean = ((1 << VMCB_DIRTY_MAX) - 1)
+                              & ~VMCB_ALWAYS_DIRTY_MASK;
+}
+
+static inline void mark_dirty(struct vmcb *vmcb, int bit)
+{
+       vmcb->control.clean &= ~(1 << bit);
+}
+
 static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
 {
        return container_of(vcpu, struct vcpu_svm, vcpu);
@@ -195,6 +230,8 @@ static void recalc_intercepts(struct vcpu_svm *svm)
        struct vmcb_control_area *c, *h;
        struct nested_state *g;
 
+       mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
+
        if (!is_guest_mode(&svm->vcpu))
                return;
 
@@ -384,16 +421,6 @@ static inline void invlpga(unsigned long addr, u32 asid)
        asm volatile (__ex(SVM_INVLPGA) : : "a"(addr), "c"(asid));
 }
 
-static inline void force_new_asid(struct kvm_vcpu *vcpu)
-{
-       to_svm(vcpu)->asid_generation--;
-}
-
-static inline void flush_guest_tlb(struct kvm_vcpu *vcpu)
-{
-       force_new_asid(vcpu);
-}
-
 static int get_npt_level(void)
 {
 #ifdef CONFIG_X86_64
@@ -410,6 +437,7 @@ static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
                efer &= ~EFER_LME;
 
        to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME;
+       mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR);
 }
 
 static int is_external_interrupt(u32 info)
@@ -832,6 +860,8 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
        }
 
        svm->vmcb->control.tsc_offset = offset + g_tsc_offset;
+
+       mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 }
 
 static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment)
@@ -841,6 +871,7 @@ static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment)
        svm->vmcb->control.tsc_offset += adjustment;
        if (is_guest_mode(vcpu))
                svm->nested.hsave->control.tsc_offset += adjustment;
+       mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 }
 
 static void init_vmcb(struct vcpu_svm *svm)
@@ -904,6 +935,7 @@ static void init_vmcb(struct vcpu_svm *svm)
        set_intercept(svm, INTERCEPT_WBINVD);
        set_intercept(svm, INTERCEPT_MONITOR);
        set_intercept(svm, INTERCEPT_MWAIT);
+       set_intercept(svm, INTERCEPT_XSETBV);
 
        control->iopm_base_pa = iopm_base;
        control->msrpm_base_pa = __pa(svm->msrpm);
@@ -963,7 +995,7 @@ static void init_vmcb(struct vcpu_svm *svm)
                save->cr3 = 0;
                save->cr4 = 0;
        }
-       force_new_asid(&svm->vcpu);
+       svm->asid_generation = 0;
 
        svm->nested.vmcb = 0;
        svm->vcpu.arch.hflags = 0;
@@ -973,6 +1005,8 @@ static void init_vmcb(struct vcpu_svm *svm)
                set_intercept(svm, INTERCEPT_PAUSE);
        }
 
+       mark_all_dirty(svm->vmcb);
+
        enable_gif(svm);
 }
 
@@ -1089,6 +1123,7 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
        if (unlikely(cpu != vcpu->cpu)) {
                svm->asid_generation = 0;
+               mark_all_dirty(svm->vmcb);
        }
 
 #ifdef CONFIG_X86_64
@@ -1264,6 +1299,7 @@ static void svm_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 
        svm->vmcb->save.idtr.limit = dt->size;
        svm->vmcb->save.idtr.base = dt->address ;
+       mark_dirty(svm->vmcb, VMCB_DT);
 }
 
 static void svm_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
@@ -1280,6 +1316,7 @@ static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 
        svm->vmcb->save.gdtr.limit = dt->size;
        svm->vmcb->save.gdtr.base = dt->address ;
+       mark_dirty(svm->vmcb, VMCB_DT);
 }
 
 static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
@@ -1301,6 +1338,7 @@ static void update_cr0_intercept(struct vcpu_svm *svm)
                *hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK)
                        | (gcr0 & SVM_CR0_SELECTIVE_MASK);
 
+       mark_dirty(svm->vmcb, VMCB_CR);
 
        if (gcr0 == *hcr0 && svm->vcpu.fpu_active) {
                clr_cr_intercept(svm, INTERCEPT_CR0_READ);
@@ -1367,6 +1405,7 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
         */
        cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
        svm->vmcb->save.cr0 = cr0;
+       mark_dirty(svm->vmcb, VMCB_CR);
        update_cr0_intercept(svm);
 }
 
