From: Sean Christopherson <seanjc@google.com>
To: Dave Hansen <dave.hansen@intel.com>
Cc: "Edgecombe, Rick P" <rick.p.edgecombe@intel.com>,
"linux-sgx@vger.kernel.org" <linux-sgx@vger.kernel.org>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
"Huang, Kai" <kai.huang@intel.com>,
"x86@kernel.org" <x86@kernel.org>,
"corbet@lwn.net" <corbet@lwn.net>,
"luto@kernel.org" <luto@kernel.org>,
"jethro@fortanix.com" <jethro@fortanix.com>,
"wanpengli@tencent.com" <wanpengli@tencent.com>,
"mingo@redhat.com" <mingo@redhat.com>,
"b.thiel@posteo.de" <b.thiel@posteo.de>,
"tglx@linutronix.de" <tglx@linutronix.de>,
"pbonzini@redhat.com" <pbonzini@redhat.com>,
"jarkko@kernel.org" <jarkko@kernel.org>,
"joro@8bytes.org" <joro@8bytes.org>,
"hpa@zytor.com" <hpa@zytor.com>,
"jmattson@google.com" <jmattson@google.com>,
"vkuznets@redhat.com" <vkuznets@redhat.com>,
"bp@alien8.de" <bp@alien8.de>,
"Huang, Haitao" <haitao.huang@intel.com>
Subject: Re: [RFC PATCH v3 00/27] KVM SGX virtualization support
Date: Wed, 3 Feb 2021 09:36:23 -0800 [thread overview]
Message-ID: <YBrfF0XQvzQf9PhR@google.com> (raw)
In-Reply-To: <f50ac476-71f2-60d4-5008-672365f4d554@intel.com>
On Wed, Feb 03, 2021, Dave Hansen wrote:
> On 2/2/21 3:56 PM, Sean Christopherson wrote:
> >> I seem to remember much stronger language in the SDM about this. I've
> >> always thought of SGX as a big unrecoverable machine-check party waiting
> >> to happen.
> >>
> >> I'll ask around internally at Intel and see what folks say. Basically,
> >> should we be afraid of a big bad EPC access?
> > If bad accesses to the EPC can cause machine checks, then EPC should never be
> > mapped into userspace, i.e. the SGX driver should never have been merged.
>
> The SDM doesn't define the behavior well enough. I'll try to get that
> fixed.
>
> But, there is some documentation of the abort page semantics:
>
> > https://download.01.org/intel-sgx/sgx-linux/2.10/docs/Intel_SGX_Developer_Reference_Linux_2.10_Open_Source.pdf
>
> Basically, writes get dropped and reads get all 1's on all the
> implementations in the wild. I actually would have much rather gotten a
> fault, but oh well.
>
> It sounds like we need to at least modify KVM to make sure not to map
> and access EPC addresses.
Why? KVM will read garbage, but KVM needs to be careful with the data it reads,
irrespective of SGX, because the data is user/guest controlled even in the happy
case.
I'm not at all opposed to preventing KVM from accessing EPC, but I really don't
want to add a special check in KVM to avoid reading EPC. KVM generally isn't
aware of physical backings, and the relevant KVM code is shared between all
architectures.
> We might even want to add some VM_WARN_ON()s in the code that creates kernel
> mappings to catch these mappings if they happen anywhere else.
One thought for handling this would be to extend __ioremap_check_other() to flag
EPC in some way, and then disallow memremap() to EPC. A clever way to do that
without disallowing SGX's initial memremap() would be to tap into SGX's
sgx_epc_sections array, as the per-section check would activate only after each
section is initialized/map by SGX.
Disallowing memremap(), without warning, would address the KVM flow (the
memremap() in __kvm_map_gfn()) without forcing KVM to explicitly check for EPC.
E.g. something like:
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index c519fc5f6948..f263f3554f27 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -26,6 +26,19 @@ static LIST_HEAD(sgx_active_page_list);
static DEFINE_SPINLOCK(sgx_reclaimer_lock);
+bool is_sgx_epc(resource_size_t addr, unsigned long size)
+{
+ resource_size_t end = addr + size - 1;
+ int i;
+
+ for (i = 0; i < sgx_nr_epc_sections; i++) {
+ if (<check for overlap with sgx_epc_sections[i])
+ return true;
+ }
+
+ return false;
+}
+
/*
* Reset dirty EPC pages to uninitialized state. Laundry can be left with SECS
* pages whose child pages blocked EREMOVE.
