Re: [PATCH] kvm-unit-tests : The first version of VMX nested test case

[Paolo Bonzini <pbonzini@redhat.com>]

Il 16/07/2013 11:27, Arthur Chunqi Li ha scritto:
> This is the first version for VMX nested environment test case. It
> contains the basic VMX instructions test cases, including VMXON/
> VMXOFF/VMXPTRLD/VMXPTRST/VMCLEAR/VMLAUNCH/VMRESUME/VMCALL. This patch
> also tests the basic execution routine in VMX nested environment and
> let the VM print "Hello World" to inform its successfully run.
> 
> New files added:
> x86/vmx.h : contains all VMX related macro declerations
> x86/vmx.c : main file for VMX nested test case
> 
> Signed-off-by: Arthur Chunqi Li <yzt356@gmail.com>
> ---
>  config-x86-common.mak |    2 +
>  config-x86_64.mak     |    1 +
>  lib/x86/msr.h         |    5 +
>  x86/cstart64.S        |    4 +
>  x86/unittests.cfg     |    6 +
>  x86/vmx.c             |  568 +++++++++++++++++++++++++++++++++++++++++++++++++
>  x86/vmx.h             |  406 +++++++++++++++++++++++++++++++++++
>  7 files changed, 992 insertions(+)
>  create mode 100644 x86/vmx.c
>  create mode 100644 x86/vmx.h
> 
> diff --git a/config-x86-common.mak b/config-x86-common.mak
> index 455032b..34a41e1 100644
> --- a/config-x86-common.mak
> +++ b/config-x86-common.mak
> @@ -101,6 +101,8 @@ $(TEST_DIR)/asyncpf.elf: $(cstart.o) $(TEST_DIR)/asyncpf.o
>  
>  $(TEST_DIR)/pcid.elf: $(cstart.o) $(TEST_DIR)/pcid.o
>  
> +$(TEST_DIR)/vmx.elf: $(cstart.o) $(TEST_DIR)/vmx.o
> +
>  arch_clean:
>  	$(RM) $(TEST_DIR)/*.o $(TEST_DIR)/*.flat $(TEST_DIR)/*.elf \
>  	$(TEST_DIR)/.*.d $(TEST_DIR)/lib/.*.d $(TEST_DIR)/lib/*.o
> diff --git a/config-x86_64.mak b/config-x86_64.mak
> index 4e525f5..bb8ee89 100644
> --- a/config-x86_64.mak
> +++ b/config-x86_64.mak
> @@ -9,5 +9,6 @@ tests = $(TEST_DIR)/access.flat $(TEST_DIR)/apic.flat \
>  	  $(TEST_DIR)/xsave.flat $(TEST_DIR)/rmap_chain.flat \
>  	  $(TEST_DIR)/pcid.flat
>  tests += $(TEST_DIR)/svm.flat
> +tests += $(TEST_DIR)/vmx.flat
>  
>  include config-x86-common.mak
> diff --git a/lib/x86/msr.h b/lib/x86/msr.h
> index 509a421..281255a 100644
> --- a/lib/x86/msr.h
> +++ b/lib/x86/msr.h
> @@ -396,6 +396,11 @@
>  #define MSR_IA32_VMX_VMCS_ENUM          0x0000048a
>  #define MSR_IA32_VMX_PROCBASED_CTLS2    0x0000048b
>  #define MSR_IA32_VMX_EPT_VPID_CAP       0x0000048c
> +#define MSR_IA32_VMX_TRUE_PIN		0x0000048d
> +#define MSR_IA32_VMX_TRUE_PROC		0x0000048e
> +#define MSR_IA32_VMX_TRUE_EXIT		0x0000048f
> +#define MSR_IA32_VMX_TRUE_ENTRY		0x00000490
> +
>  
>  /* AMD-V MSRs */
>  
> diff --git a/x86/cstart64.S b/x86/cstart64.S
> index 24df5f8..0fe76da 100644
> --- a/x86/cstart64.S
> +++ b/x86/cstart64.S
> @@ -4,6 +4,10 @@
>  .globl boot_idt
>  boot_idt = 0
>  
> +.globl idt_descr
> +.globl tss_descr
> +.globl gdt64_desc
> +
>  ipi_vector = 0x20
>  
>  max_cpus = 64
> diff --git a/x86/unittests.cfg b/x86/unittests.cfg
> index bc9643e..e846739 100644
> --- a/x86/unittests.cfg
> +++ b/x86/unittests.cfg
> @@ -149,3 +149,9 @@ extra_params = --append "10000000 `date +%s`"
>  file = pcid.flat
>  extra_params = -cpu qemu64,+pcid
>  arch = x86_64
> +
> +[vmx]
> +file = vmx.flat
> +extra_params = -cpu Nehalem,+vmx

Should this use "-cpu host" instead? (Or "-cpu host,+vmx", I don't
remember).

> +arch = x86_64
> +
> diff --git a/x86/vmx.c b/x86/vmx.c
> new file mode 100644
> index 0000000..0435746
> --- /dev/null
> +++ b/x86/vmx.c
> @@ -0,0 +1,568 @@
> +#include "libcflat.h"
> +#include "processor.h"
> +#include "vm.h"
> +#include "desc.h"
> +#include "vmx.h"
> +#include "msr.h"
> +#include "smp.h"
> +#include "io.h"
> +
> +
> +int fails = 0, tests = 0;
> +u32 *vmxon_region;
> +struct vmcs *vmcs_root;
> +void *io_bmp1, *io_bmp2;
> +void *msr_bmp;
> +u32 vpid_ctr;
> +char *guest_stack, *host_stack;
> +char *guest_syscall_stack, *host_syscall_stack;
> +u32 ctrl_pin, ctrl_enter, ctrl_exit, ctrl_cpu[2];
> +ulong fix_cr0_set, fix_cr0_clr;
> +ulong fix_cr4_set, fix_cr4_clr;
> +struct regs regs;
> +
> +extern u64 gdt64_desc[];
> +extern u64 idt_descr[];
> +extern u64 tss_descr[];
> +extern void *entry_vmx;
> +extern void *entry_sysenter;
> +extern void *entry_guest;
> +
> +void report(const char *name, int result)
> +{
> +	++tests;
> +	if (result)
> +		printf("PASS: %s\n", name);
> +	else {
> +		printf("FAIL: %s\n", name);
> +		++fails;
> +	}
> +}
> +
> +inline u64 get_rflags(void)
> +{
> +	u64 r;
> +	asm volatile("pushf; pop %0\n\t" : "=q"(r) : : "cc");
> +	return r;
> +}
> +
> +inline void set_rflags(u64 r)
> +{
> +	asm volatile("push %0; popf\n\t" : : "q"(r) : "cc");
> +}
> +
> +int vmcs_clear(struct vmcs *vmcs)
> +{
> +	bool ret;
> +	asm volatile ("vmclear %1; seta %0" : "=q" (ret) : "m" (vmcs) : "cc");

You can use "setbe", it's clearer and avoids the ! in the return statement.

