*/
#include "mmu.h"
+#include "x86.h"
#include "kvm_cache_regs.h"
#include <linux/kvm_host.h>
#include <linux/swap.h>
#include <linux/hugetlb.h>
#include <linux/compiler.h>
+#include <linux/srcu.h>
+#include <linux/slab.h>
#include <asm/page.h>
#include <asm/cmpxchg.h>
#define PT32_LEVEL_MASK(level) \
(((1ULL << PT32_LEVEL_BITS) - 1) << PT32_LEVEL_SHIFT(level))
+#define PT32_LVL_OFFSET_MASK(level) \
+ (PT32_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
+ * PT32_LEVEL_BITS))) - 1))
#define PT32_INDEX(address, level)\
(((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1))
#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
#define PT64_DIR_BASE_ADDR_MASK \
(PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1))
+#define PT64_LVL_ADDR_MASK(level) \
+ (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
+ * PT64_LEVEL_BITS))) - 1))
+#define PT64_LVL_OFFSET_MASK(level) \
+ (PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
+ * PT64_LEVEL_BITS))) - 1))
#define PT32_BASE_ADDR_MASK PAGE_MASK
#define PT32_DIR_BASE_ADDR_MASK \
(PAGE_MASK & ~((1ULL << (PAGE_SHIFT + PT32_LEVEL_BITS)) - 1))
+#define PT32_LVL_ADDR_MASK(level) \
+ (PAGE_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
+ * PT32_LEVEL_BITS))) - 1))
#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \
| PT64_NX_MASK)
-#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 PT_PAGE_TABLE_LEVEL 1
-
#define RMAP_EXT 4
#define ACC_EXEC_MASK 1
#define ACC_USER_MASK PT_USER_MASK
#define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK)
+#include <trace/events/kvm.h>
+
+#undef TRACE_INCLUDE_FILE
+#define CREATE_TRACE_POINTS
+#include "mmutrace.h"
+
+#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
+
#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
struct kvm_rmap_desc {
static int is_write_protection(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.cr0 & X86_CR0_WP;
+ return kvm_read_cr0_bits(vcpu, X86_CR0_WP);
}
static int is_cpuid_PSE36(void)
static int is_nx(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.shadow_efer & EFER_NX;
+ return vcpu->arch.efer & EFER_NX;
}
static int is_shadow_present_pte(u64 pte)
return pte & PT_PAGE_SIZE_MASK;
}
-static int is_writeble_pte(unsigned long pte)
+static int is_writable_pte(unsigned long pte)
{
return pte & PT_WRITABLE_MASK;
}
{
if (level == PT_PAGE_TABLE_LEVEL)
return 1;
- if (level == PT_DIRECTORY_LEVEL && is_large_pte(pte))
+ if (is_large_pte(pte))
return 1;
return 0;
}
* Return the pointer to the largepage write count for a given
* gfn, handling slots that are not large page aligned.
*/
-static int *slot_largepage_idx(gfn_t gfn, struct kvm_memory_slot *slot)
+static int *slot_largepage_idx(gfn_t gfn,
+ struct kvm_memory_slot *slot,
+ int level)
{
unsigned long idx;
- idx = (gfn / KVM_PAGES_PER_HPAGE) -
- (slot->base_gfn / KVM_PAGES_PER_HPAGE);
- return &slot->lpage_info[idx].write_count;
+ idx = (gfn / KVM_PAGES_PER_HPAGE(level)) -
+ (slot->base_gfn / KVM_PAGES_PER_HPAGE(level));
+ return &slot->lpage_info[level - 2][idx].write_count;
}
static void account_shadowed(struct kvm *kvm, gfn_t gfn)
{
+ struct kvm_memory_slot *slot;
int *write_count;
+ int i;
gfn = unalias_gfn(kvm, gfn);
- write_count = slot_largepage_idx(gfn,
- gfn_to_memslot_unaliased(kvm, gfn));
- *write_count += 1;
+
+ slot = gfn_to_memslot_unaliased(kvm, gfn);
