public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: Avi Kivity <avi@redhat.com>
To: Joerg Roedel <joerg.roedel@amd.com>,
	Marcelo Tosatti <mtosatti@redhat.com>
Cc: kvm@vger.kernel.org
Subject: [PATCH] KVM: MMU: Do not unconditionally read PDPTE from guest memory
Date: Thu, 28 Jul 2011 11:36:17 +0300	[thread overview]
Message-ID: <1311842177-9542-1-git-send-email-avi@redhat.com> (raw)

Architecturally, PDPTEs are cached in the PDPTRs when CR3 is reloaded.
On SVM, it is not possible to implement this, but on VMX this is possible
and was indeed implemented until nested SVM changed this to unconditionally
read PDPTEs dynamically.  This has noticable impact when running PAE guests.

Fix by changing the MMU to read PDPTRs from the cache, falling back to
reading from memory for the nested MMU.

Signed-off-by: Avi Kivity <avi@redhat.com>
---

I was unable to test it because i386-on-i386 nsvm appears to be broken.
The immediate cause looks like fsbase leakage from guest to host.

 arch/x86/include/asm/kvm_host.h |    1 +
 arch/x86/kvm/kvm_cache_regs.h   |    7 -------
 arch/x86/kvm/mmu.c              |    5 ++++-
 arch/x86/kvm/paging_tmpl.h      |    2 +-
 arch/x86/kvm/svm.c              |   15 +++++++++++++++
 5 files changed, 21 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 307e3cf..b31a341 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -265,6 +265,7 @@ struct kvm_mmu {
 	void (*new_cr3)(struct kvm_vcpu *vcpu);
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
 	unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
+	u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index);
 	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err,
 			  bool prefault);
 	void (*inject_page_fault)(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 3377d53..544076c 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -45,13 +45,6 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
 	return vcpu->arch.walk_mmu->pdptrs[index];
 }
 
-static inline u64 kvm_pdptr_read_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, int index)
-{
-	load_pdptrs(vcpu, mmu, mmu->get_cr3(vcpu));
-
-	return mmu->pdptrs[index];
-}
-
 static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask)
 {
 	ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9335e1b..10060ac 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2770,7 +2770,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 
 		ASSERT(!VALID_PAGE(root));
 		if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) {
-			pdptr = kvm_pdptr_read_mmu(vcpu, &vcpu->arch.mmu, i);
+			pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i);
 			if (!is_present_gpte(pdptr)) {
 				vcpu->arch.mmu.pae_root[i] = 0;
 				continue;
@@ -3318,6 +3318,7 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 	context->direct_map = true;
 	context->set_cr3 = kvm_x86_ops->set_tdp_cr3;
 	context->get_cr3 = get_cr3;
+	context->get_pdptr = kvm_pdptr_read;
 	context->inject_page_fault = kvm_inject_page_fault;
 	context->nx = is_nx(vcpu);
 
@@ -3376,6 +3377,7 @@ static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.walk_mmu->set_cr3           = kvm_x86_ops->set_cr3;
 	vcpu->arch.walk_mmu->get_cr3           = get_cr3;
+	vcpu->arch.walk_mmu->get_pdptr         = kvm_pdptr_read;
 	vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
 
 	return r;
@@ -3386,6 +3388,7 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 	struct kvm_mmu *g_context = &vcpu->arch.nested_mmu;
 
 	g_context->get_cr3           = get_cr3;
+	g_context->get_pdptr         = kvm_pdptr_read;
 	g_context->inject_page_fault = kvm_inject_page_fault;
 
 	/*
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 507e2b8..f6dd9fe 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -163,7 +163,7 @@ retry_walk:
 
 #if PTTYPE == 64
 	if (walker->level == PT32E_ROOT_LEVEL) {
-		pte = kvm_pdptr_read_mmu(vcpu, mmu, (addr >> 30) & 3);
+		pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
 		trace_kvm_mmu_paging_element(pte, walker->level);
 		if (!is_present_gpte(pte))
 			goto error;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 2b24a88..f043168 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1844,6 +1844,20 @@ static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu)
 	return svm->nested.nested_cr3;
 }
 
+static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	u64 cr3 = svm->nested.nested_cr3;
+	u64 pdpte;
+	int ret;
+
+	ret = kvm_read_guest_page(vcpu->kvm, gpa_to_gfn(cr3), &pdpte,
+				  offset_in_page(cr3) + index * 8, 8);
+	if (ret)
+		return 0;
+	return pdpte;
+}
+
 static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu,
 				   unsigned long root)
 {
@@ -1875,6 +1889,7 @@ static int nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.mmu.set_cr3           = nested_svm_set_tdp_cr3;
 	vcpu->arch.mmu.get_cr3           = nested_svm_get_tdp_cr3;
+	vcpu->arch.mmu.get_pdptr         = nested_svm_get_tdp_pdptr;
 	vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit;
 	vcpu->arch.mmu.shadow_root_level = get_npt_level();
 	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
-- 
1.7.5.3


             reply	other threads:[~2011-07-28  8:36 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-07-28  8:36 Avi Kivity [this message]
2011-07-29 11:31 ` [PATCH] KVM: MMU: Do not unconditionally read PDPTE from guest memory Roedel, Joerg
2011-07-31  8:08   ` Avi Kivity
2011-08-02  9:31     ` Roedel, Joerg
2011-08-02 12:34       ` Avi Kivity
2011-08-02 13:11         ` Roedel, Joerg
2011-08-04  9:49         ` Roedel, Joerg
2011-08-05 15:14 ` Marcelo Tosatti

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=1311842177-9542-1-git-send-email-avi@redhat.com \
    --to=avi@redhat.com \
    --cc=joerg.roedel@amd.com \
    --cc=kvm@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox