#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \
| PT64_NX_MASK)
-#define RMAP_EXT 4
+#define PTE_LIST_EXT 4
#define ACC_EXEC_MASK 1
#define ACC_WRITE_MASK PT_WRITABLE_MASK
#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
-struct kvm_rmap_desc {
- u64 *sptes[RMAP_EXT];
- struct kvm_rmap_desc *more;
+struct pte_list_desc {
+ u64 *sptes[PTE_LIST_EXT];
+ struct pte_list_desc *more;
};
struct kvm_shadow_walk_iterator {
shadow_walk_okay(&(_walker)); \
shadow_walk_next(&(_walker)))
-typedef void (*mmu_parent_walk_fn) (struct kvm_mmu_page *sp, u64 *spte);
-
-static struct kmem_cache *pte_chain_cache;
-static struct kmem_cache *rmap_desc_cache;
+static struct kmem_cache *pte_list_desc_cache;
static struct kmem_cache *mmu_page_header_cache;
static struct percpu_counter kvm_total_used_mmu_pages;
-static u64 __read_mostly shadow_trap_nonpresent_pte;
-static u64 __read_mostly shadow_notrap_nonpresent_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;
return ((1ULL << (e - s + 1)) - 1) << s;
}
-void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte)
-{
- shadow_trap_nonpresent_pte = trap_pte;
- shadow_notrap_nonpresent_pte = notrap_pte;
-}
-EXPORT_SYMBOL_GPL(kvm_mmu_set_nonpresent_ptes);
-
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
u64 dirty_mask, u64 nx_mask, u64 x_mask)
{
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
-static bool is_write_protection(struct kvm_vcpu *vcpu)
-{
- return kvm_read_cr0_bits(vcpu, X86_CR0_WP);
-}
-
static int is_cpuid_PSE36(void)
{
return 1;
static int is_shadow_present_pte(u64 pte)
{
- return pte != shadow_trap_nonpresent_pte
- && pte != shadow_notrap_nonpresent_pte;
+ return pte & PT_PRESENT_MASK;
}
static int is_large_pte(u64 pte)
return pte & PT_PAGE_SIZE_MASK;
}
-static int is_writable_pte(unsigned long pte)
-{
- return pte & PT_WRITABLE_MASK;
-}
-
static int is_dirty_gpte(unsigned long pte)
{
return pte & PT_DIRTY_MASK;
{
int r;
- r = mmu_topup_memory_cache(&vcpu->arch.mmu_pte_chain_cache,
- pte_chain_cache, 4);
- if (r)
- goto out;
- r = mmu_topup_memory_cache(&vcpu->arch.mmu_rmap_desc_cache,
- rmap_desc_cache, 4 + PTE_PREFETCH_NUM);
+ r = mmu_topup_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache,
+ pte_list_desc_cache, 8 + PTE_PREFETCH_NUM);
if (r)
goto out;
r = mmu_topup_memory_cache_page(&vcpu->arch.mmu_page_cache, 8);
static void mmu_free_memory_caches(struct kvm_vcpu *vcpu)
{
- mmu_free_memory_cache(&vcpu->arch.mmu_pte_chain_cache, pte_chain_cache);
- mmu_free_memory_cache(&vcpu->arch.mmu_rmap_desc_cache, rmap_desc_cache);
+ mmu_free_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache,
+ pte_list_desc_cache);
mmu_free_memory_cache_page(&vcpu->arch.mmu_page_cache);
mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache,
mmu_page_header_cache);
return p;
}
-static struct kvm_pte_chain *mmu_alloc_pte_chain(struct kvm_vcpu *vcpu)
-{
- return mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_chain_cache,
- sizeof(struct kvm_pte_chain));
-}
-
-static void mmu_free_pte_chain(struct kvm_pte_chain *pc)
+static struct pte_list_desc *mmu_alloc_pte_list_desc(struct kvm_vcpu *vcpu)
{
- kmem_cache_free(pte_chain_cache, pc);
+ return mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_list_desc_cache,
+ sizeof(struct pte_list_desc));
}
-static struct kvm_rmap_desc *mmu_alloc_rmap_desc(struct kvm_vcpu *vcpu)
+static void mmu_free_pte_list_desc(struct pte_list_desc *pte_list_desc)
{
- return mmu_memory_cache_alloc(&vcpu->arch.mmu_rmap_desc_cache,
- sizeof(struct kvm_rmap_desc));
-}
-
-static void mmu_free_rmap_desc(struct kvm_rmap_desc *rd)
-{
- kmem_cache_free(rmap_desc_cache, rd);
+ kmem_cache_free(pte_list_desc_cache, pte_list_desc);
}
static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index)
linfo = lpage_info_slot(gfn, slot, i);
linfo->write_count += 1;
}
+ kvm->arch.indirect_shadow_pages++;
}
static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
linfo->write_count -= 1;
WARN_ON(linfo->write_count < 0);
}
+ kvm->arch.indirect_shadow_pages--;
}
static int has_wrprotected_page(struct kvm *kvm,
static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn)
{
- return gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true);
+ return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true);
}
static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
}
/*
- * Take gfn and return the reverse mapping to it.
