Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Thu, 6 Oct 2022 18:44:43 -0700
From:   "pawan.kumar.gupta@linux.intel.com" 
        <pawan.kumar.gupta@linux.intel.com>
To:     Andrew Cooper <Andrew.Cooper3@citrix.com>
Cc:     Suraj Jitindar Singh <surajjs@amazon.com>,
        "kvm@vger.kernel.org" <kvm@vger.kernel.org>,
        "sjitindarsingh@gmail.com" <sjitindarsingh@gmail.com>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "x86@kernel.org" <x86@kernel.org>,
        "tglx@linutronix.de" <tglx@linutronix.de>,
        "mingo@redhat.com" <mingo@redhat.com>, "bp@suse.de" <bp@suse.de>,
        "dave.hansen@linux.intel.com" <dave.hansen@linux.intel.com>,
        "seanjc@google.com" <seanjc@google.com>,
        "pbonzini@redhat.com" <pbonzini@redhat.com>,
        "peterz@infradead.org" <peterz@infradead.org>,
        "jpoimboe@kernel.org" <jpoimboe@kernel.org>,
        "daniel.sneddon@linux.intel.com" <daniel.sneddon@linux.intel.com>,
        "benh@kernel.crashing.org" <benh@kernel.crashing.org>,
        "stable@vger.kernel.org" <stable@vger.kernel.org>
Subject: Re: [PATCH] x86/speculation: Mitigate eIBRS PBRSB predictions with
 WRMSR
Message-ID: <20221007014443.flhhnzrtdmcsst3x@desk>
References: <20221005220227.1959-1-surajjs@amazon.com>
 <11ebe489-0734-28af-07a4-f658709cfd9e@citrix.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <11ebe489-0734-28af-07a4-f658709cfd9e@citrix.com>
Precedence: bulk

On Thu, Oct 06, 2022 at 02:42:10AM +0000, Andrew Cooper wrote:
>On 05/10/2022 23:02, Suraj Jitindar Singh wrote:
>> == Solution ==
>>
>> The WRMSR instruction can be used as a speculation barrier and a serialising
>> instruction. Use this on the VM exit path instead to ensure that a CALL
>> instruction (in this case the call to vmx_spec_ctrl_restore_host) has retired
>> before the prediction of a following unbalanced RET.
>
>While both of these sentences are true statements, you've missed the
>necessary safety property.
>
>One CALL has to retire before *any* RET can execute.
>
>There are several ways the frontend can end up eventually consuming the
>bad RSB entry; they all stem from an execute (not prediction) of the
>next RET instruction.
>
>As to the change, ...
>
>> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
>> index c9b49a09e6b5..fdcd8e10c2ab 100644
>> --- a/arch/x86/kvm/vmx/vmx.c
>> +++ b/arch/x86/kvm/vmx/vmx.c
>> @@ -7049,8 +7049,13 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx,
>
>... out of context above this hunk is:
>
>    if (!cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL))
>        return;
>
>meaning that there is a return instruction which is programmatically
>reachable ahead of the WRMSR.
>
>Whether it is speculatively reachable depends on whether the frontend
>can see through the _static_cpu_has(), as well as
>X86_FEATURE_MSR_SPEC_CTRL never becoming compile time evaluable.

In this case wouldn't _static_cpu_has() be runtime patched to a JMP
(<+8> below) or a NOP? RET (at <+13>) should not be reachable even
speculatively. What am I missing?

Dump of assembler code for function vmx_spec_ctrl_restore_host:

   arch/x86/kvm/vmx/vmx.c:
                 u64 hostval = this_cpu_read(x86_spec_ctrl_current);
   		<+0>:     mov    %gs:0x7e022e60(%rip),%r8        # 0x1ad48 <x86_spec_ctrl_current>

   ./arch/x86/include/asm/cpufeature.h:
                 asm_volatile_goto(
   		<+8>:     jmp    <vmx_spec_ctrl_restore_host+14>
   		<+10>:    nopl   (%rax)
   		<+13>:    ret

   arch/x86/kvm/vmx/vmx.c:
                 if (flags & VMX_RUN_SAVE_SPEC_CTRL)
   		<+14>:    and    $0x2,%esi
   		<+17>:    je     <vmx_spec_ctrl_restore_host+40>
   [...]