KVM: MTRR: observe maxphyaddr from guest CPUID, not host

Conversion of MTRRs to ranges used the maxphyaddr from the boot CPU.
This is wrong, because var_mtrr_range's mask variable then is discontiguous
(like FF00FFFF000, where the first run of 0s corresponds to the bits
between host and guest maxphyaddr).  Instead always set up the masks
to be full 64-bit values---we know that the reserved bits at the top
are zero, and we can restore them when reading the MSR.  This way
var_mtrr_range gets a mask that just works.

Fixes: a13842dc668b40daef4327294a6d3bdc8bd30276
Cc: qemu-stable@nongnu.org
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=107561
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index adc54e1d40a9e161c52a41b1c8860ccf4c15b00f..7747b6d716fa75aeb8a64448b44c15d73d91a88f 100644 (file)
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -300,7 +300,6 @@ static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end)
        *start = range->base & PAGE_MASK;
 
        mask = range->mask & PAGE_MASK;
-       mask |= ~0ULL << boot_cpu_data.x86_phys_bits;
 
        /* This cannot overflow because writing to the reserved bits of
         * variable MTRRs causes a #GP.
@@ -356,10 +355,14 @@ static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
        if (var_mtrr_range_is_valid(cur))
                list_del(&mtrr_state->var_ranges[index].node);
 
+       /* Extend the mask with all 1 bits to the left, since those
+        * bits must implicitly be 0.  The bits are then cleared
+        * when reading them.
+        */
        if (!is_mtrr_mask)
                cur->base = data;
        else
-               cur->mask = data;
+               cur->mask = data | (-1LL << cpuid_maxphyaddr(vcpu));
 
        /* add it to the list if it's enabled. */
        if (var_mtrr_range_is_valid(cur)) {
@@ -426,6 +429,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
                        *pdata = vcpu->arch.mtrr_state.var_ranges[index].base;
                else
                        *pdata = vcpu->arch.mtrr_state.var_ranges[index].mask;
+
+               *pdata &= (1ULL << cpuid_maxphyaddr(vcpu)) - 1;
        }
 
        return 0;