#include <asm/cmpxchg.h>
#include <asm/io.h>
#include <asm/vmx.h>
+#include <asm/kvm_page_track.h>
/*
* When setting this variable to true it enables Two-Dimensional-Paging
static bool spte_has_volatile_bits(u64 spte)
{
/*
- * Always atomicly update spte if it can be updated
+ * Always atomically update spte if it can be updated
* out of mmu-lock, it can ensure dirty bit is not lost,
* also, it can help us to get a stable is_writable_pte()
* to ensure tlb flush is not missed.
/*
* For the spte updated out of mmu-lock is safe, since
- * we always atomicly update it, see the comments in
+ * we always atomically update it, see the comments in
* spte_has_volatile_bits().
*/
if (spte_is_locklessly_modifiable(old_spte) &&
* kvm_flush_remote_tlbs() IPI to all active vcpus.
*/
local_irq_disable();
- vcpu->mode = READING_SHADOW_PAGE_TABLES;
+
/*
* Make sure a following spte read is not reordered ahead of the write
* to vcpu->mode.
*/
- smp_mb();
+ smp_store_mb(vcpu->mode, READING_SHADOW_PAGE_TABLES);
}
static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
* reads to sptes. If it does, kvm_commit_zap_page() can see us
* OUTSIDE_GUEST_MODE and proceed to free the shadow page table.
*/
- smp_mb();
- vcpu->mode = OUTSIDE_GUEST_MODE;
+ smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE);
local_irq_enable();
}
return &slot->arch.lpage_info[level - 2][idx];
}
+static void update_gfn_disallow_lpage_count(struct kvm_memory_slot *slot,
+ gfn_t gfn, int count)
+{
+ struct kvm_lpage_info *linfo;
+ int i;
+
+ for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
+ linfo = lpage_info_slot(gfn, slot, i);
+ linfo->disallow_lpage += count;
+ WARN_ON(linfo->disallow_lpage < 0);
+ }
+}
+
+void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+ update_gfn_disallow_lpage_count(slot, gfn, 1);
+}
+
+void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+ update_gfn_disallow_lpage_count(slot, gfn, -1);
+}
+
static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *slot;
- struct kvm_lpage_info *linfo;
gfn_t gfn;
- int i;
+ kvm->arch.indirect_shadow_pages++;
gfn = sp->gfn;
slots = kvm_memslots_for_spte_role(kvm, sp->role);
slot = __gfn_to_memslot(slots, gfn);
- for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
- linfo = lpage_info_slot(gfn, slot, i);
- linfo->write_count += 1;
- }
- kvm->arch.indirect_shadow_pages++;
+
+ /* the non-leaf shadow pages are keeping readonly. */
+ if (sp->role.level > PT_PAGE_TABLE_LEVEL)
+ return kvm_slot_page_track_add_page(kvm, slot, gfn,
+ KVM_PAGE_TRACK_WRITE);
+
+ kvm_mmu_gfn_disallow_lpage(slot, gfn);
}
static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *slot;
- struct kvm_lpage_info *linfo;
gfn_t gfn;
- int i;
+ kvm->arch.indirect_shadow_pages--;
gfn = sp->gfn;
slots = kvm_memslots_for_spte_role(kvm, sp->role);
slot = __gfn_to_memslot(slots, gfn);
- for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
- linfo = lpage_info_slot(gfn, slot, i);
- linfo->write_count -= 1;
- WARN_ON(linfo->write_count < 0);
- }
- kvm->arch.indirect_shadow_pages--;
+ if (sp->role.level > PT_PAGE_TABLE_LEVEL)
+ return kvm_slot_page_track_remove_page(kvm, slot, gfn,
+ KVM_PAGE_TRACK_WRITE);
+
+ kvm_mmu_gfn_allow_lpage(slot, gfn);
}
-static int __has_wrprotected_page(gfn_t gfn, int level,
- struct kvm_memory_slot *slot)
+static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
+ struct kvm_memory_slot *slot)
{
struct kvm_lpage_info *linfo;
if (slot) {
linfo = lpage_info_slot(gfn, slot, level);
- return linfo->write_count;
+ return !!linfo->disallow_lpage;
}
- return 1;
+ return true;
}
-static int has_wrprotected_page(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
+static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn,
+ int level)
{
struct kvm_memory_slot *slot;
slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
- return __has_wrprotected_page(gfn, level, slot);
+ return __mmu_gfn_lpage_is_disallowed(gfn, level, slot);
}
static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
max_level = min(kvm_x86_ops->get_lpage_level(), host_level);
for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
- if (__has_wrprotected_page(large_gfn, level, slot))
+ if (__mmu_gfn_lpage_is_disallowed(large_gfn, level, slot))
break;
return level - 1;
kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}
-static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
+bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
+ struct kvm_memory_slot *slot, u64 gfn)
{
- struct kvm_memory_slot *slot;
struct kvm_rmap_head *rmap_head;
int i;
bool write_protected = false;
- slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
-
for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
rmap_head = __gfn_to_rmap(gfn, i, slot);
- write_protected |= __rmap_write_protect(vcpu->kvm, rmap_head, true);
+ write_protected |= __rmap_write_protect(kvm, rmap_head, true);
}
return write_protected;
}
+static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
+{
+ struct kvm_memory_slot *slot;
+
+ slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+ return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn);
+}
+
static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
{
u64 *sptep;
static int nonpaging_sync_page(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp)
{
- return 1;
+ return 0;
}
static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
return nr_unsync_leaf;
}
+#define INVALID_INDEX (-1)
+
static int mmu_unsync_walk(struct kvm_mmu_page *sp,
struct kvm_mmu_pages *pvec)
{
+ pvec->nr = 0;
if (!sp->unsync_children)
return 0;
- mmu_pages_add(pvec, sp, 0);
+ mmu_pages_add(pvec, sp, INVALID_INDEX);
return __mmu_unsync_walk(sp, pvec);
}
if ((_sp)->role.direct || (_sp)->role.invalid) {} else
/* @sp->gfn should be write-protected at the call site */
-static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
- struct list_head *invalid_list, bool clear_unsync)
+static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+ struct list_head *invalid_list)
{
if (sp->role.cr4_pae != !!is_pae(vcpu)) {
kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
- return 1;
+ return false;
}
- if (clear_unsync)
- kvm_unlink_unsync_page(vcpu->kvm, sp);
-
- if (vcpu->arch.mmu.sync_page(vcpu, sp)) {
