[15/15] KVM: VMX: fully implement guest MTRR virtualization

Commit Message

Xiao Guangrong May 30, 2015, 10:59 a.m. UTC

Currently guest MTRR is completely prohibited if cache snoop is supported on
IOMMU (!noncoherent_dma) and host does the emulation based on the knowledge
from host side, however, host side is not the good point to know
what the purpose of guest is. A good example is that pass-throughed VGA
frame buffer is not always UC as host expected

This patchset enables full MTRR virtualization and currently only works on
Intel EPT architecture

Signed-off-by: Xiao Guangrong <[e-mail]>
---
 arch/x86/include/asm/kvm_host.h |  2 +-
 arch/x86/kvm/mmu.c              |  3 +--
 arch/x86/kvm/mtrr.c             |  3 +--
 arch/x86/kvm/svm.c              |  2 +-
 arch/x86/kvm/vmx.c              | 28 ++++------------------------
 5 files changed, 8 insertions(+), 30 deletions(-)

Patch

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5be8f2e..b34de27 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -806,7 +806,7 @@  struct kvm_x86_ops {
 	void (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*get_tdp_level)(void);
-	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
+	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn);
 	int (*get_lpage_level)(void);
 	bool (*rdtscp_supported)(void);
 	bool (*invpcid_supported)(void);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index c8c2a90..828fcd6 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2496,8 +2496,7 @@  static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	if (level > PT_PAGE_TABLE_LEVEL)
 		spte |= PT_PAGE_SIZE_MASK;
 	if (tdp_enabled)
-		spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
-			kvm_is_reserved_pfn(pfn));
+		spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn);
 
 	if (host_writable)
 		spte |= SPTE_HOST_WRITEABLE;
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index 703a66b..bf84218 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -259,8 +259,7 @@  static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr)
 	gfn_t start, end;
 	int index;
 
-	if (msr == MSR_IA32_CR_PAT || !tdp_enabled ||
-	      !kvm_arch_has_noncoherent_dma(vcpu->kvm))
+	if (msr == MSR_IA32_CR_PAT || !tdp_enabled)
 		return;
 
 	if (!mtrr_state->mtrr_enabled && msr != MSR_MTRRdefType)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index b9f9e10..23dd78a 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -4075,7 +4075,7 @@  static bool svm_cpu_has_accelerated_tpr(void)
 	return false;
 }
 
-static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	return 0;
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index fe7a589..78b77be 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8626,31 +8626,11 @@  static int get_ept_level(void)
 	return VMX_EPT_DEFAULT_GAW + 1;
 }
 
-static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
-	u64 ret;
-
-	/* For VT-d and EPT combination
-	 * 1. MMIO: always map as UC
-	 * 2. EPT with VT-d:
-	 *   a. VT-d without snooping control feature: can't guarantee the
-	 *	result, try to trust guest.
-	 *   b. VT-d with snooping control feature: snooping control feature of
-	 *	VT-d engine can guarantee the cache correctness. Just set it
-	 *	to WB to keep consistent with host. So the same as item 3.
-	 * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
-	 *    consistent with host MTRR
-	 */
-	if (is_mmio)
-		ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT;
-	else if (kvm_arch_has_noncoherent_dma(vcpu->kvm))
-		ret = kvm_mtrr_get_guest_memory_type(vcpu, gfn) <<
-		      VMX_EPT_MT_EPTE_SHIFT;
-	else
-		ret = (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT)
-			| VMX_EPT_IPAT_BIT;
+static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	u8 type = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
 
-	return ret;
+	return type << VMX_EPT_MT_EPTE_SHIFT;
 }
 
 static int vmx_get_lpage_level(void)