RE: [PATCH v2 2/6] x86/entry/64: Convert SYSRET validation tests to C

[Li, Xin3]

> @@ -84,6 +85,43 @@ __visible noinstr void do_syscall_64(struct pt_regs *regs, int
> nr)
> 
>  	instrumentation_end();
>  	syscall_exit_to_user_mode(regs);

Would it be better to make the following code a new function?

And then the similar changes in patch 6 could be merged into the new
function with #ifdef CONFIG_X86_64.

> +
> +	/*
> +	 * Check that the register state is valid for using SYSRET to exit
> +	 * to userspace.  Otherwise use the slower but fully capable IRET
> +	 * exit path.
> +	 */
> +
> +	/* XEN PV guests always use IRET path */
> +	if (cpu_feature_enabled(X86_FEATURE_XENPV))
> +		return false;
> +
> +	/* SYSRET requires RCX == RIP and R11 == EFLAGS */
> +	if (unlikely(regs->cx != regs->ip || regs->r11 != regs->flags))
> +		return false;
> +
> +	/* CS and SS must match the values set in MSR_STAR */
> +	if (unlikely(regs->cs != __USER_CS || regs->ss != __USER_DS))
> +		return false;
> +
> +	/*
> +	 * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
> +	 * in kernel space.  This essentially lets the user take over
> +	 * the kernel, since userspace controls RSP.
> +	 */
> +	if (unlikely(!__is_canonical_address(regs->ip, __VIRTUAL_MASK_SHIFT +
> 1)))
> +		return false;
> +
> +	/*
> +	 * SYSRET cannot restore RF.  It can restore TF, but unlike IRET,
> +	 * restoring TF results in a trap from userspace immediately after
> +	 * SYSRET.
> +	 */
> +	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)))
> +		return false;
> +
> +	/* Use SYSRET to exit to userspace */
> +	return true;
>  }
>  #endif
>