+ if (vcpu->arch.mmu.sync_page(vcpu, sp) == 0) {
kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
- return 1;
+ return false;
}
- kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
- return 0;
+ return true;
}
-static int kvm_sync_page_transient(struct kvm_vcpu *vcpu,
- struct kvm_mmu_page *sp)
+static void kvm_mmu_flush_or_zap(struct kvm_vcpu *vcpu,
+ struct list_head *invalid_list,
+ bool remote_flush, bool local_flush)
{
- LIST_HEAD(invalid_list);
- int ret;
-
- ret = __kvm_sync_page(vcpu, sp, &invalid_list, false);
- if (ret)
- kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
+ if (!list_empty(invalid_list)) {
+ kvm_mmu_commit_zap_page(vcpu->kvm, invalid_list);
+ return;
+ }
- return ret;
+ if (remote_flush)
+ kvm_flush_remote_tlbs(vcpu->kvm);
+ else if (local_flush)
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
#ifdef CONFIG_KVM_MMU_AUDIT
static void mmu_audit_disable(void) { }
#endif
-static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
struct list_head *invalid_list)
{
- return __kvm_sync_page(vcpu, sp, invalid_list, true);
+ kvm_unlink_unsync_page(vcpu->kvm, sp);
+ return __kvm_sync_page(vcpu, sp, invalid_list);
}
/* @gfn should be write-protected at the call site */
-static void kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn)
+static bool kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn,
+ struct list_head *invalid_list)
{
struct kvm_mmu_page *s;
- LIST_HEAD(invalid_list);
- bool flush = false;
+ bool ret = false;
for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
if (!s->unsync)
continue;
WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
- kvm_unlink_unsync_page(vcpu->kvm, s);
- if ((s->role.cr4_pae != !!is_pae(vcpu)) ||
- (vcpu->arch.mmu.sync_page(vcpu, s))) {
- kvm_mmu_prepare_zap_page(vcpu->kvm, s, &invalid_list);
- continue;
- }
- flush = true;
+ ret |= kvm_sync_page(vcpu, s, invalid_list);
}
- kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
- if (flush)
- kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+ return ret;
}
struct mmu_page_path {
- struct kvm_mmu_page *parent[PT64_ROOT_LEVEL-1];
- unsigned int idx[PT64_ROOT_LEVEL-1];
+ struct kvm_mmu_page *parent[PT64_ROOT_LEVEL];
+ unsigned int idx[PT64_ROOT_LEVEL];
};
#define for_each_sp(pvec, sp, parents, i) \
- for (i = mmu_pages_next(&pvec, &parents, -1), \
- sp = pvec.page[i].sp; \
+ for (i = mmu_pages_first(&pvec, &parents); \
i < pvec.nr && ({ sp = pvec.page[i].sp; 1;}); \
i = mmu_pages_next(&pvec, &parents, i))
for (n = i+1; n < pvec->nr; n++) {
struct kvm_mmu_page *sp = pvec->page[n].sp;
+ unsigned idx = pvec->page[n].idx;
+ int level = sp->role.level;
- if (sp->role.level == PT_PAGE_TABLE_LEVEL) {
- parents->idx[0] = pvec->page[n].idx;
- return n;
- }
+ parents->idx[level-1] = idx;
+ if (level == PT_PAGE_TABLE_LEVEL)
+ break;
- parents->parent[sp->role.level-2] = sp;
- parents->idx[sp->role.level-1] = pvec->page[n].idx;
+ parents->parent[level-2] = sp;
}
return n;
}
+static int mmu_pages_first(struct kvm_mmu_pages *pvec,
+ struct mmu_page_path *parents)
+{
+ struct kvm_mmu_page *sp;
+ int level;
+
+ if (pvec->nr == 0)
+ return 0;
+
+ WARN_ON(pvec->page[0].idx != INVALID_INDEX);
+
+ sp = pvec->page[0].sp;
+ level = sp->role.level;
+ WARN_ON(level == PT_PAGE_TABLE_LEVEL);
+
+ parents->parent[level-2] = sp;
+
+ /* Also set up a sentinel. Further entries in pvec are all
+ * children of sp, so this element is never overwritten.
+ */
+ parents->parent[level-1] = NULL;
+ return mmu_pages_next(pvec, parents, 0);
+}
+
static void mmu_pages_clear_parents(struct mmu_page_path *parents)
{
struct kvm_mmu_page *sp;
do {
unsigned int idx = parents->idx[level];
-
sp = parents->parent[level];
if (!sp)
return;
+ WARN_ON(idx == INVALID_INDEX);
clear_unsync_child_bit(sp, idx);
level++;
- } while (level < PT64_ROOT_LEVEL-1 && !sp->unsync_children);
-}
-
-static void kvm_mmu_pages_init(struct kvm_mmu_page *parent,
- struct mmu_page_path *parents,
- struct kvm_mmu_pages *pvec)
-{
- parents->parent[parent->role.level-1] = NULL;
- pvec->nr = 0;
+ } while (!sp->unsync_children);
}
static void mmu_sync_children(struct kvm_vcpu *vcpu,
struct mmu_page_path parents;
struct kvm_mmu_pages pages;
LIST_HEAD(invalid_list);
+ bool flush = false;
- kvm_mmu_pages_init(parent, &parents, &pages);
while (mmu_unsync_walk(parent, &pages)) {
bool protected = false;
for_each_sp(pages, sp, parents, i)
protected |= rmap_write_protect(vcpu, sp->gfn);
- if (protected)
+ if (protected) {
kvm_flush_remote_tlbs(vcpu->kvm);
+ flush = false;
+ }
for_each_sp(pages, sp, parents, i) {
- kvm_sync_page(vcpu, sp, &invalid_list);
+ flush |= kvm_sync_page(vcpu, sp, &invalid_list);
mmu_pages_clear_parents(&parents);
}
- kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
- cond_resched_lock(&vcpu->kvm->mmu_lock);
- kvm_mmu_pages_init(parent, &parents, &pages);
+ if (need_resched() || spin_needbreak(&vcpu->kvm->mmu_lock)) {
+ kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
+ cond_resched_lock(&vcpu->kvm->mmu_lock);
+ flush = false;
+ }
}
+
+ kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
}
static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
{
- sp->write_flooding_count = 0;
+ atomic_set(&sp->write_flooding_count, 0);
}
static void clear_sp_write_flooding_count(u64 *spte)
unsigned quadrant;
struct kvm_mmu_page *sp;
bool need_sync = false;
+ bool flush = false;
+ LIST_HEAD(invalid_list);
role = vcpu->arch.mmu.base_role;
role.level = level;
if (sp->role.word != role.word)
continue;
- if (sp->unsync && kvm_sync_page_transient(vcpu, sp))
- break;
+ if (sp->unsync) {
+ /* The page is good, but __kvm_sync_page might still end
+ * up zapping it. If so, break in order to rebuild it.
+ */
+ if (!__kvm_sync_page(vcpu, sp, &invalid_list))
+ break;
+
+ WARN_ON(!list_empty(&invalid_list));
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+ }
if (sp->unsync_children)
kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
hlist_add_head(&sp->hash_link,
&vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]);
if (!direct) {
- if (rmap_write_protect(vcpu, gfn))
+ /*
+ * we should do write protection before syncing pages
+ * otherwise the content of the synced shadow page may
+ * be inconsistent with guest page table.
