*/
#include "mmu.h"
+#include "kvm_cache_regs.h"
#include <linux/kvm_host.h>
#include <linux/types.h>
#define PFERR_PRESENT_MASK (1U << 0)
#define PFERR_WRITE_MASK (1U << 1)
#define PFERR_USER_MASK (1U << 2)
+#define PFERR_RSVD_MASK (1U << 3)
#define PFERR_FETCH_MASK (1U << 4)
#define PT_DIRECTORY_LEVEL 2
#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
struct kvm_rmap_desc {
- u64 *shadow_ptes[RMAP_EXT];
+ u64 *sptes[RMAP_EXT];
struct kvm_rmap_desc *more;
};
static u64 __read_mostly shadow_user_mask;
static u64 __read_mostly shadow_accessed_mask;
static u64 __read_mostly shadow_dirty_mask;
-static u64 __read_mostly shadow_mt_mask;
+
+static inline u64 rsvd_bits(int s, int e)
+{
+ return ((1ULL << (e - s + 1)) - 1) << s;
+}
void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte)
{
EXPORT_SYMBOL_GPL(kvm_mmu_set_base_ptes);
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
- u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 mt_mask)
+ u64 dirty_mask, u64 nx_mask, u64 x_mask)
{
shadow_user_mask = user_mask;
shadow_accessed_mask = accessed_mask;
shadow_dirty_mask = dirty_mask;
shadow_nx_mask = nx_mask;
shadow_x_mask = x_mask;
- shadow_mt_mask = mt_mask;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
return vcpu->arch.shadow_efer & EFER_NX;
}
-static int is_present_pte(unsigned long pte)
-{
- return pte & PT_PRESENT_MASK;
-}
-
static int is_shadow_present_pte(u64 pte)
{
return pte != shadow_trap_nonpresent_pte
return pte & PT_WRITABLE_MASK;
}
-static int is_dirty_pte(unsigned long pte)
+static int is_dirty_gpte(unsigned long pte)
{
- return pte & shadow_dirty_mask;
+ return pte & PT_DIRTY_MASK;
}
-static int is_rmap_pte(u64 pte)
+static int is_rmap_spte(u64 pte)
{
return is_shadow_present_pte(pte);
}
+static int is_last_spte(u64 pte, int level)
+{
+ if (level == PT_PAGE_TABLE_LEVEL)
+ return 1;
+ if (level == PT_DIRECTORY_LEVEL && is_large_pte(pte))
+ return 1;
+ return 0;
+}
+
static pfn_t spte_to_pfn(u64 pte)
{
return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
return (gpte & PT32_DIR_PSE36_MASK) << shift;
}
-static void set_shadow_pte(u64 *sptep, u64 spte)
+static void __set_spte(u64 *sptep, u64 spte)
{
#ifdef CONFIG_X86_64
set_64bit((unsigned long *)sptep, spte);
*
* If rmapp bit zero is one, (then rmap & ~1) points to a struct kvm_rmap_desc
* containing more mappings.
+ *
+ * Returns the number of rmap entries before the spte was added or zero if
+ * the spte was not added.
+ *
*/
-static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
+static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
{
struct kvm_mmu_page *sp;
struct kvm_rmap_desc *desc;
unsigned long *rmapp;
- int i;
+ int i, count = 0;
- if (!is_rmap_pte(*spte))
- return;
+ if (!is_rmap_spte(*spte))
+ return count;
gfn = unalias_gfn(vcpu->kvm, gfn);
sp = page_header(__pa(spte));
sp->gfns[spte - sp->spt] = gfn;
} else if (!(*rmapp & 1)) {
rmap_printk("rmap_add: %p %llx 1->many\n", spte, *spte);
desc = mmu_alloc_rmap_desc(vcpu);
- desc->shadow_ptes[0] = (u64 *)*rmapp;
- desc->shadow_ptes[1] = spte;
+ desc->sptes[0] = (u64 *)*rmapp;
+ desc->sptes[1] = spte;
*rmapp = (unsigned long)desc | 1;
} else {
rmap_printk("rmap_add: %p %llx many->many\n", spte, *spte);
desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
- while (desc->shadow_ptes[RMAP_EXT-1] && desc->more)
+ while (desc->sptes[RMAP_EXT-1] && desc->more) {
desc = desc->more;
- if (desc->shadow_ptes[RMAP_EXT-1]) {
+ count += RMAP_EXT;
+ }
+ if (desc->sptes[RMAP_EXT-1]) {
desc->more = mmu_alloc_rmap_desc(vcpu);
desc = desc->more;
}
- for (i = 0; desc->shadow_ptes[i]; ++i)
+ for (i = 0; desc->sptes[i]; ++i)
;
- desc->shadow_ptes[i] = spte;
+ desc->sptes[i] = spte;
}
+ return count;
