From: "Roedel, Joerg" <Joerg.Roedel@amd.com>
To: Avi Kivity <avi@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 16/22] KVM: MMU: Track page fault data in struct vcpu
Date: Tue, 4 May 2010 14:00:39 +0200 [thread overview]
Message-ID: <20100504120039.GH28950@amd.com> (raw)
In-Reply-To: <4BDFEDFA.3090209@redhat.com>
On Tue, May 04, 2010 at 05:50:50AM -0400, Avi Kivity wrote:
> On 05/04/2010 12:45 PM, Avi Kivity wrote:
> >
> >
> > Just a silly bug. kvm_pdptr_read() can cause a guest memory read on
> > svm, in this case with the mmu lock taken. I'll post something to fix
> > it.
>
> I guess this was not reported because most svm machines have npt, and
> this requires npt=0 to trigger. Nonpae paging disables npt, so you were
> hit. Interestingly, nsvm makes it more likely to appear, since npt on
> i386+pae will need the pdptrs.
Hmm, actually it happened on 32 bit with npt enabled. I think this
can trigger when mmu_alloc_roots is called for an pae guest because it
accidentially tries read the root_gfn from the guest before it figures
out that it runs with tdp and omits the gfn read from the guest.
I need to touch this for nested-npt and will look into a way improving
this.
Joerg
next prev parent reply other threads:[~2010-05-04 12:00 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-04-27 10:38 [PATCH 0/22] Nested Paging support for Nested SVM v2 Joerg Roedel
2010-04-27 10:38 ` [PATCH 01/22] KVM: MMU: Check for root_level instead of long mode Joerg Roedel
2010-04-27 10:38 ` [PATCH 02/22] KVM: MMU: Make tdp_enabled a mmu-context parameter Joerg Roedel
2010-04-27 12:06 ` Avi Kivity
2010-04-27 10:38 ` [PATCH 03/22] KVM: MMU: Make set_cr3 a function pointer in kvm_mmu Joerg Roedel
2010-04-27 10:38 ` [PATCH 04/22] KVM: X86: Introduce a tdp_set_cr3 function Joerg Roedel
2010-04-27 10:38 ` [PATCH 05/22] KVM: MMU: Introduce get_cr3 function pointer Joerg Roedel
2010-04-27 10:38 ` [PATCH 06/22] KVM: MMU: Introduce inject_page_fault " Joerg Roedel
2010-04-27 10:38 ` [PATCH 07/22] KVM: SVM: Implement MMU helper functions for Nested Nested Paging Joerg Roedel
2010-04-27 10:38 ` [PATCH 08/22] KVM: MMU: Change init_kvm_softmmu to take a context as parameter Joerg Roedel
2010-04-27 10:38 ` [PATCH 09/22] KVM: MMU: Let is_rsvd_bits_set take mmu context instead of vcpu Joerg Roedel
2010-04-27 10:38 ` [PATCH 10/22] KVM: MMU: Introduce generic walk_addr function Joerg Roedel
2010-04-27 10:38 ` [PATCH 11/22] KVM: MMU: Add infrastructure for two-level page walker Joerg Roedel
2010-04-27 12:34 ` Avi Kivity
2010-04-28 10:52 ` Joerg Roedel
2010-04-28 11:24 ` Avi Kivity
2010-04-28 11:03 ` Joerg Roedel
2010-04-28 11:09 ` Avi Kivity
2010-04-27 10:38 ` [PATCH 12/22] KVM: MMU: Implement nested gva_to_gpa functions Joerg Roedel
2010-04-27 12:37 ` Avi Kivity
2010-04-28 14:20 ` Joerg Roedel
2010-04-27 10:38 ` [PATCH 13/22] KVM: X86: Add kvm_read_guest_page_tdp function Joerg Roedel
2010-04-27 12:42 ` Avi Kivity
2010-04-27 13:10 ` Joerg Roedel
2010-04-27 13:40 ` Avi Kivity
2010-04-27 10:38 ` [PATCH 14/22] KVM: MMU: Make walk_addr_generic capable for two-level walking Joerg Roedel
2010-04-27 10:38 ` [PATCH 15/22] KVM: MMU: Introduce kvm_read_guest_page_x86() Joerg Roedel
2010-04-27 12:52 ` Avi Kivity
2010-04-27 13:20 ` Joerg Roedel
2010-04-27 13:35 ` Avi Kivity
2010-04-27 15:40 ` Joerg Roedel
2010-04-27 16:09 ` Avi Kivity
2010-04-27 16:27 ` Joerg Roedel
2010-04-28 15:31 ` Joerg Roedel
2010-04-27 10:38 ` [PATCH 16/22] KVM: MMU: Track page fault data in struct vcpu Joerg Roedel
2010-04-27 12:58 ` Avi Kivity
2010-04-27 13:28 ` Joerg Roedel
2010-04-27 13:37 ` Avi Kivity
2010-04-27 13:57 ` Joerg Roedel
2010-04-27 16:02 ` Avi Kivity
2010-05-03 16:32 ` Joerg Roedel
2010-05-04 7:53 ` Avi Kivity
2010-05-04 9:11 ` Roedel, Joerg
2010-05-04 9:20 ` Avi Kivity
2010-05-04 9:37 ` Roedel, Joerg
2010-05-04 9:45 ` Avi Kivity
2010-05-04 9:50 ` Avi Kivity
2010-05-04 12:00 ` Roedel, Joerg [this message]
2010-05-04 12:04 ` Avi Kivity
2010-04-27 10:38 ` [PATCH 17/22] KVM: MMU: Propagate the right fault back to the guest after gva_to_gpa Joerg Roedel
2010-04-27 10:38 ` [PATCH 18/22] KVM: X86: Propagate fetch faults Joerg Roedel
2010-04-27 10:38 ` [PATCH 19/22] KVM: MMU: Introduce init_kvm_nested_mmu() Joerg Roedel
2010-04-27 10:38 ` [PATCH 20/22] KVM: SVM: Initialize Nested Nested MMU context on VMRUN Joerg Roedel
2010-04-27 13:01 ` Avi Kivity
2010-04-27 10:38 ` [PATCH 21/22] KVM: SVM: Report Nested Paging support to userspace Joerg Roedel
2010-04-27 10:38 ` [PATCH 22/22] KVM: SVM: Expect two more candiates for exit_int_info Joerg Roedel
2010-04-27 13:03 ` [PATCH 0/22] Nested Paging support for Nested SVM v2 Avi Kivity
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=20100504120039.GH28950@amd.com \
--to=joerg.roedel@amd.com \
--cc=avi@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mtosatti@redhat.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.