+ */
+ account_shadowed(vcpu->kvm, sp);
+ if (level == PT_PAGE_TABLE_LEVEL &&
+ rmap_write_protect(vcpu, gfn))
kvm_flush_remote_tlbs(vcpu->kvm);
- if (level > PT_PAGE_TABLE_LEVEL && need_sync)
- kvm_sync_pages(vcpu, gfn);
- account_shadowed(vcpu->kvm, sp);
+ if (level > PT_PAGE_TABLE_LEVEL && need_sync)
+ flush |= kvm_sync_pages(vcpu, gfn, &invalid_list);
}
sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
clear_page(sp->spt);
trace_kvm_mmu_get_page(sp, true);
+
+ kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
return sp;
}
if (parent->role.level == PT_PAGE_TABLE_LEVEL)
return 0;
- kvm_mmu_pages_init(parent, &parents, &pages);
while (mmu_unsync_walk(parent, &pages)) {
struct kvm_mmu_page *sp;
mmu_pages_clear_parents(&parents);
zapped++;
}
- kvm_mmu_pages_init(parent, &parents, &pages);
}
return zapped;
return;
/*
- * wmb: make sure everyone sees our modifications to the page tables
- * rmb: make sure we see changes to vcpu->mode
- */
- smp_mb();
-
- /*
- * Wait for all vcpus to exit guest mode and/or lockless shadow
- * page table walks.
+ * We need to make sure everyone sees our modifications to
+ * the page tables and see changes to vcpu->mode here. The barrier
+ * in the kvm_flush_remote_tlbs() achieves this. This pairs
+ * with vcpu_enter_guest and walk_shadow_page_lockless_begin/end.
+ *
+ * In addition, kvm_flush_remote_tlbs waits for all vcpus to exit
+ * guest mode and/or lockless shadow page table walks.
*/
kvm_flush_remote_tlbs(kvm);
if (list_empty(&kvm->arch.active_mmu_pages))
return false;
- sp = list_entry(kvm->arch.active_mmu_pages.prev,
- struct kvm_mmu_page, link);
+ sp = list_last_entry(&kvm->arch.active_mmu_pages,
+ struct kvm_mmu_page, link);
kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
return true;
}
EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
-static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
trace_kvm_mmu_unsync_page(sp);
++vcpu->kvm->stat.mmu_unsync;
kvm_mmu_mark_parents_unsync(sp);
}
-static void kvm_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn)
+static bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
+ bool can_unsync)
{
- struct kvm_mmu_page *s;
-
- for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
- if (s->unsync)
- continue;
- WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
- __kvm_unsync_page(vcpu, s);
- }
-}
+ struct kvm_mmu_page *sp;
-static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
- bool can_unsync)
-{
- struct kvm_mmu_page *s;
- bool need_unsync = false;
+ if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE))
+ return true;
- for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
+ for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
if (!can_unsync)
- return 1;
+ return true;
- if (s->role.level != PT_PAGE_TABLE_LEVEL)
- return 1;
+ if (sp->unsync)
+ continue;
- if (!s->unsync)
- need_unsync = true;
+ WARN_ON(sp->role.level != PT_PAGE_TABLE_LEVEL);
+ kvm_unsync_page(vcpu, sp);
}
- if (need_unsync)
- kvm_unsync_pages(vcpu, gfn);
- return 0;
+
+ return false;
}
static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
* be fixed if guest refault.
*/
if (level > PT_PAGE_TABLE_LEVEL &&
- has_wrprotected_page(vcpu, gfn, level))
+ mmu_gfn_lpage_is_disallowed(vcpu, gfn, level))
goto done;
spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;
if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
level == PT_PAGE_TABLE_LEVEL &&
PageTransCompound(pfn_to_page(pfn)) &&
- !has_wrprotected_page(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
+ !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
unsigned long mask;
/*
* mmu_notifier_retry was successful and we hold the
static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
kvm_pfn_t pfn, unsigned access, int *ret_val)
{
- bool ret = true;
-
/* The pfn is invalid, report the error! */
if (unlikely(is_error_pfn(pfn))) {
*ret_val = kvm_handle_bad_page(vcpu, gfn, pfn);
- goto exit;
+ return true;
}
if (unlikely(is_noslot_pfn(pfn)))
vcpu_cache_mmio_info(vcpu, gva, gfn, access);
- ret = false;
-exit:
- return ret;
+ return false;
}
static bool page_fault_can_be_fast(u32 error_code)
return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level);
}
-static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
+static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
{
if (direct)
return vcpu_match_mmio_gpa(vcpu, addr);
u64 spte;
bool reserved;
- if (quickly_check_mmio_pf(vcpu, addr, direct))
+ if (mmio_info_in_cache(vcpu, addr, direct))
return RET_MMIO_PF_EMULATE;
reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte);
}
EXPORT_SYMBOL_GPL(handle_mmio_page_fault);
+static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu,
+ u32 error_code, gfn_t gfn)
+{
+ if (unlikely(error_code & PFERR_RSVD_MASK))
+ return false;
+
+ if (!(error_code & PFERR_PRESENT_MASK) ||
+ !(error_code & PFERR_WRITE_MASK))
+ return false;
+
+ /*
+ * guest is writing the page which is write tracked which can
+ * not be fixed by page fault handler.
+ */
+ if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE))
+ return true;
+
+ return false;
+}
+
+static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
+{
+ struct kvm_shadow_walk_iterator iterator;
+ u64 spte;
+
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ return;
+
+ walk_shadow_page_lockless_begin(vcpu);
+ for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
+ clear_sp_write_flooding_count(iterator.sptep);
+ if (!is_shadow_present_pte(spte))
+ break;
+ }
+ walk_shadow_page_lockless_end(vcpu);
+}
+
static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
u32 error_code, bool prefault)
{
- gfn_t gfn;
+ gfn_t gfn = gva >> PAGE_SHIFT;
int r;
pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
- if (unlikely(error_code & PFERR_RSVD_MASK)) {
- r = handle_mmio_page_fault(vcpu, gva, true);
-
- if (likely(r != RET_MMIO_PF_INVALID))
- return r;
- }
+ if (page_fault_handle_page_track(vcpu, error_code, gfn))
+ return 1;
r = mmu_topup_memory_caches(vcpu);
if (r)
MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
- gfn = gva >> PAGE_SHIFT;
return nonpaging_map(vcpu, gva & PAGE_MASK,
error_code, gfn, prefault);
MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
- if (unlikely(error_code & PFERR_RSVD_MASK)) {
- r = handle_mmio_page_fault(vcpu, gpa, true);
-
- if (likely(r != RET_MMIO_PF_INVALID))
- return r;
- }
+ if (page_fault_handle_page_track(vcpu, error_code, gfn))
+ return 1;
r = mmu_topup_memory_caches(vcpu);
if (r)
return false;
}
-static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte)
+static inline bool is_last_gpte(struct kvm_mmu *mmu,
+ unsigned level, unsigned gpte)
{
- unsigned index;
+ /*
+ * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set
+ * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means
+ * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then.
+ */
+ gpte |= level - PT_PAGE_TABLE_LEVEL - 1;
+
+ /*
+ * The RHS has bit 7 set iff level < mmu->last_nonleaf_level.
+ * If it is clear, there are no large pages at this level, so clear
+ * PT_PAGE_SIZE_MASK in gpte if that is the case.
+ */
+ gpte &= level - mmu->last_nonleaf_level;
- index = level - 1;
- index |= (gpte & PT_PAGE_SIZE_MASK) >> (PT_PAGE_SIZE_SHIFT - 2);
- return mmu->last_pte_bitmap & (1 << index);
+ return gpte & PT_PAGE_SIZE_MASK;
}
#define PTTYPE_EPT 18 /* arbitrary */
}
}
-static void update_last_pte_bitmap(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
-{
- u8 map;
- unsigned level, root_level = mmu->root_level;
- const unsigned ps_set_index = 1 << 2; /* bit 2 of index: ps */
-
- if (root_level == PT32E_ROOT_LEVEL)
- --root_level;
- /* PT_PAGE_TABLE_LEVEL always terminates */
- map = 1 | (1 << ps_set_index);
- for (level = PT_DIRECTORY_LEVEL; level <= root_level; ++level) {
- if (level <= PT_PDPE_LEVEL
- && (mmu->root_level >= PT32E_ROOT_LEVEL || is_pse(vcpu)))
- map |= 1 << (ps_set_index | (level - 1));
+/*
+* PKU is an additional mechanism by which the paging controls access to
+* user-mode addresses based on the value in the PKRU register. Protection
+* key violations are reported through a bit in the page fault error code.
+* Unlike other bits of the error code, the PK bit is not known at the
+* call site of e.g. gva_to_gpa; it must be computed directly in
+* permission_fault based on two bits of PKRU, on some machine state (CR4,
+* CR0, EFER, CPL), and on other bits of the error code and the page tables.
+*
+* In particular the following conditions come from the error code, the
+* page tables and the machine state:
+* - PK is always zero unless CR4.PKE=1 and EFER.LMA=1
+* - PK is always zero if RSVD=1 (reserved bit set) or F=1 (instruction fetch)
+* - PK is always zero if U=0 in the page tables
+* - PKRU.WD is ignored if CR0.WP=0 and the access is a supervisor access.
+*
+* The PKRU bitmask caches the result of these four conditions. The error
+* code (minus the P bit) and the page table's U bit form an index into the
+* PKRU bitmask. Two bits of the PKRU bitmask are then extracted and ANDed
+* with the two bits of the PKRU register corresponding to the protection key.
+* For the first three conditions above the bits will be 00, thus masking
+* away both AD and WD. For all reads or if the last condition holds, WD
+* only will be masked away.
+*/
+static void update_pkru_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ bool ept)
+{
+ unsigned bit;
+ bool wp;
+
+ if (ept) {
+ mmu->pkru_mask = 0;
+ return;
+ }
+
+ /* PKEY is enabled only if CR4.PKE and EFER.LMA are both set. */
+ if (!kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || !is_long_mode(vcpu)) {
+ mmu->pkru_mask = 0;
+ return;
}
- mmu->last_pte_bitmap = map;
+
+ wp = is_write_protection(vcpu);
+
+ for (bit = 0; bit < ARRAY_SIZE(mmu->permissions); ++bit) {
+ unsigned pfec, pkey_bits;
+ bool check_pkey, check_write, ff, uf, wf, pte_user;
+
+ pfec = bit << 1;
+ ff = pfec & PFERR_FETCH_MASK;
+ uf = pfec & PFERR_USER_MASK;
+ wf = pfec & PFERR_WRITE_MASK;
+
+ /* PFEC.RSVD is replaced by ACC_USER_MASK. */
+ pte_user = pfec & PFERR_RSVD_MASK;
+
+ /*
+ * Only need to check the access which is not an
+ * instruction fetch and is to a user page.
+ */
+ check_pkey = (!ff && pte_user);
+ /*
+ * write access is controlled by PKRU if it is a
+ * user access or CR0.WP = 1.
+ */
+ check_write = check_pkey && wf && (uf || wp);
+
+ /* PKRU.AD stops both read and write access. */
+ pkey_bits = !!check_pkey;
+ /* PKRU.WD stops write access. */
+ pkey_bits |= (!!check_write) << 1;
+
+ mmu->pkru_mask |= (pkey_bits & 3) << pfec;
+ }
+}
+
+static void update_last_nonleaf_level(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+{
+ unsigned root_level = mmu->root_level;
+
+ mmu->last_nonleaf_level = root_level;
+ if (root_level == PT32_ROOT_LEVEL && is_pse(vcpu))
+ mmu->last_nonleaf_level++;
}
static void paging64_init_context_common(struct kvm_vcpu *vcpu,
reset_rsvds_bits_mask(vcpu, context);
update_permission_bitmask(vcpu, context, false);
- update_last_pte_bitmap(vcpu, context);
+ update_pkru_bitmask(vcpu, context, false);
+ update_last_nonleaf_level(vcpu, context);
MMU_WARN_ON(!is_pae(vcpu));
context->page_fault = paging64_page_fault;
reset_rsvds_bits_mask(vcpu, context);
update_permission_bitmask(vcpu, context, false);
- update_last_pte_bitmap(vcpu, context);
+ update_pkru_bitmask(vcpu, context, false);
+ update_last_nonleaf_level(vcpu, context);
context->page_fault = paging32_page_fault;
context->gva_to_gpa = paging32_gva_to_gpa;
}
update_permission_bitmask(vcpu, context, false);
- update_last_pte_bitmap(vcpu, context);
+ update_pkru_bitmask(vcpu, context, false);
+ update_last_nonleaf_level(vcpu, context);
reset_tdp_shadow_zero_bits_mask(vcpu, context);
}
context->direct_map = false;
update_permission_bitmask(vcpu, context, true);
+ update_pkru_bitmask(vcpu, context, true);
reset_rsvds_bits_mask_ept(vcpu, context, execonly);
reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
}
}
update_permission_bitmask(vcpu, g_context, false);
- update_last_pte_bitmap(vcpu, g_context);
+ update_pkru_bitmask(vcpu, g_context, false);
+ update_last_nonleaf_level(vcpu, g_context);
}
static void init_kvm_mmu(struct kvm_vcpu *vcpu)
return (old & ~new & PT64_PERM_MASK) != 0;
}
-static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page,
- bool remote_flush, bool local_flush)
-{
- if (zap_page)
- return;
-
- if (remote_flush)
- kvm_flush_remote_tlbs(vcpu->kvm);
- else if (local_flush)
- kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
-}
-
static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
const u8 *new, int *bytes)
{
if (sp->role.level == PT_PAGE_TABLE_LEVEL)
return false;
- return ++sp->write_flooding_count >= 3;
+ atomic_inc(&sp->write_flooding_count);
+ return atomic_read(&sp->write_flooding_count) >= 3;
}
/*
return spte;
}
-void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
- const u8 *new, int bytes)
+static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
+ const u8 *new, int bytes)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
struct kvm_mmu_page *sp;
LIST_HEAD(invalid_list);
u64 entry, gentry, *spte;
int npte;
- bool remote_flush, local_flush, zap_page;
+ bool remote_flush, local_flush;
union kvm_mmu_page_role mask = { };
mask.cr0_wp = 1;
if (!ACCESS_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