+ for (i = PT_DIRECTORY_LEVEL;
+ i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+ write_count = slot_largepage_idx(gfn, slot, i);
+ *write_count += 1;
+ }
}
static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
{
+ struct kvm_memory_slot *slot;
int *write_count;
+ int i;
gfn = unalias_gfn(kvm, gfn);
- write_count = slot_largepage_idx(gfn,
- gfn_to_memslot_unaliased(kvm, gfn));
- *write_count -= 1;
- WARN_ON(*write_count < 0);
+ for (i = PT_DIRECTORY_LEVEL;
+ i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+ slot = gfn_to_memslot_unaliased(kvm, gfn);
+ write_count = slot_largepage_idx(gfn, slot, i);
+ *write_count -= 1;
+ WARN_ON(*write_count < 0);
+ }
}
-static int has_wrprotected_page(struct kvm *kvm, gfn_t gfn)
+static int has_wrprotected_page(struct kvm *kvm,
+ gfn_t gfn,
+ int level)
{
struct kvm_memory_slot *slot;
int *largepage_idx;
gfn = unalias_gfn(kvm, gfn);
slot = gfn_to_memslot_unaliased(kvm, gfn);
if (slot) {
- largepage_idx = slot_largepage_idx(gfn, slot);
+ largepage_idx = slot_largepage_idx(gfn, slot, level);
return *largepage_idx;
}
return 1;
}
-static int host_largepage_backed(struct kvm *kvm, gfn_t gfn)
+static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
{
- struct vm_area_struct *vma;
- unsigned long addr;
- int ret = 0;
+ unsigned long page_size;
+ int i, ret = 0;
- addr = gfn_to_hva(kvm, gfn);
- if (kvm_is_error_hva(addr))
- return ret;
+ page_size = kvm_host_page_size(kvm, gfn);
- down_read(¤t->mm->mmap_sem);
- vma = find_vma(current->mm, addr);
- if (vma && is_vm_hugetlb_page(vma))
- ret = 1;
- up_read(¤t->mm->mmap_sem);
+ for (i = PT_PAGE_TABLE_LEVEL;
+ i < (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES); ++i) {
+ if (page_size >= KVM_HPAGE_SIZE(i))
+ ret = i;
+ else
+ break;
+ }
return ret;
}
-static int is_largepage_backed(struct kvm_vcpu *vcpu, gfn_t large_gfn)
+static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
{
struct kvm_memory_slot *slot;
-
- if (has_wrprotected_page(vcpu->kvm, large_gfn))
- return 0;
-
- if (!host_largepage_backed(vcpu->kvm, large_gfn))
- return 0;
+ int host_level, level, max_level;
slot = gfn_to_memslot(vcpu->kvm, large_gfn);
if (slot && slot->dirty_bitmap)
- return 0;
+ return PT_PAGE_TABLE_LEVEL;
- return 1;
+ host_level = host_mapping_level(vcpu->kvm, large_gfn);
+
+ if (host_level == PT_PAGE_TABLE_LEVEL)
+ return host_level;
+
+ max_level = kvm_x86_ops->get_lpage_level() < host_level ?
+ kvm_x86_ops->get_lpage_level() : host_level;
+
+ for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
+ if (has_wrprotected_page(vcpu->kvm, large_gfn, level))
+ break;
+
+ return level - 1;
}
/*
* Note: gfn must be unaliased before this function get called
*/
-static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage)
+static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level)
{
struct kvm_memory_slot *slot;
unsigned long idx;
slot = gfn_to_memslot(kvm, gfn);
- if (!lpage)
+ if (likely(level == PT_PAGE_TABLE_LEVEL))
return &slot->rmap[gfn - slot->base_gfn];
- idx = (gfn / KVM_PAGES_PER_HPAGE) -
- (slot->base_gfn / KVM_PAGES_PER_HPAGE);
+ idx = (gfn / KVM_PAGES_PER_HPAGE(level)) -
+ (slot->base_gfn / KVM_PAGES_PER_HPAGE(level));
- return &slot->lpage_info[idx].rmap_pde;
+ return &slot->lpage_info[level - 2][idx].rmap_pde;
}
/*
* the spte was not added.
