}
/*
- * Return the pointer to the largepage write count for a given
- * gfn, handling slots that are not large page aligned.
+ * Return the pointer to the large page information for a given gfn,
+ * handling slots that are not large page aligned.
*/
-static int *slot_largepage_idx(gfn_t gfn,
- struct kvm_memory_slot *slot,
- int level)
+static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
+ struct kvm_memory_slot *slot,
+ int level)
{
unsigned long idx;
idx = (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
(slot->base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
- return &slot->lpage_info[level - 2][idx].write_count;
+ return &slot->lpage_info[level - 2][idx];
}
static void account_shadowed(struct kvm *kvm, gfn_t gfn)
{
struct kvm_memory_slot *slot;
- int *write_count;
+ struct kvm_lpage_info *linfo;
int i;
slot = gfn_to_memslot(kvm, gfn);
for (i = PT_DIRECTORY_LEVEL;
i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
- write_count = slot_largepage_idx(gfn, slot, i);
- *write_count += 1;
+ linfo = lpage_info_slot(gfn, slot, i);
+ linfo->write_count += 1;
}
}
static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
{
struct kvm_memory_slot *slot;
- int *write_count;
+ struct kvm_lpage_info *linfo;
int i;
slot = gfn_to_memslot(kvm, gfn);
for (i = PT_DIRECTORY_LEVEL;
i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
- write_count = slot_largepage_idx(gfn, slot, i);
- *write_count -= 1;
- WARN_ON(*write_count < 0);
+ linfo = lpage_info_slot(gfn, slot, i);
+ linfo->write_count -= 1;
+ WARN_ON(linfo->write_count < 0);
}
}
int level)
{
struct kvm_memory_slot *slot;
- int *largepage_idx;
+ struct kvm_lpage_info *linfo;
slot = gfn_to_memslot(kvm, gfn);
if (slot) {
- largepage_idx = slot_largepage_idx(gfn, slot, level);
- return *largepage_idx;
+ linfo = lpage_info_slot(gfn, slot, level);
+ return linfo->write_count;
}
return 1;
return ret;
}
-static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
+static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn)
{
struct kvm_memory_slot *slot;
- int host_level, level, max_level;
-
slot = gfn_to_memslot(vcpu->kvm, large_gfn);
if (slot && slot->dirty_bitmap)
- return PT_PAGE_TABLE_LEVEL;
+ return true;
+ return false;
+}
+
+static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
+{
+ int host_level, level, max_level;
host_level = host_mapping_level(vcpu->kvm, large_gfn);
static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level)
{
struct kvm_memory_slot *slot;
- unsigned long idx;
+ struct kvm_lpage_info *linfo;
slot = gfn_to_memslot(kvm, gfn);
if (likely(level == PT_PAGE_TABLE_LEVEL))
return &slot->rmap[gfn - slot->base_gfn];
- idx = (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
- (slot->base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
+ linfo = lpage_info_slot(gfn, slot, level);
- return &slot->lpage_info[level - 2][idx].rmap_pde;
+ return &linfo->rmap_pde;
}
/*
end = start + (memslot->npages << PAGE_SHIFT);
if (hva >= start && hva < end) {
gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
+ gfn_t gfn = memslot->base_gfn + gfn_offset;
ret = handler(kvm, &memslot->rmap[gfn_offset], data);
for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) {
- unsigned long idx;
- int sh;
-
- sh = KVM_HPAGE_GFN_SHIFT(PT_DIRECTORY_LEVEL+j);
- idx = ((memslot->base_gfn+gfn_offset) >> sh) -
- (memslot->base_gfn >> sh);
- ret |= handler(kvm,
- &memslot->lpage_info[j][idx].rmap_pde,
- data);
+ struct kvm_lpage_info *linfo;
+
+ linfo = lpage_info_slot(gfn, memslot,
+ PT_DIRECTORY_LEVEL + j);
+ ret |= handler(kvm, &linfo->rmap_pde, data);
}
trace_kvm_age_page(hva, memslot, ret);
retval |= ret;
return young;
}
+static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
+ unsigned long data)
+{
+ u64 *spte;
+ int young = 0;
+
+ /*
+ * If there's no access bit in the secondary pte set by the
+ * hardware it's up to gup-fast/gup to set the access bit in
+ * the primary pte or in the page structure.