return;
- zap_page = remote_flush = local_flush = false;
+ remote_flush = local_flush = false;
pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
if (detect_write_misaligned(sp, gpa, bytes) ||
detect_write_flooding(sp)) {
- zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp,
- &invalid_list);
+ kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list);
++vcpu->kvm->stat.mmu_flooded;
continue;
}
++spte;
}
}
- mmu_pte_write_flush_tlb(vcpu, zap_page, remote_flush, local_flush);
- kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
+ kvm_mmu_flush_or_zap(vcpu, &invalid_list, remote_flush, local_flush);
kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE);
spin_unlock(&vcpu->kvm->mmu_lock);
}
kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
}
-static bool is_mmio_page_fault(struct kvm_vcpu *vcpu, gva_t addr)
-{
- if (vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu))
- return vcpu_match_mmio_gpa(vcpu, addr);
-
- return vcpu_match_mmio_gva(vcpu, addr);
-}
-
int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
void *insn, int insn_len)
{
int r, emulation_type = EMULTYPE_RETRY;
enum emulation_result er;
+ bool direct = vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu);
+
+ if (unlikely(error_code & PFERR_RSVD_MASK)) {
+ r = handle_mmio_page_fault(vcpu, cr2, direct);
+ if (r == RET_MMIO_PF_EMULATE) {
+ emulation_type = 0;
+ goto emulate;
+ }
+ if (r == RET_MMIO_PF_RETRY)
+ return 1;
+ if (r < 0)
+ return r;
+ }
r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false);
if (r < 0)
- goto out;
-
- if (!r) {
- r = 1;
- goto out;
- }
+ return r;
+ if (!r)
+ return 1;
- if (is_mmio_page_fault(vcpu, cr2))
+ if (mmio_info_in_cache(vcpu, cr2, direct))
emulation_type = 0;
-
+emulate:
er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
switch (er) {
default:
BUG();
}
-out:
- return r;
}
EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
init_kvm_mmu(vcpu);
}
+void kvm_mmu_init_vm(struct kvm *kvm)
+{
+ struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+
+ node->track_write = kvm_mmu_pte_write;
+ kvm_page_track_register_notifier(kvm, node);
+}
+
+void kvm_mmu_uninit_vm(struct kvm *kvm)
+{
+ struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+
+ kvm_page_track_unregister_notifier(kvm, node);
+}
+
/* The return value indicates if tlb flush on all vcpus is needed. */
typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head);
struct page *pml_pg;
u64 current_tsc_ratio;
+
+ bool guest_pkru_valid;
+ u32 guest_pkru;
+ u32 host_pkru;
};
enum segment_cache_field {
static u64 construct_eptp(unsigned long root_hpa);
static void kvm_cpu_vmxon(u64 addr);
static void kvm_cpu_vmxoff(void);
-static bool vmx_mpx_supported(void);
static bool vmx_xsaves_supported(void);
static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
static void vmx_set_segment(struct kvm_vcpu *vcpu,
MSR_EFER, MSR_TSC_AUX, MSR_STAR,
};
-static inline bool is_page_fault(u32 intr_info)
+static inline bool is_exception_n(u32 intr_info, u8 vector)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
- (INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
+ (INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK);
+}
+
+static inline bool is_debug(u32 intr_info)
+{
+ return is_exception_n(intr_info, DB_VECTOR);
+}
+
+static inline bool is_breakpoint(u32 intr_info)
+{
+ return is_exception_n(intr_info, BP_VECTOR);
+}
+
+static inline bool is_page_fault(u32 intr_info)
+{
+ return is_exception_n(intr_info, PF_VECTOR);
}
static inline bool is_no_device(u32 intr_info)
{
- return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
- INTR_INFO_VALID_MASK)) ==
- (INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
+ return is_exception_n(intr_info, NM_VECTOR);
}
static inline bool is_invalid_opcode(u32 intr_info)
{
- return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
- INTR_INFO_VALID_MASK)) ==
- (INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
+ return is_exception_n(intr_info, UD_VECTOR);
}
static inline bool is_external_interrupt(u32 intr_info)
} while (cmpxchg(&pi_desc->control, old.control,
new.control) != old.control);
}
+
/*
* Switches to specified vcpu, until a matching vcpu_put(), but assumes
* vcpu mutex is already taken.
}
vmx_vcpu_pi_load(vcpu, cpu);
+ vmx->host_pkru = read_pkru();
}
static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
vmcs_writel(GUEST_RFLAGS, rflags);
}
+static u32 vmx_get_pkru(struct kvm_vcpu *vcpu)
+{
+ return to_vmx(vcpu)->guest_pkru;
+}
+
static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
{
u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
- if (vmx_mpx_supported())
+ if (kvm_mpx_supported())
vmx->nested.nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
/* We support free control of debug control saving. */
VM_ENTRY_LOAD_IA32_PAT;
vmx->nested.nested_vmx_entry_ctls_high |=
(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
- if (vmx_mpx_supported())
+ if (kvm_mpx_supported())
vmx->nested.nested_vmx_entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
/* We support free control of debug control loading. */
} else
vmx->nested.nested_vmx_ept_caps = 0;
+ /*
+ * Old versions of KVM use the single-context version without
+ * checking for support, so declare that it is supported even
+ * though it is treated as global context. The alternative is
+ * not failing the single-context invvpid, and it is worse.
+ */
if (enable_vpid)
vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
+ VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |
VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
else
vmx->nested.nested_vmx_vpid_caps = 0;
msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
break;
case MSR_IA32_BNDCFGS:
- if (!vmx_mpx_supported())
+ if (!kvm_mpx_supported())
return 1;
msr_info->data = vmcs_read64(GUEST_BNDCFGS);
break;
vmcs_writel(GUEST_SYSENTER_ESP, data);
break;
case MSR_IA32_BNDCFGS:
- if (!vmx_mpx_supported())
+ if (!kvm_mpx_supported())
return 1;
vmcs_write64(GUEST_BNDCFGS, data);
break;
for (i = j = 0; i < max_shadow_read_write_fields; i++) {
switch (shadow_read_write_fields[i]) {
case GUEST_BNDCFGS:
- if (!vmx_mpx_supported())
+ if (!kvm_mpx_supported())
continue;
break;
default:
if (!enable_unrestricted_guest && !is_paging(vcpu))
/*
- * SMEP/SMAP is disabled if CPU is in non-paging mode in
- * hardware. However KVM always uses paging mode without
- * unrestricted guest.