*
*/
-static int 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)
{
struct kvm_mmu_page *sp;
struct kvm_rmap_desc *desc;
gfn = unalias_gfn(vcpu->kvm, gfn);
sp = page_header(__pa(spte));
sp->gfns[spte - sp->spt] = gfn;
- rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage);
+ rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
if (!*rmapp) {
rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte);
*rmapp = (unsigned long)spte;
pfn = spte_to_pfn(*spte);
if (*spte & shadow_accessed_mask)
kvm_set_pfn_accessed(pfn);
- if (is_writeble_pte(*spte))
- kvm_release_pfn_dirty(pfn);
- else
- kvm_release_pfn_clean(pfn);
- rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], is_large_pte(*spte));
+ if (is_writable_pte(*spte))
+ kvm_set_pfn_dirty(pfn);
+ rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], sp->role.level);
if (!*rmapp) {
printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte);
BUG();
prev_desc = desc;
desc = desc->more;
}
+ pr_err("rmap_remove: %p %llx many->many\n", spte, *spte);
BUG();
}
}
{
unsigned long *rmapp;
u64 *spte;
- int write_protected = 0;
+ int i, write_protected = 0;
gfn = unalias_gfn(kvm, gfn);
- rmapp = gfn_to_rmap(kvm, gfn, 0);
+ rmapp = gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL);
spte = rmap_next(kvm, rmapp, NULL);
while (spte) {
BUG_ON(!spte);
BUG_ON(!(*spte & PT_PRESENT_MASK));
rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte);
- if (is_writeble_pte(*spte)) {
+ if (is_writable_pte(*spte)) {
__set_spte(spte, *spte & ~PT_WRITABLE_MASK);
write_protected = 1;
}
}
/* check for huge page mappings */
- rmapp = gfn_to_rmap(kvm, gfn, 1);
- spte = rmap_next(kvm, rmapp, NULL);
- while (spte) {
- BUG_ON(!spte);
- BUG_ON(!(*spte & PT_PRESENT_MASK));
- BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK));
- pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn);
- if (is_writeble_pte(*spte)) {
- rmap_remove(kvm, spte);
- --kvm->stat.lpages;
- __set_spte(spte, shadow_trap_nonpresent_pte);
- spte = NULL;
- write_protected = 1;
+ for (i = PT_DIRECTORY_LEVEL;
+ i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+ rmapp = gfn_to_rmap(kvm, gfn, i);
+ spte = rmap_next(kvm, rmapp, NULL);
+ while (spte) {
+ BUG_ON(!spte);
+ BUG_ON(!(*spte & PT_PRESENT_MASK));
+ BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK));
+ pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn);
+ if (is_writable_pte(*spte)) {
+ rmap_remove(kvm, spte);
+ --kvm->stat.lpages;
+ __set_spte(spte, shadow_trap_nonpresent_pte);
+ spte = NULL;
+ write_protected = 1;
+ }
+ spte = rmap_next(kvm, rmapp, spte);
}
- spte = rmap_next(kvm, rmapp, spte);
}
return write_protected;
}
-static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp)
+static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
+ unsigned long data)
{
u64 *spte;
int need_tlb_flush = 0;
return need_tlb_flush;
}
+static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
+ unsigned long data)
+{
+ int need_flush = 0;
+ u64 *spte, new_spte;
+ pte_t *ptep = (pte_t *)data;
+ pfn_t new_pfn;
+
+ WARN_ON(pte_huge(*ptep));
+ new_pfn = pte_pfn(*ptep);
+ spte = rmap_next(kvm, rmapp, NULL);
+ while (spte) {
+ BUG_ON(!is_shadow_present_pte(*spte));
+ rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", spte, *spte);
+ need_flush = 1;
+ if (pte_write(*ptep)) {
+ rmap_remove(kvm, spte);
+ __set_spte(spte, shadow_trap_nonpresent_pte);
+ spte = rmap_next(kvm, rmapp, NULL);
+ } else {
+ new_spte = *spte &~ (PT64_BASE_ADDR_MASK);
+ new_spte |= (u64)new_pfn << PAGE_SHIFT;
+
+ new_spte &= ~PT_WRITABLE_MASK;
+ new_spte &= ~SPTE_HOST_WRITEABLE;
+ if (is_writable_pte(*spte))
+ kvm_set_pfn_dirty(spte_to_pfn(*spte));
+ __set_spte(spte, new_spte);
+ spte = rmap_next(kvm, rmapp, spte);
+ }
+ }
+ if (need_flush)
+ kvm_flush_remote_tlbs(kvm);
+
+ return 0;
+}
+
static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
- int (*handler)(struct kvm *kvm, unsigned long *rmapp))
+ unsigned long data,
+ int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+ unsigned long data))
{
- int i;
+ int i, j;
+ int ret;
int retval = 0;
+ struct kvm_memslots *slots;
- /*
- * If mmap_sem isn't taken, we can look the memslots with only
- * the mmu_lock by skipping over the slots with userspace_addr == 0.
