*
*/
-#include "vmx.h"
#include "mmu.h"
#include <linux/kvm_host.h>
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/swap.h>
+#include <linux/hugetlb.h>
+#include <linux/compiler.h>
#include <asm/page.h>
#include <asm/cmpxchg.h>
#include <asm/io.h>
+#include <asm/vmx.h>
/*
* When setting this variable to true it enables Two-Dimensional-Paging
* 2. while doing 1. it walks guest-physical to host-physical
* If the hardware supports that we don't need to do shadow paging.
*/
-static bool tdp_enabled = false;
+bool tdp_enabled = false;
#undef MMU_DEBUG
#endif
#if defined(MMU_DEBUG) || defined(AUDIT)
-static int dbg = 1;
+static int dbg = 0;
+module_param(dbg, bool, 0644);
#endif
+static int oos_shadow = 1;
+module_param(oos_shadow, bool, 0644);
+
#ifndef MMU_DEBUG
#define ASSERT(x) do { } while (0)
#else
}
#endif
-#define PT64_PT_BITS 9
-#define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS)
-#define PT32_PT_BITS 10
-#define PT32_ENT_PER_PAGE (1 << PT32_PT_BITS)
-
-#define PT_WRITABLE_SHIFT 1
-
-#define PT_PRESENT_MASK (1ULL << 0)
-#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT)
-#define PT_USER_MASK (1ULL << 2)
-#define PT_PWT_MASK (1ULL << 3)
-#define PT_PCD_MASK (1ULL << 4)
-#define PT_ACCESSED_MASK (1ULL << 5)
-#define PT_DIRTY_MASK (1ULL << 6)
-#define PT_PAGE_SIZE_MASK (1ULL << 7)
-#define PT_PAT_MASK (1ULL << 7)
-#define PT_GLOBAL_MASK (1ULL << 8)
-#define PT64_NX_SHIFT 63
-#define PT64_NX_MASK (1ULL << PT64_NX_SHIFT)
-
-#define PT_PAT_SHIFT 7
-#define PT_DIR_PAT_SHIFT 12
-#define PT_DIR_PAT_MASK (1ULL << PT_DIR_PAT_SHIFT)
-
-#define PT32_DIR_PSE36_SIZE 4
-#define PT32_DIR_PSE36_SHIFT 13
-#define PT32_DIR_PSE36_MASK \
- (((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT)
-
-
#define PT_FIRST_AVAIL_BITS_SHIFT 9
#define PT64_SECOND_AVAIL_BITS_SHIFT 52
#define PFERR_USER_MASK (1U << 2)
#define PFERR_FETCH_MASK (1U << 4)
-#define PT64_ROOT_LEVEL 4
-#define PT32_ROOT_LEVEL 2
-#define PT32E_ROOT_LEVEL 3
-
#define PT_DIRECTORY_LEVEL 2
#define PT_PAGE_TABLE_LEVEL 1
#define ACC_USER_MASK PT_USER_MASK
#define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK)
+#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
+
struct kvm_rmap_desc {
u64 *shadow_ptes[RMAP_EXT];
struct kvm_rmap_desc *more;
};
+struct kvm_shadow_walk {
+ int (*entry)(struct kvm_shadow_walk *walk, struct kvm_vcpu *vcpu,
+ u64 addr, u64 *spte, int level);
+};
+
+struct kvm_shadow_walk_iterator {
+ u64 addr;
+ hpa_t shadow_addr;
+ int level;
+ u64 *sptep;
+ unsigned index;
+};
+
+#define for_each_shadow_entry(_vcpu, _addr, _walker) \
+ for (shadow_walk_init(&(_walker), _vcpu, _addr); \
+ shadow_walk_okay(&(_walker)); \
+ shadow_walk_next(&(_walker)))
+
+
+struct kvm_unsync_walk {
+ int (*entry) (struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk);
+};
+
+typedef int (*mmu_parent_walk_fn) (struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp);
+
static struct kmem_cache *pte_chain_cache;
static struct kmem_cache *rmap_desc_cache;
static struct kmem_cache *mmu_page_header_cache;
static u64 __read_mostly shadow_trap_nonpresent_pte;
static u64 __read_mostly shadow_notrap_nonpresent_pte;
+static u64 __read_mostly shadow_base_present_pte;
+static u64 __read_mostly shadow_nx_mask;
+static u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */
+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;
void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte)
{
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_nonpresent_ptes);
+void kvm_mmu_set_base_ptes(u64 base_pte)
+{
+ shadow_base_present_pte = base_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)
+{
+ 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);
+
static int is_write_protection(struct kvm_vcpu *vcpu)
{
return vcpu->arch.cr0 & X86_CR0_WP;
&& pte != shadow_notrap_nonpresent_pte;
}
+static int is_large_pte(u64 pte)
+{
+ return pte & PT_PAGE_SIZE_MASK;
+}
+
static int is_writeble_pte(unsigned long pte)
{
return pte & PT_WRITABLE_MASK;
static int is_dirty_pte(unsigned long pte)
{
- return pte & PT_DIRTY_MASK;
+ return pte & shadow_dirty_mask;
}
static int is_rmap_pte(u64 pte)
return is_shadow_present_pte(pte);
}
+static pfn_t spte_to_pfn(u64 pte)
+{
+ return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
+}
+
static gfn_t pse36_gfn_delta(u32 gpte)
{
int shift = 32 - PT32_DIR_PSE36_SHIFT - PAGE_SHIFT;
if (r)
goto out;
r = mmu_topup_memory_cache(&vcpu->arch.mmu_rmap_desc_cache,
- rmap_desc_cache, 1);
+ rmap_desc_cache, 4);
if (r)
goto out;
r = mmu_topup_memory_cache_page(&vcpu->arch.mmu_page_cache, 8);
}
/*
+ * 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)
+{
+ unsigned long idx;
+
+ idx = (gfn / KVM_PAGES_PER_HPAGE) -
+ (slot->base_gfn / KVM_PAGES_PER_HPAGE);
+ return &slot->lpage_info[idx].write_count;
+}
+
+static void account_shadowed(struct kvm *kvm, gfn_t gfn)
+{
+ int *write_count;
+
+ gfn = unalias_gfn(kvm, gfn);
+ write_count = slot_largepage_idx(gfn,
+ gfn_to_memslot_unaliased(kvm, gfn));
+ *write_count += 1;
+}
+
+static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
+{
+ int *write_count;
+
+ 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);
+}
+
+static int has_wrprotected_page(struct kvm *kvm, gfn_t gfn)
+{
+ 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);
+ return *largepage_idx;
+ }
+
+ return 1;
+}
+
+static int host_largepage_backed(struct kvm *kvm, gfn_t gfn)
+{
+ struct vm_area_struct *vma;
+ unsigned long addr;
+ int ret = 0;
+
+ addr = gfn_to_hva(kvm, gfn);
+ if (kvm_is_error_hva(addr))
+ return ret;
+
+ 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);
+
+ return ret;
+}
+
+static int is_largepage_backed(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;
+
+ slot = gfn_to_memslot(vcpu->kvm, large_gfn);
+ if (slot && slot->dirty_bitmap)
+ return 0;
+
+ return 1;
+}
+
+/*
* Take gfn and return the reverse mapping to it.
* Note: gfn must be unaliased before this function get called
*/
-static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn)
+static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage)
{
struct kvm_memory_slot *slot;
+ unsigned long idx;
slot = gfn_to_memslot(kvm, gfn);
- return &slot->rmap[gfn - slot->base_gfn];
+ if (!lpage)
+ return &slot->rmap[gfn - slot->base_gfn];
+
+ idx = (gfn / KVM_PAGES_PER_HPAGE) -
+ (slot->base_gfn / KVM_PAGES_PER_HPAGE);
+
+ return &slot->lpage_info[idx].rmap_pde;
}
/*
* If rmapp bit zero is one, (then rmap & ~1) points to a struct kvm_rmap_desc
* containing more mappings.
