Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:5 as permitted sender) client-ip=2620:137:e000::3:5;
Message-ID: <50076263-8b4f-4167-8419-e8baede7e9b0@maciej.szmigiero.name>
Date:   Mon, 27 Nov 2023 18:47:11 +0100
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH] KVM: x86: Allow XSAVES on CPUs where host doesn't use it
 due to an errata
Content-Language: en-US, pl-PL
To:     Sean Christopherson <seanjc@google.com>
Cc:     Paolo Bonzini <pbonzini@redhat.com>, kvm@vger.kernel.org,
        linux-kernel@vger.kernel.org
References: <c858817d3e3be246a1a2278e3b42d06284e615e5.1700766316.git.maciej.szmigiero@oracle.com>
 <ZWTQuRpwPkutHY-D@google.com>
From:   "Maciej S. Szmigiero" <mail@maciej.szmigiero.name>
Autocrypt: addr=mail@maciej.szmigiero.name; keydata=
 xsFNBFpGusUBEADXUMM2t7y9sHhI79+2QUnDdpauIBjZDukPZArwD+sDlx5P+jxaZ13XjUQc
 6oJdk+jpvKiyzlbKqlDtw/Y2Ob24tg1g/zvkHn8AVUwX+ZWWewSZ0vcwp7u/LvA+w2nJbIL1
 N0/QUUdmxfkWTHhNqgkNX5hEmYqhwUPozFR0zblfD/6+XFR7VM9yT0fZPLqYLNOmGfqAXlxY
 m8nWmi+lxkd/PYqQQwOq6GQwxjRFEvSc09m/YPYo9hxh7a6s8hAP88YOf2PD8oBB1r5E7KGb
 Fv10Qss4CU/3zaiyRTExWwOJnTQdzSbtnM3S8/ZO/sL0FY/b4VLtlZzERAraxHdnPn8GgxYk
 oPtAqoyf52RkCabL9dsXPWYQjkwG8WEUPScHDy8Uoo6imQujshG23A99iPuXcWc/5ld9mIo/
 Ee7kN50MOXwS4vCJSv0cMkVhh77CmGUv5++E/rPcbXPLTPeRVy6SHgdDhIj7elmx2Lgo0cyh
 uyxyBKSuzPvb61nh5EKAGL7kPqflNw7LJkInzHqKHDNu57rVuCHEx4yxcKNB4pdE2SgyPxs9
 9W7Cz0q2Hd7Yu8GOXvMfQfrBiEV4q4PzidUtV6sLqVq0RMK7LEi0RiZpthwxz0IUFwRw2KS/
 9Kgs9LmOXYimodrV0pMxpVqcyTepmDSoWzyXNP2NL1+GuQtaTQARAQABzTBNYWNpZWogUy4g
 U3ptaWdpZXJvIDxtYWlsQG1hY2llai5zem1pZ2llcm8ubmFtZT7CwZQEEwEIAD4CGwMFCwkI
 BwIGFQoJCAsCBBYCAwECHgECF4AWIQRyeg1N257Z9gOb7O+Ef143kM4JdwUCZHu3rAUJC4vC
 5wAKCRCEf143kM4Jdw74EAC6WUqhTI7MKKqJIjFpR3IxzqAKhoTl/lKPnhzwnB9Zdyj9WJlv
 wIITsQOvhHj6K2Ds63zmh/NKccMY8MDaBnffXnH8fi9kgBKHpPPMXJj1QOXCONlCVp5UGM8X
 j/gs94QmMxhr9TPY5WBa50sDW441q8zrDB8+B/hfbiE1B5k9Uwh6p/aAzEzLCb/rp9ELUz8/
 bax/e8ydtHpcbAMCRrMLkfID127dlLltOpOr+id+ACRz0jabaWqoGjCHLIjQEYGVxdSzzu+b
 27kWIcUPWm+8hNX35U3ywT7cnU/UOHorEorZyad3FkoVYfz/5necODocsIiBn2SJ3zmqTdBe
 sqmYKDf8gzhRpRqc+RrkWJJ98ze2A9w/ulLBC5lExXCjIAdckt2dLyPtsofmhJbV/mIKcbWx
 GX4vw1ufUIJmkbVFlP2MAe978rdj+DBHLuWT0uusPgOqpgO9v12HuqYgyBDpZ2cvhjU+uPAj
 Bx8eLu/tpxEHGONpdET42esoaIlsNnHC7SehyOH/liwa6Ew0roRHp+VZUaf9yE8lS0gNlKzB
 H5YPyYBMVSRNokVG4QUkzp30nJDIZ6GdAUZ1bfafSHFHH1wzmOLrbNquyZRIAkcNCFuVtHoY
 CUDuGAnZlqV+e4BLBBtl9VpJOS6PHKx0k6A8D86vtCMaX/M/SSdbL6Kd5M7AzQRaRrwiAQwA
 xnVmJqeP9VUTISps+WbyYFYlMFfIurl7tzK74bc67KUBp+PHuDP9p4ZcJUGC3UZJP85/GlUV
 dE1NairYWEJQUB7bpogTuzMI825QXIB9z842HwWfP2RW5eDtJMeujzJeFaUpmeTG9snzaYxY
 N3r0TDKj5dZwSIThIMQpsmhH2zylkT0jH7kBPxb8IkCQ1c6wgKITwoHFjTIO0B75U7bBNSDp
 XUaUDvd6T3xd1Fz57ujAvKHrZfWtaNSGwLmUYQAcFvrKDGPB5Z3ggkiTtkmW3OCQbnIxGJJw
 /+HefYhB5/kCcpKUQ2RYcYgCZ0/WcES1xU5dnNe4i0a5gsOFSOYCpNCfTHttVxKxZZTQ/rxj
 XwTuToXmTI4Nehn96t25DHZ0t9L9UEJ0yxH2y8Av4rtf75K2yAXFZa8dHnQgCkyjA/gs0ujG
 wD+Gs7dYQxP4i+rLhwBWD3mawJxLxY0vGwkG7k7npqanlsWlATHpOdqBMUiAR22hs02FikAo
 iXNgWTy7ABEBAAHCwXwEGAEIACYCGwwWIQRyeg1N257Z9gOb7O+Ef143kM4JdwUCZHu3zQUJ
 C4vBowAKCRCEf143kM4Jd2NnD/9E9Seq0HDZag4Uazn9cVsYWV/cPK4vKSqeGWMeLpJlG/UB
 PHY9q8a79jukEArt610oWj7+wL8SG61/YOyvYaC+LT9R54K8juP66hLCUTNDmv8s9DEzJkDP
 +ct8MwzA3oYtuirzbas0qaSwxHjZ3aV40vZk0uiDDG6kK24pv3SXcMDWz8m+sKu3RI3H+hdQ
 gnDrBIfTeeT6DCEgTHsaotFDc7vaNESElHHldCZTrg56T82to6TMm571tMW7mbg9O+u2pUON
 xEQ5hHCyvNrMAEel191KTWKE0Uh4SFrLmYYCRL9RIgUzxFF+ahPxjtjhkBmtQC4vQ20Bc3X6
 35ThI4munnjDmhM4eWVdcmDN4c8y+2FN/uHS5IUcfb9/7w+BWiELb3yGienDZ44U6j+ySA39
 gT6BAecNNIP47FG3AZXT3C1FZwFgkKoZ3lgN5VZgX2Gj53XiHqIGO8c3ayvHYAmrgtYYXG1q
 H5/qn1uUAhP1Oz+jKLUECbPS2ll73rFXUr+U3AKyLpx4T+/Wy1ajKn7rOB7udmTmYb8nnlQb
 0fpPzYGBzK7zWIzFotuS5x1PzLYhZQFkfegyAaxys2joryhI6YNFo+BHYTfamOVfFi8QFQL5
 5ZSOo27q/Ox95rwuC/n+PoJxBfqU36XBi886VV4LxuGZ8kfy0qDpL5neYtkC9w==
In-Reply-To: <ZWTQuRpwPkutHY-D@google.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 27.11.2023 18:24, Sean Christopherson wrote:
> On Thu, Nov 23, 2023, Maciej S. Szmigiero wrote:
>> From: "Maciej S. Szmigiero" <maciej.szmigiero@oracle.com>
>>
>> Since commit b0563468eeac ("x86/CPU/AMD: Disable XSAVES on AMD family 0x17")
>> kernel unconditionally clears the XSAVES CPU feature bit on Zen1/2 CPUs.
>>
>> Since KVM CPU caps are initialized from the kernel boot CPU features this
>> makes the XSAVES feature also unavailable for KVM guests in this case, even
>> though they might want to decide on their own whether they are affected by
>> this errata.
>>
>> Allow KVM guests to make such decision by setting the XSAVES KVM CPU
>> capability bit based on the actual CPU capability
> 
> This is not generally safe, as the guest can make such a decision if and only if
> the Family/Model/Stepping information is reasonably accurate.

If one lies to the guest about the CPU it is running on then obviously
things may work non-optimally.

>> This fixes booting Hyper-V enabled Windows Server 2016 VMs with more than
>> one vCPU on Zen1/2 CPUs.
> 
> How/why does lack of XSAVES break a multi-vCPU setup?  Is Windows blindly doing
> XSAVES based on FMS?

The hypercall from L2 Windows to L1 Hyper-V asking to boot the first AP
returns HV_STATUS_CPUID_XSAVE_FEATURE_VALIDATION_ERROR.

It's apparently a "should never happen" scenario for Windows since it
crashes soon after.

That's why uniprocessor configurations aren't broken - the BSP
doesn't need to be specifically booted by the L2 guest.

Unfortunately, Windows Server 2016 mainstream support has ended in
Jan 2022 so it is only getting security updates.
And you can't really break into an OS that you can't even start.

Thanks,
Maciej