- */
- for (i = 0; i < kvm->nmemslots; i++) {
- struct kvm_memory_slot *memslot = &kvm->memslots[i];
+ slots = rcu_dereference(kvm->memslots);
+
+ for (i = 0; i < slots->nmemslots; i++) {
+ struct kvm_memory_slot *memslot = &slots->memslots[i];
unsigned long start = memslot->userspace_addr;
unsigned long end;
- /* mmu_lock protects userspace_addr */
- if (!start)
- continue;
-
end = start + (memslot->npages << PAGE_SHIFT);
if (hva >= start && hva < end) {
gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
- retval |= handler(kvm, &memslot->rmap[gfn_offset]);
- retval |= handler(kvm,
- &memslot->lpage_info[
- gfn_offset /
- KVM_PAGES_PER_HPAGE].rmap_pde);
+
+ ret = handler(kvm, &memslot->rmap[gfn_offset], data);
+
+ for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) {
+ int idx = gfn_offset;
+ idx /= KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL + j);
+ ret |= handler(kvm,
+ &memslot->lpage_info[j][idx].rmap_pde,
+ data);
+ }
+ trace_kvm_age_page(hva, memslot, ret);
+ retval |= ret;
}
}
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
{
- return kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
+ return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp);
}
-static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp)
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+ kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
+}
+
+static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
+ unsigned long data)
{
u64 *spte;
int young = 0;
- /* always return old for EPT */
+ /*
+ * Emulate the accessed bit for EPT, by checking if this page has
+ * an EPT mapping, and clearing it if it does. On the next access,
+ * a new EPT mapping will be established.
+ * This has some overhead, but not as much as the cost of swapping
+ * out actively used pages or breaking up actively used hugepages.
+ */
if (!shadow_accessed_mask)
- return 0;
+ return kvm_unmap_rmapp(kvm, rmapp, data);
spte = rmap_next(kvm, rmapp, NULL);
while (spte) {
#define RMAP_RECYCLE_THRESHOLD 1000
-static void rmap_recycle(struct kvm_vcpu *vcpu, gfn_t gfn, int lpage)
+static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
{
unsigned long *rmapp;
+ struct kvm_mmu_page *sp;
+
+ sp = page_header(__pa(spte));
gfn = unalias_gfn(vcpu->kvm, gfn);
- rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage);
+ rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
- kvm_unmap_rmapp(vcpu->kvm, rmapp);
+ kvm_unmap_rmapp(vcpu->kvm, rmapp, 0);
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);
+ return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp);
}
#ifdef MMU_DEBUG
return 1;
}
+ trace_kvm_mmu_sync_page(sp);
if (rmap_write_protect(vcpu->kvm, sp->gfn))
kvm_flush_remote_tlbs(vcpu->kvm);
kvm_unlink_unsync_page(vcpu->kvm, sp);
quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
role.quadrant = quadrant;
}
- pgprintk("%s: looking gfn %lx role %x\n", __func__,
- gfn, role.word);
index = kvm_page_table_hashfn(gfn);
bucket = &vcpu->kvm->arch.mmu_page_hash[index];
hlist_for_each_entry_safe(sp, node, tmp, bucket, hash_link)
set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests);
kvm_mmu_mark_parents_unsync(vcpu, sp);
}
- pgprintk("%s: found\n", __func__);
+ trace_kvm_mmu_get_page(sp, false);
return sp;
}
