*/
bool tdp_enabled = false;
-#undef MMU_DEBUG
+enum {
+ AUDIT_PRE_PAGE_FAULT,
+ AUDIT_POST_PAGE_FAULT,
+ AUDIT_PRE_PTE_WRITE,
+ AUDIT_POST_PTE_WRITE
+};
-#undef AUDIT
+char *audit_point_name[] = {
+ "pre page fault",
+ "post page fault",
+ "pre pte write",
+ "post pte write"
+};
-#ifdef AUDIT
-static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg);
-#else
-static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) {}
-#endif
+#undef MMU_DEBUG
#ifdef MMU_DEBUG
#endif
-#if defined(MMU_DEBUG) || defined(AUDIT)
+#ifdef MMU_DEBUG
static int dbg = 0;
module_param(dbg, bool, 0644);
#endif
if (role.direct)
role.cr4_pae = 0;
role.access = access;
- if (!tdp_enabled && vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) {
+ if (!vcpu->arch.mmu.direct_map
+ && vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) {
quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
role.quadrant = quadrant;
spte |= shadow_user_mask;
if (level > PT_PAGE_TABLE_LEVEL)
spte |= PT_PAGE_SIZE_MASK;
- if (tdp_enabled)
+ if (vcpu->arch.mmu.direct_map)
spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
kvm_is_mmio_pfn(pfn));
spte |= (u64)pfn << PAGE_SHIFT;
if ((pte_access & ACC_WRITE_MASK)
- || (!tdp_enabled && write_fault && !is_write_protection(vcpu)
- && !user_fault)) {
+ || (!vcpu->arch.mmu.direct_map && write_fault
+ && !is_write_protection(vcpu) && !user_fault)) {
if (level > PT_PAGE_TABLE_LEVEL &&
has_wrprotected_page(vcpu->kvm, gfn, level)) {
spte |= PT_WRITABLE_MASK;
- if (!tdp_enabled && !(pte_access & ACC_WRITE_MASK))
+ if (!vcpu->arch.mmu.direct_map
+ && !(pte_access & ACC_WRITE_MASK))
spte &= ~PT_USER_MASK;
/*
int direct = 0;
u64 pdptr;
- root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT;
+ root_gfn = vcpu->arch.mmu.get_cr3(vcpu) >> PAGE_SHIFT;
if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
hpa_t root = vcpu->arch.mmu.root_hpa;
ASSERT(!VALID_PAGE(root));
if (mmu_check_root(vcpu, root_gfn))
return 1;
- if (tdp_enabled) {
+ if (vcpu->arch.mmu.direct_map) {
direct = 1;
root_gfn = 0;
}
return 0;
}
direct = !is_paging(vcpu);
+
+ if (mmu_check_root(vcpu, root_gfn))
+ return 1;
+
for (i = 0; i < 4; ++i) {
hpa_t root = vcpu->arch.mmu.pae_root[i];
continue;
}
root_gfn = pdptr >> PAGE_SHIFT;
+ if (mmu_check_root(vcpu, root_gfn))
+ return 1;
} else if (vcpu->arch.mmu.root_level == 0)
root_gfn = 0;
- if (mmu_check_root(vcpu, root_gfn))
- return 1;
- if (tdp_enabled) {
+ if (vcpu->arch.mmu.direct_map) {
direct = 1;
root_gfn = i << 30;
}
mmu_free_roots(vcpu);
}
-static int nonpaging_init_context(struct kvm_vcpu *vcpu)
+static int nonpaging_init_context(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
-
context->new_cr3 = nonpaging_new_cr3;
context->page_fault = nonpaging_page_fault;
context->gva_to_gpa = nonpaging_gva_to_gpa;
context->root_level = 0;
context->shadow_root_level = PT32E_ROOT_LEVEL;
context->root_hpa = INVALID_PAGE;
+ context->direct_map = true;
return 0;
}
mmu_free_roots(vcpu);
}
-static void inject_page_fault(struct kvm_vcpu *vcpu,
- u64 addr,