}
static void rmap_desc_remove_entry(unsigned long *rmapp,
{
int j;
- for (j = RMAP_EXT - 1; !desc->shadow_ptes[j] && j > i; --j)
+ for (j = RMAP_EXT - 1; !desc->sptes[j] && j > i; --j)
;
- desc->shadow_ptes[i] = desc->shadow_ptes[j];
- desc->shadow_ptes[j] = NULL;
+ desc->sptes[i] = desc->sptes[j];
+ desc->sptes[j] = NULL;
if (j != 0)
return;
if (!prev_desc && !desc->more)
- *rmapp = (unsigned long)desc->shadow_ptes[0];
+ *rmapp = (unsigned long)desc->sptes[0];
else
if (prev_desc)
prev_desc->more = desc->more;
unsigned long *rmapp;
int i;
- if (!is_rmap_pte(*spte))
+ if (!is_rmap_spte(*spte))
return;
sp = page_header(__pa(spte));
pfn = spte_to_pfn(*spte);
desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
prev_desc = NULL;
while (desc) {
- for (i = 0; i < RMAP_EXT && desc->shadow_ptes[i]; ++i)
- if (desc->shadow_ptes[i] == spte) {
+ for (i = 0; i < RMAP_EXT && desc->sptes[i]; ++i)
+ if (desc->sptes[i] == spte) {
rmap_desc_remove_entry(rmapp,
desc, i,
prev_desc);
prev_desc = NULL;
prev_spte = NULL;
while (desc) {
- for (i = 0; i < RMAP_EXT && desc->shadow_ptes[i]; ++i) {
+ for (i = 0; i < RMAP_EXT && desc->sptes[i]; ++i) {
if (prev_spte == spte)
- return desc->shadow_ptes[i];
- prev_spte = desc->shadow_ptes[i];
+ return desc->sptes[i];
+ prev_spte = desc->sptes[i];
}
desc = desc->more;
}
BUG_ON(!(*spte & PT_PRESENT_MASK));
rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte);
if (is_writeble_pte(*spte)) {
- set_shadow_pte(spte, *spte & ~PT_WRITABLE_MASK);
+ __set_spte(spte, *spte & ~PT_WRITABLE_MASK);
write_protected = 1;
}
spte = rmap_next(kvm, rmapp, spte);
if (is_writeble_pte(*spte)) {
rmap_remove(kvm, spte);
--kvm->stat.lpages;
- set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+ __set_spte(spte, shadow_trap_nonpresent_pte);
spte = NULL;
write_protected = 1;
}
BUG_ON(!(*spte & PT_PRESENT_MASK));
rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", spte, *spte);
rmap_remove(kvm, spte);
- set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+ __set_spte(spte, shadow_trap_nonpresent_pte);
need_tlb_flush = 1;
}
return need_tlb_flush;
return young;
}
+#define RMAP_RECYCLE_THRESHOLD 1000
+
+static void rmap_recycle(struct kvm_vcpu *vcpu, gfn_t gfn, int lpage)
+{
+ unsigned long *rmapp;
+
+ gfn = unalias_gfn(vcpu->kvm, gfn);
+ rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage);
+
+ kvm_unmap_rmapp(vcpu->kvm, rmapp);
+ kvm_flush_remote_tlbs(vcpu->kvm);
+}
+
int kvm_age_hva(struct kvm *kvm, unsigned long hva)
{
return kvm_handle_hva(kvm, hva, kvm_age_rmapp);
set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&sp->oos_link);
- ASSERT(is_empty_shadow_page(sp->spt));
bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
sp->multimapped = 0;
sp->parent_pte = parent_pte;
idx < 512; \
idx = find_next_bit(bitmap, 512, idx+1))
-int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
- int idx)
+static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
+ int idx)
{
int i;
index = kvm_page_table_hashfn(gfn);
bucket = &kvm->arch.mmu_page_hash[index];
hlist_for_each_entry(sp, node, bucket, hash_link)
- if (sp->gfn == gfn && !sp->role.metaphysical
+ if (sp->gfn == gfn && !sp->role.direct
&& !sp->role.invalid) {
pgprintk("%s: found role %x\n",
__func__, sp->role.word);
return NULL;
}
-static void kvm_unlink_unsync_global(struct kvm *kvm, struct kvm_mmu_page *sp)
-{
- list_del(&sp->oos_link);
- --kvm->stat.mmu_unsync_global;
-}
-
static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
WARN_ON(!sp->unsync);
sp->unsync = 0;
- if (sp->global)
- kvm_unlink_unsync_global(kvm, sp);
--kvm->stat.mmu_unsync;
}
i < pvec.nr && ({ sp = pvec.page[i].sp; 1;}); \
i = mmu_pages_next(&pvec, &parents, i))