++vcpu->kvm->stat.mmu_cache_miss;
sp = kvm_mmu_alloc_page(vcpu, parent_pte);
if (!sp)
return sp;
- pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word);
sp->gfn = gfn;
sp->role = role;
hlist_add_head(&sp->hash_link, bucket);
vcpu->arch.mmu.prefetch_page(vcpu, sp);
else
nonpaging_prefetch_page(vcpu, sp);
+ trace_kvm_mmu_get_page(sp, true);
return sp;
}
{
if (iterator->level < PT_PAGE_TABLE_LEVEL)
return false;
+
+ if (iterator->level == PT_PAGE_TABLE_LEVEL)
+ if (is_large_pte(*iterator->sptep))
+ return false;
+
iterator->index = SHADOW_PT_INDEX(iterator->addr, iterator->level);
iterator->sptep = ((u64 *)__va(iterator->shadow_addr)) + iterator->index;
return true;
for_each_sp(pages, sp, parents, i) {
kvm_mmu_zap_page(kvm, sp);
mmu_pages_clear_parents(&parents);
+ zapped++;
}
- zapped += pages.nr;
kvm_mmu_pages_init(parent, &parents, &pages);
}
static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
int ret;
+
+ trace_kvm_mmu_zap_page(sp);
++kvm->stat.mmu_shadow_zapped;
ret = mmu_zap_unsync_children(kvm, sp);
kvm_mmu_page_unlink_children(kvm, sp);
*/
if (used_pages > kvm_nr_mmu_pages) {
- while (used_pages > kvm_nr_mmu_pages) {
+ while (used_pages > kvm_nr_mmu_pages &&
+ !list_empty(&kvm->arch.active_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);
+ used_pages -= kvm_mmu_zap_page(kvm, page);
used_pages--;
}
+ kvm_nr_mmu_pages = used_pages;
kvm->arch.n_free_mmu_pages = 0;
}
else
&& !sp->role.invalid) {
pgprintk("%s: zap %lx %x\n",
__func__, gfn, sp->role.word);
- kvm_mmu_zap_page(kvm, sp);
+ if (kvm_mmu_zap_page(kvm, sp))
+ nn = bucket->first;
}
}
}
static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn)
{
- int slot = memslot_id(kvm, gfn_to_memslot(kvm, gfn));
+ int slot = memslot_id(kvm, gfn);
struct kvm_mmu_page *sp = page_header(__pa(pte));
__set_bit(slot, sp->slot_bitmap);
{
struct page *page;
- gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva);
+ gpa_t gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
if (gpa == UNMAPPED_GVA)
return NULL;
struct kvm_mmu_page *s;
struct hlist_node *node, *n;
+ trace_kvm_mmu_unsync_page(sp);
index = kvm_page_table_hashfn(sp->gfn);
bucket = &vcpu->kvm->arch.mmu_page_hash[index];
/* don't unsync if pagetable is shadowed with multiple roles */
static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
unsigned pte_access, int user_fault,
- int write_fault, int dirty, int largepage,
+ int write_fault, int dirty, int level,
gfn_t gfn, pfn_t pfn, bool speculative,
- bool can_unsync)
+ bool can_unsync, bool reset_host_protection)
{
u64 spte;
int ret = 0;
spte |= shadow_nx_mask;
if (pte_access & ACC_USER_MASK)
spte |= shadow_user_mask;
- if (largepage)
+ if (level > PT_PAGE_TABLE_LEVEL)
spte |= PT_PAGE_SIZE_MASK;
if (tdp_enabled)
spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
kvm_is_mmio_pfn(pfn));
+ if (reset_host_protection)
+ spte |= SPTE_HOST_WRITEABLE;
+
spte |= (u64)pfn << PAGE_SHIFT;
if ((pte_access & ACC_WRITE_MASK)
|| (write_fault && !is_write_protection(vcpu) && !user_fault)) {
- if (largepage && has_wrprotected_page(vcpu->kvm, gfn)) {
+ if (level > PT_PAGE_TABLE_LEVEL &&
+ has_wrprotected_page(vcpu->kvm, gfn, level)) {
ret = 1;
spte = shadow_trap_nonpresent_pte;
goto set_pte;
* is responsibility of mmu_get_page / kvm_sync_page.