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 9e5ccc56f8e0..145fc6fc6bc5 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -34,6 +34,7 @@
*/
struct ioremap_desc {
unsigned int flags;
+ bool sgx_epc;
};
/*
@@ -110,8 +111,14 @@ static unsigned int __ioremap_check_encrypted(struct resource *res)
* The EFI runtime services data area is not covered by walk_mem_res(), but must
* be mapped encrypted when SEV is active.
*/
-static void __ioremap_check_other(resource_size_t addr, struct ioremap_desc *desc)
+static void __ioremap_check_other(resource_size_t addr, unsigned long size,
+ struct ioremap_desc *desc)
{
+ if (sgx_is_epc(addr, size)) {
+ desc->sgx_epc = true;
+ return;
+ }
+
if (!sev_active())
return;
@@ -155,7 +162,7 @@ static void __ioremap_check_mem(resource_size_t addr, unsigned long size,
walk_mem_res(start, end, desc, __ioremap_collect_map_flags);
- __ioremap_check_other(addr, desc);
+ __ioremap_check_other(addr, size, desc);
}
/*
@@ -210,6 +217,13 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size,
return NULL;
}
+ /*
+ * Don't allow mapping SGX EPC, it's not accessible via normal reads
+ * and writes.
+ */
+ if (io_desc.epc)
+ return NULL;
+
/*
* Mappings have to be page-aligned
*/
next prev parent reply other threads:[~2021-02-03 17:37 UTC|newest]
Thread overview: 156+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-26 10:10 [RFC PATCH v3 00/27] KVM SGX virtualization support Kai Huang
2021-01-26 9:29 ` Kai Huang
2021-01-26 9:30 ` [RFC PATCH v3 01/27] x86/cpufeatures: Add SGX1 and SGX2 sub-features Kai Huang
2021-01-26 15:34 ` Dave Hansen
2021-01-26 23:18 ` Kai Huang
2021-01-30 13:20 ` Jarkko Sakkinen
2021-02-01 0:01 ` Kai Huang
2021-02-02 17:17 ` Jarkko Sakkinen
2021-02-03 1:09 ` Kai Huang
2021-02-02 17:56 ` Paolo Bonzini
2021-02-02 18:00 ` Dave Hansen
2021-02-02 18:03 ` Paolo Bonzini
2021-02-02 18:42 ` Sean Christopherson
2021-02-03 1:05 ` Kai Huang
2021-01-30 13:11 ` Jarkko Sakkinen
2021-01-26 9:30 ` [RFC PATCH v3 02/27] x86/cpufeatures: Make SGX_LC feature bit depend on SGX bit Kai Huang
2021-01-26 15:35 ` Dave Hansen
2021-01-30 13:22 ` Jarkko Sakkinen
2021-02-01 0:08 ` Kai Huang
2021-01-26 9:30 ` [RFC PATCH v3 03/27] x86/sgx: Remove a warn from sgx_free_epc_page() Kai Huang
2021-01-26 15:39 ` Dave Hansen
2021-01-26 16:30 ` Sean Christopherson
2021-01-27 1:08 ` Kai Huang
2021-01-27 1:12 ` Dave Hansen
2021-01-27 1:26 ` Kai Huang
2021-02-01 0:11 ` Kai Huang
2021-02-03 10:03 ` Jarkko Sakkinen
2021-01-26 9:30 ` [RFC PATCH v3 04/27] x86/sgx: Wipe out EREMOVE " Kai Huang
2021-01-26 16:04 ` Dave Hansen
2021-01-27 1:25 ` Kai Huang
2021-02-02 18:00 ` Paolo Bonzini
2021-02-02 19:25 ` Kai Huang
2021-02-02 19:02 ` Dave Hansen
2021-01-26 9:30 ` [RFC PATCH v3 05/27] x86/sgx: Add SGX_CHILD_PRESENT hardware error code Kai Huang
2021-01-26 15:49 ` Dave Hansen
2021-01-27 0:00 ` Kai Huang
2021-01-27 0:21 ` Dave Hansen
2021-01-27 0:52 ` Kai Huang
2021-01-26 9:30 ` [RFC PATCH v3 06/27] x86/sgx: Introduce virtual EPC for use by KVM guests Kai Huang
2021-01-26 16:19 ` Dave Hansen
2021-01-27 0:16 ` Kai Huang