We should later add tests for failure conditions, since failing to
detect errors could give rise to L2->L1 attack vectors.  When we do so,
we will have to distinguish CF from ZF.


> +	return !ret;
> +}
> +
> +u64 vmcs_read(enum Encoding enc)
> +{
> +	u64 val;
> +	asm volatile ("vmread %1, %0" : "=rm" (val) : "r" ((u64)enc) : "cc");
> +	return val;
> +}
> +
> +int vmcs_write(enum Encoding enc, u64 val)
> +{
> +	bool ret;
> +	asm volatile ("vmwrite %1, %2; seta %0"
> +		: "=q"(ret) : "rm" (val), "r" ((u64)enc) : "cc");
> +	return !ret;
> +}
> +
> +int make_vmcs_current(struct vmcs *vmcs)
> +{
> +	bool ret;
> +
> +	asm volatile ("vmptrld %1; seta %0" : "=q" (ret) : "m" (vmcs) : "cc");
> +	return !ret;
> +}
> +
> +int save_vmcs(struct vmcs **vmcs)
> +{
> +	bool ret;
> +
> +	asm volatile ("vmptrst %1; seta %0" : "=q" (ret) : "m" (*vmcs) : "cc");
> +	return !ret;
> +}
> +
> +/* entry_vmx */
> +asm(
> +	".align	4, 0x90\n\t"
> +	".globl	entry_vmx\n\t"
> +	"entry_vmx:\n\t"
> +	SAVE_GPR
> +	"	call	vmx_handler\n\t"
> +	LOAD_GPR
> +	"	vmresume\n\t"
> +);
> +
> +/* entry_sysenter */
> +asm(
> +	".align	4, 0x90\n\t"
> +	".globl	entry_sysenter\n\t"
> +	"entry_sysenter:\n\t"
> +	SAVE_GPR
> +	"	and	$0xf, %rax\n\t"
> +	"	push	%rax\n\t"
> +	"	call	syscall_handler\n\t"
> +);
> +
> +void syscall_handler(u64 syscall_no)
> +{
> +	printf("Here in syscall_handler, syscall_no = %d\n", syscall_no);
> +}
> +
> +void vmx_run()
> +{
> +	bool ret;
> +	printf("Now run vm.\n\n");
> +	asm volatile("vmlaunch;seta %0\n\t" : "=m"(ret));
> +	printf("VMLAUNCH error, ret=%d\n", ret);
> +}
> +
> +void vmx_resume()
> +{
> +	asm volatile(LOAD_GPR
> +		"vmresume\n\t");
> +	/* VMRESUME fail if reach here */
> +}
> +
> +void print_vmexit_info()
> +{
> +	u64 guest_rip, guest_rsp;
> +	ulong reason = vmcs_read(EXI_REASON) & 0xff;
> +	ulong exit_qual = vmcs_read(EXI_QUALIFICATION);
> +	guest_rip = vmcs_read(GUEST_RIP);
> +	guest_rsp = vmcs_read(GUEST_RSP);
> +	printf("VMEXIT info:\n");
> +	printf("\tvmexit reason = %d\n", reason);
> +	printf("\texit qualification = 0x%x\n", exit_qual);
> +	printf("\tBit 31 of reason = %x\n", (vmcs_read(EXI_REASON) >> 31) & 1);
> +	printf("\tguest_rip = 0x%llx\n", guest_rip);
> +	printf("\tRAX=0x%llx    RBX=0x%llx    RCX=0x%llx    RDX=0x%llx\n",
> +		regs.rax, regs.rbx, regs.rcx, regs.rdx);
> +	printf("\tRSP=0x%llx    RBP=0x%llx    RSI=0x%llx    RDI=0x%llx\n",
> +		guest_rsp, regs.rbp, regs.rsi, regs.rdi);
> +	printf("\tR8 =0x%llx    R9 =0x%llx    R10=0x%llx    R11=0x%llx\n",
> +		regs.r8, regs.r9, regs.r10, regs.r11);
> +	printf("\tR12=0x%llx    R13=0x%llx    R14=0x%llx    R15=0x%llx\n",
> +		regs.r12, regs.r13, regs.r14, regs.r15);
> +}
> +
> +void test_vmclear(void)
> +{
> +	u64 rflags;
> +
> +	rflags = get_rflags() | X86_EFLAGS_CF | X86_EFLAGS_ZF;
> +	set_rflags(rflags);
> +	report("test vmclear", vmcs_clear(vmcs_root) == 0);
> +}
> +
> +void test_vmxoff(void)
> +{
> +	bool ret;
> +	u64 rflags;
> +
> +	rflags = get_rflags() | X86_EFLAGS_CF | X86_EFLAGS_ZF;
> +	set_rflags(rflags);
> +	asm volatile("vmxoff; seta %0\n\t" : "=q"(ret) : : "cc");
> +	report("test vmxoff", ret);
> +}
> +
> +void vmx_exit(void)
> +{
> +	test_vmxoff();
> +	printf("\nSUMMARY: %d tests, %d failures\n", tests, fails);
> +	exit(fails ? -1 : 0);
> +}

Can you try to jump back to main, and do test_vmxoff there?  This will
avoid having to write our tests in callback style, which is a pain.
Basically something similar to setjmp/longjmp.  In main:

	if (setjmp(jmpbuf) == 0) {
		vmx_run();
		/* Should not reach here */
		report("test vmlaunch", 0);
	}
	test_vmxoff();

exit:
	printf("\nSUMMARY: %d tests, %d failures\n", tests, fails);
	return fails ? 1 : 0;

In vmx_handler:

	case VMX_HLT:
		printf("\nVM exit.\n");
		longjmp(jmpbuf, 1);

> +void vmx_handler()
> +{
> +	u64 guest_rip;
> +	ulong reason = vmcs_read(EXI_REASON) & 0xff;
> +
> +	if ((read_cr4() & CR4_PAE) && (read_cr0() & CR0_PG)
> +		&& !(rdmsr(MSR_EFER) & EFER_LMA))
> +		printf("ERROR : PDPTEs should be checked\n");
> +
> +	guest_rip = vmcs_read(GUEST_RIP);
> +
> +	switch (reason) {
> +	case VMX_VMCALL:
> +		switch (regs.rax) {
> +		case TEST_VMRESUME:
> +			regs.rax = 0xFFFF;
> +			break;
> +		default:
> +			printf("ERROR : Invalid VMCALL param : %d\n", regs.rax);
> +		}
> +		vmcs_write(GUEST_RIP, guest_rip + 3);
> +		goto vmx_resume;
> +	case VMX_IO:
> +		print_vmexit_info();
> +		break;
> +	case VMX_HLT:
> +		printf("\nVM exit.\n");
> +		vmx_exit();
> +		/* Should not reach here */
> +		goto vmx_exit;
> +	case VMX_EXC_NMI:
> +	case VMX_EXTINT:
> +	case VMX_INVLPG:
> +	case VMX_CR:
> +	case VMX_EPT_VIOLATION:
> +	default:
> +		break;
> +	}
> +	printf("ERROR : Unhandled vmx exit.\n");
> +	print_vmexit_info();
> +vmx_exit:
> +	exit(-1);
> +vmx_resume:
> +	vmx_resume();
> +	/* Should not reach here */
> +	exit(-1);
> +}
> +
> +void test_vmresume()
> +{
> +	u64 rax;
> +	u64 rsp, resume_rsp;
> +
> +	rax = 0;
> +	asm volatile("mov %%rsp, %0\n\t" : "=r"(rsp));
> +	asm volatile("mov %2, %%rax\n\t"
> +		"vmcall\n\t"
> +		"mov %%rax, %0\n\t"
> +		"mov %%rsp, %1\n\t"
> +		: "=r"(rax), "=r"(resume_rsp)
> +		: "g"(TEST_VMRESUME));
> +	report("test vmresume", (rax == 0xFFFF) && (rsp == resume_rsp));
> +}
> +
> +/* entry_guest */
> +asm(
> +	".align	4, 0x90\n\t"
> +	".globl	entry_guest\n\t"
> +	"entry_guest:\n\t"
> +	"	call	guest_main\n\t"
> +	"	hlt\n\t"
> +);
> +
> +void guest_main(void)
> +{
> +	/* If reach here, VMLAUNCH runs OK */
> +	report("test vmlaunch", 1);
> +	printf("cr0 in guest = %llx\n", read_cr0());
> +	printf("cr3 in guest = %llx\n", read_cr3());
> +	printf("cr4 in guest = %llx\n", read_cr4());
> +	printf("\nHello World!\n");
> +	test_vmresume();
> +}
> +
> +void init_vmcs_ctrl(void)
> +{
> +	/* 26.2 CHECKS ON VMX CONTROLS AND HOST-STATE AREA */
> +	/* 26.2.1.1 */
> +	vmcs_write(PIN_CONTROLS, ctrl_pin);
> +	/* Disable VMEXIT of IO instruction */
> +	vmcs_write(CPU_EXEC_CTRL0, ctrl_cpu[0]);
> +	if (ctrl_cpu_rev[0].set & CPU_SECONDARY) {
> +		ctrl_cpu[1] |= ctrl_cpu_rev[1].set & ctrl_cpu_rev[1].clr;
> +		vmcs_write(CPU_EXEC_CTRL1, ctrl_cpu[1]);
> +	}
> +	vmcs_write(CR3_TARGET_COUNT, 0);
> +	io_bmp1 = alloc_page();
> +	io_bmp2 = alloc_page();
> +	memset(io_bmp1, 0, PAGE_SIZE);
> +	memset(io_bmp2, 0, PAGE_SIZE);
> +	vmcs_write(IO_BITMAP_A, (u64)io_bmp1);
> +	vmcs_write(IO_BITMAP_B, (u64)io_bmp2);
> +	msr_bmp = alloc_page();
> +	memset(msr_bmp, 0, PAGE_SIZE);
> +	vmcs_write(MSR_BITMAP, (u64)msr_bmp);
> +	vmcs_write(VPID, ++vpid_ctr);
> +}
> +
> +void init_vmcs_host(void)
> +{
> +	/* 26.2 CHECKS ON VMX CONTROLS AND HOST-STATE AREA */
> +	/* 26.2.1.2 */
> +	vmcs_write(HOST_EFER, rdmsr(MSR_EFER));
> +
> +	/* 26.2.1.3 */
> +	vmcs_write(ENT_CONTROLS, ctrl_enter);
> +	vmcs_write(EXI_CONTROLS, ctrl_exit);
> +
> +	/* 26.2.2 */
> +	vmcs_write(HOST_CR0, read_cr0());
> +	vmcs_write(HOST_CR3, read_cr3());
> +	vmcs_write(HOST_CR4, read_cr4());
> +	vmcs_write(HOST_SYSENTER_ESP,
> +		(u64)(host_syscall_stack + PAGE_SIZE - 1));
> +	vmcs_write(HOST_SYSENTER_EIP, (u64)(&entry_sysenter));
> +	vmcs_write(HOST_SYSENTER_CS,  SEL_KERN_CODE_64);
> +
> +	/* 26.2.3 */
> +	vmcs_write(HOST_SEL_CS, SEL_KERN_CODE_64);
> +	vmcs_write(HOST_SEL_SS, SEL_KERN_DATA_64);
> +	vmcs_write(HOST_SEL_DS, SEL_KERN_DATA_64);
> +	vmcs_write(HOST_SEL_ES, SEL_KERN_DATA_64);
> +	vmcs_write(HOST_SEL_FS, SEL_KERN_DATA_64);
> +	vmcs_write(HOST_SEL_GS, SEL_KERN_DATA_64);
> +	vmcs_write(HOST_SEL_TR, SEL_TSS_RUN);
> +	vmcs_write(HOST_BASE_TR,   (u64)tss_descr);
