From: "Kirill A. Shutemov" <kirill@shutemov.name>
To: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: David Rientjes <rientjes@google.com>,
Andrea Arcangeli <aarcange@redhat.com>,
Kees Cook <keescook@chromium.org>, Will Drewry <wad@chromium.org>,
"Edgecombe, Rick P" <rick.p.edgecombe@intel.com>,
"Kleen, Andi" <andi.kleen@intel.com>,
x86@kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
Dave Hansen <dave.hansen@linux.intel.com>,
Andy Lutomirski <luto@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Paolo Bonzini <pbonzini@redhat.com>,
Sean Christopherson <sean.j.christopherson@intel.com>,
Wanpeng Li <wanpengli@tencent.com>,
Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>
Subject: Re: [RFC 09/16] KVM: Protected memory extension
Date: Mon, 25 May 2020 18:34:35 +0300 [thread overview]
Message-ID: <20200525153435.c6mx3pjryyk4j4go@box> (raw)
In-Reply-To: <87367o828i.fsf@vitty.brq.redhat.com>
On Mon, May 25, 2020 at 05:26:37PM +0200, Vitaly Kuznetsov wrote:
> "Kirill A. Shutemov" <kirill@shutemov.name> writes:
>
> > Add infrastructure that handles protected memory extension.
> >
> > Arch-specific code has to provide hypercalls and define non-zero
> > VM_KVM_PROTECTED.
> >
> > Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> > ---
> > include/linux/kvm_host.h | 4 ++
> > mm/mprotect.c | 1 +
> > virt/kvm/kvm_main.c | 131 +++++++++++++++++++++++++++++++++++++++
> > 3 files changed, 136 insertions(+)
> >
> > diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> > index bd0bb600f610..d7072f6d6aa0 100644
> > --- a/include/linux/kvm_host.h
> > +++ b/include/linux/kvm_host.h
> > @@ -700,6 +700,10 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm);
> > void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
> > struct kvm_memory_slot *slot);
> >
> > +int kvm_protect_all_memory(struct kvm *kvm);
> > +int kvm_protect_memory(struct kvm *kvm,
> > + unsigned long gfn, unsigned long npages, bool protect);
> > +
> > int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
> > struct page **pages, int nr_pages);
> >
> > diff --git a/mm/mprotect.c b/mm/mprotect.c
> > index 494192ca954b..552be3b4c80a 100644
> > --- a/mm/mprotect.c
> > +++ b/mm/mprotect.c
> > @@ -505,6 +505,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
> > vm_unacct_memory(charged);
> > return error;
> > }
> > +EXPORT_SYMBOL_GPL(mprotect_fixup);
> >
> > /*
> > * pkey==-1 when doing a legacy mprotect()
> > diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> > index 530af95efdf3..07d45da5d2aa 100644
> > --- a/virt/kvm/kvm_main.c
> > +++ b/virt/kvm/kvm_main.c
> > @@ -155,6 +155,8 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm);
> > static unsigned long long kvm_createvm_count;
> > static unsigned long long kvm_active_vms;
> >
> > +static int protect_memory(unsigned long start, unsigned long end, bool protect);
> > +
> > __weak int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
> > unsigned long start, unsigned long end, bool blockable)
> > {
> > @@ -1309,6 +1311,14 @@ int __kvm_set_memory_region(struct kvm *kvm,
> > if (r)
> > goto out_bitmap;
> >
> > + if (mem->memory_size && kvm->mem_protected) {
> > + r = protect_memory(new.userspace_addr,
> > + new.userspace_addr + new.npages * PAGE_SIZE,
> > + true);
> > + if (r)
> > + goto out_bitmap;
> > + }
> > +
> > if (old.dirty_bitmap && !new.dirty_bitmap)
> > kvm_destroy_dirty_bitmap(&old);