*/
-static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
+static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
{
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);
+ rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage);
if (!*rmapp) {
rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte);
*rmapp = (unsigned long)spte;
struct kvm_rmap_desc *desc;
struct kvm_rmap_desc *prev_desc;
struct kvm_mmu_page *sp;
- struct page *page;
+ pfn_t pfn;
unsigned long *rmapp;
int i;
if (!is_rmap_pte(*spte))
return;
sp = page_header(__pa(spte));
- page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT);
- mark_page_accessed(page);
+ pfn = spte_to_pfn(*spte);
+ if (*spte & shadow_accessed_mask)
+ kvm_set_pfn_accessed(pfn);
if (is_writeble_pte(*spte))
- kvm_release_page_dirty(page);
+ kvm_release_pfn_dirty(pfn);
else
- kvm_release_page_clean(page);
- rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt]);
+ kvm_release_pfn_clean(pfn);
+ rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], is_large_pte(*spte));
if (!*rmapp) {
printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte);
BUG();
return NULL;
}
-static void rmap_write_protect(struct kvm *kvm, u64 gfn)
+static int rmap_write_protect(struct kvm *kvm, u64 gfn)
{
unsigned long *rmapp;
u64 *spte;
int write_protected = 0;
gfn = unalias_gfn(kvm, gfn);
- rmapp = gfn_to_rmap(kvm, gfn);
+ rmapp = gfn_to_rmap(kvm, gfn, 0);
spte = rmap_next(kvm, rmapp, NULL);
while (spte) {
}
spte = rmap_next(kvm, rmapp, spte);
}
- if (write_protected)
- kvm_flush_remote_tlbs(kvm);
+ if (write_protected) {
+ pfn_t pfn;
+
+ spte = rmap_next(kvm, rmapp, NULL);
+ pfn = spte_to_pfn(*spte);
+ kvm_set_pfn_dirty(pfn);
+ }
+
+ /* 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_shadow_pte(spte, shadow_trap_nonpresent_pte);
+ spte = NULL;
+ write_protected = 1;
+ }
+ spte = rmap_next(kvm, rmapp, spte);
+ }
+
+ return write_protected;
+}
+
+static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp)
+{
+ u64 *spte;
+ int need_tlb_flush = 0;
+
+ while ((spte = rmap_next(kvm, rmapp, NULL))) {
+ 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);
+ need_tlb_flush = 1;
+ }
+ return need_tlb_flush;
+}
+
+static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
+ int (*handler)(struct kvm *kvm, unsigned long *rmapp))
+{
+ int i;
+ int retval = 0;
+
+ /*
+ * 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];
+ 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);
+ }
+ }
+
+ return retval;
+}
+
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+{
+ return kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
+}
+
+static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp)
+{
+ u64 *spte;
+ int young = 0;
+
+ /* always return old for EPT */
+ if (!shadow_accessed_mask)
+ return 0;
+
+ spte = rmap_next(kvm, rmapp, NULL);
+ while (spte) {
+ int _young;
+ u64 _spte = *spte;
+ BUG_ON(!(_spte & PT_PRESENT_MASK));
+ _young = _spte & PT_ACCESSED_MASK;
+ if (_young) {
+ young = 1;
+ clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte);
+ }
+ spte = rmap_next(kvm, rmapp, spte);
+ }
+ return young;
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+{
+ return kvm_handle_hva(kvm, hva, kvm_age_rmapp);
}
#ifdef MMU_DEBUG
u64 *end;
for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
- if (*pos != shadow_trap_nonpresent_pte) {
- printk(KERN_ERR "%s: %p %llx\n", __FUNCTION__,
+ if (is_shadow_present_pte(*pos)) {
+ printk(KERN_ERR "%s: %p %llx\n", __func__,
pos, *pos);
return 0;
}
sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE);
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));
- sp->slot_bitmap = 0;
+ bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
sp->multimapped = 0;
sp->parent_pte = parent_pte;
--vcpu->kvm->arch.n_free_mmu_pages;
BUG();
}
+
+static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+ mmu_parent_walk_fn fn)
+{
+ struct kvm_pte_chain *pte_chain;
+ struct hlist_node *node;
+ struct kvm_mmu_page *parent_sp;
+ int i;
+
+ if (!sp->multimapped && sp->parent_pte) {
+ parent_sp = page_header(__pa(sp->parent_pte));
+ fn(vcpu, parent_sp);
+ mmu_parent_walk(vcpu, parent_sp, fn);
+ return;
+ }
+ hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link)
+ for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) {
+ if (!pte_chain->parent_ptes[i])
+ break;
+ parent_sp = page_header(__pa(pte_chain->parent_ptes[i]));
+ fn(vcpu, parent_sp);
+ mmu_parent_walk(vcpu, parent_sp, fn);
+ }
+}
+
+static void kvm_mmu_update_unsync_bitmap(u64 *spte)
+{
+ unsigned int index;
+ struct kvm_mmu_page *sp = page_header(__pa(spte));
+
+ index = spte - sp->spt;
+ if (!__test_and_set_bit(index, sp->unsync_child_bitmap))
+ sp->unsync_children++;
+ WARN_ON(!sp->unsync_children);
+}
+
+static void kvm_mmu_update_parents_unsync(struct kvm_mmu_page *sp)
+{
+ struct kvm_pte_chain *pte_chain;
+ struct hlist_node *node;
+ int i;
+
+ if (!sp->parent_pte)
+ return;
+
+ if (!sp->multimapped) {
+ kvm_mmu_update_unsync_bitmap(sp->parent_pte);
+ return;
+ }
+
+ hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link)
+ for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) {
+ if (!pte_chain->parent_ptes[i])
+ break;
+ kvm_mmu_update_unsync_bitmap(pte_chain->parent_ptes[i]);
+ }
+}
+
+static int unsync_walk_fn(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+{
+ kvm_mmu_update_parents_unsync(sp);
+ return 1;
+}
+
+static void kvm_mmu_mark_parents_unsync(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *sp)
+{
+ mmu_parent_walk(vcpu, sp, unsync_walk_fn);
+ kvm_mmu_update_parents_unsync(sp);
+}
+
+static void nonpaging_prefetch_page(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *sp)
+{
+ int i;
+
+ for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
+ sp->spt[i] = shadow_trap_nonpresent_pte;
+}
+
+static int nonpaging_sync_page(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *sp)
+{
+ return 1;
+}
+
+static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
+{
+}
+
+#define KVM_PAGE_ARRAY_NR 16
+
+struct kvm_mmu_pages {
+ struct mmu_page_and_offset {
+ struct kvm_mmu_page *sp;
+ unsigned int idx;
+ } page[KVM_PAGE_ARRAY_NR];
+ unsigned int nr;
+};
+
+#define for_each_unsync_children(bitmap, idx) \
+ for (idx = find_first_bit(bitmap, 512); \
+ 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)
+{
+ int i;
+
+ if (sp->unsync)
+ for (i=0; i < pvec->nr; i++)
+ if (pvec->page[i].sp == sp)
+ return 0;
+
+ pvec->page[pvec->nr].sp = sp;
+ pvec->page[pvec->nr].idx = idx;
+ pvec->nr++;
+ return (pvec->nr == KVM_PAGE_ARRAY_NR);
+}
+
+static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
+ struct kvm_mmu_pages *pvec)
+{
+ int i, ret, nr_unsync_leaf = 0;
+
+ for_each_unsync_children(sp->unsync_child_bitmap, i) {
+ u64 ent = sp->spt[i];
+
+ if (is_shadow_present_pte(ent) && !is_large_pte(ent)) {
+ struct kvm_mmu_page *child;
+ child = page_header(ent & PT64_BASE_ADDR_MASK);
+
+ if (child->unsync_children) {
+ if (mmu_pages_add(pvec, child, i))
+ return -ENOSPC;
+
+ ret = __mmu_unsync_walk(child, pvec);
