KVM: nVMX: Handle dynamic MSR intercept toggling

Always check vmcs01's MSR bitmap when merging L0 and L1 bitmaps for L2,
and always update the relevant bits in vmcs02.  This fixes two distinct,
but intertwined bugs related to dynamic MSR bitmap modifications.

The first issue is that KVM fails to enable MSR interception in vmcs02
for the FS/GS base MSRs if L1 first runs L2 with interception disabled,
and later enables interception.

The second issue is that KVM fails to honor userspace MSR filtering when
preparing vmcs02.

Fix both issues simultaneous as fixing only one of the issues (doesn't
matter which) would create a mess that no one should have to bisect.
Fixing only the first bug would exacerbate the MSR filtering issue as
userspace would see inconsistent behavior depending on the whims of L1.
Fixing only the second bug (MSR filtering) effectively requires fixing
the first, as the nVMX code only knows how to transition vmcs02's
bitmap from 1->0.

Move the various accessor/mutators that are currently buried in vmx.c
into vmx.h so that they can be shared by the nested code.

Fixes: 1a155254ff93 ("KVM: x86: Introduce MSR filtering")
Fixes: d69129b4e46a ("KVM: nVMX: Disable intercept for FS/GS base MSRs in vmcs02 when possible")
Cc: stable@vger.kernel.org
Cc: Alexander Graf <graf@amazon.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211109013047.2041518-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 63 insertions, 0 deletions

diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index e7db42e3b0ce..d51311fa9ffc 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -400,6 +400,69 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
 
 void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
 
+static inline bool vmx_test_msr_bitmap_read(ulong *msr_bitmap, u32 msr)
+{
+	int f = sizeof(unsigned long);
+
+	if (msr <= 0x1fff)
+		return test_bit(msr, msr_bitmap + 0x000 / f);
+	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
+		return test_bit(msr & 0x1fff, msr_bitmap + 0x400 / f);
+	return true;
+}
+
+static inline bool vmx_test_msr_bitmap_write(ulong *msr_bitmap, u32 msr)
+{
+	int f = sizeof(unsigned long);
+
+	if (msr <= 0x1fff)
+		return test_bit(msr, msr_bitmap + 0x800 / f);
+	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
+		return test_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f);
+	return true;
+}
+
+static inline void vmx_clear_msr_bitmap_read(ulong *msr_bitmap, u32 msr)
+{
+	int f = sizeof(unsigned long);
+
+	if (msr <= 0x1fff)
+		__clear_bit(msr, msr_bitmap + 0x000 / f);
+	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
+		__clear_bit(msr & 0x1fff, msr_bitmap + 0x400 / f);
+}
+
+static inline void vmx_clear_msr_bitmap_write(ulong *msr_bitmap, u32 msr)
+{
+	int f = sizeof(unsigned long);
+
+	if (msr <= 0x1fff)
+		__clear_bit(msr, msr_bitmap + 0x800 / f);
+	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
+		__clear_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f);
+}
+
+static inline void vmx_set_msr_bitmap_read(ulong *msr_bitmap, u32 msr)
+{
+	int f = sizeof(unsigned long);
+
+	if (msr <= 0x1fff)
+		__set_bit(msr, msr_bitmap + 0x000 / f);
+	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
+		__set_bit(msr & 0x1fff, msr_bitmap + 0x400 / f);
+}
+
+static inline void vmx_set_msr_bitmap_write(ulong *msr_bitmap, u32 msr)
+{
+	int f = sizeof(unsigned long);
+
+	if (msr <= 0x1fff)
+		__set_bit(msr, msr_bitmap + 0x800 / f);
+	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
+		__set_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f);
+}
+
+
 static inline u8 vmx_get_rvi(void)
 {
 	return vmcs_read16(GUEST_INTR_STATUS) & 0xff;