-int mmu_pages_next(struct kvm_mmu_pages *pvec, struct mmu_page_path *parents,
- int i)
+static int mmu_pages_next(struct kvm_mmu_pages *pvec,
+ struct mmu_page_path *parents,
+ int i)
{
int n;
return n;
}
-void mmu_pages_clear_parents(struct mmu_page_path *parents)
+static void mmu_pages_clear_parents(struct mmu_page_path *parents)
{
struct kvm_mmu_page *sp;
unsigned int level = 0;
gfn_t gfn,
gva_t gaddr,
unsigned level,
- int metaphysical,
+ int direct,
unsigned access,
u64 *parent_pte)
{
role = vcpu->arch.mmu.base_role;
role.level = level;
- role.metaphysical = metaphysical;
+ role.direct = direct;
role.access = access;
if (vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) {
quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word);
sp->gfn = gfn;
sp->role = role;
- sp->global = role.cr4_pge;
hlist_add_head(&sp->hash_link, bucket);
- if (!metaphysical) {
+ if (!direct) {
if (rmap_write_protect(vcpu->kvm, gfn))
kvm_flush_remote_tlbs(vcpu->kvm);
account_shadowed(vcpu->kvm, gfn);
pt = sp->spt;
- if (sp->role.level == PT_PAGE_TABLE_LEVEL) {
- for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
- if (is_shadow_present_pte(pt[i]))
- rmap_remove(kvm, &pt[i]);
- pt[i] = shadow_trap_nonpresent_pte;
- }
- return;
- }
-
for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
ent = pt[i];
if (is_shadow_present_pte(ent)) {
- if (!is_large_pte(ent)) {
+ if (!is_last_spte(ent, sp->role.level)) {
ent &= PT64_BASE_ADDR_MASK;
mmu_page_remove_parent_pte(page_header(ent),
&pt[i]);
} else {
- --kvm->stat.lpages;
+ if (is_large_pte(ent))
+ --kvm->stat.lpages;
rmap_remove(kvm, &pt[i]);
}
}
static void kvm_mmu_reset_last_pte_updated(struct kvm *kvm)
{
int i;
+ struct kvm_vcpu *vcpu;
- for (i = 0; i < KVM_MAX_VCPUS; ++i)
- if (kvm->vcpus[i])
- kvm->vcpus[i]->arch.last_pte_updated = NULL;
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ vcpu->arch.last_pte_updated = NULL;
}
static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
}
BUG_ON(!parent_pte);
kvm_mmu_put_page(sp, parent_pte);
- set_shadow_pte(parent_pte, shadow_trap_nonpresent_pte);
+ __set_spte(parent_pte, shadow_trap_nonpresent_pte);
}
}
kvm_mmu_page_unlink_children(kvm, sp);
kvm_mmu_unlink_parents(kvm, sp);
kvm_flush_remote_tlbs(kvm);
- if (!sp->role.invalid && !sp->role.metaphysical)
+ if (!sp->role.invalid && !sp->role.direct)
unaccount_shadowed(kvm, sp->gfn);
if (sp->unsync)
kvm_unlink_unsync_page(kvm, sp);
*/
void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages)
{
+ int used_pages;
+
+ used_pages = kvm->arch.n_alloc_mmu_pages - kvm->arch.n_free_mmu_pages;
+ used_pages = max(0, used_pages);
+
/*
* If we set the number of mmu pages to be smaller be than the
* number of actived pages , we must to free some mmu pages before we
* change the value
*/
- if ((kvm->arch.n_alloc_mmu_pages - kvm->arch.n_free_mmu_pages) >
- kvm_nr_mmu_pages) {
- int n_used_mmu_pages = kvm->arch.n_alloc_mmu_pages
- - kvm->arch.n_free_mmu_pages;
-
- while (n_used_mmu_pages > kvm_nr_mmu_pages) {
+ if (used_pages > kvm_nr_mmu_pages) {
+ while (used_pages > kvm_nr_mmu_pages) {
struct kvm_mmu_page *page;
page = container_of(kvm->arch.active_mmu_pages.prev,
struct kvm_mmu_page, link);
kvm_mmu_zap_page(kvm, page);
- n_used_mmu_pages--;
+ used_pages--;
}
kvm->arch.n_free_mmu_pages = 0;
}
index = kvm_page_table_hashfn(gfn);
bucket = &kvm->arch.mmu_page_hash[index];
hlist_for_each_entry_safe(sp, node, n, bucket, hash_link)
- if (sp->gfn == gfn && !sp->role.metaphysical) {
+ if (sp->gfn == gfn && !sp->role.direct) {
pgprintk("%s: gfn %lx role %x\n", __func__, gfn,
sp->role.word);
r = 1;
index = kvm_page_table_hashfn(gfn);
bucket = &kvm->arch.mmu_page_hash[index];
hlist_for_each_entry_safe(sp, node, nn, bucket, hash_link) {
