public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: "Yang, Weijiang" <weijiang.yang@intel.com>
To: Sean Christopherson <seanjc@google.com>
Cc: Rick P Edgecombe <rick.p.edgecombe@intel.com>,
	Chao Gao <chao.gao@intel.com>,
	Dave Hansen <dave.hansen@intel.com>,
	"peterz@infradead.org" <peterz@infradead.org>,
	"john.allen@amd.com" <john.allen@amd.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"pbonzini@redhat.com" <pbonzini@redhat.com>,
	"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
	"mlevitsk@redhat.com" <mlevitsk@redhat.com>
Subject: Re: [PATCH v8 00/26] Enable CET Virtualization
Date: Thu, 11 Jan 2024 22:56:55 +0800	[thread overview]
Message-ID: <cf043809-430a-4072-b0fd-201cd469b602@intel.com> (raw)
In-Reply-To: <ZZ1h9GW93ckc3FlE@google.com>

On 1/9/2024 11:10 PM, Sean Christopherson wrote:
> On Mon, Jan 08, 2024, Weijiang Yang wrote:
>> On 1/6/2024 12:21 AM, Sean Christopherson wrote:
>>> On Fri, Jan 05, 2024, Weijiang Yang wrote:
>>>> On 1/5/2024 8:54 AM, Sean Christopherson wrote:
>>>>> On Fri, Jan 05, 2024, Rick P Edgecombe wrote:
>>>>>>> For CALL/RET (and presumably any branch instructions with IBT?) other
>>>>>>> instructions that are directly affected by CET, the simplest thing would
>>>>>>> probably be to disable those in KVM's emulator if shadow stacks and/or IBT
>>>>>>> are enabled, and let KVM's failure paths take it from there.
>>>>>> Right, that is what I was wondering might be the normal solution for
>>>>>> situations like this.
>>>>> If KVM can't emulate something, it either retries the instruction (with some
>>>>> decent logic to guard against infinite retries) or punts to userspace.
>>>> What kind of error is proper if KVM has to punt to userspace?
>>> KVM_INTERNAL_ERROR_EMULATION.  See prepare_emulation_failure_exit().
>>>
>>>> Or just inject #UD into guest on detecting this case?
>>> No, do not inject #UD or do anything else that deviates from architecturally
>>> defined behavior.
>> Thanks!
>> But based on current KVM implementation and patch 24, seems that if CET is exposed
>> to guest, the emulation code or shadow paging mode couldn't be activated at the same time:
> No, requiring unrestricted guest only disables the paths where KVM *delibeately*
> emulates the entire guest code stream.  In no way, shape, or form does it prevent
> KVM from attempting to emulate arbitrary instructions.

Yes, also need to prevent sporadic emulation, how about adding below patch in emulator?


diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e223043ef5b2..e817d8560ceb 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -178,6 +178,7 @@
  #define IncSP       ((u64)1 << 54)  /* SP is incremented before ModRM calc */
  #define TwoMemOp    ((u64)1 << 55)  /* Instruction has two memory operand */
  #define IsBranch    ((u64)1 << 56)  /* Instruction is considered a branch. */
+#define IsProtected ((u64)1 << 57)  /* Instruction is protected by CET. */

  #define DstXacc     (DstAccLo | SrcAccHi | SrcWrite)