- * To emulate this behavior, SMEP/SMAP needs to be manually
- * disabled when guest switches to non-paging mode.
+ * SMEP/SMAP/PKU is disabled if CPU is in non-paging mode in
+ * hardware. To emulate this behavior, SMEP/SMAP/PKU needs
+ * to be manually disabled when guest switches to non-paging
+ * mode.
+ *
+ * If !enable_unrestricted_guest, the CPU is always running
+ * with CR0.PG=1 and CR4 needs to be modified.
+ * If enable_unrestricted_guest, the CPU automatically
+ * disables SMEP/SMAP/PKU when the guest sets CR0.PG=0.
*/
- hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP);
+ hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE);
vmcs_writel(CR4_READ_SHADOW, cr4);
vmcs_writel(GUEST_CR4, hw_cr4);
return kvm_set_cr4(vcpu, val);
}
- /* called to set cr0 as approriate for clts instruction exit. */
+ /* called to set cr0 as appropriate for clts instruction exit. */
static void handle_clts(struct kvm_vcpu *vcpu)
{
if (is_guest_mode(vcpu)) {
}
if (vcpu->guest_debug == 0) {
- u32 cpu_based_vm_exec_control;
-
- cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
- cpu_based_vm_exec_control &= ~CPU_BASED_MOV_DR_EXITING;
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+ vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
+ CPU_BASED_MOV_DR_EXITING);
/*
* No more DR vmexits; force a reload of the debug registers
static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
{
- u32 cpu_based_vm_exec_control;
-
get_debugreg(vcpu->arch.db[0], 0);
get_debugreg(vcpu->arch.db[1], 1);
get_debugreg(vcpu->arch.db[2], 2);
vcpu->arch.dr7 = vmcs_readl(GUEST_DR7);
vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
-
- cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
- cpu_based_vm_exec_control |= CPU_BASED_MOV_DR_EXITING;
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+ vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_MOV_DR_EXITING);
}
static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
static int handle_vmcall(struct kvm_vcpu *vcpu)
{
- kvm_emulate_hypercall(vcpu);
- return 1;
+ return kvm_emulate_hypercall(vcpu);
}
static int handle_invd(struct kvm_vcpu *vcpu)
if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) {
/* Recycle the least recently used VMCS. */
- item = list_entry(vmx->nested.vmcs02_pool.prev,
- struct vmcs02_list, list);
+ item = list_last_entry(&vmx->nested.vmcs02_pool,
+ struct vmcs02_list, list);
item->vmptr = vmx->nested.current_vmptr;
list_move(&item->list, &vmx->nested.vmcs02_pool);
return &item->vmcs02;
/* The value to write might be 32 or 64 bits, depending on L1's long
* mode, and eventually we need to write that into a field of several
* possible lengths. The code below first zero-extends the value to 64
- * bit (field_value), and then copies only the approriate number of
+ * bit (field_value), and then copies only the appropriate number of
* bits into the vmcs12 field.
*/
u64 field_value = 0;
if (!(types & (1UL << type))) {
nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+ skip_emulated_instruction(vcpu);
return 1;
}
if (!(types & (1UL << type))) {
nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+ skip_emulated_instruction(vcpu);
return 1;
}
}
switch (type) {
+ case VMX_VPID_EXTENT_SINGLE_CONTEXT:
+ /*
+ * Old versions of KVM use the single-context version so we
+ * have to support it; just treat it the same as all-context.
+ */
case VMX_VPID_EXTENT_ALL_CONTEXT:
__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
nested_vmx_succeed(vcpu);
break;
default:
- /* Trap single context invalidation invvpid calls */
+ /* Trap individual address invalidation invvpid calls */
BUG_ON(1);
break;
}
else if (is_no_device(intr_info) &&
!(vmcs12->guest_cr0 & X86_CR0_TS))
return false;
+ else if (is_debug(intr_info) &&
+ vcpu->guest_debug &
+ (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+ return false;
+ else if (is_breakpoint(intr_info) &&
+ vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+ return false;
return vmcs12->exception_bitmap &
(1u << (intr_info & INTR_INFO_VECTOR_MASK));
case EXIT_REASON_EXTERNAL_INTERRUPT:
static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
{
u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+ register void *__sp asm(_ASM_SP);
/*
* If external interrupt exists, IF bit is set in rflags/eflags on the
"call *%[entry]\n\t"
:
#ifdef CONFIG_X86_64
- [sp]"=&r"(tmp)
+ [sp]"=&r"(tmp),
#endif
+ "+r"(__sp)
:
[entry]"r"(entry),
[ss]"i"(__KERNEL_DS),
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vmx_set_interrupt_shadow(vcpu, 0);
+ if (vmx->guest_pkru_valid)
+ __write_pkru(vmx->guest_pkru);
+
atomic_switch_perf_msrs(vmx);
debugctlmsr = get_debugctlmsr();
vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
+ /*
+ * eager fpu is enabled if PKEY is supported and CR4 is switched
+ * back on host, so it is safe to read guest PKRU from current
+ * XSAVE.
+ */
+ if (boot_cpu_has(X86_FEATURE_OSPKE)) {
+ vmx->guest_pkru = __read_pkru();
+ if (vmx->guest_pkru != vmx->host_pkru) {
+ vmx->guest_pkru_valid = true;
+ __write_pkru(vmx->host_pkru);
+ } else
+ vmx->guest_pkru_valid = false;
+ }
+
/*
* the KVM_REQ_EVENT optimization bit is only on for one entry, and if
* we did not inject a still-pending event to L1 now because of
vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
- if (vmx_mpx_supported())
+ if (kvm_mpx_supported())
vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
if (nested_cpu_has_xsaves(vmcs12))
vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP);
*/
kvm_set_msi_irq(e, &irq);
- if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu))
+ if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
+ /*
+ * Make sure the IRTE is in remapped mode if
+ * we don't handle it in posted mode.