@@ -1376,13 +1415,14 @@ static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
        unsigned long old_cr4 = to_svm(vcpu)->vmcb->save.cr4;
 
        if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE))
-               force_new_asid(vcpu);
+               svm_flush_tlb(vcpu);
 
        vcpu->arch.cr4 = cr4;
        if (!npt_enabled)
                cr4 |= X86_CR4_PAE;
        cr4 |= host_cr4_mce;
        to_svm(vcpu)->vmcb->save.cr4 = cr4;
+       mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR);
 }
 
 static void svm_set_segment(struct kvm_vcpu *vcpu,
@@ -1411,6 +1451,7 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
                        = (svm->vmcb->save.cs.attrib
                           >> SVM_SELECTOR_DPL_SHIFT) & 3;
 
+       mark_dirty(svm->vmcb, VMCB_SEG);
 }
 
 static void update_db_intercept(struct kvm_vcpu *vcpu)
@@ -1442,6 +1483,8 @@ static void svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
        else
                svm->vmcb->save.dr7 = vcpu->arch.dr7;
 
+       mark_dirty(svm->vmcb, VMCB_DR);
+
        update_db_intercept(vcpu);
 }
 
@@ -1455,6 +1498,8 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
 
        svm->asid_generation = sd->asid_generation;
        svm->vmcb->control.asid = sd->next_asid++;
+
+       mark_dirty(svm->vmcb, VMCB_ASID);
 }
 
 static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value)
@@ -1462,6 +1507,7 @@ static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value)
        struct vcpu_svm *svm = to_svm(vcpu);
 
        svm->vmcb->save.dr7 = value;
+       mark_dirty(svm->vmcb, VMCB_DR);
 }
 
 static int pf_interception(struct vcpu_svm *svm)
@@ -1711,7 +1757,8 @@ static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu,
        struct vcpu_svm *svm = to_svm(vcpu);
 
        svm->vmcb->control.nested_cr3 = root;
-       force_new_asid(vcpu);
+       mark_dirty(svm->vmcb, VMCB_NPT);
+       svm_flush_tlb(vcpu);
 }
 
 static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
@@ -2140,6 +2187,8 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
        svm->vmcb->save.cpl = 0;
        svm->vmcb->control.exit_int_info = 0;
 
+       mark_all_dirty(svm->vmcb);
+
        nested_svm_unmap(page);
 
        nested_svm_uninit_mmu_context(&svm->vcpu);
@@ -2313,7 +2362,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
        svm->nested.intercept_exceptions = nested_vmcb->control.intercept_exceptions;
        svm->nested.intercept            = nested_vmcb->control.intercept;
 
-       force_new_asid(&svm->vcpu);
+       svm_flush_tlb(&svm->vcpu);
        svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK;
        if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK)
                svm->vcpu.arch.hflags |= HF_VINTR_MASK;
@@ -2351,6 +2400,8 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
 
        enable_gif(svm);
 
+       mark_all_dirty(svm->vmcb);
+
        return true;
 }
 
@@ -2468,6 +2519,8 @@ static int clgi_interception(struct vcpu_svm *svm)
        svm_clear_vintr(svm);
        svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
 
+       mark_dirty(svm->vmcb, VMCB_INTR);
+
        return 1;
 }
 
@@ -2494,6 +2547,19 @@ static int skinit_interception(struct vcpu_svm *svm)
        return 1;
 }
 
+static int xsetbv_interception(struct vcpu_svm *svm)
+{
+       u64 new_bv = kvm_read_edx_eax(&svm->vcpu);
+       u32 index = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
+
+       if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) {
+               svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+               skip_emulated_instruction(&svm->vcpu);
+       }
+
+       return 1;
+}
+
 static int invalid_op_interception(struct vcpu_svm *svm)
 {
        kvm_queue_exception(&svm->vcpu, UD_VECTOR);
@@ -2610,16 +2676,17 @@ static int cr0_write_interception(struct vcpu_svm *svm)
 static int cr8_write_interception(struct vcpu_svm *svm)
 {
        struct kvm_run *kvm_run = svm->vcpu.run;
+       int r;
 
        u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
        /* instruction emulation calls kvm_set_cr8() */
-       emulate_instruction(&svm->vcpu, 0, 0, 0);
+       r = emulate_instruction(&svm->vcpu, 0, 0, 0);
        if (irqchip_in_kernel(svm->vcpu.kvm)) {
                clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
-               return 1;
+               return r == EMULATE_DONE;
        }
        if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
-               return 1;
+               return r == EMULATE_DONE;
        kvm_run->exit_reason = KVM_EXIT_SET_TPR;
        return 0;
 }
@@ -2786,6 +2853,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
                        return 1;
 