- if (sp->gfn == gfn && !sp->role.metaphysical
+ if (sp->gfn == gfn && !sp->role.direct
&& !sp->role.invalid) {
pgprintk("%s: zap %lx %x\n",
__func__, gfn, sp->role.word);
for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
if (pt[i] == shadow_notrap_nonpresent_pte)
- set_shadow_pte(&pt[i], shadow_trap_nonpresent_pte);
+ __set_spte(&pt[i], shadow_trap_nonpresent_pte);
}
}
return mtrr_state->def_type;
}
-static u8 get_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
+u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
{
u8 mtrr;
mtrr = MTRR_TYPE_WRBACK;
return mtrr;
}
+EXPORT_SYMBOL_GPL(kvm_get_guest_memory_type);
static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
bucket = &vcpu->kvm->arch.mmu_page_hash[index];
/* don't unsync if pagetable is shadowed with multiple roles */
hlist_for_each_entry_safe(s, node, n, bucket, hash_link) {
- if (s->gfn != sp->gfn || s->role.metaphysical)
+ if (s->gfn != sp->gfn || s->role.direct)
continue;
if (s->role.word != sp->role.word)
return 1;
++vcpu->kvm->stat.mmu_unsync;
sp->unsync = 1;
- if (sp->global) {
- list_add(&sp->oos_link, &vcpu->kvm->arch.oos_global_pages);
- ++vcpu->kvm->stat.mmu_unsync_global;
- } else
- kvm_mmu_mark_parents_unsync(vcpu, sp);
+ kvm_mmu_mark_parents_unsync(vcpu, sp);
mmu_convert_notrap(sp);
return 0;
return 0;
}
-static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
+static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
unsigned pte_access, int user_fault,
int write_fault, int dirty, int largepage,
- int global, gfn_t gfn, pfn_t pfn, bool speculative,
+ gfn_t gfn, pfn_t pfn, bool speculative,
bool can_unsync)
{
u64 spte;
int ret = 0;
- u64 mt_mask = shadow_mt_mask;
- struct kvm_mmu_page *sp = page_header(__pa(shadow_pte));
-
- if (!global && sp->global) {
- sp->global = 0;
- if (sp->unsync) {
- kvm_unlink_unsync_global(vcpu->kvm, sp);
- kvm_mmu_mark_parents_unsync(vcpu, sp);
- }
- }
/*
* We don't set the accessed bit, since we sometimes want to see
spte |= shadow_user_mask;
if (largepage)
spte |= PT_PAGE_SIZE_MASK;
- if (mt_mask) {
- if (!kvm_is_mmio_pfn(pfn)) {
- mt_mask = get_memory_type(vcpu, gfn) <<
- kvm_x86_ops->get_mt_mask_shift();
- mt_mask |= VMX_EPT_IGMT_BIT;
- } else
- mt_mask = MTRR_TYPE_UNCACHABLE <<
- kvm_x86_ops->get_mt_mask_shift();
- spte |= mt_mask;
- }
+ if (tdp_enabled)
+ spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
+ kvm_is_mmio_pfn(pfn));
spte |= (u64)pfn << PAGE_SHIFT;
* is responsibility of mmu_get_page / kvm_sync_page.
* Same reasoning can be applied to dirty page accounting.
*/
- if (!can_unsync && is_writeble_pte(*shadow_pte))
+ if (!can_unsync && is_writeble_pte(*sptep))
goto set_pte;
if (mmu_need_write_protect(vcpu, gfn, can_unsync)) {
mark_page_dirty(vcpu->kvm, gfn);
set_pte:
- set_shadow_pte(shadow_pte, spte);
+ __set_spte(sptep, spte);
return ret;
}
-static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
+static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
unsigned pt_access, unsigned pte_access,
int user_fault, int write_fault, int dirty,
- int *ptwrite, int largepage, int global,
- gfn_t gfn, pfn_t pfn, bool speculative)
+ int *ptwrite, int largepage, gfn_t gfn,
+ pfn_t pfn, bool speculative)
{
int was_rmapped = 0;
- int was_writeble = is_writeble_pte(*shadow_pte);
+ int was_writeble = is_writeble_pte(*sptep);
+ int rmap_count;
pgprintk("%s: spte %llx access %x write_fault %d"
" user_fault %d gfn %lx\n",
- __func__, *shadow_pte, pt_access,
+ __func__, *sptep, pt_access,
write_fault, user_fault, gfn);
- if (is_rmap_pte(*shadow_pte)) {
+ if (is_rmap_spte(*sptep)) {
/*
* If we overwrite a PTE page pointer with a 2MB PMD, unlink
* the parent of the now unreachable PTE.
*/
- if (largepage && !is_large_pte(*shadow_pte)) {
+ if (largepage && !is_large_pte(*sptep)) {
struct kvm_mmu_page *child;
- u64 pte = *shadow_pte;
+ u64 pte = *sptep;
child = page_header(pte & PT64_BASE_ADDR_MASK);
- mmu_page_remove_parent_pte(child, shadow_pte);
- } else if (pfn != spte_to_pfn(*shadow_pte)) {
+ mmu_page_remove_parent_pte(child, sptep);
+ } else if (pfn != spte_to_pfn(*sptep)) {
pgprintk("hfn old %lx new %lx\n",
- spte_to_pfn(*shadow_pte), pfn);
- rmap_remove(vcpu->kvm, shadow_pte);
- } else {
- if (largepage)
- was_rmapped = is_large_pte(*shadow_pte);
- else
- was_rmapped = 1;
- }
+ spte_to_pfn(*sptep), pfn);
+ rmap_remove(vcpu->kvm, sptep);
+ } else
+ was_rmapped = 1;
}
- if (set_spte(vcpu, shadow_pte, pte_access, user_fault, write_fault,
- dirty, largepage, global, gfn, pfn, speculative, true)) {
+ if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault,
+ dirty, largepage, gfn, pfn, speculative, true)) {
if (write_fault)
*ptwrite = 1;
kvm_x86_ops->tlb_flush(vcpu);
}
- pgprintk("%s: setting spte %llx\n", __func__, *shadow_pte);
+ pgprintk("%s: setting spte %llx\n", __func__, *sptep);
pgprintk("instantiating %s PTE (%s) at %ld (%llx) addr %p\n",
- is_large_pte(*shadow_pte)? "2MB" : "4kB",
- is_present_pte(*shadow_pte)?"RW":"R", gfn,
- *shadow_pte, shadow_pte);
- if (!was_rmapped && is_large_pte(*shadow_pte))
+ is_large_pte(*sptep)? "2MB" : "4kB",
+ is_present_pte(*sptep)?"RW":"R", gfn,
+ *shadow_pte, sptep);
+ if (!was_rmapped && is_large_pte(*sptep))
++vcpu->kvm->stat.lpages;
- page_header_update_slot(vcpu->kvm, shadow_pte, gfn);
+ page_header_update_slot(vcpu->kvm, sptep, gfn);
if (!was_rmapped) {
- rmap_add(vcpu, shadow_pte, gfn, largepage);
- if (!is_rmap_pte(*shadow_pte))
+ rmap_count = rmap_add(vcpu, sptep, gfn, largepage);
+ if (!is_rmap_spte(*sptep))
kvm_release_pfn_clean(pfn);
+ if (rmap_count > RMAP_RECYCLE_THRESHOLD)
+ rmap_recycle(vcpu, gfn, largepage);
} else {
if (was_writeble)
kvm_release_pfn_dirty(pfn);
kvm_release_pfn_clean(pfn);
}
if (speculative) {
- vcpu->arch.last_pte_updated = shadow_pte;
+ vcpu->arch.last_pte_updated = sptep;
vcpu->arch.last_pte_gfn = gfn;
}
}
|| (largepage && iterator.level == PT_DIRECTORY_LEVEL)) {
mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL,
0, write, 1, &pt_write,
- largepage, 0, gfn, pfn, false);
+ largepage, gfn, pfn, false);
++vcpu->stat.pf_fixed;
break;
}
return -ENOMEM;
}
- set_shadow_pte(iterator.sptep,
- __pa(sp->spt)
- | PT_PRESENT_MASK | PT_WRITABLE_MASK
- | shadow_user_mask | shadow_x_mask);
+ __set_spte(iterator.sptep,
+ __pa(sp->spt)
+ | PT_PRESENT_MASK | PT_WRITABLE_MASK
+ | shadow_user_mask | shadow_x_mask);
}
}
return pt_write;
vcpu->arch.mmu.root_hpa = INVALID_PAGE;
}
-static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
+static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn)
+{
+ int ret = 0;
+
+ if (!kvm_is_visible_gfn(vcpu->kvm, root_gfn)) {
+ set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
+ ret = 1;
+ }
+
+ return ret;
+}
+
+static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
{
int i;
gfn_t root_gfn;
struct kvm_mmu_page *sp;
- int metaphysical = 0;
+ int direct = 0;
+ u64 pdptr;
root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT;
ASSERT(!VALID_PAGE(root));
if (tdp_enabled)
- metaphysical = 1;
+ direct = 1;
+ if (mmu_check_root(vcpu, root_gfn))
+ return 1;
sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
- PT64_ROOT_LEVEL, metaphysical,
+ PT64_ROOT_LEVEL, direct,
ACC_ALL, NULL);
root = __pa(sp->spt);
++sp->root_count;
vcpu->arch.mmu.root_hpa = root;