- */
-
-static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level)
-{
- struct kvm_memory_slot *slot;
- struct kvm_lpage_info *linfo;
-
- slot = gfn_to_memslot(kvm, gfn);
- if (likely(level == PT_PAGE_TABLE_LEVEL))
- return &slot->rmap[gfn - slot->base_gfn];
-
- linfo = lpage_info_slot(gfn, slot, level);
-
- return &linfo->rmap_pde;
-}
-
-/*
- * Reverse mapping data structures:
+ * Pte mapping structures:
*
- * If rmapp bit zero is zero, then rmapp point to the shadw page table entry
- * that points to page_address(page).
+ * If pte_list bit zero is zero, then pte_list point to the spte.
*
- * If rmapp bit zero is one, (then rmap & ~1) points to a struct kvm_rmap_desc
- * containing more mappings.
+ * If pte_list bit zero is one, (then pte_list & ~1) points to a struct
+ * pte_list_desc containing more mappings.
*
- * Returns the number of rmap entries before the spte was added or zero if
+ * Returns the number of pte entries before the spte was added or zero if
* the spte was not added.
*
*/
-static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
+static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte,
+ unsigned long *pte_list)
{
- struct kvm_mmu_page *sp;
- struct kvm_rmap_desc *desc;
- unsigned long *rmapp;
+ struct pte_list_desc *desc;
int i, count = 0;
- if (!is_rmap_spte(*spte))
- return count;
- sp = page_header(__pa(spte));
- kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn);
- 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;
- } else if (!(*rmapp & 1)) {
- rmap_printk("rmap_add: %p %llx 1->many\n", spte, *spte);
- desc = mmu_alloc_rmap_desc(vcpu);
- desc->sptes[0] = (u64 *)*rmapp;
+ if (!*pte_list) {
+ rmap_printk("pte_list_add: %p %llx 0->1\n", spte, *spte);
+ *pte_list = (unsigned long)spte;
+ } else if (!(*pte_list & 1)) {
+ rmap_printk("pte_list_add: %p %llx 1->many\n", spte, *spte);
+ desc = mmu_alloc_pte_list_desc(vcpu);
+ desc->sptes[0] = (u64 *)*pte_list;
desc->sptes[1] = spte;
- *rmapp = (unsigned long)desc | 1;
+ *pte_list = (unsigned long)desc | 1;
++count;
} else {
- rmap_printk("rmap_add: %p %llx many->many\n", spte, *spte);
- desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
- while (desc->sptes[RMAP_EXT-1] && desc->more) {
+ rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte);
+ desc = (struct pte_list_desc *)(*pte_list & ~1ul);
+ while (desc->sptes[PTE_LIST_EXT-1] && desc->more) {
desc = desc->more;
- count += RMAP_EXT;
+ count += PTE_LIST_EXT;
}
- if (desc->sptes[RMAP_EXT-1]) {
- desc->more = mmu_alloc_rmap_desc(vcpu);
+ if (desc->sptes[PTE_LIST_EXT-1]) {
+ desc->more = mmu_alloc_pte_list_desc(vcpu);
desc = desc->more;
}
for (i = 0; desc->sptes[i]; ++i)
return count;
}
-static void rmap_desc_remove_entry(unsigned long *rmapp,
- struct kvm_rmap_desc *desc,
- int i,
- struct kvm_rmap_desc *prev_desc)
+static u64 *pte_list_next(unsigned long *pte_list, u64 *spte)
+{
+ struct pte_list_desc *desc;
+ u64 *prev_spte;
+ int i;
+
+ if (!*pte_list)
+ return NULL;
+ else if (!(*pte_list & 1)) {
+ if (!spte)
+ return (u64 *)*pte_list;
+ return NULL;
+ }