                svm->vmcb->save.dbgctl = data;
+               mark_dirty(svm->vmcb, VMCB_LBR);
                if (data & (1ULL<<0))
                        svm_enable_lbrv(svm);
                else
@@ -2838,6 +2906,7 @@ static int interrupt_window_interception(struct vcpu_svm *svm)
        kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
        svm_clear_vintr(svm);
        svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
+       mark_dirty(svm->vmcb, VMCB_INTR);
        /*
         * If the user space waits to inject interrupts, exit as soon as
         * possible
@@ -2917,6 +2986,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
        [SVM_EXIT_WBINVD]                       = emulate_on_interception,
        [SVM_EXIT_MONITOR]                      = invalid_op_interception,
        [SVM_EXIT_MWAIT]                        = invalid_op_interception,
+       [SVM_EXIT_XSETBV]                       = xsetbv_interception,
        [SVM_EXIT_NPF]                          = pf_interception,
 };
 
@@ -3104,7 +3174,6 @@ static void pre_svm_run(struct vcpu_svm *svm)
 
        struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 
-       svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
        /* FIXME: handle wraparound of asid_generation */
        if (svm->asid_generation != sd->asid_generation)
                new_asid(svm, sd);
@@ -3129,6 +3198,7 @@ static inline void svm_inject_irq(struct vcpu_svm *svm, int irq)
        control->int_ctl &= ~V_INTR_PRIO_MASK;
        control->int_ctl |= V_IRQ_MASK |
                ((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT);
+       mark_dirty(svm->vmcb, VMCB_INTR);
 }
 
 static void svm_set_irq(struct kvm_vcpu *vcpu)
@@ -3248,7 +3318,12 @@ static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr)
 
 static void svm_flush_tlb(struct kvm_vcpu *vcpu)
 {
-       force_new_asid(vcpu);
+       struct vcpu_svm *svm = to_svm(vcpu);
+
+       if (static_cpu_has(X86_FEATURE_FLUSHBYASID))
+               svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID;
+       else
+               svm->asid_generation--;
 }
 
 static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu)
@@ -3474,6 +3549,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 
        svm->next_rip = 0;
 
+       svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
+
        /* if exit due to PF check for async PF */
        if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR)
                svm->apf_reason = kvm_read_and_reset_pf_reason();
@@ -3490,6 +3567,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
        if (unlikely(svm->vmcb->control.exit_code ==
                     SVM_EXIT_EXCP_BASE + MC_VECTOR))
                svm_handle_mce(svm);
+
+       mark_all_clean(svm->vmcb);
 }
 
 #undef R
@@ -3499,7 +3578,8 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root)
        struct vcpu_svm *svm = to_svm(vcpu);
 
        svm->vmcb->save.cr3 = root;
-       force_new_asid(vcpu);
+       mark_dirty(svm->vmcb, VMCB_CR);
+       svm_flush_tlb(vcpu);
 }
 
 static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root)
@@ -3507,11 +3587,13 @@ static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root)
        struct vcpu_svm *svm = to_svm(vcpu);
 
        svm->vmcb->control.nested_cr3 = root;
+       mark_dirty(svm->vmcb, VMCB_NPT);
 
        /* Also sync guest cr3 here in case we live migrate */
        svm->vmcb->save.cr3 = vcpu->arch.cr3;
+       mark_dirty(svm->vmcb, VMCB_CR);
 
-       force_new_asid(vcpu);
+       svm_flush_tlb(vcpu);
 }
 
 static int is_disabled(void)
@@ -3558,10 +3640,6 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 {
        switch (func) {
-       case 0x00000001:
-               /* Mask out xsave bit as long as it is not supported by SVM */
-               entry->ecx &= ~(bit(X86_FEATURE_XSAVE));
-               break;
        case 0x80000001:
                if (nested)
                        entry->ecx |= (1 << 2); /* Set SVM bit */
@@ -3635,6 +3713,7 @@ static const struct trace_print_flags svm_exit_reasons_str[] = {
        { SVM_EXIT_WBINVD,                      "wbinvd" },
        { SVM_EXIT_MONITOR,                     "monitor" },
        { SVM_EXIT_MWAIT,                       "mwait" },
+       { SVM_EXIT_XSETBV,                      "xsetbv" },
        { SVM_EXIT_NPF,                         "npf" },
        { -1, NULL }
 };