> +	vmcs_write(HOST_BASE_GDTR, (u64)gdt64_desc);
> +	vmcs_write(HOST_BASE_IDTR, (u64)idt_descr);
> +	vmcs_write(HOST_BASE_FS, 0);
> +	vmcs_write(HOST_BASE_GS, 0);
> +
> +	/* Set other vmcs area */
> +	vmcs_write(PF_ERROR_MASK, 0);
> +	vmcs_write(PF_ERROR_MATCH, 0);
> +	vmcs_write(VMCS_LINK_PTR, ~0ul);
> +	vmcs_write(VMCS_LINK_PTR_HI, ~0ul);
> +	vmcs_write(HOST_RSP, (u64)(host_stack + PAGE_SIZE - 1));
> +	vmcs_write(HOST_RIP, (u64)(&entry_vmx));
> +}
> +
> +void init_vmcs_guest(void)
> +{
> +	/* 26.3 CHECKING AND LOADING GUEST STATE */
> +	ulong guest_cr0, guest_cr4, guest_cr3;
> +	/* 26.3.1.1 */
> +	guest_cr0 = read_cr0();
> +	guest_cr4 = read_cr4();
> +	guest_cr3 = read_cr3();
> +	if (ctrl_enter & ENT_GUEST_64) {
> +		guest_cr0 |= CR0_PG;
> +		guest_cr4 |= CR4_PAE;
> +	}
> +	if ((ctrl_enter & ENT_GUEST_64) == 0)
> +		guest_cr4 &= (~CR4_PCIDE);
> +	if (guest_cr0 & CR0_PG)
> +		guest_cr0 |= CR0_PE;
> +	vmcs_write(GUEST_CR0, guest_cr0);
> +	vmcs_write(GUEST_CR3, guest_cr3);
> +	vmcs_write(GUEST_CR4, guest_cr4);
> +	vmcs_write(GUEST_SYSENTER_CS,  SEL_KERN_CODE_64);
> +	vmcs_write(GUEST_SYSENTER_ESP,
> +		(u64)(guest_syscall_stack + PAGE_SIZE - 1));
> +	vmcs_write(GUEST_SYSENTER_EIP, (u64)(&entry_sysenter));
> +	vmcs_write(GUEST_DR7, 0);
> +	vmcs_write(GUEST_EFER, rdmsr(MSR_EFER));
> +
> +	/* 26.3.1.2 */
> +	vmcs_write(GUEST_SEL_CS, SEL_KERN_CODE_64);
> +	vmcs_write(GUEST_SEL_SS, SEL_KERN_DATA_64);
> +	vmcs_write(GUEST_SEL_DS, SEL_KERN_DATA_64);
> +	vmcs_write(GUEST_SEL_ES, SEL_KERN_DATA_64);
> +	vmcs_write(GUEST_SEL_FS, SEL_KERN_DATA_64);
> +	vmcs_write(GUEST_SEL_GS, SEL_KERN_DATA_64);
> +	vmcs_write(GUEST_SEL_TR, SEL_TSS_RUN);
> +	vmcs_write(GUEST_SEL_LDTR, 0);
> +
> +	vmcs_write(GUEST_BASE_CS, 0);
> +	vmcs_write(GUEST_BASE_ES, 0);
> +	vmcs_write(GUEST_BASE_SS, 0);
> +	vmcs_write(GUEST_BASE_DS, 0);
> +	vmcs_write(GUEST_BASE_FS, 0);
> +	vmcs_write(GUEST_BASE_GS, 0);
> +	vmcs_write(GUEST_BASE_TR,   (u64)tss_descr);
> +	vmcs_write(GUEST_BASE_LDTR, 0);
> +
> +	vmcs_write(GUEST_LIMIT_CS, 0xFFFFFFFF);
> +	vmcs_write(GUEST_LIMIT_DS, 0xFFFFFFFF);
> +	vmcs_write(GUEST_LIMIT_ES, 0xFFFFFFFF);
> +	vmcs_write(GUEST_LIMIT_SS, 0xFFFFFFFF);
> +	vmcs_write(GUEST_LIMIT_FS, 0xFFFFFFFF);
> +	vmcs_write(GUEST_LIMIT_GS, 0xFFFFFFFF);
> +	vmcs_write(GUEST_LIMIT_LDTR, 0xffff);
> +	vmcs_write(GUEST_LIMIT_TR, ((struct descr *)tss_descr)->limit);
> +
> +	vmcs_write(GUEST_AR_CS, 0xa09b);
> +	vmcs_write(GUEST_AR_DS, 0xc093);
> +	vmcs_write(GUEST_AR_ES, 0xc093);
> +	vmcs_write(GUEST_AR_FS, 0xc093);
> +	vmcs_write(GUEST_AR_GS, 0xc093);
> +	vmcs_write(GUEST_AR_SS, 0xc093);
> +	vmcs_write(GUEST_AR_LDTR, 0x82);
> +	vmcs_write(GUEST_AR_TR, 0x8b);
> +
> +	/* 26.3.1.3 */
> +	vmcs_write(GUEST_BASE_GDTR, (u64)gdt64_desc);
> +	vmcs_write(GUEST_BASE_IDTR, (u64)idt_descr);
> +	vmcs_write(GUEST_LIMIT_GDTR,
> +		((struct descr *)gdt64_desc)->limit & 0xffff);
> +	vmcs_write(GUEST_LIMIT_IDTR,
> +		((struct descr *)idt_descr)->limit & 0xffff);
> +
> +	/* 26.3.1.4 */
> +	vmcs_write(GUEST_RIP, (u64)(&entry_guest));
> +	vmcs_write(GUEST_RSP, (u64)(guest_stack + PAGE_SIZE - 1));
> +	vmcs_write(GUEST_RFLAGS, 0x2);
> +
> +	/* 26.3.1.5 */
> +	vmcs_write(GUEST_ACTV_STATE, 0);
> +	vmcs_write(GUEST_INTR_STATE, 0);
> +}
> +
> +int init_vmcs(struct vmcs **vmcs)
> +{
> +	*vmcs = alloc_page();
> +	memset(*vmcs, 0, PAGE_SIZE);
> +	(*vmcs)->revision_id = basic.revision;
> +	/* vmclear first to init vmcs */
> +	if (vmcs_clear(*vmcs)) {
> +		printf("%s : vmcs_clear error\n", __func__);
> +		return 1;
> +	}
> +
> +	if (make_vmcs_current(*vmcs)) {
> +		printf("%s : make_vmcs_current error\n", __func__);
> +		return 1;
> +	}
> +
> +	/* All settings to pin/exit/enter/cpu
> +	   control fields should place here */