+ desc = (struct pte_list_desc *)(*pte_list & ~1ul);
+ prev_spte = NULL;
+ while (desc) {
+ for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) {
+ if (prev_spte == spte)
+ return desc->sptes[i];
+ prev_spte = desc->sptes[i];
+ }
+ desc = desc->more;
+ }
+ return NULL;
+}
+
+static void
+pte_list_desc_remove_entry(unsigned long *pte_list, struct pte_list_desc *desc,
+ int i, struct pte_list_desc *prev_desc)
{
int j;
- for (j = RMAP_EXT - 1; !desc->sptes[j] && j > i; --j)
+ for (j = PTE_LIST_EXT - 1; !desc->sptes[j] && j > i; --j)
;
desc->sptes[i] = desc->sptes[j];
desc->sptes[j] = NULL;
if (j != 0)
return;
if (!prev_desc && !desc->more)
- *rmapp = (unsigned long)desc->sptes[0];
+ *pte_list = (unsigned long)desc->sptes[0];
else
if (prev_desc)
prev_desc->more = desc->more;
else
- *rmapp = (unsigned long)desc->more | 1;
- mmu_free_rmap_desc(desc);
+ *pte_list = (unsigned long)desc->more | 1;
+ mmu_free_pte_list_desc(desc);
}
-static void rmap_remove(struct kvm *kvm, u64 *spte)
+static void pte_list_remove(u64 *spte, unsigned long *pte_list)
{
- struct kvm_rmap_desc *desc;
- struct kvm_rmap_desc *prev_desc;
- struct kvm_mmu_page *sp;
- gfn_t gfn;
- unsigned long *rmapp;
+ struct pte_list_desc *desc;
+ struct pte_list_desc *prev_desc;
int i;
- sp = page_header(__pa(spte));
- gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt);
- rmapp = gfn_to_rmap(kvm, gfn, sp->role.level);
- if (!*rmapp) {
- printk(KERN_ERR "rmap_remove: %p 0->BUG\n", spte);
+ if (!*pte_list) {
+ printk(KERN_ERR "pte_list_remove: %p 0->BUG\n", spte);
BUG();
- } else if (!(*rmapp & 1)) {
- rmap_printk("rmap_remove: %p 1->0\n", spte);
- if ((u64 *)*rmapp != spte) {
- printk(KERN_ERR "rmap_remove: %p 1->BUG\n", spte);
+ } else if (!(*pte_list & 1)) {
+ rmap_printk("pte_list_remove: %p 1->0\n", spte);
+ if ((u64 *)*pte_list != spte) {
+ printk(KERN_ERR "pte_list_remove: %p 1->BUG\n", spte);
BUG();
}
- *rmapp = 0;
+ *pte_list = 0;
} else {
- rmap_printk("rmap_remove: %p many->many\n", spte);
- desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
+ rmap_printk("pte_list_remove: %p many->many\n", spte);
+ desc = (struct pte_list_desc *)(*pte_list & ~1ul);
prev_desc = NULL;
while (desc) {
- for (i = 0; i < RMAP_EXT && desc->sptes[i]; ++i)
+ for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i)
if (desc->sptes[i] == spte) {
- rmap_desc_remove_entry(rmapp,
+ pte_list_desc_remove_entry(pte_list,
desc, i,
prev_desc);
return;
prev_desc = desc;
desc = desc->more;
}
- pr_err("rmap_remove: %p many->many\n", spte);
+ pr_err("pte_list_remove: %p many->many\n", spte);
BUG();
}
}
+typedef void (*pte_list_walk_fn) (u64 *spte);
+static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn)
+{
+ struct pte_list_desc *desc;
+ int i;
+
+ if (!*pte_list)
+ return;
+
+ if (!(*pte_list & 1))
+ return fn((u64 *)*pte_list);
+
+ desc = (struct pte_list_desc *)(*pte_list & ~1ul);
+ while (desc) {
+ for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i)
+ fn(desc->sptes[i]);
+ desc = desc->more;
+ }
+}
+
+/*
+ * Take gfn and return the reverse mapping to it.