+ */
+ if (!shadow_accessed_mask)
+ goto out;
+
+ spte = rmap_next(kvm, rmapp, NULL);
+ while (spte) {
+ u64 _spte = *spte;
+ BUG_ON(!(_spte & PT_PRESENT_MASK));
+ young = _spte & PT_ACCESSED_MASK;
+ if (young) {
+ young = 1;
+ break;
+ }
+ spte = rmap_next(kvm, rmapp, spte);
+ }
+out:
+ return young;
+}
+
#define RMAP_RECYCLE_THRESHOLD 1000
static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp);
}
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+ return kvm_handle_hva(kvm, hva, 0, kvm_test_age_rmapp);
+}
+
#ifdef MMU_DEBUG
static int is_empty_shadow_page(u64 *spt)
{
if (host_writable)
spte |= SPTE_HOST_WRITEABLE;
+ else
+ pte_access &= ~ACC_WRITE_MASK;
spte |= (u64)pfn << PAGE_SHIFT;
}
static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
- int map_writable, int level, gfn_t gfn, pfn_t pfn)
+ int map_writable, int level, gfn_t gfn, pfn_t pfn,
+ bool prefault)
{
struct kvm_shadow_walk_iterator iterator;
struct kvm_mmu_page *sp;
if (iterator.level == level) {
unsigned pte_access = ACC_ALL;
- if (!map_writable)
- pte_access &= ~ACC_WRITE_MASK;
mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, pte_access,
0, write, 1, &pt_write,
- level, gfn, pfn, false, map_writable);
+ level, gfn, pfn, prefault, map_writable);
direct_pte_prefetch(vcpu, iterator.sptep);
++vcpu->stat.pf_fixed;
break;
return 1;
}
-static bool try_async_pf(struct kvm_vcpu *vcpu, bool no_apf, gfn_t gfn,
+static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
+ gfn_t *gfnp, pfn_t *pfnp, int *levelp)
+{
+ pfn_t pfn = *pfnp;
+ gfn_t gfn = *gfnp;
+ int level = *levelp;
+
+ /*
+ * Check if it's a transparent hugepage. If this would be an
+ * hugetlbfs page, level wouldn't be set to
+ * PT_PAGE_TABLE_LEVEL and there would be no adjustment done
+ * here.
+ */
+ if (!is_error_pfn(pfn) && !kvm_is_mmio_pfn(pfn) &&
+ level == PT_PAGE_TABLE_LEVEL &&
+ PageTransCompound(pfn_to_page(pfn)) &&
+ !has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) {
+ unsigned long mask;
+ /*
+ * mmu_notifier_retry was successful and we hold the
+ * mmu_lock here, so the pmd can't become splitting
+ * from under us, and in turn
+ * __split_huge_page_refcount() can't run from under
+ * us and we can safely transfer the refcount from
+ * PG_tail to PG_head as we switch the pfn to tail to
+ * head.
+ */
+ *levelp = level = PT_DIRECTORY_LEVEL;
+ mask = KVM_PAGES_PER_HPAGE(level) - 1;
+ VM_BUG_ON((gfn & mask) != (pfn & mask));
+ if (pfn & mask) {
+ gfn &= ~mask;
+ *gfnp = gfn;
+ kvm_release_pfn_clean(pfn);
+ pfn &= ~mask;
+ if (!get_page_unless_zero(pfn_to_page(pfn)))
+ BUG();
+ *pfnp = pfn;
+ }
+ }
+}
+
+static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
gva_t gva, pfn_t *pfn, bool write, bool *writable);
static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn,
- bool no_apf)
+ bool prefault)
{
int r;
int level;
+ int force_pt_level;
pfn_t pfn;
unsigned long mmu_seq;
bool map_writable;
- level = mapping_level(vcpu, gfn);
-
- /*
- * This path builds a PAE pagetable - so we can map 2mb pages at
- * maximum. Therefore check if the level is larger than that.
- */
- if (level > PT_DIRECTORY_LEVEL)
- level = PT_DIRECTORY_LEVEL;
+ force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn);
+ if (likely(!force_pt_level)) {
+ level = mapping_level(vcpu, gfn);
+ /*
+ * This path builds a PAE pagetable - so we can map
+ * 2mb pages at maximum. Therefore check if the level
+ * is larger than that.