should be placed here

> +	ctrl_pin |= PIN_EXTINT | PIN_NMI | PIN_VIRT_NMI;
> +	ctrl_exit = EXI_LOAD_EFER | EXI_HOST_64;
> +	ctrl_enter = (ENT_LOAD_EFER | ENT_GUEST_64);
> +	ctrl_cpu[0] |= CPU_HLT;
> +	/* DIsable IO instruction VMEXIT now */
> +	ctrl_cpu[0] &= (~(CPU_IO | CPU_IO_BITMAP));
> +	ctrl_cpu[1] = 0;
> +
> +	ctrl_pin = (ctrl_pin | ctrl_pin_rev.set) & ctrl_pin_rev.clr;
> +	ctrl_enter = (ctrl_enter | ctrl_enter_rev.set) & ctrl_enter_rev.clr;
> +	ctrl_exit = (ctrl_exit | ctrl_exit_rev.set) & ctrl_exit_rev.clr;
> +	ctrl_cpu[0] = (ctrl_cpu[0] | ctrl_cpu_rev[0].set) & ctrl_cpu_rev[0].clr;
> +
> +	init_vmcs_ctrl();
> +	init_vmcs_host();
> +	init_vmcs_guest();
> +	return 0;
> +}
> +
> +void init_vmx(void)
> +{
> +	vmxon_region = alloc_page();
> +	memset(vmxon_region, 0, PAGE_SIZE);
> +
> +	fix_cr0_set =  rdmsr(MSR_IA32_VMX_CR0_FIXED0);
> +	fix_cr0_clr =  rdmsr(MSR_IA32_VMX_CR0_FIXED1);
> +	fix_cr4_set =  rdmsr(MSR_IA32_VMX_CR4_FIXED0);
> +	fix_cr4_clr = rdmsr(MSR_IA32_VMX_CR4_FIXED1);
> +	basic.val = rdmsr(MSR_IA32_VMX_BASIC);
> +	ctrl_pin_rev.val = rdmsr(basic.ctrl ? MSR_IA32_VMX_TRUE_PIN
> +			: MSR_IA32_VMX_PINBASED_CTLS);
> +	ctrl_exit_rev.val = rdmsr(basic.ctrl ? MSR_IA32_VMX_TRUE_EXIT
> +			: MSR_IA32_VMX_EXIT_CTLS);
> +	ctrl_enter_rev.val = rdmsr(basic.ctrl ? MSR_IA32_VMX_TRUE_ENTRY
> +			: MSR_IA32_VMX_ENTRY_CTLS);
> +	ctrl_cpu_rev[0].val = rdmsr(basic.ctrl ? MSR_IA32_VMX_TRUE_PROC
> +			: MSR_IA32_VMX_PROCBASED_CTLS);
> +	if (ctrl_cpu_rev[0].set & CPU_SECONDARY)
> +		ctrl_cpu_rev[1].val = rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2);
> +	if (ctrl_cpu_rev[1].set & CPU_EPT || ctrl_cpu_rev[1].set & CPU_VPID)
> +		ept_vpid.val = rdmsr(MSR_IA32_VMX_EPT_VPID_CAP);
> +
> +	write_cr0((read_cr0() & fix_cr0_clr) | fix_cr0_set);
> +	write_cr4((read_cr4() & fix_cr4_clr) | fix_cr4_set | CR4_VMXE);
> +
> +	*vmxon_region = basic.revision;
> +
> +	guest_stack = alloc_page();
> +	memset(guest_stack, 0, PAGE_SIZE);
> +	guest_syscall_stack = alloc_page();
> +	memset(guest_syscall_stack, 0, PAGE_SIZE);
> +	host_stack = alloc_page();
> +	memset(host_stack, 0, PAGE_SIZE);
> +	host_syscall_stack = alloc_page();
> +	memset(host_syscall_stack, 0, PAGE_SIZE);
> +}
> +
> +int test_vmx_capability(void)
> +{
> +	struct cpuid r;
> +	u64 ret1, ret2;
> +	r = cpuid(1);
> +	ret1 = ((r.c) >> 5) & 1;
> +	ret2 = ((rdmsr(MSR_IA32_FEATURE_CONTROL) & 0x5) == 0x5);
> +	report("test vmx capability", ret1 & ret2);
> +	/* TODO: Fix here after patches are accepted */

It's fine to include a failing test.

> +	return 0;
> +	return !(ret1 & ret2);
> +}
> +
> +int test_vmxon(void)
> +{
> +	bool ret;
> +	u64 rflags;
> +
> +	rflags = get_rflags() | X86_EFLAGS_CF | X86_EFLAGS_ZF;
> +	set_rflags(rflags);
> +	asm volatile ("vmxon %1; seta %0\n\t"
> +		: "=q"(ret) : "m"(vmxon_region) : "cc");
> +	report("test vmxon", ret);
> +	/* TODO: Change here after bug fixed */
> +	return 0;
> +	/* return !ret; */
> +}
> +
> +void test_vmptrld(void)
> +{
> +	u64 rflags;
> +	struct vmcs *vmcs;
> +
> +	vmcs = alloc_page();
> +	vmcs->revision_id = basic.revision;
> +	rflags = get_rflags() | X86_EFLAGS_CF | X86_EFLAGS_ZF;
> +	set_rflags(rflags);
> +	report("test vmptrld", make_vmcs_current(vmcs) == 0);
> +}
> +
> +void test_vmptrst(void)
> +{
> +	u64 rflags;
> +	int ret;
> +	struct vmcs *vmcs1, *vmcs2;
> +
> +	vmcs1 = alloc_page();
> +	memset(vmcs1, 0, PAGE_SIZE);
> +	init_vmcs(&vmcs1);
> +	rflags = get_rflags() | X86_EFLAGS_CF | X86_EFLAGS_ZF;
> +	set_rflags(rflags);
> +	ret = save_vmcs(&vmcs2);
> +	report("test vmptrst", (!ret) && (vmcs1 == vmcs2));
> +}
> +
> +int main(void)
> +{
> +	setup_vm();
> +	setup_idt();
> +
> +	if (test_vmx_capability() != 0) {
> +		printf("ERROR : vmx not supported, check +vmx option\n");
> +		goto exit;
> +	}
> +	init_vmx();
> +	if (test_vmxon() != 0)
> +		goto exit;
> +	test_vmptrld();
> +	test_vmclear();
> +	test_vmptrst();
> +	init_vmcs(&vmcs_root);
> +
> +	vmx_run();
> +	/* Should not reach here */
> +	report("test vmlaunch", 0);
> +
> +exit:
> +	printf("\nSUMMARY: %d tests, %d failures\n", tests, fails);
> +	return fails ? 1 : 0;
> +}
> diff --git a/x86/vmx.h b/x86/vmx.h
> new file mode 100644
> index 0000000..167815d
> --- /dev/null
> +++ b/x86/vmx.h
> @@ -0,0 +1,406 @@
> +#ifndef __HYPERVISOR_H
> +#define __HYPERVISOR_H
> +
> +#include "libcflat.h"
> +
> +struct vmcs {
> +	u32 revision_id; /* vmcs revision identifier */
> +	u32 abort; /* VMX-abort indicator */
> +	/* VMCS data */
> +	char data[0];
> +};
> +
> +struct regs {
> +	u64 rax;
> +	u64 rcx;
> +	u64 rdx;
> +	u64 rbx;
> +	u64 cr2;
> +	u64 rbp;
> +	u64 rsi;
> +	u64 rdi;
> +	u64 r8;
> +	u64 r9;
> +	u64 r10;
> +	u64 r11;
> +	u64 r12;
> +	u64 r13;
> +	u64 r14;
> +	u64 r15;
> +};
> +
> +static union vmx_basic {
> +	u64 val;
> +	struct {
> +		u32 revision;
> +		u32	size:13,
> +			: 3,
> +			width:1,
> +			dual:1,
> +			type:4,
> +			insouts:1,
> +			ctrl:1;
> +	};
> +} basic;
> +
> +static union vmx_ctrl_pin {
> +	u64 val;
> +	struct {
> +		u32 set, clr;
> +	};
> +} ctrl_pin_rev;
> +
> +static union vmx_ctrl_cpu {
> +	u64 val;
> +	struct {
> +		u32 set, clr;
> +	};
> +} ctrl_cpu_rev[2];
> +
> +static union vmx_ctrl_exit {
> +	u64 val;
> +	struct {
> +		u32 set, clr;
> +	};
> +} ctrl_exit_rev;
> +
> +static union vmx_ctrl_ent {
> +	u64 val;
> +	struct {
> +		u32 set, clr;
> +	};
> +} ctrl_enter_rev;
> +
> +static union vmx_ept_vpid {
> +	u64 val;
> +	struct {
> +		u32:16,
> +			super:2,
> +			: 2,
> +			invept:1,
> +			: 11;
> +		u32	invvpid:1;
> +	};
> +} ept_vpid;
> +
> +struct descr {
> +	u16 limit;
> +	u64 addr;
> +};
> +
> +enum Encoding {
> +	/* 16-Bit Control Fields */
> +	VPID			= 0x0000ul,
> +	/* Posted-interrupt notification vector */
> +	PINV			= 0x0002ul,
> +	/* EPTP index */
> +	EPTP_IDX		= 0x0004ul,
> +
> +	/* 16-Bit Guest State Fields */
> +	GUEST_SEL_ES		= 0x0800ul,
> +	GUEST_SEL_CS		= 0x0802ul,
> +	GUEST_SEL_SS		= 0x0804ul,
> +	GUEST_SEL_DS		= 0x0806ul,
> +	GUEST_SEL_FS		= 0x0808ul,
> +	GUEST_SEL_GS		= 0x080aul,
> +	GUEST_SEL_LDTR		= 0x080cul,
> +	GUEST_SEL_TR		= 0x080eul,
> +	GUEST_INT_STATUS	= 0x0810ul,
> +
> +	/* 16-Bit Host State Fields */
> +	HOST_SEL_ES		= 0x0c00ul,
> +	HOST_SEL_CS		= 0x0c02ul,
> +	HOST_SEL_SS		= 0x0c04ul,
> +	HOST_SEL_DS		= 0x0c06ul,
> +	HOST_SEL_FS		= 0x0c08ul,
> +	HOST_SEL_GS		= 0x0c0aul,
> +	HOST_SEL_TR		= 0x0c0cul,
> +
> +	/* 64-Bit Control Fields */
> +	IO_BITMAP_A		= 0x2000ul,
> +	IO_BITMAP_B		= 0x2002ul,
> +	MSR_BITMAP		= 0x2004ul,
> +	EXIT_MSR_ST_ADDR	= 0x2006ul,
> +	EXIT_MSR_LD_ADDR	= 0x2008ul,
> +	ENTER_MSR_LD_ADDR	= 0x200aul,
> +	VMCS_EXEC_PTR		= 0x200cul,
> +	TSC_OFFSET		= 0x2010ul,
> +	TSC_OFFSET_HI		= 0x2011ul,
> +	APIC_VIRT_ADDR		= 0x2012ul,
> +	APIC_ACCS_ADDR		= 0x2014ul,
> +	EPTP			= 0x201aul,
> +	EPTP_HI			= 0x201bul,
> +
> +	/* 64-Bit Readonly Data Field */
> +	INFO_PHYS_ADDR		= 0x2400ul,
> +
> +	/* 64-Bit Guest State */
> +	VMCS_LINK_PTR		= 0x2800ul,
> +	VMCS_LINK_PTR_HI	= 0x2801ul,
> +	GUEST_DEBUGCTL		= 0x2802ul,
> +	GUEST_DEBUGCTL_HI	= 0x2803ul,
> +	GUEST_EFER		= 0x2806ul,
> +	GUEST_PERF_GLOBAL_CTRL	= 0x2808ul,
> +	GUEST_PDPTE		= 0x280aul,
> +
> +	/* 64-Bit Host State */
> +	HOST_EFER		= 0x2c02ul,
> +	HOST_PERF_GLOBAL_CTRL	= 0x2c04ul,
> +
> +	/* 32-Bit Control Fields */
> +	PIN_CONTROLS		= 0x4000ul,
> +	CPU_EXEC_CTRL0		= 0x4002ul,
> +	EXC_BITMAP		= 0x4004ul,
> +	PF_ERROR_MASK		= 0x4006ul,
> +	PF_ERROR_MATCH		= 0x4008ul,
> +	CR3_TARGET_COUNT	= 0x400aul,
> +	EXI_CONTROLS		= 0x400cul,
> +	EXI_MSR_ST_CNT		= 0x400eul,
> +	EXI_MSR_LD_CNT		= 0x4010ul,
> +	ENT_CONTROLS		= 0x4012ul,
> +	ENT_MSR_LD_CNT		= 0x4014ul,
> +	ENT_INTR_INFO		= 0x4016ul,
> +	ENT_INTR_ERROR		= 0x4018ul,
> +	ENT_INST_LEN		= 0x401aul,
> +	TPR_THRESHOLD		= 0x401cul,
> +	CPU_EXEC_CTRL1		= 0x401eul,
> +
> +	/* 32-Bit R/O Data Fields */
> +	VMX_INST_ERROR		= 0x4400ul,
> +	EXI_REASON		= 0x4402ul,
> +	EXI_INTR_INFO		= 0x4404ul,
> +	EXI_INTR_ERROR		= 0x4406ul,
> +	IDT_VECT_INFO		= 0x4408ul,
> +	IDT_VECT_ERROR		= 0x440aul,
> +	EXI_INST_LEN		= 0x440cul,
> +	EXI_INST_INFO		= 0x440eul,
> +
> +	/* 32-Bit Guest State Fields */
> +	GUEST_LIMIT_ES		= 0x4800ul,
> +	GUEST_LIMIT_CS		= 0x4802ul,
> +	GUEST_LIMIT_SS		= 0x4804ul,
> +	GUEST_LIMIT_DS		= 0x4806ul,
> +	GUEST_LIMIT_FS		= 0x4808ul,
> +	GUEST_LIMIT_GS		= 0x480aul,
> +	GUEST_LIMIT_LDTR	= 0x480cul,
> +	GUEST_LIMIT_TR		= 0x480eul,
> +	GUEST_LIMIT_GDTR	= 0x4810ul,
> +	GUEST_LIMIT_IDTR	= 0x4812ul,
> +	GUEST_AR_ES		= 0x4814ul,
> +	GUEST_AR_CS		= 0x4816ul,
> +	GUEST_AR_SS		= 0x4818ul,
> +	GUEST_AR_DS		= 0x481aul,
> +	GUEST_AR_FS		= 0x481cul,
> +	GUEST_AR_GS		= 0x481eul,
> +	GUEST_AR_LDTR		= 0x4820ul,
> +	GUEST_AR_TR		= 0x4822ul,
> +	GUEST_INTR_STATE	= 0x4824ul,
> +	GUEST_ACTV_STATE	= 0x4826ul,
> +	GUEST_SMBASE		= 0x4828ul,
> +	GUEST_SYSENTER_CS	= 0x482aul,
> +
> +	/* 32-Bit Host State Fields */
> +	HOST_SYSENTER_CS	= 0x4c00ul,
> +
> +	/* Natural-Width Control Fields */
> +	CR0_MASK		= 0x6000ul,
> +	CR4_MASK		= 0x6002ul,
> +	CR0_READ_SHADOW	= 0x6004ul,
> +	CR4_READ_SHADOW	= 0x6006ul,
> +	CR3_TARGET_0		= 0x6008ul,
> +	CR3_TARGET_1		= 0x600aul,
> +	CR3_TARGET_2		= 0x600cul,
> +	CR3_TARGET_3		= 0x600eul,
> +
> +	/* Natural-Width R/O Data Fields */
> +	EXI_QUALIFICATION	= 0x6400ul,
> +	IO_RCX			= 0x6402ul,
> +	IO_RSI			= 0x6404ul,
> +	IO_RDI			= 0x6406ul,
> +	IO_RIP			= 0x6408ul,
> +	GUEST_LINEAR_ADDRESS	= 0x640aul,
> +
> +	/* Natural-Width Guest State Fields */
> +	GUEST_CR0		= 0x6800ul,
> +	GUEST_CR3		= 0x6802ul,
> +	GUEST_CR4		= 0x6804ul,
> +	GUEST_BASE_ES		= 0x6806ul,
> +	GUEST_BASE_CS		= 0x6808ul,
> +	GUEST_BASE_SS		= 0x680aul,
> +	GUEST_BASE_DS		= 0x680cul,
> +	GUEST_BASE_FS		= 0x680eul,
> +	GUEST_BASE_GS		= 0x6810ul,
> +	GUEST_BASE_LDTR		= 0x6812ul,
> +	GUEST_BASE_TR		= 0x6814ul,
> +	GUEST_BASE_GDTR		= 0x6816ul,
> +	GUEST_BASE_IDTR		= 0x6818ul,
> +	GUEST_DR7		= 0x681aul,
> +	GUEST_RSP		= 0x681cul,
> +	GUEST_RIP		= 0x681eul,
> +	GUEST_RFLAGS		= 0x6820ul,
> +	GUEST_PENDING_DEBUG	= 0x6822ul,
> +	GUEST_SYSENTER_ESP	= 0x6824ul,
> +	GUEST_SYSENTER_EIP	= 0x6826ul,
> +
> +	/* Natural-Width Host State Fields */
> +	HOST_CR0		= 0x6c00ul,
> +	HOST_CR3		= 0x6c02ul,
> +	HOST_CR4		= 0x6c04ul,
> +	HOST_BASE_FS		= 0x6c06ul,
> +	HOST_BASE_GS		= 0x6c08ul,
> +	HOST_BASE_TR		= 0x6c0aul,
> +	HOST_BASE_GDTR		= 0x6c0cul,