+ */
+static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level)
+{
+ struct kvm_memory_slot *slot;
+ struct kvm_lpage_info *linfo;
+
+ slot = gfn_to_memslot(kvm, gfn);
+ if (likely(level == PT_PAGE_TABLE_LEVEL))
+ return &slot->rmap[gfn - slot->base_gfn];
+
+ linfo = lpage_info_slot(gfn, slot, level);
+
+ return &linfo->rmap_pde;
+}
+
+static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
+{
+ struct kvm_mmu_page *sp;
+ unsigned long *rmapp;
+
+ sp = page_header(__pa(spte));
+ kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn);
+ rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
+ return pte_list_add(vcpu, spte, rmapp);
+}
+
+static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte)
+{
+ return pte_list_next(rmapp, spte);
+}
+
+static void rmap_remove(struct kvm *kvm, u64 *spte)
+{
+ struct kvm_mmu_page *sp;
+ gfn_t gfn;
+ unsigned long *rmapp;
+
+ sp = page_header(__pa(spte));
+ gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt);
+ rmapp = gfn_to_rmap(kvm, gfn, sp->role.level);
+ pte_list_remove(spte, rmapp);
+}
+
static int set_spte_track_bits(u64 *sptep, u64 new_spte)
{
pfn_t pfn;
return 1;
}
-static void drop_spte(struct kvm *kvm, u64 *sptep, u64 new_spte)
+static void drop_spte(struct kvm *kvm, u64 *sptep)
{
- if (set_spte_track_bits(sptep, new_spte))
+ if (set_spte_track_bits(sptep, 0ull))
rmap_remove(kvm, sptep);
}
-static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte)
-{
- struct kvm_rmap_desc *desc;
- u64 *prev_spte;
- int i;
-
- if (!*rmapp)
- return NULL;
- else if (!(*rmapp & 1)) {
- if (!spte)
- return (u64 *)*rmapp;
- return NULL;
- }
- desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
- prev_spte = NULL;
- while (desc) {
- for (i = 0; i < RMAP_EXT && desc->sptes[i]; ++i) {
- if (prev_spte == spte)
- return desc->sptes[i];
- prev_spte = desc->sptes[i];
- }
- desc = desc->more;
- }
- return NULL;
-}
-
static int rmap_write_protect(struct kvm *kvm, u64 gfn)
{
unsigned long *rmapp;
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)) {
- drop_spte(kvm, spte,
- shadow_trap_nonpresent_pte);
+ drop_spte(kvm, spte);
--kvm->stat.lpages;
spte = NULL;
write_protected = 1;
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);
- drop_spte(kvm, spte, shadow_trap_nonpresent_pte);
+ drop_spte(kvm, spte);
need_tlb_flush = 1;
}
return need_tlb_flush;
rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", spte, *spte);
need_flush = 1;
if (pte_write(*ptep)) {
- drop_spte(kvm, spte, shadow_trap_nonpresent_pte);
+ drop_spte(kvm, spte);
spte = rmap_next(kvm, rmapp, NULL);
} else {
new_spte = *spte &~ (PT64_BASE_ADDR_MASK);
percpu_counter_add(&kvm_total_used_mmu_pages, nr);
}
-static void kvm_mmu_free_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+/*
+ * Remove the sp from shadow page cache, after call it,
+ * we can not find this sp from the cache, and the shadow
+ * page table is still valid.
+ * It should be under the protection of mmu lock.
