linux-kernel - Re: [PATCH v36 21/24] x86/vdso: Implement a vDSO for Intel SGX enclave call

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20200811145419.GC20623@linux.intel.com>
Date:   Tue, 11 Aug 2020 07:54:19 -0700
From:   Sean Christopherson <sean.j.christopherson@...el.com>
To:     Jethro Beekman <jethro@...tanix.com>
Cc:     Nathaniel McCallum <npmccallum@...hat.com>,
        Jarkko Sakkinen <jarkko.sakkinen@...ux.intel.com>,
        x86@...nel.org, linux-sgx@...r.kernel.org,
        linux-kernel@...r.kernel.org,
        Andy Lutomirski <luto@...capital.net>,
        Cedric Xing <cedric.xing@...el.com>, akpm@...ux-foundation.org,
        andriy.shevchenko@...ux.intel.com, asapek@...gle.com, bp@...en8.de,
        chenalexchen@...gle.com, conradparker@...gle.com,
        cyhanish@...gle.com, dave.hansen@...el.com,
        "Huang, Haitao" <haitao.huang@...el.com>,
        Josh Triplett <josh@...htriplett.org>, kai.huang@...el.com,
        "Svahn, Kai" <kai.svahn@...el.com>, kmoy@...gle.com,
        ludloff@...gle.com, luto@...nel.org,
        Neil Horman <nhorman@...hat.com>,
        Patrick Uiterwijk <puiterwijk@...hat.com>,
        David Rientjes <rientjes@...gle.com>,
        Thomas Gleixner <tglx@...utronix.de>, yaozhangx@...gle.com
Subject: Re: [PATCH v36 21/24] x86/vdso: Implement a vDSO for Intel SGX
 enclave call

On Tue, Aug 11, 2020 at 09:16:28AM +0200, Jethro Beekman wrote:
> On 2020-08-11 00:23, Sean Christopherson wrote:
> > Another thought would be to wrap sgx_enclave_exception in a struct to give
> > room for supporting additional exit information (if such a thing ever pops
> > up) and to allow the caller to opt in to select behavior, e.g. Jethro's
> > request to invoke the exit handler on IRQ exits.  This is basically the
> > equivalent of "struct kvm_run", minus the vCPU/enclave state.
> 
> Actually, the flag I need is “return from the vdso on IRQ exits” (See Andy's
> email about preferring returns over callbacks). But maybe the flag should be
> “interpret IRQ exit as a normal exit” and let it be handled the same as any
> other exit based on whether an exit handler fnptr was passed or not.

Ya, slip of the tongue, the behavior would apply to both paths.