- return;
+ return 0;
}
- metaphysical = !is_paging(vcpu);
+ direct = !is_paging(vcpu);
if (tdp_enabled)
- metaphysical = 1;
+ direct = 1;
for (i = 0; i < 4; ++i) {
hpa_t root = vcpu->arch.mmu.pae_root[i];
ASSERT(!VALID_PAGE(root));
if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) {
- if (!is_present_pte(vcpu->arch.pdptrs[i])) {
+ pdptr = kvm_pdptr_read(vcpu, i);
+ if (!is_present_gpte(pdptr)) {
vcpu->arch.mmu.pae_root[i] = 0;
continue;
}
- root_gfn = vcpu->arch.pdptrs[i] >> PAGE_SHIFT;
+ root_gfn = pdptr >> PAGE_SHIFT;
} else if (vcpu->arch.mmu.root_level == 0)
root_gfn = 0;
+ if (mmu_check_root(vcpu, root_gfn))
+ return 1;
sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
- PT32_ROOT_LEVEL, metaphysical,
+ PT32_ROOT_LEVEL, direct,
ACC_ALL, NULL);
root = __pa(sp->spt);
++sp->root_count;
vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK;
}
vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
+ return 0;
}
static void mmu_sync_roots(struct kvm_vcpu *vcpu)
for (i = 0; i < 4; ++i) {
hpa_t root = vcpu->arch.mmu.pae_root[i];
- if (root) {
+ if (root && VALID_PAGE(root)) {
root &= PT64_BASE_ADDR_MASK;
sp = page_header(root);
mmu_sync_children(vcpu, sp);
}
}
-static void mmu_sync_global(struct kvm_vcpu *vcpu)
-{
- struct kvm *kvm = vcpu->kvm;
- struct kvm_mmu_page *sp, *n;
-
- list_for_each_entry_safe(sp, n, &kvm->arch.oos_global_pages, oos_link)
- kvm_sync_page(vcpu, sp);
-}
-
void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
{
spin_lock(&vcpu->kvm->mmu_lock);
spin_unlock(&vcpu->kvm->mmu_lock);
}
-void kvm_mmu_sync_global(struct kvm_vcpu *vcpu)
-{
- spin_lock(&vcpu->kvm->mmu_lock);
- mmu_sync_global(vcpu);
- spin_unlock(&vcpu->kvm->mmu_lock);
-}
-
static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr)
{
return vaddr;
nonpaging_free(vcpu);
}
+static bool is_rsvd_bits_set(struct kvm_vcpu *vcpu, u64 gpte, int level)
+{
+ int bit7;
+
+ bit7 = (gpte >> 7) & 1;
+ return (gpte & vcpu->arch.mmu.rsvd_bits_mask[bit7][level-1]) != 0;
+}
+
#define PTTYPE 64
#include "paging_tmpl.h"
#undef PTTYPE
#include "paging_tmpl.h"
#undef PTTYPE
+static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
+{
+ struct kvm_mmu *context = &vcpu->arch.mmu;
+ int maxphyaddr = cpuid_maxphyaddr(vcpu);
+ u64 exb_bit_rsvd = 0;
+
+ if (!is_nx(vcpu))
+ exb_bit_rsvd = rsvd_bits(63, 63);
+ switch (level) {
+ case PT32_ROOT_LEVEL:
+ /* no rsvd bits for 2 level 4K page table entries */
+ context->rsvd_bits_mask[0][1] = 0;
+ context->rsvd_bits_mask[0][0] = 0;
+ if (is_cpuid_PSE36())
+ /* 36bits PSE 4MB page */
+ context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
+ else
+ /* 32 bits PSE 4MB page */
+ context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
+ context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
+ break;
+ case PT32E_ROOT_LEVEL:
+ context->rsvd_bits_mask[0][2] =
+ rsvd_bits(maxphyaddr, 63) |
+ rsvd_bits(7, 8) | rsvd_bits(1, 2); /* PDPTE */
+ context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
+ rsvd_bits(maxphyaddr, 62); /* PDE */
+ context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+ rsvd_bits(maxphyaddr, 62); /* PTE */
+ context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
+ rsvd_bits(maxphyaddr, 62) |
+ rsvd_bits(13, 20); /* large page */
+ context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
+ break;
+ case PT64_ROOT_LEVEL:
+ context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
+ rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8);
+ context->rsvd_bits_mask[0][2] = exb_bit_rsvd |
+ rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8);
+ context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
+ rsvd_bits(maxphyaddr, 51);
+ context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+ rsvd_bits(maxphyaddr, 51);
+ context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
+ context->rsvd_bits_mask[1][2] = context->rsvd_bits_mask[0][2];
+ context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
+ rsvd_bits(maxphyaddr, 51) |
+ rsvd_bits(13, 20); /* large page */
+ context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
+ break;
+ }
+}
+
static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level)
{
struct kvm_mmu *context = &vcpu->arch.mmu;
static int paging64_init_context(struct kvm_vcpu *vcpu)
{
+ reset_rsvds_bits_mask(vcpu, PT64_ROOT_LEVEL);
return paging64_init_context_common(vcpu, PT64_ROOT_LEVEL);
}
{
struct kvm_mmu *context = &vcpu->arch.mmu;
+ 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;
static int paging32E_init_context(struct kvm_vcpu *vcpu)
{
+ reset_rsvds_bits_mask(vcpu, PT32E_ROOT_LEVEL);
return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL);
}
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);
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);
context->gva_to_gpa = paging64_gva_to_gpa;
context->root_level = PT32E_ROOT_LEVEL;
} else {
+ reset_rsvds_bits_mask(vcpu, PT32_ROOT_LEVEL);
context->gva_to_gpa = paging32_gva_to_gpa;
context->root_level = PT32_ROOT_LEVEL;
}
goto out;
spin_lock(&vcpu->kvm->mmu_lock);
kvm_mmu_free_some_pages(vcpu);
- mmu_alloc_roots(vcpu);
+ r = mmu_alloc_roots(vcpu);
mmu_sync_roots(vcpu);
spin_unlock(&vcpu->kvm->mmu_lock);
+ if (r)
+ goto out;
kvm_x86_ops->set_cr3(vcpu, vcpu->arch.mmu.root_hpa);
kvm_mmu_flush_tlb(vcpu);
out:
pte = *spte;
if (is_shadow_present_pte(pte)) {
- if (sp->role.level == PT_PAGE_TABLE_LEVEL ||
- is_large_pte(pte))
+ if (is_last_spte(pte, sp->role.level))
rmap_remove(vcpu->kvm, spte);
else {
child = page_header(pte & PT64_BASE_ADDR_MASK);
mmu_page_remove_parent_pte(child, spte);
}
}
- set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+ __set_spte(spte, shadow_trap_nonpresent_pte);
if (is_large_pte(pte))
--vcpu->kvm->stat.lpages;
}
if ((bytes == 4) && (gpa % 4 == 0))
memcpy((void *)&gpte, new, 4);
}
- if (!is_present_pte(gpte))
+ if (!is_present_gpte(gpte))
return;
gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
index = kvm_page_table_hashfn(gfn);
bucket = &vcpu->kvm->arch.mmu_page_hash[index];
hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) {
- if (sp->gfn != gfn || sp->role.metaphysical || sp->role.invalid)
+ if (sp->gfn != gfn || sp->role.direct || sp->role.invalid)
continue;
pte_size = sp->role.glevels == PT32_ROOT_LEVEL ? 4 : 8;
misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1);
++vcpu->stat.mmio_exits;
return 0;
case EMULATE_FAIL:
- kvm_report_emulation_failure(vcpu, "pagetable");
- return 1;
+ vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ return 0;
default:
BUG();
}
static void free_mmu_pages(struct kvm_vcpu *vcpu)
{
- struct kvm_mmu_page *sp;
-
- while (!list_empty(&vcpu->kvm->arch.active_mmu_pages)) {
- sp = container_of(vcpu->kvm->arch.active_mmu_pages.next,
- struct kvm_mmu_page, link);
- kvm_mmu_zap_page(vcpu->kvm, sp);
- cond_resched();
- }
free_page((unsigned long)vcpu->arch.mmu.pae_root);
}
{
struct kvm_mmu_page *sp;
- spin_lock(&kvm->mmu_lock);
list_for_each_entry(sp, &kvm->arch.active_mmu_pages, link) {
int i;
u64 *pt;
pt[i] &= ~PT_WRITABLE_MASK;
}
kvm_flush_remote_tlbs(kvm);
- spin_unlock(&kvm->mmu_lock);
}
void kvm_mmu_zap_all(struct kvm *kvm)
static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu)
{
- kvm_x86_ops->tlb_flush(vcpu);
- set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests);
+ kvm_set_cr3(vcpu, vcpu->arch.cr3);
return 1;
}
return gva;
}
+
+typedef void (*inspect_spte_fn) (struct kvm *kvm, struct kvm_mmu_page *sp,
+ 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 (sp->role.level > 1 && !is_large_pte(ent)) {
+ struct kvm_mmu_page *child;
+ child = page_header(ent & PT64_BASE_ADDR_MASK);
+ __mmu_spte_walk(kvm, child, fn);
+ }
+ if (sp->role.level == 1)
+ fn(kvm, sp, &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)
{
" in nonleaf level: levels %d gva %lx"
" level %d pte %llx\n", audit_msg,
vcpu->arch.mmu.root_level, va, level, ent);
-
- audit_mappings_page(vcpu, ent, va, level - 1);
+ else
+ audit_mappings_page(vcpu, ent, va, level - 1);
} else {
gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, va);
- hpa_t hpa = (hpa_t)gpa_to_pfn(vcpu, gpa) << PAGE_SHIFT;
+ 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_shadow_present_pte(ent)
&& (ent & PT64_BASE_ADDR_MASK) != hpa)
d = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
while (d) {
for (k = 0; k < RMAP_EXT; ++k)
- if (d->shadow_ptes[k])
+ if (d->sptes[k])
++nmaps;
else
break;
return nmaps;
}
-static int count_writable_mappings(struct kvm_vcpu *vcpu)
+void inspect_spte_has_rmap(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *sptep)
+{
+ unsigned long *rmapp;
+ struct kvm_mmu_page *rev_sp;
+ gfn_t gfn;
+
+ if (*sptep & PT_WRITABLE_MASK) {
+ rev_sp = page_header(__pa(sptep));
+ gfn = rev_sp->gfns[sptep - rev_sp->spt];
+
+ if (!gfn_to_memslot(kvm, gfn)) {
+ if (!printk_ratelimit())
+ return;
+ printk(KERN_ERR "%s: no memslot for gfn %ld\n",
+ audit_msg, gfn);
+ printk(KERN_ERR "%s: index %ld of sp (gfn=%lx)\n",
+ audit_msg, sptep - rev_sp->spt,
+ rev_sp->gfn);
+ dump_stack();
+ return;
+ }
+
+ rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt], 0);
+ if (!*rmapp) {
+ if (!printk_ratelimit())
+ return;
+ printk(KERN_ERR "%s: no rmap for writable spte %llx\n",
+ audit_msg, *sptep);
+ dump_stack();
+ }
+ }
+
+}
+
+void audit_writable_sptes_have_rmaps(struct kvm_vcpu *vcpu)
+{
+ mmu_spte_walk(vcpu, inspect_spte_has_rmap);
+}
+
+static void check_writable_mappings_rmap(struct kvm_vcpu *vcpu)
{
- int nmaps = 0;
struct kvm_mmu_page *sp;
int i;
continue;
if (!(ent & PT_WRITABLE_MASK))
continue;
- ++nmaps;
+ inspect_spte_has_rmap(vcpu->kvm, sp, &pt[i]);
}
}
- return nmaps;
+ return;
}
static void audit_rmap(struct kvm_vcpu *vcpu)
{
- int n_rmap = count_rmaps(vcpu);
- int n_actual = count_writable_mappings(vcpu);
-
- if (n_rmap != n_actual)
- printk(KERN_ERR "%s: (%s) rmap %d actual %d\n",
- __func__, audit_msg, n_rmap, n_actual);
+ check_writable_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.metaphysical)
+ if (sp->role.direct)
+ continue;
+ if (sp->unsync)
continue;
gfn = unalias_gfn(vcpu->kvm, sp->gfn);
slot = gfn_to_memslot_unaliased(vcpu->kvm, sp->gfn);
rmapp = &slot->rmap[gfn - slot->base_gfn];
- if (*rmapp)
- printk(KERN_ERR "%s: (%s) shadow page has writable"
- " mappings: gfn %lx role %x\n",
+
+ spte = rmap_next(vcpu->kvm, rmapp, NULL);
+ while (spte) {
+ if (*spte & PT_WRITABLE_MASK)
+ printk(KERN_ERR "%s: (%s) shadow page has "
+ "writable mappings: gfn %lx role %x\n",
__func__, audit_msg, sp->gfn,
sp->role.word);
+ spte = rmap_next(vcpu->kvm, rmapp, spte);
+ }
}
}
audit_rmap(vcpu);
audit_write_protection(vcpu);
audit_mappings(vcpu);
+ audit_writable_sptes_have_rmaps(vcpu);
dbg = olddbg;
}