+ if (!ret)
+ __clear_bit(i, sp->unsync_child_bitmap);
+ else if (ret > 0)
+ nr_unsync_leaf += ret;
+ else
+ return ret;
+ }
+
+ if (child->unsync) {
+ nr_unsync_leaf++;
+ if (mmu_pages_add(pvec, child, i))
+ return -ENOSPC;
+ }
+ }
+ }
+
+ if (find_first_bit(sp->unsync_child_bitmap, 512) == 512)
+ sp->unsync_children = 0;
+
+ return nr_unsync_leaf;
+}
+
+static int mmu_unsync_walk(struct kvm_mmu_page *sp,
+ struct kvm_mmu_pages *pvec)
+{
+ if (!sp->unsync_children)
+ return 0;
+
+ mmu_pages_add(pvec, sp, 0);
+ return __mmu_unsync_walk(sp, pvec);
+}
+
static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
{
unsigned index;
struct kvm_mmu_page *sp;
struct hlist_node *node;
- pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn);
+ pgprintk("%s: looking for gfn %lx\n", __func__, gfn);
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.metaphysical
+ && !sp->role.invalid) {
pgprintk("%s: found role %x\n",
- __FUNCTION__, sp->role.word);
+ __func__, sp->role.word);
return sp;
}
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;
+}
+
+static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp);
+
+static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+{
+ if (sp->role.glevels != vcpu->arch.mmu.root_level) {
+ kvm_mmu_zap_page(vcpu->kvm, sp);
+ return 1;
+ }
+
+ if (rmap_write_protect(vcpu->kvm, sp->gfn))
+ kvm_flush_remote_tlbs(vcpu->kvm);
+ kvm_unlink_unsync_page(vcpu->kvm, sp);
+ if (vcpu->arch.mmu.sync_page(vcpu, sp)) {
+ kvm_mmu_zap_page(vcpu->kvm, sp);
+ return 1;
+ }
+
+ kvm_mmu_flush_tlb(vcpu);
+ return 0;
+}
+
+struct mmu_page_path {
+ struct kvm_mmu_page *parent[PT64_ROOT_LEVEL-1];
+ unsigned int idx[PT64_ROOT_LEVEL-1];
+};
+
+#define for_each_sp(pvec, sp, parents, i) \
+ for (i = mmu_pages_next(&pvec, &parents, -1), \
+ sp = pvec.page[i].sp; \
+ 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)
+{
+ int n;
+
+ for (n = i+1; n < pvec->nr; n++) {
+ struct kvm_mmu_page *sp = pvec->page[n].sp;
+
+ if (sp->role.level == PT_PAGE_TABLE_LEVEL) {
+ parents->idx[0] = pvec->page[n].idx;
+ return n;
+ }
+
+ parents->parent[sp->role.level-2] = sp;
+ parents->idx[sp->role.level-1] = pvec->page[n].idx;
+ }
+
+ return n;
+}
+
+void mmu_pages_clear_parents(struct mmu_page_path *parents)
+{
+ struct kvm_mmu_page *sp;
+ unsigned int level = 0;
+
+ do {
+ unsigned int idx = parents->idx[level];
+
+ sp = parents->parent[level];
+ if (!sp)
+ return;
+
+ --sp->unsync_children;
+ WARN_ON((int)sp->unsync_children < 0);
+ __clear_bit(idx, sp->unsync_child_bitmap);
+ 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;
+}
+
+static void mmu_sync_children(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *parent)
+{
+ int i;
+ struct kvm_mmu_page *sp;
+ struct mmu_page_path parents;
+ struct kvm_mmu_pages pages;
+
+ kvm_mmu_pages_init(parent, &parents, &pages);
+ while (mmu_unsync_walk(parent, &pages)) {
+ int protected = 0;
+
+ for_each_sp(pages, sp, parents, i)
+ protected |= rmap_write_protect(vcpu->kvm, sp->gfn);
+
+ if (protected)
+ kvm_flush_remote_tlbs(vcpu->kvm);
+
+ for_each_sp(pages, sp, parents, i) {
+ kvm_sync_page(vcpu, sp);
+ mmu_pages_clear_parents(&parents);
+ }
+ cond_resched_lock(&vcpu->kvm->mmu_lock);
+ kvm_mmu_pages_init(parent, &parents, &pages);
+ }
+}
+
static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
gfn_t gfn,
gva_t gaddr,
unsigned quadrant;
struct hlist_head *bucket;
struct kvm_mmu_page *sp;
- struct hlist_node *node;
+ struct hlist_node *node, *tmp;
- role.word = 0;
- role.glevels = vcpu->arch.mmu.root_level;
+ role = vcpu->arch.mmu.base_role;
role.level = level;
role.metaphysical = metaphysical;
role.access = access;
quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
role.quadrant = quadrant;
}
- pgprintk("%s: looking gfn %lx role %x\n", __FUNCTION__,
+ 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(sp, node, bucket, hash_link)
- if (sp->gfn == gfn && sp->role.word == role.word) {
+ hlist_for_each_entry_safe(sp, node, tmp, bucket, hash_link)
+ if (sp->gfn == gfn) {
+ if (sp->unsync)
+ if (kvm_sync_page(vcpu, sp))
+ continue;
+
+ if (sp->role.word != role.word)
+ continue;
+
mmu_page_add_parent_pte(vcpu, sp, parent_pte);
- pgprintk("%s: found\n", __FUNCTION__);
+ if (sp->unsync_children) {
+ set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests);
+ kvm_mmu_mark_parents_unsync(vcpu, sp);
+ }
+ pgprintk("%s: found\n", __func__);
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", __FUNCTION__, gfn, role.word);
+ 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);
- vcpu->arch.mmu.prefetch_page(vcpu, sp);
- if (!metaphysical)
- rmap_write_protect(vcpu->kvm, gfn);
+ if (!metaphysical) {
+ if (rmap_write_protect(vcpu->kvm, gfn))
+ kvm_flush_remote_tlbs(vcpu->kvm);
+ account_shadowed(vcpu->kvm, gfn);
+ }
+ if (shadow_trap_nonpresent_pte != shadow_notrap_nonpresent_pte)
+ vcpu->arch.mmu.prefetch_page(vcpu, sp);
+ else
+ nonpaging_prefetch_page(vcpu, sp);
return sp;
}
+static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
+ struct kvm_vcpu *vcpu, u64 addr)
+{
+ iterator->addr = addr;
+ iterator->shadow_addr = vcpu->arch.mmu.root_hpa;
+ iterator->level = vcpu->arch.mmu.shadow_root_level;
+ if (iterator->level == PT32E_ROOT_LEVEL) {
+ iterator->shadow_addr
+ = vcpu->arch.mmu.pae_root[(addr >> 30) & 3];
+ iterator->shadow_addr &= PT64_BASE_ADDR_MASK;
+ --iterator->level;
+ if (!iterator->shadow_addr)
+ iterator->level = 0;
+ }
+}
+
+static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator)
+{
+ if (iterator->level < PT_PAGE_TABLE_LEVEL)
+ return false;
+ iterator->index = SHADOW_PT_INDEX(iterator->addr, iterator->level);
+ iterator->sptep = ((u64 *)__va(iterator->shadow_addr)) + iterator->index;
+ return true;
+}
+
+static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator)
+{
+ iterator->shadow_addr = *iterator->sptep & PT64_BASE_ADDR_MASK;
+ --iterator->level;
+}
+
+static int walk_shadow(struct kvm_shadow_walk *walker,
+ struct kvm_vcpu *vcpu, u64 addr)
+{
+ struct kvm_shadow_walk_iterator iterator;
+ int r;
+
+ for_each_shadow_entry(vcpu, addr, iterator) {
+ r = walker->entry(walker, vcpu, addr,
+ iterator.sptep, iterator.level);
+ if (r)
+ return r;
+ }
+ return 0;
+}
+
static void kvm_mmu_page_unlink_children(struct kvm *kvm,
struct kvm_mmu_page *sp)
{
rmap_remove(kvm, &pt[i]);
pt[i] = shadow_trap_nonpresent_pte;
}
- kvm_flush_remote_tlbs(kvm);
return;
}
for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
ent = pt[i];
+ if (is_shadow_present_pte(ent)) {
+ if (!is_large_pte(ent)) {
+ ent &= PT64_BASE_ADDR_MASK;
+ mmu_page_remove_parent_pte(page_header(ent),
+ &pt[i]);
+ } else {
+ --kvm->stat.lpages;
+ rmap_remove(kvm, &pt[i]);
+ }
+ }
pt[i] = shadow_trap_nonpresent_pte;
- if (!is_shadow_present_pte(ent))
- continue;
- ent &= PT64_BASE_ADDR_MASK;
- mmu_page_remove_parent_pte(page_header(ent), &pt[i]);
}
- kvm_flush_remote_tlbs(kvm);
}
static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte)
kvm->vcpus[i]->arch.last_pte_updated = NULL;
}
-static void kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
