Merge tag 'trace-v4.4-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt...

[firefly-linux-kernel-4.4.55.git] / arch / x86 / kvm / vmx.c

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 5eb56ed77c1fdea01652acf0da476761cf7a9aaa..af823a388c1994ba244e3ef0098f1a578408101e 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -107,6 +107,8 @@ static u64 __read_mostly host_xss;
 static bool __read_mostly enable_pml = 1;
 module_param_named(pml, enable_pml, bool, S_IRUGO);
 
+#define KVM_VMX_TSC_MULTIPLIER_MAX     0xffffffffffffffffULL
+
 #define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
 #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE)
 #define KVM_VM_CR0_ALWAYS_ON                                           \
@@ -1172,6 +1174,12 @@ static inline bool cpu_has_vmx_pml(void)
        return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_PML;
 }
 
+static inline bool cpu_has_vmx_tsc_scaling(void)
+{
+       return vmcs_config.cpu_based_2nd_exec_ctrl &
+               SECONDARY_EXEC_TSC_SCALING;
+}
+
 static inline bool report_flexpriority(void)
 {
        return flexpriority_enabled;
@@ -1631,7 +1639,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
        u32 eb;
 
        eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) |
-            (1u << NM_VECTOR) | (1u << DB_VECTOR);
+            (1u << NM_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR);
        if ((vcpu->guest_debug &
             (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) ==
            (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP))
@@ -2053,6 +2061,12 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
                rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
                vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
+
+               /* Setup TSC multiplier */
+               if (cpu_has_vmx_tsc_scaling())
+                       vmcs_write64(TSC_MULTIPLIER,
+                                    vcpu->arch.tsc_scaling_ratio);
+
                vmx->loaded_vmcs->cpu = cpu;
        }
 
@@ -2357,15 +2371,16 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 
 /*
  * reads and returns guest's timestamp counter "register"
- * guest_tsc = host_tsc + tsc_offset    -- 21.3
+ * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset
+ * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3
  */
-static u64 guest_read_tsc(void)
+static u64 guest_read_tsc(struct kvm_vcpu *vcpu)
 {
        u64 host_tsc, tsc_offset;
 
        host_tsc = rdtsc();
        tsc_offset = vmcs_read64(TSC_OFFSET);
-       return host_tsc + tsc_offset;
+       return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset;
 }
 
 /*
@@ -2382,22 +2397,6 @@ static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
        return host_tsc + tsc_offset;
 }
 
-/*
- * Engage any workarounds for mis-matched TSC rates.  Currently limited to
- * software catchup for faster rates on slower CPUs.
- */
-static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
-{
-       if (!scale)
-               return;
-
-       if (user_tsc_khz > tsc_khz) {
-               vcpu->arch.tsc_catchup = 1;
-               vcpu->arch.tsc_always_catchup = 1;
-       } else
-               WARN(1, "user requested TSC rate below hardware speed\n");
-}
-
 static u64 vmx_read_tsc_offset(struct kvm_vcpu *vcpu)
 {
        return vmcs_read64(TSC_OFFSET);
@@ -2429,7 +2428,7 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
        }
 }
 
-static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host)
+static void vmx_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment)
 {
        u64 offset = vmcs_read64(TSC_OFFSET);
 
@@ -2442,11 +2441,6 @@ static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho
                                           offset + adjustment);
 }
 
-static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
-{
-       return target_tsc - rdtsc();
-}
-
 static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu)
 {
        struct kvm_cpuid_entry2 *best = kvm_find_cpuid_entry(vcpu, 1, 0);
@@ -2778,7 +2772,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
        case MSR_EFER:
                return kvm_get_msr_common(vcpu, msr_info);
        case MSR_IA32_TSC:
-               msr_info->data = guest_read_tsc();
+               msr_info->data = guest_read_tsc(vcpu);
                break;
        case MSR_IA32_SYSENTER_CS:
                msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
@@ -3154,7 +3148,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
                        SECONDARY_EXEC_SHADOW_VMCS |
                        SECONDARY_EXEC_XSAVES |
                        SECONDARY_EXEC_ENABLE_PML |
-                       SECONDARY_EXEC_PCOMMIT;
+                       SECONDARY_EXEC_PCOMMIT |
+                       SECONDARY_EXEC_TSC_SCALING;
                if (adjust_vmx_controls(min2, opt2,
                                        MSR_IA32_VMX_PROCBASED_CTLS2,
                                        &_cpu_based_2nd_exec_control) < 0)
@@ -5266,6 +5261,9 @@ static int handle_exception(struct kvm_vcpu *vcpu)
                return handle_rmode_exception(vcpu, ex_no, error_code);
 
        switch (ex_no) {
+       case AC_VECTOR:
+               kvm_queue_exception_e(vcpu, AC_VECTOR, error_code);
+               return 1;
        case DB_VECTOR:
                dr6 = vmcs_readl(EXIT_QUALIFICATION);
                if (!(vcpu->guest_debug &
@@ -5908,7 +5906,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
                return 1;
        }
 
-       ret = handle_mmio_page_fault_common(vcpu, gpa, true);
+       ret = handle_mmio_page_fault(vcpu, gpa, true);
        if (likely(ret == RET_MMIO_PF_EMULATE))
                return x86_emulate_instruction(vcpu, gpa, 0, NULL, 0) ==
                                              EMULATE_DONE;
@@ -6199,6 +6197,12 @@ static __init int hardware_setup(void)
        if (!cpu_has_vmx_apicv())
                enable_apicv = 0;
 
+       if (cpu_has_vmx_tsc_scaling()) {
+               kvm_has_tsc_control = true;
+               kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX;
+               kvm_tsc_scaling_ratio_frac_bits = 48;
+       }
+
        if (enable_apicv)
                kvm_x86_ops->update_cr8_intercept = NULL;
        else {
@@ -7390,11 +7394,6 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 
        switch (type) {
        case VMX_VPID_EXTENT_ALL_CONTEXT:
-               if (get_vmcs12(vcpu)->virtual_processor_id == 0) {
-                       nested_vmx_failValid(vcpu,
-                               VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
-                       return 1;
-               }
                __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
                nested_vmx_succeed(vcpu);
                break;
@@ -8008,6 +8007,9 @@ static void dump_vmcs(void)
               vmcs_read32(IDT_VECTORING_INFO_FIELD),
               vmcs_read32(IDT_VECTORING_ERROR_CODE));
        pr_err("TSC Offset = 0x%016lx\n", vmcs_readl(TSC_OFFSET));
+       if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING)
+               pr_err("TSC Multiplier = 0x%016lx\n",
+                      vmcs_readl(TSC_MULTIPLIER));
        if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW)
                pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD));
        if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR)
@@ -10752,7 +10754,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
        .vcpu_load = vmx_vcpu_load,
        .vcpu_put = vmx_vcpu_put,
 
-       .update_db_bp_intercept = update_exception_bitmap,
+       .update_bp_intercept = update_exception_bitmap,
        .get_msr = vmx_get_msr,
        .set_msr = vmx_set_msr,
        .get_segment_base = vmx_get_segment_base,
@@ -10826,11 +10828,9 @@ static struct kvm_x86_ops vmx_x86_ops = {
 
        .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
 
-       .set_tsc_khz = vmx_set_tsc_khz,
        .read_tsc_offset = vmx_read_tsc_offset,
        .write_tsc_offset = vmx_write_tsc_offset,
-       .adjust_tsc_offset = vmx_adjust_tsc_offset,
-       .compute_tsc_offset = vmx_compute_tsc_offset,
+       .adjust_tsc_offset_guest = vmx_adjust_tsc_offset_guest,
        .read_l1_tsc = vmx_read_l1_tsc,
 
        .set_tdp_cr3 = vmx_set_cr3,