From: Binbin Wu <binbin.wu@linux.intel.com>
To: Robert Hoo <robert.hu@linux.intel.com>,
seanjc@google.com, pbonzini@redhat.com, chao.gao@intel.com
Cc: kvm@vger.kernel.org
Subject: Re: [PATCH v5 4/5] KVM: x86: emulation: Apply LAM mask when emulating data access in 64-bit mode
Date: Fri, 3 Mar 2023 18:18:30 +0800 [thread overview]
Message-ID: <c5fe1e65-60dd-fc53-8239-e8e181d66208@linux.intel.com> (raw)
In-Reply-To: <e87a40cd49200d7cd7178cc7839ce1ffdf587ff4.camel@linux.intel.com>
On 3/3/2023 5:00 PM, Robert Hoo wrote:
> On Fri, 2023-03-03 at 11:35 +0800, Binbin Wu wrote:
>>>>>> Also the instruction INVLPG, INVPCID should have some special
>>>>>> handling
>>>>>> since LAM is not applied to the memory operand of the two
>>>>>> instruction
>>>>>> according to the LAM spec.
>>>>> The spec's meaning on these 2 is: LAM masking doesn't apply to
>>>>> their
>>>>> operands (the address), so the behavior is like before LAM
>>>>> feature
>>>>> introduced. No change.
>>>> Yes, LAM are not applied to the 2 instrustions, but the
>>>> __linearize
>>>> is
>>>> changed.
>>>> For example, the emulation of invlpg (em_invpg) will also call
>>>> it.
> Can you elaborate more on this? what emulation case of INVLPG? do you
> mean vm-exit handling due to Guest execute INVLPG when
> VMCS_control.INVLPG_exiting set? or other case?
Not the vm-exit handling code. em_invpg() belongs to instruction emulation.
But I am not sure this code is reachable or not. Let me double check.
>
>>>> So
>>>> need to handle the case specificlly.
>>>> Can add a flag as the input of linearize to indicate the LAM
>>>> check
>>>> and
>>>> untag is needed or not.
>>>>
>>> No need.
>>>
>>> "The INVLPG instruction ...
>>> LAM does not apply to the specified memory address. Thus, in 64-bit
>>> mode, ** if the memory address specified is in non-canonical form
>>> then
>>> the INVLPG is the same as a NOP. **
>> Based on current patch, if the address of invlpg is non-canonical,
>> it
>> will be first checked and converted by the new LAM handling.
>> After that, I will be canonical and do the invalidition, but not NOP.
>> Maybe we can say do an additional TLB invalidation may be no big
>> different as NOP, but it need to be documented/comment somewhere
>>
>>
>>> The INVPCID instruction ...
>>> LAM does not apply to the specified memory address, and in 64-bit
>>> mode ** if this memory address is in non-canonical form then the
>>> processor generates a #GP(0) exception. **"
>>>
>>> You can double confirm in SDM: Before-and-After LAM introduced, the
>>> behavior hasn't changed. Thus you don't need to worry about these 2
>>> INS's emulations.
>> This is because currently, VMX vmexit handling is not considered yet.
>> The linear address of guest is retrived from get_vmx_mem_address,
>> which
>> is also will be called by INVPCID.
> Again, nested LAM isn't in this patch set's scope.
> In terms of handle_invpcid() --> get_vmx_mem_address(), per Spec, no
> behavior changes, no changes needed.
OK.
>> What arguable is that we need to cover all supervisor mode pointer
>> cases
>> in this phase.
>> But IMO if thesel cases are not covered, CR4.LAM_SUP should be not
>> allow
>> to be set by guest.
>>
next prev parent reply other threads:[~2023-03-03 10:18 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-02-27 8:45 [PATCH v5 0/5] Linear Address Masking (LAM) KVM Enabling Robert Hoo
2023-02-27 8:45 ` [PATCH v5 1/5] KVM: x86: Virtualize CR4.LAM_SUP Robert Hoo
2023-03-02 7:17 ` Chao Gao
2023-03-02 12:03 ` Binbin Wu
2023-03-02 13:00 ` Robert Hoo
2023-02-27 8:45 ` [PATCH v5 2/5] [Trivial]KVM: x86: Explicitly cast ulong to bool in kvm_set_cr3() Robert Hoo
2023-03-02 7:24 ` Chao Gao
2023-03-03 3:23 ` Robert Hoo
2023-03-10 20:22 ` Sean Christopherson
2023-03-20 12:05 ` Binbin Wu
2023-03-20 13:56 ` Binbin Wu
2023-03-21 16:03 ` Sean Christopherson
2023-02-27 8:45 ` [PATCH v5 3/5] KVM: x86: Virtualize CR3.LAM_{U48,U57} Robert Hoo
2023-03-03 6:21 ` Chao Gao
2023-03-03 14:23 ` Robert Hoo
2023-03-03 15:53 ` Chao Gao
2023-03-05 1:31 ` Robert Hoo
2023-03-10 20:12 ` Sean Christopherson
2023-03-20 6:57 ` Binbin Wu
2023-02-27 8:45 ` [PATCH v5 4/5] KVM: x86: emulation: Apply LAM mask when emulating data access in 64-bit mode Robert Hoo
2023-03-02 6:41 ` Binbin Wu
2023-03-02 13:16 ` Robert Hoo
2023-03-03 1:08 ` Binbin Wu
2023-03-03 3:16 ` Robert Hoo
2023-03-03 3:35 ` Binbin Wu
2023-03-03 9:00 ` Robert Hoo
2023-03-03 10:18 ` Binbin Wu [this message]
2023-03-10 20:26 ` Sean Christopherson
2023-03-02 8:55 ` Chao Gao
2023-03-02 11:31 ` Binbin Wu
2023-03-10 20:23 ` Sean Christopherson
2023-02-27 8:45 ` [PATCH v5 5/5] KVM: x86: LAM: Expose LAM CPUID to user space VMM Robert Hoo
2023-03-03 6:46 ` Chao Gao
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=c5fe1e65-60dd-fc53-8239-e8e181d66208@linux.intel.com \
--to=binbin.wu@linux.intel.com \
--cc=chao.gao@intel.com \
--cc=kvm@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=robert.hu@linux.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;
as well as URLs for NNTP newsgroup(s).