- u32 err_code)
+static unsigned long get_cr3(struct kvm_vcpu *vcpu)
{
- kvm_inject_page_fault(vcpu, addr, err_code);
+ return vcpu->arch.cr3;
+}
+
+static void inject_page_fault(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.mmu.inject_page_fault(vcpu);
}
static void paging_free(struct kvm_vcpu *vcpu)
nonpaging_free(vcpu);
}
-static bool is_rsvd_bits_set(struct kvm_vcpu *vcpu, u64 gpte, int level)
+static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
{
int bit7;
bit7 = (gpte >> 7) & 1;
- return (gpte & vcpu->arch.mmu.rsvd_bits_mask[bit7][level-1]) != 0;
+ return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0;
}
#define PTTYPE 64
#include "paging_tmpl.h"
#undef PTTYPE
-static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
+static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context,
+ int level)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
int maxphyaddr = cpuid_maxphyaddr(vcpu);
u64 exb_bit_rsvd = 0;
}
}
-static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level)
+static int paging64_init_context_common(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context,
+ int level)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
+ reset_rsvds_bits_mask(vcpu, context, level);
ASSERT(is_pae(vcpu));
context->new_cr3 = paging_new_cr3;
context->root_level = level;
context->shadow_root_level = level;
context->root_hpa = INVALID_PAGE;
+ context->direct_map = false;
return 0;
}
-static int paging64_init_context(struct kvm_vcpu *vcpu)
+static int paging64_init_context(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context)
{
- reset_rsvds_bits_mask(vcpu, PT64_ROOT_LEVEL);
- return paging64_init_context_common(vcpu, PT64_ROOT_LEVEL);
+ return paging64_init_context_common(vcpu, context, PT64_ROOT_LEVEL);
}
-static int paging32_init_context(struct kvm_vcpu *vcpu)
+static int paging32_init_context(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
+ reset_rsvds_bits_mask(vcpu, context, PT32_ROOT_LEVEL);
- reset_rsvds_bits_mask(vcpu, PT32_ROOT_LEVEL);
context->new_cr3 = paging_new_cr3;
context->page_fault = paging32_page_fault;
context->gva_to_gpa = paging32_gva_to_gpa;
context->root_level = PT32_ROOT_LEVEL;
context->shadow_root_level = PT32E_ROOT_LEVEL;
context->root_hpa = INVALID_PAGE;
+ context->direct_map = false;
return 0;
}
-static int paging32E_init_context(struct kvm_vcpu *vcpu)
+static int paging32E_init_context(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context)
{
- reset_rsvds_bits_mask(vcpu, PT32E_ROOT_LEVEL);
- return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL);
+ return paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL);
}
static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
context->invlpg = nonpaging_invlpg;
context->shadow_root_level = kvm_x86_ops->get_tdp_level();
context->root_hpa = INVALID_PAGE;
+ context->direct_map = true;
+ context->set_cr3 = kvm_x86_ops->set_tdp_cr3;
+ context->get_cr3 = get_cr3;
+ context->inject_page_fault = kvm_inject_page_fault;
if (!is_paging(vcpu)) {