+ */
+ ret = irq_set_vcpu_affinity(host_irq, NULL);
+ if (ret < 0) {
+ printk(KERN_INFO
+ "failed to back to remapped mode, irq: %u\n",
+ host_irq);
+ goto out;
+ }
+
continue;
+ }
vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
vcpu_info.vector = irq.vector;
- trace_kvm_pi_irte_update(vcpu->vcpu_id, e->gsi,
+ trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi,
vcpu_info.vector, vcpu_info.pi_desc_addr, set);
if (set)
.cache_reg = vmx_cache_reg,
.get_rflags = vmx_get_rflags,
.set_rflags = vmx_set_rflags,
+
+ .get_pkru = vmx_get_pkru,
+
.fpu_activate = vmx_fpu_activate,
.fpu_deactivate = vmx_fpu_deactivate,
unsigned int __read_mostly lapic_timer_advance_ns = 0;
module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
+static bool __read_mostly vector_hashing = true;
+module_param(vector_hashing, bool, S_IRUGO);
+
static bool __read_mostly backwards_tsc_observed = false;
#define KVM_NR_SHARED_MSRS 16
{
unsigned long old_cr4 = kvm_read_cr4(vcpu);
unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
- X86_CR4_SMEP | X86_CR4_SMAP;
+ X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
if (cr4 & CR4_RESERVED_BITS)
return 1;
if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_FSGSBASE))
return 1;
+ if (!guest_cpuid_has_pku(vcpu) && (cr4 & X86_CR4_PKE))
+ return 1;
+
if (is_long_mode(vcpu)) {
if (!(cr4 & X86_CR4_PAE))
return 1;
(!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
kvm_mmu_reset_context(vcpu);
- if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
+ if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE))
kvm_update_cpuid(vcpu);
return 0;
static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
{
- uint32_t quotient, remainder;
-
- /* Don't try to replace with do_div(), this one calculates
- * "(dividend << 32) / divisor" */
- __asm__ ( "divl %4"
- : "=a" (quotient), "=d" (remainder)
- : "0" (0), "1" (dividend), "r" (divisor) );
- return quotient;
+ do_shl32_div32(dividend, divisor);
+ return dividend;
}
-static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
+static void kvm_get_time_scale(uint64_t scaled_hz, uint64_t base_hz,
s8 *pshift, u32 *pmultiplier)
{
uint64_t scaled64;
uint64_t tps64;
uint32_t tps32;
- tps64 = base_khz * 1000LL;
- scaled64 = scaled_khz * 1000LL;
+ tps64 = base_hz;
+ scaled64 = scaled_hz;
while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) {
tps64 >>= 1;
shift--;
*pshift = shift;
*pmultiplier = div_frac(scaled64, tps32);
- pr_debug("%s: base_khz %u => %u, shift %d, mul %u\n",
- __func__, base_khz, scaled_khz, shift, *pmultiplier);
+ pr_debug("%s: base_hz %llu => %llu, shift %d, mul %u\n",
+ __func__, base_hz, scaled_hz, shift, *pmultiplier);
}
#ifdef CONFIG_X86_64
return 0;
}
-static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz)
+static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz)
{
u32 thresh_lo, thresh_hi;
int use_scaling = 0;
/* tsc_khz can be zero if TSC calibration fails */
- if (this_tsc_khz == 0) {
+ if (user_tsc_khz == 0) {
/* set tsc_scaling_ratio to a safe value */
vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio;
return -1;
}
/* Compute a scale to convert nanoseconds in TSC cycles */
- kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000,
+ kvm_get_time_scale(user_tsc_khz * 1000LL, NSEC_PER_SEC,
&vcpu->arch.virtual_tsc_shift,
&vcpu->arch.virtual_tsc_mult);
- vcpu->arch.virtual_tsc_khz = this_tsc_khz;
+ vcpu->arch.virtual_tsc_khz = user_tsc_khz;
/*
* Compute the variation in TSC rate which is acceptable
*/
thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm);
thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm);
- if (this_tsc_khz < thresh_lo || this_tsc_khz > thresh_hi) {
- pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi);
+ if (user_tsc_khz < thresh_lo || user_tsc_khz > thresh_hi) {
+ pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", user_tsc_khz, thresh_lo, thresh_hi);
use_scaling = 1;
}
- return set_tsc_khz(vcpu, this_tsc_khz, use_scaling);
+ return set_tsc_khz(vcpu, user_tsc_khz, use_scaling);
}
static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
/*
* GCC likes to generate cmov here, but this branch is extremely
- * predictable (it's just a funciton of time and the likely is
+ * predictable (it's just a function of time and the likely is
* very likely) and there's a data dependence, so force GCC
* to generate a branch instead. I don't barrier() because
* we don't actually need a barrier, and if this function
static int kvm_guest_time_update(struct kvm_vcpu *v)
{
- unsigned long flags, this_tsc_khz, tgt_tsc_khz;
+ unsigned long flags, tgt_tsc_khz;
struct kvm_vcpu_arch *vcpu = &v->arch;
struct kvm_arch *ka = &v->kvm->arch;
s64 kernel_ns;
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
- this_tsc_khz = __this_cpu_read(cpu_tsc_khz);
- if (unlikely(this_tsc_khz == 0)) {
+ tgt_tsc_khz = __this_cpu_read(cpu_tsc_khz);
+ if (unlikely(tgt_tsc_khz == 0)) {
local_irq_restore(flags);
kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
return 1;
if (!vcpu->pv_time_enabled)
return 0;
- if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
- tgt_tsc_khz = kvm_has_tsc_control ?
- vcpu->virtual_tsc_khz : this_tsc_khz;
- kvm_get_time_scale(NSEC_PER_SEC / 1000, tgt_tsc_khz,
+ if (kvm_has_tsc_control)
+ tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz);
+
+ if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
+ kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
&vcpu->hv_clock.tsc_shift,
&vcpu->hv_clock.tsc_to_system_mul);
- vcpu->hw_tsc_khz = this_tsc_khz;
+ vcpu->hw_tsc_khz = tgt_tsc_khz;
}
/* With all the info we got, fill in the values */
kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked);
if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR &&
- kvm_vcpu_has_lapic(vcpu))
+ lapic_in_kernel(vcpu))
vcpu->arch.apic->sipi_vector = events->sipi_vector;
if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
else
vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
- if (kvm_vcpu_has_lapic(vcpu)) {
+ if (lapic_in_kernel(vcpu)) {
if (events->smi.latched_init)
set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
else
switch (ioctl) {
case KVM_GET_LAPIC: {
r = -EINVAL;
- if (!vcpu->arch.apic)
+ if (!lapic_in_kernel(vcpu))
goto out;
u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
}
case KVM_SET_LAPIC: {
r = -EINVAL;
- if (!vcpu->arch.apic)
+ if (!lapic_in_kernel(vcpu))
goto out;
u.lapic = memdup_user(argp, sizeof(*u.lapic));
if (IS_ERR(u.lapic))
static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
{
- mutex_lock(&kvm->arch.vpit->pit_state.lock);
- memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state));
- mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+ struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state;
+
+ BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels));
+
+ mutex_lock(&kps->lock);
+ memcpy(ps, &kps->channels, sizeof(*ps));
+ mutex_unlock(&kps->lock);
return 0;
}
static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
{
int i;
- mutex_lock(&kvm->arch.vpit->pit_state.lock);
- memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
+ struct kvm_pit *pit = kvm->arch.vpit;
+
+ mutex_lock(&pit->pit_state.lock);
+ memcpy(&pit->pit_state.channels, ps, sizeof(*ps));
for (i = 0; i < 3; i++)
- kvm_pit_load_count(kvm, i, ps->channels[i].count, 0);
- mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+ kvm_pit_load_count(pit, i, ps->channels[i].count, 0);
+ mutex_unlock(&pit->pit_state.lock);
return 0;
}
int start = 0;
int i;
u32 prev_legacy, cur_legacy;
- mutex_lock(&kvm->arch.vpit->pit_state.lock);
- prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
+ struct kvm_pit *pit = kvm->arch.vpit;
+
+ mutex_lock(&pit->pit_state.lock);
+ prev_legacy = pit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY;
if (!prev_legacy && cur_legacy)
start = 1;
- memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels,
- sizeof(kvm->arch.vpit->pit_state.channels));
- kvm->arch.vpit->pit_state.flags = ps->flags;
+ memcpy(&pit->pit_state.channels, &ps->channels,
+ sizeof(pit->pit_state.channels));
+ pit->pit_state.flags = ps->flags;
for (i = 0; i < 3; i++)
- kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count,
+ kvm_pit_load_count(pit, i, pit->pit_state.channels[i].count,
start && i == 0);
- mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+ mutex_unlock(&pit->pit_state.lock);
return 0;
}
static int kvm_vm_ioctl_reinject(struct kvm *kvm,
struct kvm_reinject_control *control)
{
- if (!kvm->arch.vpit)
+ struct kvm_pit *pit = kvm->arch.vpit;
+
+ if (!pit)
return -ENXIO;
- mutex_lock(&kvm->arch.vpit->pit_state.lock);
- kvm->arch.vpit->pit_state.reinject = control->pit_reinject;
- mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+
+ /* pit->pit_state.lock was overloaded to prevent userspace from getting
+ * an inconsistent state after running multiple KVM_REINJECT_CONTROL
+ * ioctls in parallel. Use a separate lock if that ioctl isn't rare.