> > return 0;
> > @@ -2652,6 +2662,127 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn)
> > }
> > EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty);
> >
> > +static int protect_memory(unsigned long start, unsigned long end, bool protect)
> > +{
> > + struct mm_struct *mm = current->mm;
> > + struct vm_area_struct *vma, *prev;
> > + int ret;
> > +
> > + if (down_write_killable(&mm->mmap_sem))
> > + return -EINTR;
> > +
> > + ret = -ENOMEM;
> > + vma = find_vma(current->mm, start);
> > + if (!vma)
> > + goto out;
> > +
> > + ret = -EINVAL;
> > + if (vma->vm_start > start)
> > + goto out;
> > +
> > + if (start > vma->vm_start)
> > + prev = vma;
> > + else
> > + prev = vma->vm_prev;
> > +
> > + ret = 0;
> > + while (true) {
> > + unsigned long newflags, tmp;
> > +
> > + tmp = vma->vm_end;
> > + if (tmp > end)
> > + tmp = end;
> > +
> > + newflags = vma->vm_flags;
> > + if (protect)
> > + newflags |= VM_KVM_PROTECTED;
> > + else
> > + newflags &= ~VM_KVM_PROTECTED;
> > +
> > + /* The VMA has been handled as part of other memslot */
> > + if (newflags == vma->vm_flags)
> > + goto next;
> > +
> > + ret = mprotect_fixup(vma, &prev, start, tmp, newflags);
> > + if (ret)
> > + goto out;
> > +
> > +next:
> > + start = tmp;
> > + if (start < prev->vm_end)
> > + start = prev->vm_end;
> > +
> > + if (start >= end)
> > + goto out;
> > +
> > + vma = prev->vm_next;
> > + if (!vma || vma->vm_start != start) {
> > + ret = -ENOMEM;
> > + goto out;
> > + }
> > + }
> > +out:
> > + up_write(&mm->mmap_sem);
> > + return ret;
> > +}
> > +
> > +int kvm_protect_memory(struct kvm *kvm,
> > + unsigned long gfn, unsigned long npages, bool protect)
> > +{
> > + struct kvm_memory_slot *memslot;
> > + unsigned long start, end;
> > + gfn_t numpages;
> > +
> > + if (!VM_KVM_PROTECTED)
> > + return -KVM_ENOSYS;
> > +
> > + if (!npages)
> > + return 0;
> > +
> > + memslot = gfn_to_memslot(kvm, gfn);
> > + /* Not backed by memory. It's okay. */
> > + if (!memslot)
> > + return 0;
> > +
> > + start = gfn_to_hva_many(memslot, gfn, &numpages);
> > + end = start + npages * PAGE_SIZE;
> > +
> > + /* XXX: Share range across memory slots? */
> > + if (WARN_ON(numpages < npages))
> > + return -EINVAL;
> > +
> > + return protect_memory(start, end, protect);
> > +}
> > +EXPORT_SYMBOL_GPL(kvm_protect_memory);
> > +
> > +int kvm_protect_all_memory(struct kvm *kvm)
> > +{
> > + struct kvm_memslots *slots;
> > + struct kvm_memory_slot *memslot;
> > + unsigned long start, end;
> > + int i, ret = 0;;
> > +
> > + if (!VM_KVM_PROTECTED)
> > + return -KVM_ENOSYS;
> > +
> > + mutex_lock(&kvm->slots_lock);
> > + kvm->mem_protected = true;
>
> What will happen upon guest reboot? Do we need to unprotect everything
> to make sure we'll be able to boot? Also, after the reboot how will the
> guest know that it is protected and needs to unprotect things? -> see my
> idea about converting KVM_HC_ENABLE_MEM_PROTECTED to a stateful MSR (but
> we'll likely have to reset it upon reboot anyway).
That's extremely good question. I have not considered reboot. I tend to use
-no-reboot in my setup.
I'll think how to deal with reboot. I don't know how it works now to give
a good answer.
The may not be a good solution: unprotecting memory on reboot means we
expose user data. We can wipe the data before unprotecting, but we should
not wipe BIOS and anything else that is required on reboot. I donno.
> > + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
> > + slots = __kvm_memslots(kvm, i);
> > + kvm_for_each_memslot(memslot, slots) {
> > + start = memslot->userspace_addr;
> > + end = start + memslot->npages * PAGE_SIZE;
> > + ret = protect_memory(start, end, true);
> > + if (ret)
> > + goto out;
> > + }
> > + }
> > +out:
> > + mutex_unlock(&kvm->slots_lock);
> > + return ret;
> > +}
> > +EXPORT_SYMBOL_GPL(kvm_protect_all_memory);
> > +
> > void kvm_sigset_activate(struct kvm_vcpu *vcpu)
> > {
> > if (!vcpu->sigset_active)
>
> --
> Vitaly
>
>
--
Kirill A. Shutemov
next prev parent reply other threads:[~2020-05-25 15:34 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-22 12:51 [RFC 00/16] KVM protected memory extension Kirill A. Shutemov
2020-05-22 12:51 ` [RFC 01/16] x86/mm: Move force_dma_unencrypted() to common code Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 02/16] x86/kvm: Introduce KVM memory protection feature Kirill A. Shutemov
2020-05-25 14:58 ` Vitaly Kuznetsov
2020-05-25 15:15 ` Kirill A. Shutemov
2020-05-27 5:03 ` Sean Christopherson
2020-05-27 8:39 ` Vitaly Kuznetsov
2020-05-27 8:52 ` Sean Christopherson
2020-06-03 2:09 ` Huang, Kai
2020-06-03 11:14 ` Vitaly Kuznetsov
2020-05-22 12:52 ` [RFC 03/16] x86/kvm: Make DMA pages shared Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 04/16] x86/kvm: Use bounce buffers for KVM memory protection Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 05/16] x86/kvm: Make VirtIO use DMA API in KVM guest Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 06/16] KVM: Use GUP instead of copy_from/to_user() to access guest memory Kirill A. Shutemov
2020-05-25 15:08 ` Vitaly Kuznetsov
2020-05-25 15:17 ` Kirill A. Shutemov
2020-06-01 16:35 ` Paolo Bonzini
2020-06-02 13:33 ` Kirill A. Shutemov
2020-05-26 6:14 ` Mike Rapoport
2020-05-26 21:56 ` Kirill A. Shutemov
2020-05-29 15:24 ` Kees Cook
2020-05-22 12:52 ` [RFC 07/16] KVM: mm: Introduce VM_KVM_PROTECTED Kirill A. Shutemov
2020-05-26 6:15 ` Mike Rapoport
2020-05-26 22:01 ` Kirill A. Shutemov
2020-05-26 6:40 ` John Hubbard
2020-05-26 22:04 ` Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 08/16] KVM: x86: Use GUP for page walk instead of __get_user() Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 09/16] KVM: Protected memory extension Kirill A. Shutemov
2020-05-25 15:26 ` Vitaly Kuznetsov
2020-05-25 15:34 ` Kirill A. Shutemov [this message]
2020-06-03 1:34 ` Huang, Kai
2020-05-22 12:52 ` [RFC 10/16] KVM: x86: Enabled protected " Kirill A. Shutemov
2020-05-25 15:26 ` Vitaly Kuznetsov
2020-05-26 6:16 ` Mike Rapoport
2020-05-26 21:58 ` Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 11/16] KVM: Rework copy_to/from_guest() to avoid direct mapping Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 12/16] x86/kvm: Share steal time page with host Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 13/16] x86/kvmclock: Share hvclock memory with the host Kirill A. Shutemov
2020-05-25 15:22 ` Vitaly Kuznetsov
2020-05-25 15:25 ` Kirill A. Shutemov
2020-05-25 15:42 ` Vitaly Kuznetsov
2020-05-22 12:52 ` [RFC 14/16] KVM: Introduce gfn_to_pfn_memslot_protected() Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 15/16] KVM: Handle protected memory in __kvm_map_gfn()/__kvm_unmap_gfn() Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 16/16] KVM: Unmap protected pages from direct mapping Kirill A. Shutemov
2020-05-26 6:16 ` Mike Rapoport
2020-05-26 22:10 ` Kirill A. Shutemov
2020-05-25 5:27 ` [RFC 00/16] KVM protected memory extension Kirill A. Shutemov
2020-05-25 13:47 ` Liran Alon
2020-05-25 14:46 ` Kirill A. Shutemov
2020-05-25 15:56 ` Liran Alon
2020-05-26 6:17 ` Mike Rapoport
2020-05-26 10:16 ` Liran Alon
2020-05-26 11:38 ` Mike Rapoport
2020-05-27 15:45 ` Dave Hansen
2020-05-27 21:22 ` Mike Rapoport
2020-06-04 15:15 ` Marc Zyngier
2020-06-04 15:48 ` Sean Christopherson
2020-06-04 16:27 ` Marc Zyngier
2020-06-04 16:35 ` Will Deacon
2020-06-04 19:09 ` Nakajima, Jun
2020-06-04 21:03 ` Jim Mattson
2020-06-04 23:29 ` Nakajima, Jun
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=20200525153435.c6mx3pjryyk4j4go@box \
--to=kirill@shutemov.name \
--cc=aarcange@redhat.com \
--cc=andi.kleen@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=keescook@chromium.org \
--cc=kirill.shutemov@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=rick.p.edgecombe@intel.com \
--cc=rientjes@google.com \
--cc=sean.j.christopherson@intel.com \
--cc=vkuznets@redhat.com \
--cc=wad@chromium.org \
--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).