+ */
+static void kvm_mmu_isolate_page(struct kvm_mmu_page *sp)
{
ASSERT(is_empty_shadow_page(sp->spt));
hlist_del(&sp->hash_link);
- list_del(&sp->link);
- free_page((unsigned long)sp->spt);
if (!sp->role.direct)
free_page((unsigned long)sp->gfns);
- kmem_cache_free(mmu_page_header_cache, sp);
- kvm_mod_used_mmu_pages(kvm, -1);
}
-static unsigned kvm_page_table_hashfn(gfn_t gfn)
+/*
+ * Free the shadow page table and the sp, we can do it
+ * out of the protection of mmu lock.
+ */
+static void kvm_mmu_free_page(struct kvm_mmu_page *sp)
{
- return gfn & ((1 << KVM_MMU_HASH_SHIFT) - 1);
+ list_del(&sp->link);
+ free_page((unsigned long)sp->spt);
+ kmem_cache_free(mmu_page_header_cache, sp);
}
-static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
- u64 *parent_pte, int direct)
+static unsigned kvm_page_table_hashfn(gfn_t gfn)
{
- struct kvm_mmu_page *sp;
-
- sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache, sizeof *sp);
- sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE);
- if (!direct)
- 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);
- bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
- sp->multimapped = 0;
- sp->parent_pte = parent_pte;
- kvm_mod_used_mmu_pages(vcpu->kvm, +1);
- return sp;
+ return gfn & ((1 << KVM_MMU_HASH_SHIFT) - 1);
}
static void mmu_page_add_parent_pte(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp, u64 *parent_pte)
{
- struct kvm_pte_chain *pte_chain;
- struct hlist_node *node;
- int i;
-
if (!parent_pte)
return;
- if (!sp->multimapped) {
- u64 *old = sp->parent_pte;
- if (!old) {
- sp->parent_pte = parent_pte;
- return;
- }
- sp->multimapped = 1;
- pte_chain = mmu_alloc_pte_chain(vcpu);
- INIT_HLIST_HEAD(&sp->parent_ptes);
- hlist_add_head(&pte_chain->link, &sp->parent_ptes);
- pte_chain->parent_ptes[0] = old;
- }
- hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link) {
- if (pte_chain->parent_ptes[NR_PTE_CHAIN_ENTRIES-1])
- continue;
- for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i)
- if (!pte_chain->parent_ptes[i]) {
- pte_chain->parent_ptes[i] = parent_pte;
- return;
- }
- }
- pte_chain = mmu_alloc_pte_chain(vcpu);
- BUG_ON(!pte_chain);
- hlist_add_head(&pte_chain->link, &sp->parent_ptes);
- pte_chain->parent_ptes[0] = parent_pte;
+ pte_list_add(vcpu, parent_pte, &sp->parent_ptes);
}
static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
u64 *parent_pte)
{
- struct kvm_pte_chain *pte_chain;
- struct hlist_node *node;
- int i;
-
- if (!sp->multimapped) {
- BUG_ON(sp->parent_pte != parent_pte);
- sp->parent_pte = NULL;
- 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;
- if (pte_chain->parent_ptes[i] != parent_pte)
- continue;
- while (i + 1 < NR_PTE_CHAIN_ENTRIES
- && pte_chain->parent_ptes[i + 1]) {
- pte_chain->parent_ptes[i]
- = pte_chain->parent_ptes[i + 1];
- ++i;
- }
- pte_chain->parent_ptes[i] = NULL;
- if (i == 0) {
- hlist_del(&pte_chain->link);
- mmu_free_pte_chain(pte_chain);
- if (hlist_empty(&sp->parent_ptes)) {
- sp->multimapped = 0;
- sp->parent_pte = NULL;
- }
- }
- return;
- }
- BUG();
+ pte_list_remove(parent_pte, &sp->parent_ptes);
}
-static void mmu_parent_walk(struct kvm_mmu_page *sp, mmu_parent_walk_fn fn)
