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;
Message-ID: <3cf239c8-ccc4-d112-fb42-605661816cf0@intel.com>
Date:   Wed, 3 Aug 2022 14:18:53 -0700
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.11.0
Subject: Re: [PATCH v1.1 1/2] x86/sev: Use per-CPU PSC structure in prep for
 unaccepted memory support
Content-Language: en-US
To:     Tom Lendacky <thomas.lendacky@amd.com>,
        linux-kernel@vger.kernel.org, x86@kernel.org
Cc:     Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        "Kirill A. Shutemov" <kirill@shutemov.name>,
        "H. Peter Anvin" <hpa@zytor.com>,
        Michael Roth <michael.roth@amd.com>,
        Joerg Roedel <jroedel@suse.de>,
        Andy Lutomirski <luto@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>
References: <1b50311c-448b-96aa-1d96-f4bfed409c1f@amd.com>
 <cover.1659550264.git.thomas.lendacky@amd.com>
 <2a2adc3570ae9c24d03fff877c4fe79ed43605e0.1659550264.git.thomas.lendacky@amd.com>
 <d5902382-70f4-be07-99f6-80d17cdfdcaa@intel.com>
 <9f47ed0f-99cc-a237-f09b-45291feffcd3@amd.com>
 <e52341be-076e-92d1-a649-421dac5a4f5d@intel.com>
 <0eccea46-648d-ff70-dcc6-fdca88ff1234@amd.com>
From:   Dave Hansen <dave.hansen@intel.com>
In-Reply-To: <0eccea46-648d-ff70-dcc6-fdca88ff1234@amd.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 8/3/22 14:03, Tom Lendacky wrote:
>> This whole iteration does look good to me versus the per-cpu version, so
>> I say go ahead with doing this for v2 once you wait a bit for any more
>> feedback.
> 
> I'm still concerned about the whole spinlock and performance. What if I
> reduce the number of entries in the PSC structure to, say, 64, which
> reduces the size of the struct to 520 bytes. Any issue if that is put on
> the stack, instead? It definitely makes things less complicated and
> feels like a good compromise on the size vs the number of PSC VMGEXIT
> requests.

That would be fine too.

But, I doubt there will be any real performance issues coming out of
this.  As bad as this MSR thing is, I suspect it's not half as
disastrous as the global spinlock in Kirill's patches.

Also, private<->shared page conversions are *NOT* common from what I can
tell.  There are a few pages converted at boot, but most host the
guest<->host communications are through the swiotlb pages which are static.

Are there other things that SEV uses this structure for that I'm missing?