{
u64 *parent_pte;
- ++kvm->stat.mmu_shadow_zapped;
while (sp->multimapped || sp->parent_pte) {
if (!sp->multimapped)
parent_pte = sp->parent_pte;
kvm_mmu_put_page(sp, parent_pte);
set_shadow_pte(parent_pte, shadow_trap_nonpresent_pte);
}
+}
+
+static int mmu_zap_unsync_children(struct kvm *kvm,
+ struct kvm_mmu_page *parent)
+{
+ int i, zapped = 0;
+ struct mmu_page_path parents;
+ struct kvm_mmu_pages pages;
+
+ 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;
+
+ for_each_sp(pages, sp, parents, i) {
+ kvm_mmu_zap_page(kvm, sp);
+ mmu_pages_clear_parents(&parents);
+ }
+ zapped += pages.nr;
+ kvm_mmu_pages_init(parent, &parents, &pages);
+ }
+
+ return zapped;
+}
+
+static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ int ret;
+ ++kvm->stat.mmu_shadow_zapped;
+ ret = mmu_zap_unsync_children(kvm, sp);
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)
+ unaccount_shadowed(kvm, sp->gfn);
+ if (sp->unsync)
+ kvm_unlink_unsync_page(kvm, sp);
if (!sp->root_count) {
hlist_del(&sp->hash_link);
kvm_mmu_free_page(kvm, sp);
- } else
+ } else {
+ sp->role.invalid = 1;
list_move(&sp->link, &kvm->arch.active_mmu_pages);
+ kvm_reload_remote_mmus(kvm);
+ }
kvm_mmu_reset_last_pte_updated(kvm);
+ return ret;
}
/*
struct hlist_node *node, *n;
int r;
- pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn);
+ pgprintk("%s: looking for gfn %lx\n", __func__, gfn);
r = 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) {
- pgprintk("%s: gfn %lx role %x\n", __FUNCTION__, gfn,
+ pgprintk("%s: gfn %lx role %x\n", __func__, gfn,
sp->role.word);
- kvm_mmu_zap_page(kvm, sp);
r = 1;
+ if (kvm_mmu_zap_page(kvm, sp))
+ n = bucket->first;
}
return r;
}
struct kvm_mmu_page *sp;
while ((sp = kvm_mmu_lookup_page(kvm, gfn)) != NULL) {
- pgprintk("%s: zap %lx %x\n", __FUNCTION__, gfn, sp->role.word);
+ pgprintk("%s: zap %lx %x\n", __func__, gfn, sp->role.word);
kvm_mmu_zap_page(kvm, sp);
}
}
int slot = memslot_id(kvm, gfn_to_memslot(kvm, gfn));
struct kvm_mmu_page *sp = page_header(__pa(pte));
- __set_bit(slot, &sp->slot_bitmap);
+ __set_bit(slot, sp->slot_bitmap);
+}
+
+static void mmu_convert_notrap(struct kvm_mmu_page *sp)
+{
+ int i;
+ u64 *pt = sp->spt;
+
+ if (shadow_trap_nonpresent_pte == shadow_notrap_nonpresent_pte)
+ return;
+
+ 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);
+ }
}
struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva)
if (gpa == UNMAPPED_GVA)
return NULL;
- down_read(¤t->mm->mmap_sem);
page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
- up_read(¤t->mm->mmap_sem);
return page;
}
-static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
- unsigned pt_access, unsigned pte_access,
- int user_fault, int write_fault, int dirty,
- int *ptwrite, gfn_t gfn, struct page *page)
+/*
+ * The function is based on mtrr_type_lookup() in
+ * arch/x86/kernel/cpu/mtrr/generic.c
+ */
+static int get_mtrr_type(struct mtrr_state_type *mtrr_state,
+ u64 start, u64 end)
{
- u64 spte;
- int was_rmapped = 0;
- int was_writeble = is_writeble_pte(*shadow_pte);
- hfn_t host_pfn = (*shadow_pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
+ int i;
+ u64 base, mask;
+ u8 prev_match, curr_match;
+ int num_var_ranges = KVM_NR_VAR_MTRR;
+
+ if (!mtrr_state->enabled)
+ return 0xFF;
+
+ /* Make end inclusive end, instead of exclusive */
+ end--;
+
+ /* Look in fixed ranges. Just return the type as per start */
+ if (mtrr_state->have_fixed && (start < 0x100000)) {
+ int idx;
+
+ if (start < 0x80000) {
+ idx = 0;
+ idx += (start >> 16);
+ return mtrr_state->fixed_ranges[idx];
+ } else if (start < 0xC0000) {
+ idx = 1 * 8;
+ idx += ((start - 0x80000) >> 14);
+ return mtrr_state->fixed_ranges[idx];
+ } else if (start < 0x1000000) {
+ idx = 3 * 8;
+ idx += ((start - 0xC0000) >> 12);
+ return mtrr_state->fixed_ranges[idx];
+ }
+ }
- pgprintk("%s: spte %llx access %x write_fault %d"
- " user_fault %d gfn %lx\n",
- __FUNCTION__, *shadow_pte, pt_access,
- write_fault, user_fault, gfn);
+ /*
+ * Look in variable ranges
+ * Look of multiple ranges matching this address and pick type
+ * as per MTRR precedence
+ */
+ if (!(mtrr_state->enabled & 2))
+ return mtrr_state->def_type;
- if (is_rmap_pte(*shadow_pte)) {
- if (host_pfn != page_to_pfn(page)) {
- pgprintk("hfn old %lx new %lx\n",
- host_pfn, page_to_pfn(page));
- rmap_remove(vcpu->kvm, shadow_pte);
+ prev_match = 0xFF;
+ for (i = 0; i < num_var_ranges; ++i) {
+ unsigned short start_state, end_state;
+
+ if (!(mtrr_state->var_ranges[i].mask_lo & (1 << 11)))
+ continue;
+
+ base = (((u64)mtrr_state->var_ranges[i].base_hi) << 32) +
+ (mtrr_state->var_ranges[i].base_lo & PAGE_MASK);
+ mask = (((u64)mtrr_state->var_ranges[i].mask_hi) << 32) +
+ (mtrr_state->var_ranges[i].mask_lo & PAGE_MASK);
+
+ start_state = ((start & mask) == (base & mask));
+ end_state = ((end & mask) == (base & mask));
+ if (start_state != end_state)
+ return 0xFE;
+
+ if ((start & mask) != (base & mask))
+ continue;
+
+ curr_match = mtrr_state->var_ranges[i].base_lo & 0xff;
+ if (prev_match == 0xFF) {
+ prev_match = curr_match;
+ continue;
+ }
+
+ if (prev_match == MTRR_TYPE_UNCACHABLE ||
+ curr_match == MTRR_TYPE_UNCACHABLE)
+ return MTRR_TYPE_UNCACHABLE;
+
+ if ((prev_match == MTRR_TYPE_WRBACK &&
+ curr_match == MTRR_TYPE_WRTHROUGH) ||
+ (prev_match == MTRR_TYPE_WRTHROUGH &&
+ curr_match == MTRR_TYPE_WRBACK)) {
+ prev_match = MTRR_TYPE_WRTHROUGH;
+ curr_match = MTRR_TYPE_WRTHROUGH;
+ }
+
+ if (prev_match != curr_match)
+ return MTRR_TYPE_UNCACHABLE;
+ }
+
+ if (prev_match != 0xFF)
+ return prev_match;
+
+ return mtrr_state->def_type;
+}
+
+static u8 get_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ u8 mtrr;
+
+ mtrr = get_mtrr_type(&vcpu->arch.mtrr_state, gfn << PAGE_SHIFT,
+ (gfn << PAGE_SHIFT) + PAGE_SIZE);
+ if (mtrr == 0xfe || mtrr == 0xff)
+ mtrr = MTRR_TYPE_WRBACK;
+ return mtrr;
+}
+
+static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+{
+ unsigned index;
+ struct hlist_head *bucket;
+ struct kvm_mmu_page *s;
+ struct hlist_node *node, *n;
+
+ 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 */
+ hlist_for_each_entry_safe(s, node, n, bucket, hash_link) {
+ if (s->gfn != sp->gfn || s->role.metaphysical)
+ 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);
+
+ mmu_convert_notrap(sp);
+ return 0;
+}
+
+static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
+ bool can_unsync)
+{
+ struct kvm_mmu_page *shadow;
+
+ shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn);
+ if (shadow) {
+ if (shadow->role.level != PT_PAGE_TABLE_LEVEL)
+ return 1;
+ if (shadow->unsync)
+ return 0;
+ if (can_unsync && oos_shadow)
+ return kvm_unsync_page(vcpu, shadow);
+ return 1;
+ }
+ return 0;
+}
+
+static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
+ unsigned pte_access, int user_fault,
+ int write_fault, int dirty, int largepage,
+ int global, 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);
}
- else
- was_rmapped = 1;
}
/*
* whether the guest actually used the pte (in order to detect
* demand paging).
