KVM: MMU: store generation-number into mmio spte

Store the generation-number into bit3 ~ bit11 and bit52 ~ bit61, totally
19 bits can be used, it should be enough for nearly all most common cases

In this patch, the generation-number is always 0, it will be changed in
the later patch

[Gleb: masking generation bits from spte in get_mmio_spte_gfn() and
       get_mmio_spte_access()]

Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 6941fa7..5d9a1fb 100644 (file)
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -197,15 +197,52 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
 
-static void mark_mmio_spte(u64 *sptep, u64 gfn, unsigned access)
+/*
+ * spte bits of bit 3 ~ bit 11 are used as low 9 bits of generation number,
+ * the bits of bits 52 ~ bit 61 are used as high 10 bits of generation
+ * number.
+ */
+#define MMIO_SPTE_GEN_LOW_SHIFT                3
+#define MMIO_SPTE_GEN_HIGH_SHIFT       52
+
+#define MMIO_GEN_LOW_SHIFT             9
+#define MMIO_GEN_LOW_MASK              ((1 << MMIO_GEN_LOW_SHIFT) - 1)
+#define MMIO_MAX_GEN                   ((1 << 19) - 1)
+
+static u64 generation_mmio_spte_mask(unsigned int gen)
+{
+       u64 mask;
+
+       WARN_ON(gen > MMIO_MAX_GEN);
+
+       mask = (gen & MMIO_GEN_LOW_MASK) << MMIO_SPTE_GEN_LOW_SHIFT;
+       mask |= ((u64)gen >> MMIO_GEN_LOW_SHIFT) << MMIO_SPTE_GEN_HIGH_SHIFT;
+       return mask;
+}
+
+static unsigned int get_mmio_spte_generation(u64 spte)
+{
+       unsigned int gen;
+
+       spte &= ~shadow_mmio_mask;
+
+       gen = (spte >> MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_GEN_LOW_MASK;
+       gen |= (spte >> MMIO_SPTE_GEN_HIGH_SHIFT) << MMIO_GEN_LOW_SHIFT;
+       return gen;
+}
+
+static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn,
+                          unsigned access)
 {
        struct kvm_mmu_page *sp =  page_header(__pa(sptep));
+       u64 mask = generation_mmio_spte_mask(0);
 
        access &= ACC_WRITE_MASK | ACC_USER_MASK;
-
+       mask |= shadow_mmio_mask | access | gfn << PAGE_SHIFT;
        sp->mmio_cached = true;
-       trace_mark_mmio_spte(sptep, gfn, access);
-       mmu_spte_set(sptep, shadow_mmio_mask | access | gfn << PAGE_SHIFT);
+
+       trace_mark_mmio_spte(sptep, gfn, access, 0);
+       mmu_spte_set(sptep, mask);
 }
 
 static bool is_mmio_spte(u64 spte)
@@ -215,18 +252,21 @@ static bool is_mmio_spte(u64 spte)
 
 static gfn_t get_mmio_spte_gfn(u64 spte)
 {
-       return (spte & ~shadow_mmio_mask) >> PAGE_SHIFT;
+       u64 mask = generation_mmio_spte_mask(MMIO_MAX_GEN) | shadow_mmio_mask;
+       return (spte & ~mask) >> PAGE_SHIFT;
 }
 
 static unsigned get_mmio_spte_access(u64 spte)
 {
-       return (spte & ~shadow_mmio_mask) & ~PAGE_MASK;
+       u64 mask = generation_mmio_spte_mask(MMIO_MAX_GEN) | shadow_mmio_mask;
+       return (spte & ~mask) & ~PAGE_MASK;
 }
 
-static bool set_mmio_spte(u64 *sptep, gfn_t gfn, pfn_t pfn, unsigned access)
+static bool set_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
+                         pfn_t pfn, unsigned access)
 {
        if (unlikely(is_noslot_pfn(pfn))) {
-               mark_mmio_spte(sptep, gfn, access);
+               mark_mmio_spte(kvm, sptep, gfn, access);
                return true;
        }
 
@@ -2364,7 +2404,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
        u64 spte;
        int ret = 0;
 
-       if (set_mmio_spte(sptep, gfn, pfn, pte_access))
+       if (set_mmio_spte(vcpu->kvm, sptep, gfn, pfn, pte_access))
                return 0;
 
        spte = PT_PRESENT_MASK;
@@ -3427,8 +3467,8 @@ static inline void protect_clean_gpte(unsigned *access, unsigned gpte)
        *access &= mask;
 }
 
-static bool sync_mmio_spte(u64 *sptep, gfn_t gfn, unsigned access,
-                          int *nr_present)
+static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
+                          unsigned access, int *nr_present)
 {
        if (unlikely(is_mmio_spte(*sptep))) {
                if (gfn != get_mmio_spte_gfn(*sptep)) {
@@ -3437,7 +3477,7 @@ static bool sync_mmio_spte(u64 *sptep, gfn_t gfn, unsigned access,
                }
 
                (*nr_present)++;
-               mark_mmio_spte(sptep, gfn, access);
+               mark_mmio_spte(kvm, sptep, gfn, access);
                return true;
        }
 

diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index eb444dd..ad24757 100644 (file)
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -199,23 +199,25 @@ DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_prepare_zap_page,
 
 TRACE_EVENT(
        mark_mmio_spte,
-       TP_PROTO(u64 *sptep, gfn_t gfn, unsigned access),
-       TP_ARGS(sptep, gfn, access),
+       TP_PROTO(u64 *sptep, gfn_t gfn, unsigned access, unsigned int gen),
+       TP_ARGS(sptep, gfn, access, gen),
 
        TP_STRUCT__entry(
                __field(void *, sptep)
                __field(gfn_t, gfn)
                __field(unsigned, access)
+               __field(unsigned int, gen)
        ),
 
        TP_fast_assign(
                __entry->sptep = sptep;
                __entry->gfn = gfn;
                __entry->access = access;
+               __entry->gen = gen;
        ),
 
-       TP_printk("sptep:%p gfn %llx access %x", __entry->sptep, __entry->gfn,
-                 __entry->access)
+       TP_printk("sptep:%p gfn %llx access %x gen %x", __entry->sptep,
+                 __entry->gfn, __entry->access, __entry->gen)
 );
 
 TRACE_EVENT(

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index da20860..fb50fa6 100644 (file)
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -792,7 +792,8 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
                pte_access &= gpte_access(vcpu, gpte);
                protect_clean_gpte(&pte_access, gpte);
 
-               if (sync_mmio_spte(&sp->spt[i], gfn, pte_access, &nr_present))
+               if (sync_mmio_spte(vcpu->kvm, &sp->spt[i], gfn, pte_access,
+                     &nr_present))
                        continue;
 
                if (gfn != sp->gfns[i]) {