+ */
+ mutex_lock(&pit->pit_state.lock);
+ kvm_pit_set_reinject(pit, control->pit_reinject);
+ mutex_unlock(&pit->pit_state.lock);
+
return 0;
}
do {
n = min(len, 8);
- if (!(vcpu->arch.apic &&
+ if (!(lapic_in_kernel(vcpu) &&
!kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, addr, n, v))
&& kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, n, v))
break;
do {
n = min(len, 8);
- if (!(vcpu->arch.apic &&
+ if (!(lapic_in_kernel(vcpu) &&
!kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev,
addr, n, v))
&& kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v))
u32 access = ((kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0)
| (write ? PFERR_WRITE_MASK : 0);
+ /*
+ * currently PKRU is only applied to ept enabled guest so
+ * there is no pkey in EPT page table for L1 guest or EPT
+ * shadow page table for L2 guest.
+ */
if (vcpu_match_mmio_gva(vcpu, gva)
&& !permission_fault(vcpu, vcpu->arch.walk_mmu,
- vcpu->arch.access, access)) {
+ vcpu->arch.access, 0, access)) {
*gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT |
(gva & (PAGE_SIZE - 1));
trace_vcpu_match_mmio(gva, *gpa, write, false);
ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes);
if (ret < 0)
return 0;
- kvm_mmu_pte_write(vcpu, gpa, val, bytes);
+ kvm_page_track_write(vcpu, gpa, val, bytes);
return 1;
}
return X86EMUL_CMPXCHG_FAILED;
kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
- kvm_mmu_pte_write(vcpu, gpa, new, bytes);
+ kvm_page_track_write(vcpu, gpa, new, bytes);
return X86EMUL_CONTINUE;
if (!kvm_x86_ops->update_cr8_intercept)
return;
- if (!vcpu->arch.apic)
+ if (!lapic_in_kernel(vcpu))
return;
if (vcpu->arch.apicv_active)
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
- /* We should set ->mode before check ->requests,
- * see the comment in make_all_cpus_request.
+ /*
+ * We should set ->mode before check ->requests,
+ * Please see the comment in kvm_make_all_cpus_request.
+ * This also orders the write to mode from any reads
+ * to the page tables done while the VCPU is running.
+ * Please see the comment in kvm_flush_remote_tlbs.
*/
smp_mb__after_srcu_read_unlock();
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
- if (!kvm_vcpu_has_lapic(vcpu) &&
+ if (!lapic_in_kernel(vcpu) &&
mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
return -EINVAL;
mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
- if (sregs->cr4 & X86_CR4_OSXSAVE)
+ if (sregs->cr4 & (X86_CR4_OSXSAVE | X86_CR4_PKE))
kvm_update_cpuid(vcpu);
idx = srcu_read_lock(&vcpu->kvm->srcu);
* Every 255 times fpu_counter rolls over to 0; a guest that uses
* the FPU in bursts will revert to loading it on demand.
*/
- if (!vcpu->arch.eager_fpu) {
+ if (!use_eager_fpu()) {
if (++vcpu->fpu_counter < 5)
kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
}
}
struct static_key kvm_no_apic_vcpu __read_mostly;
+EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu);
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);
+ kvm_page_track_init(kvm);
+ kvm_mmu_init_vm(kvm);
+
return 0;
}
kfree(kvm->arch.vioapic);
kvm_free_vcpus(kvm);
kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
+ kvm_mmu_uninit_vm(kvm);
}
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
free->arch.lpage_info[i - 1] = NULL;
}
}
+
+ kvm_page_track_free_memslot(free, dont);
}
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
int i;
for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
+ struct kvm_lpage_info *linfo;
unsigned long ugfn;
int lpages;
int level = i + 1;
if (i == 0)
continue;
- slot->arch.lpage_info[i - 1] = kvm_kvzalloc(lpages *
- sizeof(*slot->arch.lpage_info[i - 1]));
- if (!slot->arch.lpage_info[i - 1])
+ linfo = kvm_kvzalloc(lpages * sizeof(*linfo));
+ if (!linfo)
goto out_free;
+ slot->arch.lpage_info[i - 1] = linfo;
+
if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
- slot->arch.lpage_info[i - 1][0].write_count = 1;
+ linfo[0].disallow_lpage = 1;
if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
- slot->arch.lpage_info[i - 1][lpages - 1].write_count = 1;
+ linfo[lpages - 1].disallow_lpage = 1;
ugfn = slot->userspace_addr >> PAGE_SHIFT;
/*
* If the gfn and userspace address are not aligned wrt each
unsigned long j;
for (j = 0; j < lpages; ++j)
- slot->arch.lpage_info[i - 1][j].write_count = 1;
+ linfo[j].disallow_lpage = 1;
}
}
+ if (kvm_page_track_create_memslot(slot, npages))
+ goto out_free;
+
return 0;
out_free:
return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set);
}
+bool kvm_vector_hashing_enabled(void)
+{
+ return vector_hashing;
+}
+EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled);
+
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);