@@ -4098,9 +4099,9 @@ static const struct opcode group4[] = {
  static const struct opcode group5[] = {
         F(DstMem | SrcNone | Lock,              em_inc),
         F(DstMem | SrcNone | Lock,              em_dec),
-       I(SrcMem | NearBranch | IsBranch,       em_call_near_abs),
-       I(SrcMemFAddr | ImplicitOps | IsBranch, em_call_far),
-       I(SrcMem | NearBranch | IsBranch,       em_jmp_abs),
+       I(SrcMem | NearBranch | IsBranch | IsProtected, em_call_near_abs),
+       I(SrcMemFAddr | ImplicitOps | IsBranch | IsProtected, em_call_far),
+       I(SrcMem | NearBranch | IsBranch | IsProtected, em_jmp_abs),
         I(SrcMemFAddr | ImplicitOps | IsBranch, em_jmp_far),
         I(SrcMem | Stack | TwoMemOp,            em_push), D(Undefined),
  };
@@ -4362,11 +4363,11 @@ static const struct opcode opcode_table[256] = {
         /* 0xC8 - 0xCF */
         I(Stack | SrcImmU16 | Src2ImmByte | IsBranch, em_enter),
         I(Stack | IsBranch, em_leave),
-       I(ImplicitOps | SrcImmU16 | IsBranch, em_ret_far_imm),
-       I(ImplicitOps | IsBranch, em_ret_far),
-       D(ImplicitOps | IsBranch), DI(SrcImmByte | IsBranch, intn),
+       I(ImplicitOps | SrcImmU16 | IsBranch | IsProtected, em_ret_far_imm),
+       I(ImplicitOps | IsBranch | IsProtected, em_ret_far),
+       D(ImplicitOps | IsBranch), DI(SrcImmByte | IsBranch | IsProtected, intn),
         D(ImplicitOps | No64 | IsBranch),
-       II(ImplicitOps | IsBranch, em_iret, iret),
+       II(ImplicitOps | IsBranch | IsProtected, em_iret, iret),
         /* 0xD0 - 0xD7 */
         G(Src2One | ByteOp, group2), G(Src2One, group2),
         G(Src2CL | ByteOp, group2), G(Src2CL, group2),
@@ -4382,7 +4383,7 @@ static const struct opcode opcode_table[256] = {
         I2bvIP(SrcImmUByte | DstAcc, em_in,  in,  check_perm_in),
         I2bvIP(SrcAcc | DstImmUByte, em_out, out, check_perm_out),
         /* 0xE8 - 0xEF */
-       I(SrcImm | NearBranch | IsBranch, em_call),
+       I(SrcImm | NearBranch | IsBranch | IsProtected, em_call),
         D(SrcImm | ImplicitOps | NearBranch | IsBranch),
         I(SrcImmFAddr | No64 | IsBranch, em_jmp_far),
         D(SrcImmByte | ImplicitOps | NearBranch | IsBranch),
@@ -4401,7 +4402,7 @@ static const struct opcode opcode_table[256] = {
  static const struct opcode twobyte_table[256] = {
         /* 0x00 - 0x0F */
         G(0, group6), GD(0, &group7), N, N,
-       N, I(ImplicitOps | EmulateOnUD | IsBranch, em_syscall),
+       N, I(ImplicitOps | EmulateOnUD | IsBranch | IsProtected, em_syscall),
         II(ImplicitOps | Priv, em_clts, clts), N,
         DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N,
         N, D(ImplicitOps | ModRM | SrcMem | NoAccess), N, N,
@@ -4432,8 +4433,8 @@ static const struct opcode twobyte_table[256] = {
         IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc),
         II(ImplicitOps | Priv, em_rdmsr, rdmsr),
         IIP(ImplicitOps, em_rdpmc, rdpmc, check_rdpmc),
-       I(ImplicitOps | EmulateOnUD | IsBranch, em_sysenter),
-       I(ImplicitOps | Priv | EmulateOnUD | IsBranch, em_sysexit),
+       I(ImplicitOps | EmulateOnUD | IsBranch | IsProtected, em_sysenter),
+       I(ImplicitOps | Priv | EmulateOnUD | IsBranch | IsProtected, em_sysexit),
         N, N,
         N, N, N, N, N, N, N, N,
         /* 0x40 - 0x4F */
@@ -4971,6 +4972,12 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int
         if (ctxt->d == 0)
                 return EMULATION_FAILED;
+       if ((opcode.flags & IsProtected) &&
+           (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_CET)) {
+               WARN_ONCE(1, "CET is active, emulation aborted.\n");
+               return EMULATION_FAILED;
+       }
+
         ctxt->execute = opcode.u.execute;

         if (unlikely(emulation_type & EMULTYPE_TRAP_UD) &&


  reply	other threads:[~2024-01-11 14:57 UTC|newest]