2021-01-27 0:27 ` Dave Hansen
2021-01-27 0:48 ` Kai Huang
2021-01-30 14:41 ` Jarkko Sakkinen
2021-01-26 9:30 ` [RFC PATCH v3 07/27] x86/cpu/intel: Allow SGX virtualization without Launch Control support Kai Huang
2021-01-26 16:26 ` Dave Hansen
2021-01-26 17:00 ` Sean Christopherson
2021-01-26 23:54 ` Kai Huang
2021-01-26 23:56 ` Kai Huang
2021-01-27 0:18 ` Dave Hansen
2021-01-27 2:02 ` Kai Huang
2021-01-27 17:13 ` Sean Christopherson
2021-01-30 14:42 ` Jarkko Sakkinen
2021-02-01 5:38 ` Kai Huang
2021-01-26 9:31 ` [RFC PATCH v3 08/27] x86/sgx: Initialize virtual EPC driver even when SGX driver is disabled Kai Huang
2021-01-26 17:03 ` Dave Hansen
2021-01-26 18:10 ` Andy Lutomirski
2021-01-26 23:25 ` Kai Huang
2021-01-30 14:45 ` Jarkko Sakkinen
2021-02-01 5:40 ` Kai Huang
2021-02-01 15:25 ` Dave Hansen
2021-02-01 17:23 ` Sean Christopherson
2021-02-02 0:12 ` Kai Huang
2021-02-02 23:10 ` Jarkko Sakkinen
2021-02-02 23:07 ` Jarkko Sakkinen
2021-02-02 17:32 ` Jarkko Sakkinen
2021-02-02 18:20 ` Sean Christopherson
2021-02-02 23:16 ` Jarkko Sakkinen
2021-02-03 0:49 ` Kai Huang
2021-02-03 22:02 ` Jarkko Sakkinen
2021-02-03 22:59 ` Sean Christopherson
2021-02-04 1:39 ` Jarkko Sakkinen
2021-02-04 2:59 ` Kai Huang
2021-02-04 3:05 ` Jarkko Sakkinen
2021-02-04 3:09 ` Jarkko Sakkinen
2021-02-04 3:20 ` Kai Huang
2021-02-04 14:51 ` Jarkko Sakkinen
2021-02-04 22:41 ` Dave Hansen
2021-02-04 22:56 ` Kai Huang
2021-02-05 2:08 ` Jarkko Sakkinen
2021-02-05 3:00 ` Huang, Kai
2021-02-02 18:49 ` Kai Huang
2021-02-02 23:17 ` Jarkko Sakkinen
2021-01-26 9:31 ` [RFC PATCH v3 09/27] x86/sgx: Expose SGX architectural definitions to the kernel Kai Huang
2021-01-30 14:46 ` Jarkko Sakkinen
2021-01-26 9:31 ` [RFC PATCH v3 10/27] x86/sgx: Move ENCLS leaf definitions to sgx_arch.h Kai Huang
2021-01-26 9:31 ` [RFC PATCH v3 11/27] x86/sgx: Add SGX2 ENCLS leaf definitions (EAUG, EMODPR and EMODT) Kai Huang
2021-01-26 9:31 ` [RFC PATCH v3 12/27] x86/sgx: Add encls_faulted() helper Kai Huang
2021-01-30 14:48 ` Jarkko Sakkinen
2021-01-26 9:31 ` [RFC PATCH v3 13/27] x86/sgx: Add helper to update SGX_LEPUBKEYHASHn MSRs Kai Huang
2021-01-30 14:49 ` Jarkko Sakkinen
2021-02-01 1:17 ` Kai Huang
2021-02-01 21:22 ` Dave Hansen
2021-01-26 9:31 ` [RFC PATCH v3 14/27] x86/sgx: Add helpers to expose ECREATE and EINIT to KVM Kai Huang
2021-01-30 14:51 ` Jarkko Sakkinen
2021-02-01 0:17 ` Kai Huang
2021-02-02 17:20 ` Jarkko Sakkinen
2021-02-02 20:35 ` Kai Huang
2021-02-04 3:53 ` Kai Huang
2021-02-05 0:32 ` Sean Christopherson
2021-02-05 1:39 ` Huang, Kai
2021-01-26 9:31 ` [RFC PATCH v3 15/27] x86/sgx: Move provisioning device creation out of SGX driver Kai Huang
2021-01-30 14:52 ` Jarkko Sakkinen
2021-01-26 9:31 ` [RFC PATCH v3 16/27] KVM: VMX: Convert vcpu_vmx.exit_reason to a union Kai Huang
2021-01-30 15:00 ` Jarkko Sakkinen
2021-02-01 0:32 ` Kai Huang
2021-02-02 17:24 ` Jarkko Sakkinen
2021-02-02 19:23 ` Kai Huang
2021-02-02 22:41 ` Jarkko Sakkinen
2021-02-03 0:42 ` Kai Huang
2021-02-01 17:12 ` Sean Christopherson
2021-02-02 22:38 ` Jarkko Sakkinen