*/
- spte = PT_PRESENT_MASK | PT_DIRTY_MASK;
+ spte = shadow_base_present_pte | shadow_dirty_mask;
+ if (!speculative)
+ spte |= shadow_accessed_mask;
if (!dirty)
pte_access &= ~ACC_WRITE_MASK;
- if (!(pte_access & ACC_EXEC_MASK))
- spte |= PT64_NX_MASK;
-
- spte |= PT_PRESENT_MASK;
+ if (pte_access & ACC_EXEC_MASK)
+ spte |= shadow_x_mask;
+ else
+ spte |= shadow_nx_mask;
if (pte_access & ACC_USER_MASK)
- spte |= PT_USER_MASK;
+ 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;
+ }
- spte |= page_to_phys(page);
+ spte |= (u64)pfn << PAGE_SHIFT;
if ((pte_access & ACC_WRITE_MASK)
|| (write_fault && !is_write_protection(vcpu) && !user_fault)) {
- struct kvm_mmu_page *shadow;
- spte |= PT_WRITABLE_MASK;
- if (user_fault) {
- mmu_unshadow(vcpu->kvm, gfn);
- goto unshadowed;
+ if (largepage && has_wrprotected_page(vcpu->kvm, gfn)) {
+ ret = 1;
+ spte = shadow_trap_nonpresent_pte;
+ goto set_pte;
}
- shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn);
- if (shadow) {
+ spte |= PT_WRITABLE_MASK;
+
+ /*
+ * Optimization: for pte sync, if spte was writable the hash
+ * lookup is unnecessary (and expensive). Write protection
+ * 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))
+ goto set_pte;
+
+ if (mmu_need_write_protect(vcpu, gfn, can_unsync)) {
pgprintk("%s: found shadow page for %lx, marking ro\n",
- __FUNCTION__, gfn);
+ __func__, gfn);
+ ret = 1;
pte_access &= ~ACC_WRITE_MASK;
- if (is_writeble_pte(spte)) {
+ if (is_writeble_pte(spte))
spte &= ~PT_WRITABLE_MASK;
- kvm_x86_ops->tlb_flush(vcpu);
- }
- if (write_fault)
- *ptwrite = 1;
}
}
-unshadowed:
-
if (pte_access & ACC_WRITE_MASK)
mark_page_dirty(vcpu->kvm, gfn);
- pgprintk("%s: setting spte %llx\n", __FUNCTION__, spte);
+set_pte:
set_shadow_pte(shadow_pte, spte);
+ return ret;
+}
+
+static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
+ 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 was_rmapped = 0;
+ int was_writeble = is_writeble_pte(*shadow_pte);
+
+ pgprintk("%s: spte %llx access %x write_fault %d"
+ " user_fault %d gfn %lx\n",
+ __func__, *shadow_pte, pt_access,
+ write_fault, user_fault, gfn);
+
+ if (is_rmap_pte(*shadow_pte)) {
+ /*
+ * 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)) {
+ struct kvm_mmu_page *child;
+ u64 pte = *shadow_pte;
+
+ child = page_header(pte & PT64_BASE_ADDR_MASK);
+ mmu_page_remove_parent_pte(child, shadow_pte);
+ } else if (pfn != spte_to_pfn(*shadow_pte)) {
+ 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;
+ }
+ }
+ if (set_spte(vcpu, shadow_pte, pte_access, user_fault, write_fault,
+ dirty, largepage, global, 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("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))
+ ++vcpu->kvm->stat.lpages;
+
page_header_update_slot(vcpu->kvm, shadow_pte, gfn);
if (!was_rmapped) {
- rmap_add(vcpu, shadow_pte, gfn);
+ rmap_add(vcpu, shadow_pte, gfn, largepage);
if (!is_rmap_pte(*shadow_pte))
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
} else {
if (was_writeble)
- kvm_release_page_dirty(page);
+ kvm_release_pfn_dirty(pfn);
else
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
}
- if (!ptwrite || !*ptwrite)
+ if (speculative) {
vcpu->arch.last_pte_updated = shadow_pte;
+ vcpu->arch.last_pte_gfn = gfn;
+ }
}
static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
{
}
-static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write,
- gfn_t gfn, struct page *page)
+static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
+ int largepage, gfn_t gfn, pfn_t pfn)
{
- int level = PT32E_ROOT_LEVEL;
- hpa_t table_addr = vcpu->arch.mmu.root_hpa;
+ struct kvm_shadow_walk_iterator iterator;
+ struct kvm_mmu_page *sp;
int pt_write = 0;
-
- for (; ; level--) {
- u32 index = PT64_INDEX(v, level);
- u64 *table;
-
- ASSERT(VALID_PAGE(table_addr));
- table = __va(table_addr);
-
- if (level == 1) {
- mmu_set_spte(vcpu, &table[index], ACC_ALL, ACC_ALL,
- 0, write, 1, &pt_write, gfn, page);
- return pt_write;
+ 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)) {
+ mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL,
+ 0, write, 1, &pt_write,
+ largepage, 0, gfn, pfn, false);
+ ++vcpu->stat.pf_fixed;
+ break;
}
- if (table[index] == shadow_trap_nonpresent_pte) {
- struct kvm_mmu_page *new_table;
- gfn_t pseudo_gfn;
-
- pseudo_gfn = (v & PT64_DIR_BASE_ADDR_MASK)
- >> PAGE_SHIFT;
- new_table = kvm_mmu_get_page(vcpu, pseudo_gfn,
- v, level - 1,
- 1, ACC_ALL, &table[index]);
- if (!new_table) {
+ if (*iterator.sptep == shadow_trap_nonpresent_pte) {
+ pseudo_gfn = (iterator.addr & PT64_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT;
+ sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr,
+ iterator.level - 1,
+ 1, ACC_ALL, iterator.sptep);
+ if (!sp) {
pgprintk("nonpaging_map: ENOMEM\n");
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
return -ENOMEM;
}
- table[index] = __pa(new_table->spt) | PT_PRESENT_MASK
- | PT_WRITABLE_MASK | PT_USER_MASK;
+ set_shadow_pte(iterator.sptep,
+ __pa(sp->spt)
+ | PT_PRESENT_MASK | PT_WRITABLE_MASK
+ | shadow_user_mask | shadow_x_mask);
}
- table_addr = table[index] & PT64_BASE_ADDR_MASK;
}
+ return pt_write;
}
static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
{
int r;
+ int largepage = 0;
+ pfn_t pfn;
+ unsigned long mmu_seq;
- struct page *page;
-
- down_read(&vcpu->kvm->slots_lock);
+ if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
+ gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+ largepage = 1;
+ }
- down_read(¤t->mm->mmap_sem);
- page = gfn_to_page(vcpu->kvm, gfn);
- up_read(¤t->mm->mmap_sem);
+ mmu_seq = vcpu->kvm->mmu_notifier_seq;
+ smp_rmb();
+ pfn = gfn_to_pfn(vcpu->kvm, gfn);
/* mmio */
- if (is_error_page(page)) {
- kvm_release_page_clean(page);
- up_read(&vcpu->kvm->slots_lock);
+ if (is_error_pfn(pfn)) {
+ kvm_release_pfn_clean(pfn);
return 1;
}
spin_lock(&vcpu->kvm->mmu_lock);
+ if (mmu_notifier_retry(vcpu, mmu_seq))
