Re: [PATCHv2.1 05/29] x86/tdx: Add HLT support for TDX guests

[Kirill A. Shutemov]

On Wed, Feb 09, 2022 at 06:05:52PM +0000, Sean Christopherson wrote:
> On Wed, Feb 09, 2022, Kirill A. Shutemov wrote:
> > On Mon, Feb 07, 2022 at 10:52:19PM +0000, Sean Christopherson wrote:
> > .Lskip_sti:
> > 	tdcall
> > 
> > 	/*
> > 	 * TDVMCALL leaf does not suppose to fail. If it fails something
> > 	 * is horribly wrong with TDX module. Stop the world.
> > 	 */
> > 	test %rax, %rax
> > 	je .Lsuccess
> > 	ud2
> 
> If the ud2 or call to an external "do panic" helper is out-of-line, then the happy
> path avoids a taken branch.  Not a big deal, but it's also trivial to do.

Something like this?

I assume FRAME_END is irrelevent after UD2.

SYM_FUNC_START(__tdx_hypercall)
	FRAME_BEGIN

	/* Save callee-saved GPRs as mandated by the x86_64 ABI */
	push %r15
	push %r14
	push %r13
	push %r12

	/* Mangle function call ABI into TDCALL ABI: */
	/* Set TDCALL leaf ID (TDVMCALL (0)) in RAX */
	xor %eax, %eax

	/* Copy hypercall registers from arg struct: */
	movq TDX_HYPERCALL_r10(%rdi), %r10
	movq TDX_HYPERCALL_r11(%rdi), %r11
	movq TDX_HYPERCALL_r12(%rdi), %r12
	movq TDX_HYPERCALL_r13(%rdi), %r13
	movq TDX_HYPERCALL_r14(%rdi), %r14
	movq TDX_HYPERCALL_r15(%rdi), %r15

	movl $TDVMCALL_EXPOSE_REGS_MASK, %ecx

	/*
	 * For the idle loop STI needs to be called directly before the TDCALL
	 * that enters idle (EXIT_REASON_HLT case). STI instruction enables
	 * interrupts only one instruction later. If there is a window between
	 * STI and the instruction that emulates the HALT state, there is a
	 * chance for interrupts to happen in this window, which can delay the
	 * HLT operation indefinitely. Since this is the not the desired
	 * result, conditionally call STI before TDCALL.
	 */
	testq $TDX_HCALL_ISSUE_STI, %rsi
	jz .Lskip_sti
	sti
.Lskip_sti:
	tdcall

	/*
	 * TDVMCALL leaf does not suppose to fail. If it fails something
	 * is horribly wrong with TDX module. Stop the world.
	 */
	testq %rax, %rax
	jne .Lpanic

	/* TDVMCALL leaf return code is in R10 */
	movq %r10, %rax

	/* Copy hypercall result registers to arg struct if needed */
	testq $TDX_HCALL_HAS_OUTPUT, %rsi
	jz .Lout

	movq %r10, TDX_HYPERCALL_r10(%rdi)
	movq %r11, TDX_HYPERCALL_r11(%rdi)
	movq %r12, TDX_HYPERCALL_r12(%rdi)
	movq %r13, TDX_HYPERCALL_r13(%rdi)
	movq %r14, TDX_HYPERCALL_r14(%rdi)
	movq %r15, TDX_HYPERCALL_r15(%rdi)
.Lout:
	/*
	 * Zero out registers exposed to the VMM to avoid speculative execution
	 * with VMM-controlled values. This needs to include all registers
	 * present in TDVMCALL_EXPOSE_REGS_MASK (except R12-R15). R12-R15
	 * context will be restored.
	 */
	xor %r10d, %r10d
	xor %r11d, %r11d

	/* Restore callee-saved GPRs as mandated by the x86_64 ABI */
	pop %r12
	pop %r13
	pop %r14
	pop %r15

	FRAME_END

	retq
.Lpanic:
	ud2
SYM_FUNC_END(__tdx_hypercall)
-- 
 Kirill A. Shutemov