2021-01-26 9:31 ` [RFC PATCH v3 17/27] KVM: x86: Export kvm_mmu_gva_to_gpa_{read,write}() for SGX (VMX) Kai Huang
2021-01-26 9:31 ` [RFC PATCH v3 18/27] KVM: x86: Define new #PF SGX error code bit Kai Huang
2021-01-26 9:31 ` [RFC PATCH v3 19/27] KVM: x86: Add support for reverse CPUID lookup of scattered features Kai Huang
2021-01-26 9:31 ` [RFC PATCH v3 20/27] KVM: x86: Add reverse-CPUID lookup support for scattered SGX features Kai Huang
2021-01-26 9:31 ` [RFC PATCH v3 21/27] KVM: VMX: Add basic handling of VM-Exit from SGX enclave Kai Huang
2021-01-26 9:31 ` [RFC PATCH v3 22/27] KVM: VMX: Frame in ENCLS handler for SGX virtualization Kai Huang
2021-01-26 9:31 ` [RFC PATCH v3 23/27] KVM: VMX: Add SGX ENCLS[ECREATE] handler to enforce CPUID restrictions Kai Huang
2021-02-03 0:52 ` Edgecombe, Rick P
2021-02-03 1:36 ` Sean Christopherson
2021-02-03 9:11 ` Kai Huang
2021-02-03 17:07 ` Sean Christopherson
2021-02-03 23:11 ` Kai Huang
2021-02-03 18:47 ` Edgecombe, Rick P
2021-02-03 19:36 ` Sean Christopherson
2021-02-03 23:29 ` Kai Huang
2021-02-03 23:36 ` Sean Christopherson
2021-02-03 23:45 ` Kai Huang
2021-02-03 23:59 ` Sean Christopherson
2021-02-04 0:11 ` Kai Huang
2021-02-04 2:01 ` Sean Christopherson
2021-01-26 9:31 ` [RFC PATCH v3 24/27] KVM: VMX: Add emulation of SGX Launch Control LE hash MSRs Kai Huang
2021-01-26 9:31 ` [RFC PATCH v3 25/27] KVM: VMX: Add ENCLS[EINIT] handler to support SGX Launch Control (LC) Kai Huang
2021-01-26 9:31 ` [RFC PATCH v3 26/27] KVM: VMX: Enable SGX virtualization for SGX1, SGX2 and LC Kai Huang
2021-01-26 9:32 ` [RFC PATCH v3 27/27] KVM: x86: Add capability to grant VM access to privileged SGX attribute Kai Huang
2021-02-02 22:21 ` [RFC PATCH v3 00/27] KVM SGX virtualization support Edgecombe, Rick P
2021-02-02 22:33 ` Sean Christopherson
2021-02-02 23:21 ` Dave Hansen
2021-02-02 23:56 ` Sean Christopherson
2021-02-03 0:43 ` Dave Hansen
2021-02-03 15:10 ` Dave Hansen
2021-02-03 17:36 ` Sean Christopherson [this message]
2021-02-03 17:43 ` Paolo Bonzini
2021-02-03 17:46 ` Dave Hansen
2021-02-03 23:09 ` Kai Huang
2021-02-03 23:32 ` Sean Christopherson
2021-02-03 23:37 ` Dave Hansen
2021-02-04 0:04 ` Kai Huang
2021-02-04 0:28 ` Sean Christopherson
2021-02-04 3:18 ` Kai Huang
2021-02-04 16:28 ` Sean Christopherson
2021-02-04 16:48 ` Dave Hansen
2021-02-05 12:32 ` Kai Huang
2021-02-05 16:51 ` Sean Christopherson
2021-02-02 22:36 ` Dave Hansen
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=YBrfF0XQvzQf9PhR@google.com \
--to=seanjc@google.com \
--cc=b.thiel@posteo.de \
--cc=bp@alien8.de \
--cc=corbet@lwn.net \
--cc=dave.hansen@intel.com \
--cc=haitao.huang@intel.com \
--cc=hpa@zytor.com \
--cc=jarkko@kernel.org \
--cc=jethro@fortanix.com \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=kai.huang@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-sgx@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=rick.p.edgecombe@intel.com \
--cc=tglx@linutronix.de \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
--cc=x86@kernel.org \
/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).