* Same reasoning can be applied to dirty page accounting.
*/
- if (!can_unsync && is_writeble_pte(*sptep))
+ if (!can_unsync && is_writable_pte(*sptep))
goto set_pte;
if (mmu_need_write_protect(vcpu, gfn, can_unsync)) {
__func__, gfn);
ret = 1;
pte_access &= ~ACC_WRITE_MASK;
- if (is_writeble_pte(spte))
+ if (is_writable_pte(spte))
spte &= ~PT_WRITABLE_MASK;
}
}
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, gfn_t gfn,
- pfn_t pfn, bool speculative)
+ int *ptwrite, int level, gfn_t gfn,
+ pfn_t pfn, bool speculative,
+ bool reset_host_protection)
{
int was_rmapped = 0;
- int was_writeble = is_writeble_pte(*sptep);
+ int was_writable = is_writable_pte(*sptep);
int rmap_count;
pgprintk("%s: spte %llx access %x write_fault %d"
* If we overwrite a PTE page pointer with a 2MB PMD, unlink
* the parent of the now unreachable PTE.
*/
- if (largepage && !is_large_pte(*sptep)) {
+ if (level > PT_PAGE_TABLE_LEVEL &&
+ !is_large_pte(*sptep)) {
struct kvm_mmu_page *child;
u64 pte = *sptep;
} else
was_rmapped = 1;
}
+
if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault,
- dirty, largepage, gfn, pfn, speculative, true)) {
+ dirty, level, gfn, pfn, speculative, true,
+ reset_host_protection)) {
if (write_fault)
*ptwrite = 1;
kvm_x86_ops->tlb_flush(vcpu);
pgprintk("%s: setting spte %llx\n", __func__, *sptep);
pgprintk("instantiating %s PTE (%s) at %ld (%llx) addr %p\n",
is_large_pte(*sptep)? "2MB" : "4kB",
- is_present_pte(*sptep)?"RW":"R", gfn,
- *shadow_pte, sptep);
+ *sptep & PT_PRESENT_MASK ?"RW":"R", gfn,
+ *sptep, sptep);
if (!was_rmapped && is_large_pte(*sptep))
++vcpu->kvm->stat.lpages;
page_header_update_slot(vcpu->kvm, sptep, gfn);
if (!was_rmapped) {
- rmap_count = rmap_add(vcpu, sptep, gfn, largepage);
- if (!is_rmap_spte(*sptep))
- kvm_release_pfn_clean(pfn);
+ rmap_count = rmap_add(vcpu, sptep, gfn);
+ kvm_release_pfn_clean(pfn);
if (rmap_count > RMAP_RECYCLE_THRESHOLD)
- rmap_recycle(vcpu, gfn, largepage);
+ rmap_recycle(vcpu, sptep, gfn);
} else {
- if (was_writeble)
+ if (was_writable)
kvm_release_pfn_dirty(pfn);
else
kvm_release_pfn_clean(pfn);
}
static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
- int largepage, gfn_t gfn, pfn_t pfn)
+ int level, gfn_t gfn, pfn_t pfn)
{
struct kvm_shadow_walk_iterator iterator;
struct kvm_mmu_page *sp;
gfn_t pseudo_gfn;
for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
- if (iterator.level == PT_PAGE_TABLE_LEVEL
- || (largepage && iterator.level == PT_DIRECTORY_LEVEL)) {
+ if (iterator.level == level) {
mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL,
0, write, 1, &pt_write,
- largepage, gfn, pfn, false);
+ level, gfn, pfn, false, true);
++vcpu->stat.pf_fixed;
break;
}
static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
{
int r;
- int largepage = 0;
+ int level;
pfn_t pfn;
unsigned long mmu_seq;
- if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
- gfn &= ~(KVM_PAGES_PER_HPAGE-1);
- largepage = 1;
- }
+ level = mapping_level(vcpu, gfn);
+
+ /*
+ * This path builds a PAE pagetable - so we can map 2mb pages at
+ * maximum. Therefore check if the level is larger than that.