+ goto out_unlock;
kvm_mmu_free_some_pages(vcpu);
- r = __nonpaging_map(vcpu, v, write, gfn, page);
+ r = __direct_map(vcpu, v, write, largepage, gfn, pfn);
spin_unlock(&vcpu->kvm->mmu_lock);
- up_read(&vcpu->kvm->slots_lock);
return r;
-}
-
-
-static void nonpaging_prefetch_page(struct kvm_vcpu *vcpu,
- struct kvm_mmu_page *sp)
-{
- int i;
- for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
- sp->spt[i] = shadow_trap_nonpresent_pte;
+out_unlock:
+ spin_unlock(&vcpu->kvm->mmu_lock);
+ kvm_release_pfn_clean(pfn);
+ return 0;
}
+
static void mmu_free_roots(struct kvm_vcpu *vcpu)
{
int i;
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
return;
spin_lock(&vcpu->kvm->mmu_lock);
-#ifdef CONFIG_X86_64
if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
hpa_t root = vcpu->arch.mmu.root_hpa;
sp = page_header(root);
--sp->root_count;
+ if (!sp->root_count && sp->role.invalid)
+ kvm_mmu_zap_page(vcpu->kvm, sp);
vcpu->arch.mmu.root_hpa = INVALID_PAGE;
spin_unlock(&vcpu->kvm->mmu_lock);
return;
}
-#endif
for (i = 0; i < 4; ++i) {
hpa_t root = vcpu->arch.mmu.pae_root[i];
root &= PT64_BASE_ADDR_MASK;
sp = page_header(root);
--sp->root_count;
+ if (!sp->root_count && sp->role.invalid)
+ kvm_mmu_zap_page(vcpu->kvm, sp);
}
vcpu->arch.mmu.pae_root[i] = INVALID_PAGE;
}
int i;
gfn_t root_gfn;
struct kvm_mmu_page *sp;
+ int metaphysical = 0;
root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT;
-#ifdef CONFIG_X86_64
if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
hpa_t root = vcpu->arch.mmu.root_hpa;
ASSERT(!VALID_PAGE(root));
+ if (tdp_enabled)
+ metaphysical = 1;
sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
- PT64_ROOT_LEVEL, 0, ACC_ALL, NULL);
+ PT64_ROOT_LEVEL, metaphysical,
+ ACC_ALL, NULL);
root = __pa(sp->spt);
++sp->root_count;
vcpu->arch.mmu.root_hpa = root;
return;
}
-#endif
+ metaphysical = !is_paging(vcpu);
+ if (tdp_enabled)
+ metaphysical = 1;
for (i = 0; i < 4; ++i) {
hpa_t root = vcpu->arch.mmu.pae_root[i];
} else if (vcpu->arch.mmu.root_level == 0)
root_gfn = 0;
sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
- PT32_ROOT_LEVEL, !is_paging(vcpu),
+ PT32_ROOT_LEVEL, metaphysical,
ACC_ALL, NULL);
root = __pa(sp->spt);
++sp->root_count;
vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
}
+static void mmu_sync_roots(struct kvm_vcpu *vcpu)
+{
+ 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_sync_children(vcpu, sp);
+ return;
+ }
+ for (i = 0; i < 4; ++i) {
+ hpa_t root = vcpu->arch.mmu.pae_root[i];
+
+ if (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);
+ mmu_sync_roots(vcpu);
+ 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;
gfn_t gfn;
int r;
- pgprintk("%s: gva %lx error %x\n", __FUNCTION__, gva, error_code);
+ pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
r = mmu_topup_memory_caches(vcpu);
if (r)
return r;
error_code & PFERR_WRITE_MASK, gfn);
}
+static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
+ u32 error_code)
+{
+ pfn_t pfn;
+ int r;
+ int largepage = 0;
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+ unsigned long mmu_seq;
+
+ ASSERT(vcpu);
+ ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa));
+
+ r = mmu_topup_memory_caches(vcpu);
+ if (r)
+ return r;
+
+ if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
+ gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+ largepage = 1;
+ }
+ mmu_seq = vcpu->kvm->mmu_notifier_seq;
+ smp_rmb();
+ pfn = gfn_to_pfn(vcpu->kvm, gfn);
+ if (is_error_pfn(pfn)) {
+ kvm_release_pfn_clean(pfn);
+ return 1;
+ }
+ spin_lock(&vcpu->kvm->mmu_lock);
+ if (mmu_notifier_retry(vcpu, mmu_seq))
+ goto out_unlock;
+ kvm_mmu_free_some_pages(vcpu);
+ r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK,
+ largepage, gfn, pfn);
+ spin_unlock(&vcpu->kvm->mmu_lock);
+
+ return r;
+
+out_unlock:
+ spin_unlock(&vcpu->kvm->mmu_lock);
+ kvm_release_pfn_clean(pfn);
+ return 0;
+}
+
static void nonpaging_free(struct kvm_vcpu *vcpu)
{
mmu_free_roots(vcpu);
context->gva_to_gpa = nonpaging_gva_to_gpa;
context->free = nonpaging_free;
context->prefetch_page = nonpaging_prefetch_page;
+ context->sync_page = nonpaging_sync_page;
+ context->invlpg = nonpaging_invlpg;
context->root_level = 0;
context->shadow_root_level = PT32E_ROOT_LEVEL;
context->root_hpa = INVALID_PAGE;
static void paging_new_cr3(struct kvm_vcpu *vcpu)
{
- pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->arch.cr3);
+ pgprintk("%s: cr3 %lx\n", __func__, vcpu->arch.cr3);
mmu_free_roots(vcpu);
}
context->page_fault = paging64_page_fault;
context->gva_to_gpa = paging64_gva_to_gpa;
context->prefetch_page = paging64_prefetch_page;
+ context->sync_page = paging64_sync_page;
+ context->invlpg = paging64_invlpg;
context->free = paging_free;
context->root_level = level;
context->shadow_root_level = level;
context->gva_to_gpa = paging32_gva_to_gpa;
context->free = paging_free;
context->prefetch_page = paging32_prefetch_page;
+ context->sync_page = paging32_sync_page;
+ context->invlpg = paging32_invlpg;
context->root_level = PT32_ROOT_LEVEL;
context->shadow_root_level = PT32E_ROOT_LEVEL;
context->root_hpa = INVALID_PAGE;
return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL);
}
-static int init_kvm_mmu(struct kvm_vcpu *vcpu)
+static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
+{
+ struct kvm_mmu *context = &vcpu->arch.mmu;
+
+ context->new_cr3 = nonpaging_new_cr3;
+ context->page_fault = tdp_page_fault;
+ context->free = nonpaging_free;
+ context->prefetch_page = nonpaging_prefetch_page;
+ context->sync_page = nonpaging_sync_page;
+ context->invlpg = nonpaging_invlpg;
+ context->shadow_root_level = kvm_x86_ops->get_tdp_level();
+ context->root_hpa = INVALID_PAGE;
+
+ if (!is_paging(vcpu)) {
+ context->gva_to_gpa = nonpaging_gva_to_gpa;
+ context->root_level = 0;
+ } else if (is_long_mode(vcpu)) {
+ context->gva_to_gpa = paging64_gva_to_gpa;
+ context->root_level = PT64_ROOT_LEVEL;
