[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <69a807a3-770a-662d-9cf0-25fad035a323@amd.com>
Date: Thu, 12 Oct 2017 16:52:32 -0500
From: Brijesh Singh <brijesh.singh@....com>
To: Borislav Petkov <bp@...e.de>
Cc: brijesh.singh@....com, Paolo Bonzini <pbonzini@...hat.com>,
Radim Krčmář <rkrcmar@...hat.com>,
Herbert Xu <herbert@...dor.apana.org.au>,
Gary Hook <gary.hook@....com>,
Tom Lendacky <thomas.lendacky@....com>,
linux-crypto@...r.kernel.org, kvm@...r.kernel.org,
linux-kernel@...r.kernel.org
Subject: Re: [Part2 PATCH v5.2 12.2/31] crypto: ccp: Add Secure Encrypted
Virtualization (SEV) command support
On 10/12/17 4:41 PM, Borislav Petkov wrote:
> On Thu, Oct 12, 2017 at 04:11:18PM -0500, Brijesh Singh wrote:
>> The sev_exit() will be called for all the psp_device instance. we need
>> to set psp_misc_dev = NULL after deregistering the device.
>>
>> if (psp_misc_dev) {
>> misc_deregister(psp_misc_dev);
>> psp_misc_dev = NULL;
> Right, except we assign that misc device to every psp device:
>
> psp->sev_misc = psp_misc_dev;
>
> so the question now is, how do you want this to work: the misc device
> should be destroyed after the last psp device is destroyed or how?
We don't know when the last psp device is getting destroyed. Since we
are making the sev_misc_dev as a global variable then there is no
reason for 'sev_misc' field in the psp_device.
> Because after the first:
>
> psp_misc_dev = NULL;
>
> the respective psp->sev_misc will still keep references to that device
> but the device itself will be already deregistered. And that sounds
> strange.
See my above comment, I think the simplest solution is remove psp->sev_misc
Powered by blists - more mailing lists