#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/moduleparam.h>
+#include <linux/ftrace_event.h>
#include "kvm_cache_regs.h"
#include "x86.h"
#include <asm/virtext.h>
#include <asm/mce.h>
+#include "trace.h"
+
#define __ex(x) __kvm_handle_fault_on_reboot(x)
MODULE_AUTHOR("Qumranet");
cpu_has_vmx_virtualize_apic_accesses();
}
+static inline bool cpu_has_vmx_ept_execute_only(void)
+{
+ return !!(vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT);
+}
+
+static inline bool cpu_has_vmx_eptp_uncacheable(void)
+{
+ return !!(vmx_capability.ept & VMX_EPTP_UC_BIT);
+}
+
+static inline bool cpu_has_vmx_eptp_writeback(void)
+{
+ return !!(vmx_capability.ept & VMX_EPTP_WB_BIT);
+}
+
+static inline bool cpu_has_vmx_ept_2m_page(void)
+{
+ return !!(vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT);
+}
+
static inline int cpu_has_vmx_invept_individual_addr(void)
{
return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT);
if (!cpu_has_vmx_tpr_shadow())
kvm_x86_ops->update_cr8_intercept = NULL;
+ if (enable_ept && !cpu_has_vmx_ept_2m_page())
+ kvm_disable_largepages();
+
return alloc_kvm_area();
}
uint32_t intr;
int irq = vcpu->arch.interrupt.nr;
- KVMTRACE_1D(INJ_VIRQ, vcpu, (u32)irq, handler);
+ trace_kvm_inj_virq(irq);
++vcpu->stat.irq_injections;
if (vmx->rmode.vm86_active) {
if (enable_ept)
BUG();
cr2 = vmcs_readl(EXIT_QUALIFICATION);
- KVMTRACE_3D(PAGE_FAULT, vcpu, error_code, (u32)cr2,
- (u32)((u64)cr2 >> 32), handler);
+ trace_kvm_page_fault(cr2, error_code);
+
if (kvm_event_needs_reinjection(vcpu))
kvm_mmu_unprotect_page_virt(vcpu, cr2);
return kvm_mmu_page_fault(vcpu, cr2, error_code);
struct kvm_run *kvm_run)
{
++vcpu->stat.irq_exits;
- KVMTRACE_1D(INTR, vcpu, vmcs_read32(VM_EXIT_INTR_INFO), handler);
return 1;
}
static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
- unsigned long exit_qualification;
+ unsigned long exit_qualification, val;
int cr;
int reg;
reg = (exit_qualification >> 8) & 15;
switch ((exit_qualification >> 4) & 3) {
case 0: /* mov to cr */
- KVMTRACE_3D(CR_WRITE, vcpu, (u32)cr,
- (u32)kvm_register_read(vcpu, reg),
- (u32)((u64)kvm_register_read(vcpu, reg) >> 32),
- handler);
+ val = kvm_register_read(vcpu, reg);
+ trace_kvm_cr_write(cr, val);
switch (cr) {
case 0:
- kvm_set_cr0(vcpu, kvm_register_read(vcpu, reg));
+ kvm_set_cr0(vcpu, val);
skip_emulated_instruction(vcpu);
return 1;
case 3:
- kvm_set_cr3(vcpu, kvm_register_read(vcpu, reg));
+ kvm_set_cr3(vcpu, val);
skip_emulated_instruction(vcpu);
return 1;
case 4:
- kvm_set_cr4(vcpu, kvm_register_read(vcpu, reg));
+ kvm_set_cr4(vcpu, val);
skip_emulated_instruction(vcpu);
return 1;
case 8: {
vcpu->arch.cr0 &= ~X86_CR0_TS;
vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
vmx_fpu_activate(vcpu);
- KVMTRACE_0D(CLTS, vcpu, handler);
skip_emulated_instruction(vcpu);
return 1;
case 1: /*mov from cr*/
switch (cr) {
case 3:
kvm_register_write(vcpu, reg, vcpu->arch.cr3);
- KVMTRACE_3D(CR_READ, vcpu, (u32)cr,
- (u32)kvm_register_read(vcpu, reg),
- (u32)((u64)kvm_register_read(vcpu, reg) >> 32),
- handler);
+ trace_kvm_cr_read(cr, vcpu->arch.cr3);
skip_emulated_instruction(vcpu);
return 1;
case 8:
- kvm_register_write(vcpu, reg, kvm_get_cr8(vcpu));
- KVMTRACE_2D(CR_READ, vcpu, (u32)cr,
- (u32)kvm_register_read(vcpu, reg), handler);
+ val = kvm_get_cr8(vcpu);
+ kvm_register_write(vcpu, reg, val);
+ trace_kvm_cr_read(cr, val);
skip_emulated_instruction(vcpu);
return 1;
}
val = 0;
}
kvm_register_write(vcpu, reg, val);
- KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler);
} else {
val = vcpu->arch.regs[reg];
switch (dr) {
}
break;
}
- KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)val, handler);
}
skip_emulated_instruction(vcpu);
return 1;
return 1;
}
- KVMTRACE_3D(MSR_READ, vcpu, ecx, (u32)data, (u32)(data >> 32),
- handler);
+ trace_kvm_msr_read(ecx, data);
/* FIXME: handling of bits 32:63 of rax, rdx */
vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u;
u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u)
| ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32);
- KVMTRACE_3D(MSR_WRITE, vcpu, ecx, (u32)data, (u32)(data >> 32),
- handler);
+ trace_kvm_msr_write(ecx, data);
if (vmx_set_msr(vcpu, ecx, data) != 0) {
kvm_inject_gp(vcpu, 0);
cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
- KVMTRACE_0D(PEND_INTR, vcpu, handler);
++vcpu->stat.irq_window_exits;
/*
}
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+ trace_kvm_page_fault(gpa, exit_qualification);
return kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0);
}
+static u64 ept_rsvd_mask(u64 spte, int level)
+{
+ int i;
+ u64 mask = 0;
+
+ for (i = 51; i > boot_cpu_data.x86_phys_bits; i--)
+ mask |= (1ULL << i);
+
+ if (level > 2)
+ /* bits 7:3 reserved */
+ mask |= 0xf8;
+ else if (level == 2) {
+ if (spte & (1ULL << 7))
+ /* 2MB ref, bits 20:12 reserved */
+ mask |= 0x1ff000;
+ else
+ /* bits 6:3 reserved */
+ mask |= 0x78;
+ }
+
+ return mask;
+}
+
+static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte,
+ int level)
+{
+ printk(KERN_ERR "%s: spte 0x%llx level %d\n", __func__, spte, level);
+
+ /* 010b (write-only) */
+ WARN_ON((spte & 0x7) == 0x2);
+
+ /* 110b (write/execute) */
+ WARN_ON((spte & 0x7) == 0x6);
+
+ /* 100b (execute-only) and value not supported by logical processor */
+ if (!cpu_has_vmx_ept_execute_only())
+ WARN_ON((spte & 0x7) == 0x4);
+
+ /* not 000b */
+ if ((spte & 0x7)) {
+ u64 rsvd_bits = spte & ept_rsvd_mask(spte, level);
+
+ if (rsvd_bits != 0) {
+ printk(KERN_ERR "%s: rsvd_bits = 0x%llx\n",
+ __func__, rsvd_bits);
+ WARN_ON(1);
+ }
+
+ if (level == 1 || (level == 2 && (spte & (1ULL << 7)))) {
+ u64 ept_mem_type = (spte & 0x38) >> 3;
+
+ if (ept_mem_type == 2 || ept_mem_type == 3 ||
+ ept_mem_type == 7) {
+ printk(KERN_ERR "%s: ept_mem_type=0x%llx\n",
+ __func__, ept_mem_type);
+ WARN_ON(1);
+ }
+ }
+ }
+}
+
+static int handle_ept_misconfig(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ u64 sptes[4];
+ int nr_sptes, i;
+ gpa_t gpa;
+
+ gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+
+ printk(KERN_ERR "EPT: Misconfiguration.\n");
+ printk(KERN_ERR "EPT: GPA: 0x%llx\n", gpa);
+
+ nr_sptes = kvm_mmu_get_spte_hierarchy(vcpu, gpa, sptes);
+
+ for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i)
+ ept_misconfig_inspect_spte(vcpu, sptes[i-1], i);
+
+ kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
+ kvm_run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG;
+
+ return 0;
+}
+
static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
u32 cpu_based_vm_exec_control;
[EXIT_REASON_APIC_ACCESS] = handle_apic_access,
[EXIT_REASON_WBINVD] = handle_wbinvd,
[EXIT_REASON_TASK_SWITCH] = handle_task_switch,
- [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation,
[EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check,
+ [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation,
+ [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig,
};
static const int kvm_vmx_max_exit_handlers =
u32 exit_reason = vmx->exit_reason;
u32 vectoring_info = vmx->idt_vectoring_info;
- KVMTRACE_3D(VMEXIT, vcpu, exit_reason, (u32)kvm_rip_read(vcpu),
- (u32)((u64)kvm_rip_read(vcpu) >> 32), entryexit);
+ trace_kvm_exit(exit_reason, kvm_rip_read(vcpu));
/* If we need to emulate an MMIO from handle_invalid_guest_state
* we just return 0 */
/* We need to handle NMIs before interrupts are enabled */
if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR &&
- (exit_intr_info & INTR_INFO_VALID_MASK)) {
- KVMTRACE_0D(NMI, &vmx->vcpu, handler);
+ (exit_intr_info & INTR_INFO_VALID_MASK))
asm("int $2");
- }
idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;
"mov %%"R"sp, %c[host_rsp](%0) \n\t"
__ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t"
"1: \n\t"
+ /* Reload cr2 if changed */
+ "mov %c[cr2](%0), %%"R"ax \n\t"
+ "mov %%cr2, %%"R"dx \n\t"
+ "cmp %%"R"ax, %%"R"dx \n\t"
+ "je 2f \n\t"
+ "mov %%"R"ax, %%cr2 \n\t"
+ "2: \n\t"
/* Check if vmlaunch of vmresume is needed */
"cmpl $0, %c[launched](%0) \n\t"
/* Load guest registers. Don't clobber flags. */
- "mov %c[cr2](%0), %%"R"ax \n\t"
- "mov %%"R"ax, %%cr2 \n\t"
"mov %c[rax](%0), %%"R"ax \n\t"
"mov %c[rbx](%0), %%"R"bx \n\t"
"mov %c[rdx](%0), %%"R"dx \n\t"
return ret;
}
+static const struct trace_print_flags vmx_exit_reasons_str[] = {
+ { EXIT_REASON_EXCEPTION_NMI, "exception" },
+ { EXIT_REASON_EXTERNAL_INTERRUPT, "ext_irq" },
+ { EXIT_REASON_TRIPLE_FAULT, "triple_fault" },
+ { EXIT_REASON_NMI_WINDOW, "nmi_window" },
+ { EXIT_REASON_IO_INSTRUCTION, "io_instruction" },
+ { EXIT_REASON_CR_ACCESS, "cr_access" },
+ { EXIT_REASON_DR_ACCESS, "dr_access" },
+ { EXIT_REASON_CPUID, "cpuid" },
+ { EXIT_REASON_MSR_READ, "rdmsr" },
+ { EXIT_REASON_MSR_WRITE, "wrmsr" },
+ { EXIT_REASON_PENDING_INTERRUPT, "interrupt_window" },
+ { EXIT_REASON_HLT, "halt" },
+ { EXIT_REASON_INVLPG, "invlpg" },
+ { EXIT_REASON_VMCALL, "hypercall" },
+ { EXIT_REASON_TPR_BELOW_THRESHOLD, "tpr_below_thres" },
+ { EXIT_REASON_APIC_ACCESS, "apic_access" },
+ { EXIT_REASON_WBINVD, "wbinvd" },
+ { EXIT_REASON_TASK_SWITCH, "task_switch" },
+ { EXIT_REASON_EPT_VIOLATION, "ept_violation" },
+ { -1, NULL }
+};
+
static struct kvm_x86_ops vmx_x86_ops = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
.set_tss_addr = vmx_set_tss_addr,
.get_tdp_level = get_ept_level,
.get_mt_mask = vmx_get_mt_mask,
+
+ .exit_reasons_str = vmx_exit_reasons_str,
};
static int __init vmx_init(void)