+ } else if (is_pae(vcpu)) {
+ context->gva_to_gpa = paging64_gva_to_gpa;
+ context->root_level = PT32E_ROOT_LEVEL;
+ } else {
+ context->gva_to_gpa = paging32_gva_to_gpa;
+ context->root_level = PT32_ROOT_LEVEL;
+ }
+
+ return 0;
+}
+
+static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
{
+ int r;
+
ASSERT(vcpu);
ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
if (!is_paging(vcpu))
- return nonpaging_init_context(vcpu);
+ r = nonpaging_init_context(vcpu);
else if (is_long_mode(vcpu))
- return paging64_init_context(vcpu);
+ r = paging64_init_context(vcpu);
else if (is_pae(vcpu))
- return paging32E_init_context(vcpu);
+ r = paging32E_init_context(vcpu);
+ else
+ r = paging32_init_context(vcpu);
+
+ vcpu->arch.mmu.base_role.glevels = vcpu->arch.mmu.root_level;
+
+ return r;
+}
+
+static int init_kvm_mmu(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.update_pte.pfn = bad_pfn;
+
+ if (tdp_enabled)
+ return init_kvm_tdp_mmu(vcpu);
else
- return paging32_init_context(vcpu);
+ return init_kvm_softmmu(vcpu);
}
static void destroy_kvm_mmu(struct kvm_vcpu *vcpu)
spin_lock(&vcpu->kvm->mmu_lock);
kvm_mmu_free_some_pages(vcpu);
mmu_alloc_roots(vcpu);
+ mmu_sync_roots(vcpu);
spin_unlock(&vcpu->kvm->mmu_lock);
kvm_x86_ops->set_cr3(vcpu, vcpu->arch.mmu.root_hpa);
kvm_mmu_flush_tlb(vcpu);
pte = *spte;
if (is_shadow_present_pte(pte)) {
- if (sp->role.level == PT_PAGE_TABLE_LEVEL)
+ if (sp->role.level == PT_PAGE_TABLE_LEVEL ||
+ is_large_pte(pte))
rmap_remove(vcpu->kvm, spte);
else {
child = page_header(pte & PT64_BASE_ADDR_MASK);
}
}
set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+ if (is_large_pte(pte))
+ --vcpu->kvm->stat.lpages;
}
static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
const void *new)
{
if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
- ++vcpu->kvm->stat.mmu_pde_zapped;
- return;
- }
+ if (!vcpu->arch.update_pte.largepage ||
+ sp->role.glevels == PT32_ROOT_LEVEL) {
+ ++vcpu->kvm->stat.mmu_pde_zapped;
+ return;
+ }
+ }
++vcpu->kvm->stat.mmu_pte_updated;
if (sp->role.glevels == PT32_ROOT_LEVEL)
{
u64 *spte = vcpu->arch.last_pte_updated;
- return !!(spte && (*spte & PT_ACCESSED_MASK));
+ return !!(spte && (*spte & shadow_accessed_mask));
}
static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
gfn_t gfn;
int r;
u64 gpte = 0;
- struct page *page;
+ pfn_t pfn;
+
+ vcpu->arch.update_pte.largepage = 0;
if (bytes != 4 && bytes != 8)
return;
return;
gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
- down_read(&vcpu->kvm->slots_lock);
- page = gfn_to_page(vcpu->kvm, gfn);
- up_read(&vcpu->kvm->slots_lock);
+ 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);
- if (is_error_page(page)) {
- kvm_release_page_clean(page);
+ if (is_error_pfn(pfn)) {
+ kvm_release_pfn_clean(pfn);
return;
}
vcpu->arch.update_pte.gfn = gfn;
- vcpu->arch.update_pte.page = page;
+ vcpu->arch.update_pte.pfn = pfn;
+}
+
+static void kvm_mmu_access_page(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ u64 *spte = vcpu->arch.last_pte_updated;
+
+ if (spte
+ && vcpu->arch.last_pte_gfn == gfn
+ && shadow_accessed_mask
+ && !(*spte & shadow_accessed_mask)
+ && is_shadow_present_pte(*spte))
+ set_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte);
}
void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
- const u8 *new, int bytes)
+ const u8 *new, int bytes,
+ bool guest_initiated)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
struct kvm_mmu_page *sp;
int npte;
int r;
- pgprintk("%s: gpa %llx bytes %d\n", __FUNCTION__, gpa, bytes);
+ pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes);
spin_lock(&vcpu->kvm->mmu_lock);
+ kvm_mmu_access_page(vcpu, gfn);
kvm_mmu_free_some_pages(vcpu);
++vcpu->kvm->stat.mmu_pte_write;
kvm_mmu_audit(vcpu, "pre pte write");
- if (gfn == vcpu->arch.last_pt_write_gfn
- && !last_updated_pte_accessed(vcpu)) {
- ++vcpu->arch.last_pt_write_count;
- if (vcpu->arch.last_pt_write_count >= 3)
- flooded = 1;
- } else {
- vcpu->arch.last_pt_write_gfn = gfn;
- vcpu->arch.last_pt_write_count = 1;
- vcpu->arch.last_pte_updated = NULL;
+ if (guest_initiated) {
+ if (gfn == vcpu->arch.last_pt_write_gfn
+ && !last_updated_pte_accessed(vcpu)) {
+ ++vcpu->arch.last_pt_write_count;
+ if (vcpu->arch.last_pt_write_count >= 3)
+ flooded = 1;
+ } else {
+ vcpu->arch.last_pt_write_gfn = gfn;
+ vcpu->arch.last_pt_write_count = 1;
+ vcpu->arch.last_pte_updated = NULL;
+ }
}
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)
+ if (sp->gfn != gfn || sp->role.metaphysical || sp->role.invalid)
continue;
pte_size = sp->role.glevels == PT32_ROOT_LEVEL ? 4 : 8;
misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1);
*/
pgprintk("misaligned: gpa %llx bytes %d role %x\n",
gpa, bytes, sp->role.word);
- kvm_mmu_zap_page(vcpu->kvm, sp);
+ if (kvm_mmu_zap_page(vcpu->kvm, sp))
+ n = bucket->first;
++vcpu->kvm->stat.mmu_flooded;
continue;
}
}
kvm_mmu_audit(vcpu, "post pte write");
spin_unlock(&vcpu->kvm->mmu_lock);
- if (vcpu->arch.update_pte.page) {
- kvm_release_page_clean(vcpu->arch.update_pte.page);
- vcpu->arch.update_pte.page = NULL;
+ if (!is_error_pfn(vcpu->arch.update_pte.pfn)) {
+ kvm_release_pfn_clean(vcpu->arch.update_pte.pfn);
+ vcpu->arch.update_pte.pfn = bad_pfn;
}
}
gpa_t gpa;
int r;
- down_read(&vcpu->kvm->slots_lock);
gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva);
- up_read(&vcpu->kvm->slots_lock);
spin_lock(&vcpu->kvm->mmu_lock);
r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
spin_unlock(&vcpu->kvm->mmu_lock);
return r;
}
+EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt);
void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
{
}
EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
+void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
+{
+ vcpu->arch.mmu.invlpg(vcpu, gva);
+ kvm_mmu_flush_tlb(vcpu);
+ ++vcpu->stat.invlpg;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);
+
void kvm_enable_tdp(void)
{
tdp_enabled = true;
}
EXPORT_SYMBOL_GPL(kvm_enable_tdp);
+void kvm_disable_tdp(void)
+{
+ tdp_enabled = false;
+}
+EXPORT_SYMBOL_GPL(kvm_disable_tdp);
+
static void free_mmu_pages(struct kvm_vcpu *vcpu)
{
struct kvm_mmu_page *sp;
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;
- if (!test_bit(slot, &sp->slot_bitmap))
+ if (!test_bit(slot, sp->slot_bitmap))
continue;
pt = sp->spt;
if (pt[i] & PT_WRITABLE_MASK)
pt[i] &= ~PT_WRITABLE_MASK;
}
+ kvm_flush_remote_tlbs(kvm);
+ spin_unlock(&kvm->mmu_lock);
}
void kvm_mmu_zap_all(struct kvm *kvm)
spin_lock(&kvm->mmu_lock);
list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link)
- kvm_mmu_zap_page(kvm, sp);
+ if (kvm_mmu_zap_page(kvm, sp))
+ node = container_of(kvm->arch.active_mmu_pages.next,
+ struct kvm_mmu_page, link);
spin_unlock(&kvm->mmu_lock);
kvm_flush_remote_tlbs(kvm);
}
-void kvm_mmu_module_exit(void)
+static void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm)
+{
+ 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);
+}
+
+static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
+{
+ struct kvm *kvm;
+ struct kvm *kvm_freed = NULL;
+ int cache_count = 0;
+
+ spin_lock(&kvm_lock);
+
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ int npages;
+
+ if (!down_read_trylock(&kvm->slots_lock))
+ continue;
+ spin_lock(&kvm->mmu_lock);
+ npages = kvm->arch.n_alloc_mmu_pages -
+ kvm->arch.n_free_mmu_pages;
+ cache_count += npages;
+ if (!kvm_freed && nr_to_scan > 0 && npages > 0) {
+ kvm_mmu_remove_one_alloc_mmu_page(kvm);
+ cache_count--;
+ kvm_freed = kvm;
+ }
+ nr_to_scan--;
+
+ spin_unlock(&kvm->mmu_lock);
+ up_read(&kvm->slots_lock);
+ }
+ if (kvm_freed)
+ list_move_tail(&kvm_freed->vm_list, &vm_list);
+
+ spin_unlock(&kvm_lock);
+
+ return cache_count;
+}
+
+static struct shrinker mmu_shrinker = {
+ .shrink = mmu_shrink,
+ .seeks = DEFAULT_SEEKS * 10,
+};
+
+static void mmu_destroy_caches(void)
{
if (pte_chain_cache)
kmem_cache_destroy(pte_chain_cache);
kmem_cache_destroy(mmu_page_header_cache);
}
+void kvm_mmu_module_exit(void)
+{
+ mmu_destroy_caches();
+ unregister_shrinker(&mmu_shrinker);
+}
+
int kvm_mmu_module_init(void)
{
pte_chain_cache = kmem_cache_create("kvm_pte_chain",
if (!mmu_page_header_cache)
goto nomem;
+ register_shrinker(&mmu_shrinker);
+
return 0;
nomem:
- kvm_mmu_module_exit();
+ mmu_destroy_caches();
return -ENOMEM;
}
return nr_mmu_pages;
}
+static void *pv_mmu_peek_buffer(struct kvm_pv_mmu_op_buffer *buffer,
+ unsigned len)
+{
+ if (len > buffer->len)
+ return NULL;
+ return buffer->ptr;
+}
+
+static void *pv_mmu_read_buffer(struct kvm_pv_mmu_op_buffer *buffer,
+ unsigned len)
+{
+ void *ret;
+
+ ret = pv_mmu_peek_buffer(buffer, len);
+ if (!ret)
+ return ret;
+ buffer->ptr += len;
+ buffer->len -= len;
+ buffer->processed += len;
+ return ret;
+}
+
+static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu,
+ gpa_t addr, gpa_t value)
+{
+ int bytes = 8;
+ int r;
+
+ if (!is_long_mode(vcpu) && !is_pae(vcpu))
+ bytes = 4;
+
+ r = mmu_topup_memory_caches(vcpu);
+ if (r)
+ return r;
+
+ if (!emulator_write_phys(vcpu, addr, &value, bytes))
+ return -EFAULT;
+
+ return 1;
+}
+
+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);
+ return 1;
+}
+
+static int kvm_pv_mmu_release_pt(struct kvm_vcpu *vcpu, gpa_t addr)
+{
+ spin_lock(&vcpu->kvm->mmu_lock);
+ mmu_unshadow(vcpu->kvm, addr >> PAGE_SHIFT);
+ spin_unlock(&vcpu->kvm->mmu_lock);
+ return 1;
+}
+
+static int kvm_pv_mmu_op_one(struct kvm_vcpu *vcpu,
+ struct kvm_pv_mmu_op_buffer *buffer)
+{
+ struct kvm_mmu_op_header *header;
+
+ header = pv_mmu_peek_buffer(buffer, sizeof *header);
+ if (!header)
+ return 0;
+ switch (header->op) {
+ case KVM_MMU_OP_WRITE_PTE: {
+ struct kvm_mmu_op_write_pte *wpte;
+
+ wpte = pv_mmu_read_buffer(buffer, sizeof *wpte);
+ if (!wpte)
+ return 0;
+ return kvm_pv_mmu_write(vcpu, wpte->pte_phys,
+ wpte->pte_val);
+ }
+ case KVM_MMU_OP_FLUSH_TLB: {
+ struct kvm_mmu_op_flush_tlb *ftlb;
+
+ ftlb = pv_mmu_read_buffer(buffer, sizeof *ftlb);
+ if (!ftlb)
+ return 0;
+ return kvm_pv_mmu_flush_tlb(vcpu);
+ }
+ case KVM_MMU_OP_RELEASE_PT: {
+ struct kvm_mmu_op_release_pt *rpt;
+
+ rpt = pv_mmu_read_buffer(buffer, sizeof *rpt);
+ if (!rpt)
+ return 0;
+ return kvm_pv_mmu_release_pt(vcpu, rpt->pt_phys);
+ }
+ default: return 0;
+ }
+}
+
+int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
+ gpa_t addr, unsigned long *ret)
+{
+ int r;
+ struct kvm_pv_mmu_op_buffer *buffer = &vcpu->arch.mmu_op_buffer;
+
+ buffer->ptr = buffer->buf;
+ buffer->len = min_t(unsigned long, bytes, sizeof buffer->buf);
+ buffer->processed = 0;
+
+ r = kvm_read_guest(vcpu->kvm, addr, buffer->buf, buffer->len);
+ if (r)
+ goto out;
+
+ while (buffer->len) {
+ r = kvm_pv_mmu_op_one(vcpu, buffer);
+ if (r < 0)
+ goto out;
+ if (r == 0)
+ break;
+ }
+
+ r = 1;
+out:
+ *ret = buffer->processed;
+ return r;
+}
+
#ifdef AUDIT
static const char *audit_msg;
audit_mappings_page(vcpu, ent, va, level - 1);
} else {
gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, va);
- struct page *page = gpa_to_page(vcpu, gpa);
- hpa_t hpa = page_to_phys(page);
+ hpa_t hpa = (hpa_t)gpa_to_pfn(vcpu, gpa) << PAGE_SHIFT;
if (is_shadow_present_pte(ent)
&& (ent & PT64_BASE_ADDR_MASK) != hpa)
&& !is_error_hpa(hpa))
printk(KERN_ERR "audit: (%s) notrap shadow,"
" valid guest gva %lx\n", audit_msg, va);
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
}
}
if (n_rmap != n_actual)
printk(KERN_ERR "%s: (%s) rmap %d actual %d\n",
- __FUNCTION__, audit_msg, n_rmap, n_actual);
+ __func__, audit_msg, n_rmap, n_actual);
}
static void audit_write_protection(struct kvm_vcpu *vcpu)
if (sp->role.metaphysical)
continue;
- slot = gfn_to_memslot(vcpu->kvm, sp->gfn);
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",
- __FUNCTION__, audit_msg, sp->gfn,
+ __func__, audit_msg, sp->gfn,
sp->role.word);
}
}