context->gva_to_gpa = nonpaging_gva_to_gpa;
context->root_level = 0;
} else if (is_long_mode(vcpu)) {
- reset_rsvds_bits_mask(vcpu, PT64_ROOT_LEVEL);
+ reset_rsvds_bits_mask(vcpu, context, PT64_ROOT_LEVEL);
context->gva_to_gpa = paging64_gva_to_gpa;
context->root_level = PT64_ROOT_LEVEL;
} else if (is_pae(vcpu)) {
- reset_rsvds_bits_mask(vcpu, PT32E_ROOT_LEVEL);
+ reset_rsvds_bits_mask(vcpu, context, PT32E_ROOT_LEVEL);
context->gva_to_gpa = paging64_gva_to_gpa;
context->root_level = PT32E_ROOT_LEVEL;
} else {
- reset_rsvds_bits_mask(vcpu, PT32_ROOT_LEVEL);
+ reset_rsvds_bits_mask(vcpu, context, PT32_ROOT_LEVEL);
context->gva_to_gpa = paging32_gva_to_gpa;
context->root_level = PT32_ROOT_LEVEL;
}
return 0;
}
-static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
+int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
{
int r;
-
ASSERT(vcpu);
ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
if (!is_paging(vcpu))
- r = nonpaging_init_context(vcpu);
+ r = nonpaging_init_context(vcpu, context);
else if (is_long_mode(vcpu))
- r = paging64_init_context(vcpu);
+ r = paging64_init_context(vcpu, context);
else if (is_pae(vcpu))
- r = paging32E_init_context(vcpu);
+ r = paging32E_init_context(vcpu, context);
else
- r = paging32_init_context(vcpu);
+ r = paging32_init_context(vcpu, context);
vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu);
- vcpu->arch.mmu.base_role.cr0_wp = is_write_protection(vcpu);
+ vcpu->arch.mmu.base_role.cr0_wp = is_write_protection(vcpu);
+
+ return r;
+}
+EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
+
+static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
+{
+ int r = kvm_init_shadow_mmu(vcpu, &vcpu->arch.mmu);
+
+ vcpu->arch.mmu.set_cr3 = kvm_x86_ops->set_cr3;
+ vcpu->arch.mmu.get_cr3 = get_cr3;
+ vcpu->arch.mmu.inject_page_fault = kvm_inject_page_fault;
return r;
}
if (r)
goto out;
/* set_cr3() should ensure TLB has been flushed */
- kvm_x86_ops->set_cr3(vcpu, vcpu->arch.mmu.root_hpa);
+ vcpu->arch.mmu.set_cr3(vcpu, vcpu->arch.mmu.root_hpa);
out:
return r;
}
return;
}
- if (is_rsvd_bits_set(vcpu, *(u64 *)new, PT_PAGE_TABLE_LEVEL))
+ if (is_rsvd_bits_set(&vcpu->arch.mmu, *(u64 *)new, PT_PAGE_TABLE_LEVEL))
return;
++vcpu->kvm->stat.mmu_pte_updated;
kvm_mmu_access_page(vcpu, gfn);
kvm_mmu_free_some_pages(vcpu);
++vcpu->kvm->stat.mmu_pte_write;
- kvm_mmu_audit(vcpu, "pre pte write");
+ trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
if (guest_initiated) {
if (gfn == vcpu->arch.last_pt_write_gfn
&& !last_updated_pte_accessed(vcpu)) {
}
mmu_pte_write_flush_tlb(vcpu, zap_page, remote_flush, local_flush);
kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
- kvm_mmu_audit(vcpu, "post pte write");
+ trace_kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE);
spin_unlock(&vcpu->kvm->mmu_lock);
if (!is_error_pfn(vcpu->arch.update_pte.pfn)) {
kvm_release_pfn_clean(vcpu->arch.update_pte.pfn);
gpa_t gpa;
int r;
- if (tdp_enabled)
+ if (vcpu->arch.mmu.direct_map)
return 0;
gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
}
EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy);
-#ifdef AUDIT
-
-static const char *audit_msg;
-
-static gva_t canonicalize(gva_t gva)
-{
-#ifdef CONFIG_X86_64
- gva = (long long)(gva << 16) >> 16;
-#endif
- return gva;
-}
-
-
-typedef void (*inspect_spte_fn) (struct kvm *kvm, u64 *sptep);
-
-static void __mmu_spte_walk(struct kvm *kvm, struct kvm_mmu_page *sp,
- inspect_spte_fn fn)
-{
- int i;
-
- for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
- u64 ent = sp->spt[i];
-
- if (is_shadow_present_pte(ent)) {
- if (!is_last_spte(ent, sp->role.level)) {
- struct kvm_mmu_page *child;
- child = page_header(ent & PT64_BASE_ADDR_MASK);
- __mmu_spte_walk(kvm, child, fn);
- } else
- fn(kvm, &sp->spt[i]);
- }
- }
-}
-
-static void mmu_spte_walk(struct kvm_vcpu *vcpu, inspect_spte_fn fn)
-{
- int i;
- struct kvm_mmu_page *sp;
-
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
- return;
- if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
- hpa_t root = vcpu->arch.mmu.root_hpa;
- sp = page_header(root);
- __mmu_spte_walk(vcpu->kvm, sp, fn);
- return;
- }
- for (i = 0; i < 4; ++i) {
- hpa_t root = vcpu->arch.mmu.pae_root[i];
-
- if (root && VALID_PAGE(root)) {
- root &= PT64_BASE_ADDR_MASK;
- sp = page_header(root);
- __mmu_spte_walk(vcpu->kvm, sp, fn);
- }
- }
- return;
-}
-
-static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte,
- gva_t va, int level)
-{
- u64 *pt = __va(page_pte & PT64_BASE_ADDR_MASK);
- int i;
- gva_t va_delta = 1ul << (PAGE_SHIFT + 9 * (level - 1));
-
- for (i = 0; i < PT64_ENT_PER_PAGE; ++i, va += va_delta) {
- u64 ent = pt[i];
-
- if (ent == shadow_trap_nonpresent_pte)
- continue;
-
- va = canonicalize(va);
- if (is_shadow_present_pte(ent) && !is_last_spte(ent, level))
- audit_mappings_page(vcpu, ent, va, level - 1);
- else {
- gpa_t gpa = kvm_mmu_gva_to_gpa_read(vcpu, va, NULL);
- gfn_t gfn = gpa >> PAGE_SHIFT;
- pfn_t pfn = gfn_to_pfn(vcpu->kvm, gfn);
- hpa_t hpa = (hpa_t)pfn << PAGE_SHIFT;
-
- if (is_error_pfn(pfn)) {
- kvm_release_pfn_clean(pfn);
- continue;
- }
-
- if (is_shadow_present_pte(ent)
- && (ent & PT64_BASE_ADDR_MASK) != hpa)
- printk(KERN_ERR "xx audit error: (%s) levels %d"
- " gva %lx gpa %llx hpa %llx ent %llx %d\n",
- audit_msg, vcpu->arch.mmu.root_level,
- va, gpa, hpa, ent,
- is_shadow_present_pte(ent));
- else if (ent == shadow_notrap_nonpresent_pte
- && !is_error_hpa(hpa))
- printk(KERN_ERR "audit: (%s) notrap shadow,"
- " valid guest gva %lx\n", audit_msg, va);
- kvm_release_pfn_clean(pfn);
-
- }
- }
-}
-
-static void audit_mappings(struct kvm_vcpu *vcpu)
-{
- unsigned i;
-
- if (vcpu->arch.mmu.root_level == 4)
- audit_mappings_page(vcpu, vcpu->arch.mmu.root_hpa, 0, 4);
- else
- for (i = 0; i < 4; ++i)
- if (vcpu->arch.mmu.pae_root[i] & PT_PRESENT_MASK)
- audit_mappings_page(vcpu,
- vcpu->arch.mmu.pae_root[i],
- i << 30,
- 2);
-}
-
-static int count_rmaps(struct kvm_vcpu *vcpu)
-{
- struct kvm *kvm = vcpu->kvm;
- struct kvm_memslots *slots;
- int nmaps = 0;
- int i, j, k, idx;
-