Thread overview: 75+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-12-21 14:02 [PATCH v8 00/26] Enable CET Virtualization Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 01/26] x86/fpu/xstate: Always preserve non-user xfeatures/flags in __state_perm Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 02/26] x86/fpu/xstate: Refine CET user xstate bit enabling Yang Weijiang
2024-01-02 22:24   ` Maxim Levitsky
2023-12-21 14:02 ` [PATCH v8 03/26] x86/fpu/xstate: Add CET supervisor mode state support Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 04/26] x86/fpu/xstate: Introduce XFEATURE_MASK_KERNEL_DYNAMIC xfeature set Yang Weijiang
2024-01-02 22:25   ` Maxim Levitsky
2024-01-03  9:10     ` Yang, Weijiang
2024-01-04 22:26     ` Edgecombe, Rick P
2024-01-04 22:26   ` Edgecombe, Rick P
2023-12-21 14:02 ` [PATCH v8 05/26] x86/fpu/xstate: Introduce fpu_guest_cfg for guest FPU configuration Yang Weijiang
2024-01-02 22:32   ` Maxim Levitsky
2024-01-03  9:17     ` Yang, Weijiang
2024-01-04 22:42     ` Edgecombe, Rick P
2023-12-21 14:02 ` [PATCH v8 06/26] x86/fpu/xstate: Create guest fpstate with guest specific config Yang Weijiang
2024-01-02 22:32   ` Maxim Levitsky
2024-01-03 18:16   ` Edgecombe, Rick P
2024-01-04  2:16     ` Yang, Weijiang
2024-01-04 22:47   ` Edgecombe, Rick P
2024-01-05  8:16     ` Yang, Weijiang
2023-12-21 14:02 ` [PATCH v8 07/26] x86/fpu/xstate: Warn if kernel dynamic xfeatures detected in normal fpstate Yang Weijiang
2024-01-02 22:33   ` Maxim Levitsky
2023-12-21 14:02 ` [PATCH v8 08/26] KVM: x86: Rework cpuid_get_supported_xcr0() to operate on vCPU data Yang Weijiang
2024-01-02 22:33   ` Maxim Levitsky
2023-12-21 14:02 ` [PATCH v8 09/26] KVM: x86: Rename kvm_{g,s}et_msr() to menifest emulation operations Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 10/26] KVM: x86: Refine xsave-managed guest register/MSR reset handling Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 11/26] KVM: x86: Add kvm_msr_{read,write}() helpers Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 12/26] KVM: x86: Report XSS as to-be-saved if there are supported features Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 13/26] KVM: x86: Refresh CPUID on write to guest MSR_IA32_XSS Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 14/26] KVM: x86: Initialize kvm_caps.supported_xss Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 15/26] KVM: x86: Load guest FPU state when access XSAVE-managed MSRs Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 16/26] KVM: x86: Add fault checks for guest CR4.CET setting Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 17/26] KVM: x86: Report KVM supported CET MSRs as to-be-saved Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 18/26] KVM: VMX: Introduce CET VMCS fields and control bits Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 19/26] KVM: x86: Use KVM-governed feature framework to track "SHSTK/IBT enabled" Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 20/26] KVM: VMX: Emulate read and write to CET MSRs Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 21/26] KVM: x86: Save and reload SSP to/from SMRAM Yang Weijiang
2024-01-02 22:34   ` Maxim Levitsky
2023-12-21 14:02 ` [PATCH v8 22/26] KVM: VMX: Set up interception for CET MSRs Yang Weijiang
2024-01-02 22:34   ` Maxim Levitsky
2024-01-15  9:58   ` Yuan Yao
2024-01-17  1:41     ` Yang, Weijiang
2024-01-17  1:58       ` Yang, Weijiang
2024-01-17  5:31         ` Yuan Yao
2024-01-17  6:16           ` Yang, Weijiang
2023-12-21 14:02 ` [PATCH v8 23/26] KVM: VMX: Set host constant supervisor states to VMCS fields Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 24/26] KVM: x86: Enable CET virtualization for VMX and advertise to userspace Yang Weijiang
2024-01-02 22:34   ` Maxim Levitsky
2024-01-16  7:25   ` Yuan Yao
2024-01-17  1:43     ` Yang, Weijiang
2023-12-21 14:02 ` [PATCH v8 25/26] KVM: nVMX: Introduce new VMX_BASIC bit for event error_code delivery to L1 Yang Weijiang
2023-12-21 14:02 ` [PATCH v8 26/26] KVM: nVMX: Enable CET support for nested guest Yang Weijiang
2024-01-02 22:35   ` Maxim Levitsky
2024-01-16  7:22   ` Yuan Yao
2024-01-17  1:53     ` Yang, Weijiang
2024-01-03 18:50 ` [PATCH v8 00/26] Enable CET Virtualization Edgecombe, Rick P
2024-01-04  7:11   ` Yang, Weijiang
2024-01-04 21:10     ` Edgecombe, Rick P
2024-01-05  0:22       ` Sean Christopherson
2024-01-05  0:34         ` Edgecombe, Rick P
2024-01-05  0:44           ` Jim Mattson
2024-01-05  0:54           ` Sean Christopherson
2024-01-05  9:28             ` Yang, Weijiang
2024-01-05 16:21               ` Sean Christopherson
2024-01-05 17:52                 ` Edgecombe, Rick P
2024-01-05 18:09                   ` Jim Mattson
2024-01-05 18:51                     ` Edgecombe, Rick P
2024-01-05 19:34                       ` Sean Christopherson
2024-01-08 14:17                 ` Yang, Weijiang
2024-01-09 15:10                   ` Sean Christopherson
2024-01-11 14:56                     ` Yang, Weijiang [this message]
2024-01-15  1:55                       ` Chao Gao
2024-01-17  0:53                         ` Yang, Weijiang
2024-01-05  9:04       ` Yang, Weijiang
2024-01-04 22:29 ` Edgecombe, Rick P

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=cf043809-430a-4072-b0fd-201cd469b602@intel.com \
    --to=weijiang.yang@intel.com \
    --cc=chao.gao@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=john.allen@amd.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mlevitsk@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rick.p.edgecombe@intel.com \
    --cc=seanjc@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox