[Qemu-devel] [PATCH] x86: Reset MTRR on vCPU reset

[Alex Williamson <alex.williamson@redhat.com>]

The SDM specifies (June 2014 Vol3 11.11.5):

    On a hardware reset, the P6 and more recent processors clear the
    valid flags in variable-range MTRRs and clear the E flag in the
    IA32_MTRR_DEF_TYPE MSR to disable all MTRRs. All other bits in the
    MTRRs are undefined.

We currently do none of that, so whatever MTRR settings you had prior
to reset is what you have after reset.  Usually this doesn't matter
because KVM often ignores the guest mappings and uses write-back
anyway.  However, if you have an assigned device and an IOMMU that
allows NoSnoop for that device, KVM defers to the guest memory
mappings which are now stale after reset.  The result is that OVMF
rebooting on such a configuration takes a full minute to LZMA
decompress the EFI volume, a process that is nearly instant on the
initial boot.

Add support for reseting the SDM defined bits on vCPU reset.

Also, by my count we're already in danger of overflowing the entries
array that we pass to KVM, so I've topped it up for a bit of headroom.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Cc: qemu-stable@nongnu.org
---

 target-i386/cpu.c |    6 ++++++
 target-i386/cpu.h |    4 ++++
 target-i386/kvm.c |   14 +++++++++++++-
 3 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/target-i386/cpu.c b/target-i386/cpu.c
index 6d008ab..b5ae654 100644
--- a/target-i386/cpu.c
+++ b/target-i386/cpu.c
@@ -2588,6 +2588,12 @@ static void x86_cpu_reset(CPUState *s)
 
     env->xcr0 = 1;
 
+    /* MTRR init - Clear global enable bit and valid bit in each variable reg */
+    env->mtrr_deftype &= ~MSR_MTRRdefType_Enable;
+    for (i = 0; i < MSR_MTRRcap_VCNT; i++) {
+        env->mtrr_var[i].mask &= ~MSR_MTRRphysMask_Valid;
+    }
+
 #if !defined(CONFIG_USER_ONLY)
     /* We hard-wire the BSP to the first CPU. */
     if (s->cpu_index == 0) {
diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index e634d83..139890f 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -337,6 +337,8 @@
 #define MSR_MTRRphysBase(reg)           (0x200 + 2 * (reg))
 #define MSR_MTRRphysMask(reg)           (0x200 + 2 * (reg) + 1)
 
+#define MSR_MTRRphysMask_Valid (1 << 11)
+
 #define MSR_MTRRfix64K_00000            0x250
 #define MSR_MTRRfix16K_80000            0x258
 #define MSR_MTRRfix16K_A0000            0x259
@@ -353,6 +355,8 @@
 
 #define MSR_MTRRdefType                 0x2ff
 
+#define MSR_MTRRdefType_Enable (1 << 11)
+
 #define MSR_CORE_PERF_FIXED_CTR0        0x309
 #define MSR_CORE_PERF_FIXED_CTR1        0x30a
 #define MSR_CORE_PERF_FIXED_CTR2        0x30b
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 097fe11..cb31338 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -79,6 +79,7 @@ static int lm_capable_kernel;
 static bool has_msr_hv_hypercall;
 static bool has_msr_hv_vapic;
 static bool has_msr_hv_tsc;
+static bool has_msr_mtrr;
 
 static bool has_msr_architectural_pmu;
 static uint32_t num_architectural_pmu_counters;
@@ -739,6 +740,10 @@ int kvm_arch_init_vcpu(CPUState *cs)
         env->kvm_xsave_buf = qemu_memalign(4096, sizeof(struct kvm_xsave));
     }
 
+    if (env->features[FEAT_1_EDX] & CPUID_MTRR) {
+        has_msr_mtrr = true;
+    }
+
     return 0;
 }
 
@@ -1183,7 +1188,7 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
     CPUX86State *env = &cpu->env;
     struct {
         struct kvm_msrs info;
-        struct kvm_msr_entry entries[100];
+        struct kvm_msr_entry entries[128];
     } msr_data;
     struct kvm_msr_entry *msrs = msr_data.entries;
     int n = 0, i;
@@ -1278,6 +1283,13 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
             kvm_msr_entry_set(&msrs[n++], HV_X64_MSR_REFERENCE_TSC,
                               env->msr_hv_tsc);
         }
+        if (has_msr_mtrr) {
+            kvm_msr_entry_set(&msrs[n++], MSR_MTRRdefType, env->mtrr_deftype);
+            for (i = 0; i < MSR_MTRRcap_VCNT; i++) {
+                kvm_msr_entry_set(&msrs[n++],
+                                  MSR_MTRRphysMask(i), env->mtrr_var[i].mask);
+            }
+        }
 
         /* Note: MSR_IA32_FEATURE_CONTROL is written separately, see
          *       kvm_put_msr_feature_control. */