+ */
+ if (level > PT_DIRECTORY_LEVEL)
+ level = PT_DIRECTORY_LEVEL;
- gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
+ gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
+ } else
+ level = PT_PAGE_TABLE_LEVEL;
mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
- if (try_async_pf(vcpu, no_apf, gfn, v, &pfn, write, &map_writable))
+ if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable))
return 0;
/* mmio */
if (mmu_notifier_retry(vcpu, mmu_seq))
goto out_unlock;
kvm_mmu_free_some_pages(vcpu);
- r = __direct_map(vcpu, v, write, map_writable, level, gfn, pfn);
+ if (likely(!force_pt_level))
+ transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
+ r = __direct_map(vcpu, v, write, map_writable, level, gfn, pfn,
+ prefault);
spin_unlock(&vcpu->kvm->mmu_lock);
}
static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
- u32 error_code, bool no_apf)
+ u32 error_code, bool prefault)
{
gfn_t gfn;
int r;
gfn = gva >> PAGE_SHIFT;
return nonpaging_map(vcpu, gva & PAGE_MASK,
- error_code & PFERR_WRITE_MASK, gfn, no_apf);
+ error_code & PFERR_WRITE_MASK, gfn, prefault);
}
static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
{
struct kvm_arch_async_pf arch;
+
arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
arch.gfn = gfn;
arch.direct_map = vcpu->arch.mmu.direct_map;
+ arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
return kvm_setup_async_pf(vcpu, gva, gfn, &arch);
}
return kvm_x86_ops->interrupt_allowed(vcpu);
}
-static bool try_async_pf(struct kvm_vcpu *vcpu, bool no_apf, gfn_t gfn,
+static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
gva_t gva, pfn_t *pfn, bool write, bool *writable)
{
bool async;
put_page(pfn_to_page(*pfn));
- if (!no_apf && can_do_async_pf(vcpu)) {
+ if (!prefault && can_do_async_pf(vcpu)) {
trace_kvm_try_async_get_page(gva, gfn);
if (kvm_find_async_pf_gfn(vcpu, gfn)) {
trace_kvm_async_pf_doublefault(gva, gfn);
}
static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
- bool no_apf)
+ bool prefault)
{
pfn_t pfn;
int r;
int level;
+ int force_pt_level;
gfn_t gfn = gpa >> PAGE_SHIFT;
unsigned long mmu_seq;
int write = error_code & PFERR_WRITE_MASK;
if (r)
return r;
- level = mapping_level(vcpu, gfn);
-
- gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
+ force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn);
+ if (likely(!force_pt_level)) {
+ level = mapping_level(vcpu, gfn);
+ gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
+ } else
+ level = PT_PAGE_TABLE_LEVEL;
mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
- if (try_async_pf(vcpu, no_apf, gfn, gpa, &pfn, write, &map_writable))
+ if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
return 0;
/* mmio */
if (mmu_notifier_retry(vcpu, mmu_seq))
goto out_unlock;
kvm_mmu_free_some_pages(vcpu);
+ if (likely(!force_pt_level))
+ transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
r = __direct_map(vcpu, gpa, write, map_writable,
- level, gfn, pfn);
+ level, gfn, pfn, prefault);
spin_unlock(&vcpu->kvm->mmu_lock);
return r;
static void paging_new_cr3(struct kvm_vcpu *vcpu)
{
- pgprintk("%s: cr3 %lx\n", __func__, vcpu->arch.cr3);
+ pgprintk("%s: cr3 %lx\n", __func__, kvm_read_cr3(vcpu));
mmu_free_roots(vcpu);
}
static unsigned long get_cr3(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.cr3;
+ return kvm_read_cr3(vcpu);
}
static void inject_page_fault(struct kvm_vcpu *vcpu,
{
struct kvm_mmu *context = vcpu->arch.walk_mmu;
+ context->base_role.word = 0;
context->new_cr3 = nonpaging_new_cr3;
context->page_fault = tdp_page_fault;
context->free = nonpaging_free;
}
}
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code)
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
+ void *insn, int insn_len)
{
int r;
enum emulation_result er;
if (r)
goto out;
- er = emulate_instruction(vcpu, cr2, error_code, 0);
+ er = x86_emulate_instruction(vcpu, cr2, 0, insn, insn_len);
switch (er) {
case EMULATE_DONE:
if (!test_bit(slot, sp->slot_bitmap))
continue;
+ if (sp->role.level != PT_PAGE_TABLE_LEVEL)
+ continue;
+
pt = sp->spt;
for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
/* avoid RMW */
if (is_writable_pte(pt[i]))
- pt[i] &= ~PT_WRITABLE_MASK;
+ update_spte(&pt[i], pt[i] & ~PT_WRITABLE_MASK);
}
kvm_flush_remote_tlbs(kvm);
}
kmem_cache_destroy(mmu_page_header_cache);
}
-void kvm_mmu_module_exit(void)
-{
- mmu_destroy_caches();
- percpu_counter_destroy(&kvm_total_used_mmu_pages);
- unregister_shrinker(&mmu_shrinker);
-}
-
int kvm_mmu_module_init(void)
{
pte_chain_cache = kmem_cache_create("kvm_pte_chain",
static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu)
{
- (void)kvm_set_cr3(vcpu, vcpu->arch.cr3);
+ (void)kvm_set_cr3(vcpu, kvm_read_cr3(vcpu));
return 1;
}
}
EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy);
-#ifdef CONFIG_KVM_MMU_AUDIT
-#include "mmu_audit.c"
-#else
-static void mmu_audit_disable(void) { }
-#endif
-
void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
{
ASSERT(vcpu);
destroy_kvm_mmu(vcpu);
free_mmu_pages(vcpu);
mmu_free_memory_caches(vcpu);
+}
+
+#ifdef CONFIG_KVM_MMU_AUDIT
+#include "mmu_audit.c"
+#else
+static void mmu_audit_disable(void) { }
+#endif
+
+void kvm_mmu_module_exit(void)
+{
+ mmu_destroy_caches();
+ percpu_counter_destroy(&kvm_total_used_mmu_pages);
+ unregister_shrinker(&mmu_shrinker);
mmu_audit_disable();
}
git.openpandora.org / pandora-kernel.git / blobdiff