> +	HOST_BASE_IDTR		= 0x6c0eul,
> +	HOST_SYSENTER_ESP	= 0x6c10ul,
> +	HOST_SYSENTER_EIP	= 0x6c12ul,
> +	HOST_RSP		= 0x6c14ul,
> +	HOST_RIP		= 0x6c16ul
> +};
> +
> +enum Reason {
> +	VMX_EXC_NMI		= 0,
> +	VMX_EXTINT		= 1,
> +	VMX_TRIPLE_FAULT	= 2,
> +	VMX_INIT		= 3,
> +	VMX_SIPI		= 4,
> +	VMX_SMI_IO		= 5,
> +	VMX_SMI_OTHER		= 6,
> +	VMX_INTR_WINDOW		= 7,
> +	VMX_NMI_WINDOW		= 8,
> +	VMX_TASK_SWITCH		= 9,
> +	VMX_CPUID		= 10,
> +	VMX_GETSEC		= 11,
> +	VMX_HLT			= 12,
> +	VMX_INVD		= 13,
> +	VMX_INVLPG		= 14,
> +	VMX_RDPMC		= 15,
> +	VMX_RDTSC		= 16,
> +	VMX_RSM			= 17,
> +	VMX_VMCALL		= 18,
> +	VMX_VMCLEAR		= 19,
> +	VMX_VMLAUNCH		= 20,
> +	VMX_VMPTRLD		= 21,
> +	VMX_VMPTRST		= 22,
> +	VMX_VMREAD		= 23,
> +	VMX_VMRESUME		= 24,
> +	VMX_VMWRITE		= 25,
> +	VMX_VMXOFF		= 26,
> +	VMX_VMXON		= 27,
> +	VMX_CR			= 28,
> +	VMX_DR			= 29,
> +	VMX_IO			= 30,
> +	VMX_RDMSR		= 31,
> +	VMX_WRMSR		= 32,
> +	VMX_FAIL_STATE		= 33,
> +	VMX_FAIL_MSR		= 34,
> +	VMX_MWAIT		= 36,
> +	VMX_MTF			= 37,
> +	VMX_MONITOR		= 39,
> +	VMX_PAUSE		= 40,
> +	VMX_FAIL_MCHECK		= 41,
> +	VMX_TPR_THRESHOLD	= 43,
> +	VMX_APIC_ACCESS		= 44,
> +	VMX_GDTR_IDTR		= 46,
> +	VMX_LDTR_TR		= 47,
> +	VMX_EPT_VIOLATION	= 48,
> +	VMX_EPT_MISCONFIG	= 49,
> +	VMX_INVEPT		= 50,
> +	VMX_PREEMPT		= 52,
> +	VMX_INVVPID		= 53,
> +	VMX_WBINVD		= 54,
> +	VMX_XSETBV		= 55
> +};
> +
> +#define X86_EFLAGS_CF	0x00000001 /* Carry Flag */
> +#define X86_EFLAGS_ZF	0x00000040 /* Zero Flag */
> +
> +enum Ctrl_exi {
> +	EXI_HOST_64             = 1UL << 9,
> +	EXI_LOAD_PERF		= 1UL << 12,
> +	EXI_INTA                = 1UL << 15,
> +	EXI_LOAD_EFER           = 1UL << 21,
> +};
> +
> +enum Ctrl_ent {
> +	ENT_GUEST_64            = 1UL << 9,
> +	ENT_LOAD_EFER           = 1UL << 15,
> +};
> +
> +enum Ctrl_pin {
> +	PIN_EXTINT              = 1ul << 0,
> +	PIN_NMI                 = 1ul << 3,
> +	PIN_VIRT_NMI            = 1ul << 5,
> +};
> +
> +enum Ctrl0 {
> +	CPU_INTR_WINDOW		= 1ul << 2,
> +	CPU_HLT			= 1ul << 7,
> +	CPU_INVLPG		= 1ul << 9,
> +	CPU_CR3_LOAD		= 1ul << 15,
> +	CPU_CR3_STORE		= 1ul << 16,
> +	CPU_TPR_SHADOW		= 1ul << 21,
> +	CPU_NMI_WINDOW		= 1ul << 22,
> +	CPU_IO			= 1ul << 24,
> +	CPU_IO_BITMAP		= 1ul << 25,
> +	CPU_SECONDARY		= 1ul << 31,
> +};
> +
> +enum Ctrl1 {
> +	CPU_EPT			= 1ul << 1,
> +	CPU_VPID		= 1ul << 5,
> +	CPU_URG			= 1ul << 7,
> +};
> +
> +#define SEL_NULL_DESC		0x0
> +#define SEL_KERN_CODE_64	0x8
> +#define SEL_KERN_DATA_64	0x10
> +#define SEL_USER_CODE_64	0x18
> +#define SEL_USER_DATA_64	0x20
> +#define SEL_CODE_32		0x28
> +#define SEL_DATA_32		0x30
> +#define SEL_CODE_16		0x38
> +#define SEL_DATA_16		0x40
> +#define SEL_TSS_RUN		0x48
> +
> +#define SAVE_GPR				\
> +	"xchg %rax, regs\n\t"			\
> +	"xchg %rbx, regs+0x8\n\t"		\
> +	"xchg %rcx, regs+0x10\n\t"		\
> +	"xchg %rdx, regs+0x18\n\t"		\
> +	"xchg %rbp, regs+0x28\n\t"		\
> +	"xchg %rsi, regs+0x30\n\t"		\
> +	"xchg %rdi, regs+0x38\n\t"		\
> +	"xchg %r8, regs+0x40\n\t"		\
> +	"xchg %r9, regs+0x48\n\t"		\
> +	"xchg %r10, regs+0x50\n\t"		\
> +	"xchg %r11, regs+0x58\n\t"		\
> +	"xchg %r12, regs+0x60\n\t"		\
> +	"xchg %r13, regs+0x68\n\t"		\
> +	"xchg %r14, regs+0x70\n\t"		\
> +	"xchg %r15, regs+0x78\n\t"
> +
> +#define LOAD_GPR	SAVE_GPR
> +
> +#define CR0_PE		(1ul << 0)
> +#define CR0_PG		(1ul << 31)
> +#define CR4_VMXE	(1ul << 0)
> +#define CR4_PAE		(1ul << 5)
> +#define CR4_PCIDE	(1ul << 17)
> +
> +#define VMX_IO_SIZE_MASK		0x7
> +#define _VMX_IO_BYTE			1
> +#define _VMX_IO_WORD			2
> +#define _VMX_IO_LONG			3
> +#define VMX_IO_DIRECTION_MASK		(1ul << 3)
> +#define VMX_IO_IN			(1ul << 3)
> +#define VMX_IO_OUT			0
> +#define VMX_IO_STRING			(1ul << 4)
> +#define VMX_IO_REP			(1ul << 5)
> +#define VMX_IO_OPRAND_DX		(1ul << 6)
> +#define VMX_IO_PORT_MASK		0xFFFF0000
> +#define VMX_IO_PORT_SHIFT		16
> +
> +#define TEST_VMRESUME		0x1001
> +
> +#endif
> +
>