+ */
+ if (level > PT_DIRECTORY_LEVEL)
+ level = PT_DIRECTORY_LEVEL;
+
+ gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
if (mmu_notifier_retry(vcpu, mmu_seq))
goto out_unlock;
kvm_mmu_free_some_pages(vcpu);
- r = __direct_map(vcpu, v, write, largepage, gfn, pfn);
+ r = __direct_map(vcpu, v, write, level, gfn, pfn);
spin_unlock(&vcpu->kvm->mmu_lock);
spin_unlock(&vcpu->kvm->mmu_lock);
}
-static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr)
+static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr,
+ u32 access, u32 *error)
{
+ if (error)
+ *error = 0;
return vaddr;
}
{
pfn_t pfn;
int r;
- int largepage = 0;
+ int level;
gfn_t gfn = gpa >> PAGE_SHIFT;
unsigned long mmu_seq;
if (r)
return r;
- if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
- gfn &= ~(KVM_PAGES_PER_HPAGE-1);
- largepage = 1;
- }
+ level = mapping_level(vcpu, gfn);
+
+ gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
+
mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
pfn = gfn_to_pfn(vcpu->kvm, gfn);
goto out_unlock;
kvm_mmu_free_some_pages(vcpu);
r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK,
- largepage, gfn, pfn);
+ level, gfn, pfn);
spin_unlock(&vcpu->kvm->mmu_lock);
return r;
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][2] = exb_bit_rsvd |
+ rsvd_bits(maxphyaddr, 51) |
+ rsvd_bits(13, 29);
context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
rsvd_bits(maxphyaddr, 51) |
rsvd_bits(13, 20); /* large page */
spin_unlock(&vcpu->kvm->mmu_lock);
if (r)
goto out;
+ /* set_cr3() should ensure TLB has been flushed */
kvm_x86_ops->set_cr3(vcpu, vcpu->arch.mmu.root_hpa);
- kvm_mmu_flush_tlb(vcpu);
out:
return r;
}
const void *new)
{
if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
- if (!vcpu->arch.update_pte.largepage ||
- sp->role.glevels == PT32_ROOT_LEVEL) {
- ++vcpu->kvm->stat.mmu_pde_zapped;
- return;
- }
+ ++vcpu->kvm->stat.mmu_pde_zapped;
+ return;
}
++vcpu->kvm->stat.mmu_pte_updated;
u64 gpte = 0;
pfn_t pfn;
- vcpu->arch.update_pte.largepage = 0;
-
if (bytes != 4 && bytes != 8)
return;
return;
gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
- if (is_large_pte(gpte) && is_largepage_backed(vcpu, gfn)) {
- gfn &= ~(KVM_PAGES_PER_HPAGE-1);
- vcpu->arch.update_pte.largepage = 1;
- }
vcpu->arch.update_pte.mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
pfn = gfn_to_pfn(vcpu->kvm, gfn);
gpa_t gpa;
int r;
- gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva);
+ if (tdp_enabled)
+ return 0;
+
+ gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
spin_lock(&vcpu->kvm->mmu_lock);
r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
{
- while (vcpu->kvm->arch.n_free_mmu_pages < KVM_REFILL_PAGES) {
+ while (vcpu->kvm->arch.n_free_mmu_pages < KVM_REFILL_PAGES &&
+ !list_empty(&vcpu->kvm->arch.active_mmu_pages)) {
struct kvm_mmu_page *sp;
sp = container_of(vcpu->kvm->arch.active_mmu_pages.prev,
if (r)
goto out;
- er = emulate_instruction(vcpu, vcpu->run, cr2, error_code, 0);
+ er = emulate_instruction(vcpu, cr2, error_code, 0);
switch (er) {
case EMULATE_DONE:
case EMULATE_FAIL:
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ vcpu->run->internal.ndata = 0;
return 0;
default:
BUG();
ASSERT(vcpu);
- if (vcpu->kvm->arch.n_requested_mmu_pages)
- vcpu->kvm->arch.n_free_mmu_pages =
- vcpu->kvm->arch.n_requested_mmu_pages;
- else
- vcpu->kvm->arch.n_free_mmu_pages =
- vcpu->kvm->arch.n_alloc_mmu_pages;
/*
* When emulating 32-bit mode, cr3 is only 32 bits even on x86_64.
* Therefore we need to allocate shadow page tables in the first
*/
page = alloc_page(GFP_KERNEL | __GFP_DMA32);
if (!page)
- goto error_1;
+ return -ENOMEM;
+
vcpu->arch.mmu.pae_root = page_address(page);
for (i = 0; i < 4; ++i)
vcpu->arch.mmu.pae_root[i] = INVALID_PAGE;
return 0;
-
-error_1:
- free_mmu_pages(vcpu);
- return -ENOMEM;
}
int kvm_mmu_create(struct kvm_vcpu *vcpu)
spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
- int npages;
+ int npages, idx;
- if (!down_read_trylock(&kvm->slots_lock))
- continue;
+ idx = srcu_read_lock(&kvm->srcu);
spin_lock(&kvm->mmu_lock);
npages = kvm->arch.n_alloc_mmu_pages -
kvm->arch.n_free_mmu_pages;
nr_to_scan--;
spin_unlock(&kvm->mmu_lock);
- up_read(&kvm->slots_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
}
if (kvm_freed)
list_move_tail(&kvm_freed->vm_list, &vm_list);
int i;
unsigned int nr_mmu_pages;
unsigned int nr_pages = 0;
+ struct kvm_memslots *slots;
- for (i = 0; i < kvm->nmemslots; i++)
- nr_pages += kvm->memslots[i].npages;
+ slots = rcu_dereference(kvm->memslots);
+ for (i = 0; i < slots->nmemslots; i++)
+ nr_pages += slots->memslots[i].npages;
nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
nr_mmu_pages = max(nr_mmu_pages,
return r;
}
+int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4])
+{
+ struct kvm_shadow_walk_iterator iterator;
+ int nr_sptes = 0;
+
+ spin_lock(&vcpu->kvm->mmu_lock);
+ for_each_shadow_entry(vcpu, addr, iterator) {
+ sptes[iterator.level-1] = *iterator.sptep;
+ nr_sptes++;
+ if (!is_shadow_present_pte(*iterator.sptep))
+ break;
+ }
+ spin_unlock(&vcpu->kvm->mmu_lock);
+
+ return nr_sptes;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy);
+
#ifdef AUDIT
static const char *audit_msg;
u64 ent = sp->spt[i];
if (is_shadow_present_pte(ent)) {
- if (sp->role.level > 1 && !is_large_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);
- }
- if (sp->role.level == 1)
+ } else
fn(kvm, sp, &sp->spt[i]);
}
}
continue;
va = canonicalize(va);
- if (level > 1) {
- if (ent == shadow_notrap_nonpresent_pte)
- printk(KERN_ERR "audit: (%s) nontrapping pte"
- " in nonleaf level: levels %d gva %lx"
- " level %d pte %llx\n", audit_msg,
- vcpu->arch.mmu.root_level, va, level, ent);
- else
- audit_mappings_page(vcpu, ent, va, level - 1);
- } else {
- gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, 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"
static int count_rmaps(struct kvm_vcpu *vcpu)
{
int nmaps = 0;
- int i, j, k;
+ int i, j, k, idx;
+ idx = srcu_read_lock(&kvm->srcu);
+ slots = rcu_dereference(kvm->memslots);
for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
- struct kvm_memory_slot *m = &vcpu->kvm->memslots[i];
+ struct kvm_memory_slot *m = &slots->memslots[i];
struct kvm_rmap_desc *d;
for (j = 0; j < m->npages; ++j) {
}
}
}
+ srcu_read_unlock(&kvm->srcu, idx);
return nmaps;
}
return;
}
- rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt], 0);
+ rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt],
+ is_large_pte(*sptep));
if (!*rmapp) {
if (!printk_ratelimit())
return;
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;
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_msg = msg;
audit_rmap(vcpu);
audit_write_protection(vcpu);
- audit_mappings(vcpu);
+ if (strcmp("pre pte write", audit_msg) != 0)
+ audit_mappings(vcpu);
audit_writable_sptes_have_rmaps(vcpu);
dbg = olddbg;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff