vmenter.S

/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/linkage.h>
#include <asm/asm.h>
#include <asm/bitsperlong.h>
#include <asm/kvm_vcpu_regs.h>
#include <asm/nospec-branch.h>
#include <asm/percpu.h>
#include <asm/segment.h>
#include "kvm-asm-offsets.h"
#include "run_flags.h"

#define WORD_SIZE (BITS_PER_LONG / 8)

#define VCPU_RAX	__VCPU_REGS_RAX * WORD_SIZE
#define VCPU_RCX	__VCPU_REGS_RCX * WORD_SIZE
#define VCPU_RDX	__VCPU_REGS_RDX * WORD_SIZE
#define VCPU_RBX	__VCPU_REGS_RBX * WORD_SIZE
/* Intentionally omit RSP as it's context switched by hardware */
#define VCPU_RBP	__VCPU_REGS_RBP * WORD_SIZE
#define VCPU_RSI	__VCPU_REGS_RSI * WORD_SIZE
#define VCPU_RDI	__VCPU_REGS_RDI * WORD_SIZE

#ifdef CONFIG_X86_64
#define VCPU_R8		__VCPU_REGS_R8  * WORD_SIZE
#define VCPU_R9		__VCPU_REGS_R9  * WORD_SIZE
#define VCPU_R10	__VCPU_REGS_R10 * WORD_SIZE
#define VCPU_R11	__VCPU_REGS_R11 * WORD_SIZE
#define VCPU_R12	__VCPU_REGS_R12 * WORD_SIZE
#define VCPU_R13	__VCPU_REGS_R13 * WORD_SIZE
#define VCPU_R14	__VCPU_REGS_R14 * WORD_SIZE
#define VCPU_R15	__VCPU_REGS_R15 * WORD_SIZE
#endif

.macro VMX_DO_EVENT_IRQOFF call_insn call_target
	/*
	 * Unconditionally create a stack frame, getting the correct RSP on the
	 * stack (for x86-64) would take two instructions anyways, and RBP can
	 * be used to restore RSP to make objtool happy (see below).
	 */
	push %_ASM_BP
	mov %_ASM_SP, %_ASM_BP

#ifdef CONFIG_X86_64
	/*
	 * Align RSP to a 16-byte boundary (to emulate CPU behavior) before
	 * creating the synthetic interrupt stack frame for the IRQ/NMI.
	 */
	and  $-16, %rsp
	push $__KERNEL_DS
	push %rbp
#endif
	pushf
	push $__KERNEL_CS
	\call_insn \call_target

	/*
	 * "Restore" RSP from RBP, even though IRET has already unwound RSP to
	 * the correct value.  objtool doesn't know the callee will IRET and,
	 * without the explicit restore, thinks the stack is getting walloped.
	 * Using an unwind hint is problematic due to x86-64's dynamic alignment.
	 */
	leave
	RET
.endm

.section .noinstr.text, "ax"

/**
 * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode
 * @vmx:	struct vcpu_vmx *
 * @regs:	unsigned long * (to guest registers)
 * @flags:	VMX_RUN_VMRESUME:	use VMRESUME instead of VMLAUNCH
 *		VMX_RUN_SAVE_SPEC_CTRL: save guest SPEC_CTRL into vmx->spec_ctrl
 *		VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO: vCPU can access host MMIO
 *
 * Returns:
 *	0 on VM-Exit, 1 on VM-Fail
 */
SYM_FUNC_START(__vmx_vcpu_run)
	push %_ASM_BP
	mov  %_ASM_SP, %_ASM_BP
#ifdef CONFIG_X86_64
	push %r15
	push %r14
	push %r13
	push %r12
#else
	push %edi
	push %esi
#endif
	push %_ASM_BX

	/* Save @vmx for SPEC_CTRL handling */
	push %_ASM_ARG1

	/* Save @flags (used for VMLAUNCH vs. VMRESUME and mitigations). */
	push %_ASM_ARG3

	/*
	 * Save @regs, _ASM_ARG2 may be modified by vmx_update_host_rsp() and
	 * @regs is needed after VM-Exit to save the guest's register values.
	 */
	push %_ASM_ARG2

	lea (%_ASM_SP), %_ASM_ARG2
	call vmx_update_host_rsp

	ALTERNATIVE "jmp .Lspec_ctrl_done", "", X86_FEATURE_MSR_SPEC_CTRL

	/*
	 * SPEC_CTRL handling: if the guest's SPEC_CTRL value differs from the
	 * host's, write the MSR.
	 *
	 * IMPORTANT: To avoid RSB underflow attacks and any other nastiness,
	 * there must not be any returns or indirect branches between this code
	 * and vmentry.
	 */
	mov 2*WORD_SIZE(%_ASM_SP), %_ASM_DI
#ifdef CONFIG_X86_64
	mov VMX_spec_ctrl(%rdi), %rdx
	cmp PER_CPU_VAR(x86_spec_ctrl_current), %rdx
	je .Lspec_ctrl_done
	movl %edx, %eax
	shr $32, %rdx
#else
	mov VMX_spec_ctrl(%edi), %eax
	mov PER_CPU_VAR(x86_spec_ctrl_current), %ecx
	xor %eax, %ecx
	mov VMX_spec_ctrl + 4(%edi), %edx
	mov PER_CPU_VAR(x86_spec_ctrl_current + 4), %edi
	xor %edx, %edi
	or %edi, %ecx
	je .Lspec_ctrl_done
#endif
	mov $MSR_IA32_SPEC_CTRL, %ecx
	wrmsr

.Lspec_ctrl_done:

	/*
	 * Since vmentry is serializing on affected CPUs, there's no need for
	 * an LFENCE to stop speculation from skipping the wrmsr.
	 */

	/* Load @regs to RAX. */
	mov (%_ASM_SP), %_ASM_AX

	/* Load guest registers.  Don't clobber flags. */
	mov VCPU_RCX(%_ASM_AX), %_ASM_CX
	mov VCPU_RDX(%_ASM_AX), %_ASM_DX
	mov VCPU_RBX(%_ASM_AX), %_ASM_BX
	mov VCPU_RBP(%_ASM_AX), %_ASM_BP
	mov VCPU_RSI(%_ASM_AX), %_ASM_SI
	mov VCPU_RDI(%_ASM_AX), %_ASM_DI
#ifdef CONFIG_X86_64
	mov VCPU_R8 (%_ASM_AX),  %r8
	mov VCPU_R9 (%_ASM_AX),  %r9
	mov VCPU_R10(%_ASM_AX), %r10
	mov VCPU_R11(%_ASM_AX), %r11
	mov VCPU_R12(%_ASM_AX), %r12
	mov VCPU_R13(%_ASM_AX), %r13
	mov VCPU_R14(%_ASM_AX), %r14
	mov VCPU_R15(%_ASM_AX), %r15
#endif
	/* Load guest RAX.  This kills the @regs pointer! */
	mov VCPU_RAX(%_ASM_AX), %_ASM_AX

	/*
	 * Note, ALTERNATIVE_2 works in reverse order.  If CLEAR_CPU_BUF_VM is
	 * enabled, do VERW unconditionally.  If CPU_BUF_VM_MMIO is enabled,
	 * check @flags to see if the vCPU has access to host MMIO, and if so,
	 * do VERW.  Else, do nothing (no mitigations needed/enabled).
	 */
	ALTERNATIVE_2 "",									  \
		      __stringify(testl $VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO, WORD_SIZE(%_ASM_SP); \
				  jz .Lskip_mmio_verw;						  \
				  VERW;								  \
				  .Lskip_mmio_verw:),					  	  \
		      X86_FEATURE_CLEAR_CPU_BUF_VM_MMIO,					  \
		      __stringify(VERW), X86_FEATURE_CLEAR_CPU_BUF_VM

	/* Check @flags to see if VMLAUNCH or VMRESUME is needed. */
	testl $VMX_RUN_VMRESUME, WORD_SIZE(%_ASM_SP)
	jz .Lvmlaunch

	/*
	 * After a successful VMRESUME/VMLAUNCH, control flow "magically"
	 * resumes below at 'vmx_vmexit' due to the VMCS HOST_RIP setting.
	 * So this isn't a typical function and objtool needs to be told to
	 * save the unwind state here and restore it below.
	 */
	UNWIND_HINT_SAVE

/*
 * If VMRESUME/VMLAUNCH and corresponding vmexit succeed, execution resumes at
 * the 'vmx_vmexit' label below.
 */
.Lvmresume:
	vmresume
	jmp .Lvmfail

.Lvmlaunch:
	vmlaunch
	jmp .Lvmfail

	_ASM_EXTABLE(.Lvmresume, .Lfixup)
	_ASM_EXTABLE(.Lvmlaunch, .Lfixup)

SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL)

	/* Restore unwind state from before the VMRESUME/VMLAUNCH. */
	UNWIND_HINT_RESTORE
	ENDBR

	/* Temporarily save guest's RAX. */
	push %_ASM_AX

	/* Reload @regs to RAX. */
	mov WORD_SIZE(%_ASM_SP), %_ASM_AX

	/* Save all guest registers, including RAX from the stack */
	pop           VCPU_RAX(%_ASM_AX)
	mov %_ASM_CX, VCPU_RCX(%_ASM_AX)
	mov %_ASM_DX, VCPU_RDX(%_ASM_AX)
	mov %_ASM_BX, VCPU_RBX(%_ASM_AX)
	mov %_ASM_BP, VCPU_RBP(%_ASM_AX)
	mov %_ASM_SI, VCPU_RSI(%_ASM_AX)
	mov %_ASM_DI, VCPU_RDI(%_ASM_AX)
#ifdef CONFIG_X86_64
	mov %r8,  VCPU_R8 (%_ASM_AX)
	mov %r9,  VCPU_R9 (%_ASM_AX)
	mov %r10, VCPU_R10(%_ASM_AX)
	mov %r11, VCPU_R11(%_ASM_AX)
	mov %r12, VCPU_R12(%_ASM_AX)
	mov %r13, VCPU_R13(%_ASM_AX)
	mov %r14, VCPU_R14(%_ASM_AX)
	mov %r15, VCPU_R15(%_ASM_AX)
#endif

	/* Clear return value to indicate VM-Exit (as opposed to VM-Fail). */
	xor %ebx, %ebx

.Lclear_regs:
	/* Discard @regs.  The register is irrelevant, it just can't be RBX. */
	pop %_ASM_AX

	/*
	 * Clear all general purpose registers except RSP and RBX to prevent
	 * speculative use of the guest's values, even those that are reloaded
	 * via the stack.  In theory, an L1 cache miss when restoring registers
	 * could lead to speculative execution with the guest's values.
	 * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially
	 * free.  RSP and RBX are exempt as RSP is restored by hardware during
	 * VM-Exit and RBX is explicitly loaded with 0 or 1 to hold the return
	 * value.
	 */
	xor %eax, %eax
	xor %ecx, %ecx
	xor %edx, %edx
	xor %ebp, %ebp
	xor %esi, %esi
	xor %edi, %edi
#ifdef CONFIG_X86_64
	xor %r8d,  %r8d
	xor %r9d,  %r9d
	xor %r10d, %r10d
	xor %r11d, %r11d
	xor %r12d, %r12d
	xor %r13d, %r13d
	xor %r14d, %r14d
	xor %r15d, %r15d
#endif

	/*
	 * IMPORTANT: RSB filling and SPEC_CTRL handling must be done before
	 * the first unbalanced RET after vmexit!
	 *
	 * For retpoline or IBRS, RSB filling is needed to prevent poisoned RSB
	 * entries and (in some cases) RSB underflow.
	 *
	 * eIBRS has its own protection against poisoned RSB, so it doesn't
	 * need the RSB filling sequence.  But it does need to be enabled, and a
	 * single call to retire, before the first unbalanced RET.
	 */

	FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\
			   X86_FEATURE_RSB_VMEXIT_LITE

	pop %_ASM_ARG2	/* @flags */
	pop %_ASM_ARG1	/* @vmx */

	call vmx_spec_ctrl_restore_host

	CLEAR_BRANCH_HISTORY_VMEXIT

	/* Put return value in AX */
	mov %_ASM_BX, %_ASM_AX

	pop %_ASM_BX
#ifdef CONFIG_X86_64
	pop %r12
	pop %r13
	pop %r14
	pop %r15
#else
	pop %esi
	pop %edi
#endif
	pop %_ASM_BP
	RET

.Lfixup:
	cmpb $0, _ASM_RIP(kvm_rebooting)
	jne .Lvmfail
	ud2
.Lvmfail:
	/* VM-Fail: set return value to 1 */
	mov $1, %_ASM_BX
	jmp .Lclear_regs

SYM_FUNC_END(__vmx_vcpu_run)

SYM_FUNC_START(vmx_do_nmi_irqoff)
	VMX_DO_EVENT_IRQOFF call asm_exc_nmi_kvm_vmx
SYM_FUNC_END(vmx_do_nmi_irqoff)

#ifndef CONFIG_CC_HAS_ASM_GOTO_OUTPUT

/**
 * vmread_error_trampoline - Trampoline from inline asm to vmread_error()
 * @field:	VMCS field encoding that failed
 * @fault:	%true if the VMREAD faulted, %false if it failed
 *
 * Save and restore volatile registers across a call to vmread_error().  Note,
 * all parameters are passed on the stack.
 */
SYM_FUNC_START(vmread_error_trampoline)
	push %_ASM_BP
	mov  %_ASM_SP, %_ASM_BP

	push %_ASM_AX
	push %_ASM_CX
	push %_ASM_DX
#ifdef CONFIG_X86_64
	push %rdi
	push %rsi
	push %r8
	push %r9
	push %r10
	push %r11
#endif

	/* Load @field and @fault to arg1 and arg2 respectively. */
	mov 3*WORD_SIZE(%_ASM_BP), %_ASM_ARG2
	mov 2*WORD_SIZE(%_ASM_BP), %_ASM_ARG1

	call vmread_error_trampoline2

	/* Zero out @fault, which will be popped into the result register. */
	_ASM_MOV $0, 3*WORD_SIZE(%_ASM_BP)

#ifdef CONFIG_X86_64
	pop %r11
	pop %r10
	pop %r9
	pop %r8
	pop %rsi
	pop %rdi
#endif
	pop %_ASM_DX
	pop %_ASM_CX
	pop %_ASM_AX
	pop %_ASM_BP

	RET
SYM_FUNC_END(vmread_error_trampoline)
#endif

.section .text, "ax"

#ifndef CONFIG_X86_FRED

SYM_FUNC_START(vmx_do_interrupt_irqoff)
	VMX_DO_EVENT_IRQOFF CALL_NOSPEC _ASM_ARG1
SYM_FUNC_END(vmx_do_interrupt_irqoff)

#endif