- idx = srcu_read_lock(&kvm->srcu);
- slots = kvm_memslots(kvm);
- for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
- struct kvm_memory_slot *m = &slots->memslots[i];
- struct kvm_rmap_desc *d;
-
- for (j = 0; j < m->npages; ++j) {
- unsigned long *rmapp = &m->rmap[j];
-
- if (!*rmapp)
- continue;
- if (!(*rmapp & 1)) {
- ++nmaps;
- continue;
- }
- d = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
- while (d) {
- for (k = 0; k < RMAP_EXT; ++k)
- if (d->sptes[k])
- ++nmaps;
- else
- break;
- d = d->more;
- }
- }
- }
- srcu_read_unlock(&kvm->srcu, idx);
- return nmaps;
-}
-
-void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
-{
- unsigned long *rmapp;
- struct kvm_mmu_page *rev_sp;
- gfn_t gfn;
-
-
- rev_sp = page_header(__pa(sptep));
- gfn = kvm_mmu_page_get_gfn(rev_sp, sptep - rev_sp->spt);
-
- if (!gfn_to_memslot(kvm, gfn)) {
- if (!printk_ratelimit())
- return;
- printk(KERN_ERR "%s: no memslot for gfn %llx\n",
- audit_msg, gfn);
- printk(KERN_ERR "%s: index %ld of sp (gfn=%llx)\n",
- audit_msg, (long int)(sptep - rev_sp->spt),
- rev_sp->gfn);
- dump_stack();
- return;
- }
-
- rmapp = gfn_to_rmap(kvm, gfn, rev_sp->role.level);
- if (!*rmapp) {
- if (!printk_ratelimit())
- return;
- printk(KERN_ERR "%s: no rmap for writable spte %llx\n",
- audit_msg, *sptep);
- dump_stack();
- }
-}
-
-void audit_sptes_have_rmaps(struct kvm_vcpu *vcpu)
-{
- mmu_spte_walk(vcpu, inspect_spte_has_rmap);
-}
-
-static void check_mappings_rmap(struct kvm_vcpu *vcpu)
-{
- struct kvm_mmu_page *sp;
- int i;
-
- list_for_each_entry(sp, &vcpu->kvm->arch.active_mmu_pages, link) {
- u64 *pt = sp->spt;
-
- if (sp->role.level != PT_PAGE_TABLE_LEVEL)
- continue;
-
- for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
- if (!is_rmap_spte(pt[i]))
- continue;
-
- inspect_spte_has_rmap(vcpu->kvm, &pt[i]);
- }
- }
- return;
-}
-
-static void audit_rmap(struct kvm_vcpu *vcpu)
-{
- check_mappings_rmap(vcpu);
- count_rmaps(vcpu);
-}
-
-static void audit_write_protection(struct kvm_vcpu *vcpu)
-{
- struct kvm_mmu_page *sp;
- struct kvm_memory_slot *slot;
- unsigned long *rmapp;
- u64 *spte;
- gfn_t gfn;
-
- list_for_each_entry(sp, &vcpu->kvm->arch.active_mmu_pages, link) {
- if (sp->role.direct)
- continue;
- if (sp->unsync)
- continue;
-
- slot = gfn_to_memslot(vcpu->kvm, sp->gfn);
- rmapp = &slot->rmap[gfn - slot->base_gfn];
-
- spte = rmap_next(vcpu->kvm, rmapp, NULL);
- while (spte) {
- if (is_writable_pte(*spte))
- printk(KERN_ERR "%s: (%s) shadow page has "
- "writable mappings: gfn %llx role %x\n",
- __func__, audit_msg, sp->gfn,
- sp->role.word);
- spte = rmap_next(vcpu->kvm, rmapp, spte);
- }
- }
-}
-
-static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg)
-{
- int olddbg = dbg;
-
- dbg = 0;
- audit_msg = msg;
- audit_rmap(vcpu);
- audit_write_protection(vcpu);
- if (strcmp("pre pte write", audit_msg) != 0)
- audit_mappings(vcpu);
- audit_sptes_have_rmaps(vcpu);
- dbg = olddbg;
-}
-
+#ifdef CONFIG_KVM_MMU_AUDIT
+#include "mmu_audit.c"
#endif
projects / linux-2.6-block.git / blobdiff