+static void drop_parent_pte(struct kvm_mmu_page *sp,
+ u64 *parent_pte)
{
- 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(parent_sp, sp->parent_pte);
- return;
- }
-
- hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link)
- for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) {
- u64 *spte = pte_chain->parent_ptes[i];
+ mmu_page_remove_parent_pte(sp, parent_pte);
+ __set_spte(parent_pte, 0ull);
+}
- if (!spte)
- break;
- parent_sp = page_header(__pa(spte));
- fn(parent_sp, spte);
- }
+static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
+ u64 *parent_pte, int direct)
+{
+ struct kvm_mmu_page *sp;
+ sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache,
+ sizeof *sp);
+ sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE);
+ if (!direct)
+ 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);
+ bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
+ sp->parent_ptes = 0;
+ mmu_page_add_parent_pte(vcpu, sp, parent_pte);
+ kvm_mod_used_mmu_pages(vcpu->kvm, +1);
+ return sp;
}
-static void mark_unsync(struct kvm_mmu_page *sp, u64 *spte);
+static void mark_unsync(u64 *spte);
static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp)
{
- mmu_parent_walk(sp, mark_unsync);
+ pte_list_walk(&sp->parent_ptes, mark_unsync);
}
-static void mark_unsync(struct kvm_mmu_page *sp, u64 *spte)
+static void mark_unsync(u64 *spte)
{
+ struct kvm_mmu_page *sp;
unsigned int index;
+ sp = page_header(__pa(spte));
index = spte - sp->spt;
if (__test_and_set_bit(index, sp->unsync_child_bitmap))
return;
kvm_mmu_mark_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)
{
}
}
+static void init_shadow_page_table(struct kvm_mmu_page *sp)
+{
+ int i;
+
+ for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
+ sp->spt[i] = 0ull;
+}
+
static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
gfn_t gfn,
gva_t gaddr,
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);
+ init_shadow_page_table(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;
static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator)
{
+ if (is_last_spte(*iterator->sptep, iterator->level)) {
+ iterator->level = 0;
+ return;
+ }
+
iterator->shadow_addr = *iterator->sptep & PT64_BASE_ADDR_MASK;
--iterator->level;
}
static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
{
if (is_large_pte(*sptep)) {
- drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte);
+ drop_spte(vcpu->kvm, sptep);
kvm_flush_remote_tlbs(vcpu->kvm);
}
}
if (child->role.access == direct_access)
return;
- mmu_page_remove_parent_pte(child, sptep);
- __set_spte(sptep, shadow_trap_nonpresent_pte);
+ drop_parent_pte(child, sptep);
kvm_flush_remote_tlbs(vcpu->kvm);
}
}
+static void mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
+ u64 *spte)
+{
+ u64 pte;
+ struct kvm_mmu_page *child;
+
+ pte = *spte;
+ if (is_shadow_present_pte(pte)) {
+ if (is_last_spte(pte, sp->role.level))
+ drop_spte(kvm, spte);
+ else {
+ child = page_header(pte & PT64_BASE_ADDR_MASK);
+ drop_parent_pte(child, spte);
+ }
+ }
+
+ if (is_large_pte(pte))
+ --kvm->stat.lpages;
+}
+
static void kvm_mmu_page_unlink_children(struct kvm *kvm,
struct kvm_mmu_page *sp)
{
unsigned i;
- u64 *pt;
- u64 ent;
-
- pt = sp->spt;
-
- for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
- ent = pt[i];
-
- if (is_shadow_present_pte(ent)) {
- if (!is_last_spte(ent, sp->role.level)) {
- ent &= PT64_BASE_ADDR_MASK;
- mmu_page_remove_parent_pte(page_header(ent),
- &pt[i]);
- } else {
- if (is_large_pte(ent))
- --kvm->stat.lpages;
- drop_spte(kvm, &pt[i],
- shadow_trap_nonpresent_pte);
- }
- }
- pt[i] = shadow_trap_nonpresent_pte;
- }
+
+ for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
+ mmu_page_zap_pte(kvm, sp, sp->spt + i);
}
static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte)
{
u64 *parent_pte;
- while (sp->multimapped || sp->parent_pte) {
- if (!sp->multimapped)
- parent_pte = sp->parent_pte;
- else {
- struct kvm_pte_chain *chain;
-
- chain = container_of(sp->parent_ptes.first,
- struct kvm_pte_chain, link);
- parent_pte = chain->parent_ptes[0];
- }
- BUG_ON(!parent_pte);
- kvm_mmu_put_page(sp, parent_pte);
- __set_spte(parent_pte, shadow_trap_nonpresent_pte);
- }
+ while ((parent_pte = pte_list_next(&sp->parent_ptes, NULL)))
+ drop_parent_pte(sp, parent_pte);
}
static int mmu_zap_unsync_children(struct kvm *kvm,
/* Count self */
ret++;
list_move(&sp->link, invalid_list);
+ kvm_mod_used_mmu_pages(kvm, -1);
} else {
list_move(&sp->link, &kvm->arch.active_mmu_pages);
kvm_reload_remote_mmus(kvm);
do {
sp = list_first_entry(invalid_list, struct kvm_mmu_page, link);
WARN_ON(!sp->role.invalid || sp->root_count);
- kvm_mmu_free_page(kvm, sp);
+ kvm_mmu_isolate_page(sp);
+ kvm_mmu_free_page(sp);
} while (!list_empty(invalid_list));
}
page = container_of(kvm->arch.active_mmu_pages.prev,
struct kvm_mmu_page, link);
kvm_mmu_prepare_zap_page(kvm, page, &invalid_list);
- kvm_mmu_commit_zap_page(kvm, &invalid_list);
}
+ kvm_mmu_commit_zap_page(kvm, &invalid_list);
goal_nr_mmu_pages = kvm->arch.n_used_mmu_pages;
}
__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_spte(&pt[i], shadow_trap_nonpresent_pte);
- }
-}
-
/*
* The function is based on mtrr_type_lookup() in
* arch/x86/kernel/cpu/mtrr/generic.c
sp->unsync = 1;
kvm_mmu_mark_parents_unsync(sp);
- mmu_convert_notrap(sp);
}
static void kvm_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn)
static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
unsigned pte_access, int user_fault,
- int write_fault, int dirty, int level,
+ int write_fault, int level,
gfn_t gfn, pfn_t pfn, bool speculative,
bool can_unsync, bool host_writable)
{
spte = PT_PRESENT_MASK;
if (!speculative)
spte |= shadow_accessed_mask;
- if (!dirty)
- pte_access &= ~ACC_WRITE_MASK;
+
if (pte_access & ACC_EXEC_MASK)
spte |= shadow_x_mask;
else
if (level > PT_PAGE_TABLE_LEVEL &&
has_wrprotected_page(vcpu->kvm, gfn, level)) {
ret = 1;
- drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte);
+ drop_spte(vcpu->kvm, sptep);
goto done;
}
spte |= PT_WRITABLE_MASK;
if (!vcpu->arch.mmu.direct_map
- && !(pte_access & ACC_WRITE_MASK))
+ && !(pte_access & ACC_WRITE_MASK)) {
spte &= ~PT_USER_MASK;
+ /*
+ * If we converted a user page to a kernel page,
+ * so that the kernel can write to it when cr0.wp=0,
+ * then we should prevent the kernel from executing it
+ * if SMEP is enabled.
+ */
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))
+ spte |= PT64_NX_MASK;
+ }
/*
* Optimization: for pte sync, if spte was writable the hash
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 level, gfn_t gfn,
+ int user_fault, int write_fault,
+ int *emulate, int level, gfn_t gfn,
pfn_t pfn, bool speculative,
bool host_writable)
{
u64 pte = *sptep;
child = page_header(pte & PT64_BASE_ADDR_MASK);
- mmu_page_remove_parent_pte(child, sptep);
- __set_spte(sptep, shadow_trap_nonpresent_pte);
+ drop_parent_pte(child, sptep);
kvm_flush_remote_tlbs(vcpu->kvm);
} else if (pfn != spte_to_pfn(*sptep)) {
pgprintk("hfn old %llx new %llx\n",
spte_to_pfn(*sptep), pfn);
- drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte);
+ drop_spte(vcpu->kvm, sptep);
kvm_flush_remote_tlbs(vcpu->kvm);
} else
was_rmapped = 1;
}
if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault,
- dirty, level, gfn, pfn, speculative, true,
+ level, gfn, pfn, speculative, true,
host_writable)) {
if (write_fault)
- *ptwrite = 1;
+ *emulate = 1;
kvm_mmu_flush_tlb(vcpu);
}
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);
- if (rmap_count > RMAP_RECYCLE_THRESHOLD)
- rmap_recycle(vcpu, sptep, gfn);
+ if (is_shadow_present_pte(*sptep)) {
+ page_header_update_slot(vcpu->kvm, sptep, gfn);
+ if (!was_rmapped) {
+ rmap_count = rmap_add(vcpu, sptep, gfn);
+ if (rmap_count > RMAP_RECYCLE_THRESHOLD)
+ rmap_recycle(vcpu, sptep, gfn);
+ }
}
kvm_release_pfn_clean(pfn);
if (speculative) {
slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, no_dirty_log);
if (!slot) {
- get_page(bad_page);
- return page_to_pfn(bad_page);
+ get_page(fault_page);
+ return page_to_pfn(fault_page);
}
hva = gfn_to_hva_memslot(slot, gfn);
for (i = 0; i < ret; i++, gfn++, start++)
mmu_set_spte(vcpu, start, ACC_ALL,
- access, 0, 0, 1, NULL,
+ access, 0, 0, NULL,
sp->role.level, gfn,
page_to_pfn(pages[i]), true, true);
spte = sp->spt + i;
for (i = 0; i < PTE_PREFETCH_NUM; i++, spte++) {
- if (*spte != shadow_trap_nonpresent_pte || spte == sptep) {
+ if (is_shadow_present_pte(*spte) || spte == sptep) {
if (!start)
continue;
if (direct_pte_prefetch_many(vcpu, sp, start, spte) < 0)
{
struct kvm_shadow_walk_iterator iterator;
struct kvm_mmu_page *sp;
- int pt_write = 0;
+ int emulate = 0;
gfn_t pseudo_gfn;
for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
unsigned pte_access = ACC_ALL;
mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, pte_access,
- 0, write, 1, &pt_write,
+ 0, write, &emulate,
level, gfn, pfn, prefault, map_writable);
direct_pte_prefetch(vcpu, iterator.sptep);
++vcpu->stat.pf_fixed;
break;
}
- if (*iterator.sptep == shadow_trap_nonpresent_pte) {
+ if (!is_shadow_present_pte(*iterator.sptep)) {
u64 base_addr = iterator.addr;
base_addr &= PT64_LVL_ADDR_MASK(iterator.level);
| shadow_accessed_mask);
}
}
- return pt_write;
+ return emulate;
}
static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk)
send_sig_info(SIGBUS, &info, tsk);
}
-static int kvm_handle_bad_page(struct kvm *kvm, gfn_t gfn, pfn_t pfn)
+static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gva_t gva,
+ unsigned access, gfn_t gfn, pfn_t pfn)
{
kvm_release_pfn_clean(pfn);
if (is_hwpoison_pfn(pfn)) {
- kvm_send_hwpoison_signal(gfn_to_hva(kvm, gfn), current);
+ kvm_send_hwpoison_signal(gfn_to_hva(vcpu->kvm, gfn), current);
return 0;
} else if (is_fault_pfn(pfn))
return -EFAULT;
+ vcpu_cache_mmio_info(vcpu, gva, gfn, access);
return 1;
}
/* mmio */
if (is_error_pfn(pfn))
- return kvm_handle_bad_page(vcpu->kvm, gfn, pfn);
+ return kvm_handle_bad_page(vcpu, v, ACC_ALL, gfn, pfn);
spin_lock(&vcpu->kvm->mmu_lock);
if (mmu_notifier_retry(vcpu, mmu_seq))
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
return;
+ vcpu_clear_mmio_info(vcpu, ~0ul);
trace_kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) {
hpa_t root = vcpu->arch.mmu.root_hpa;
/* mmio */
if (is_error_pfn(pfn))
- return kvm_handle_bad_page(vcpu->kvm, gfn, pfn);
+ return kvm_handle_bad_page(vcpu, 0, 0, gfn, pfn);
spin_lock(&vcpu->kvm->mmu_lock);
if (mmu_notifier_retry(vcpu, mmu_seq))
goto out_unlock;
context->page_fault = nonpaging_page_fault;
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->update_pte = nonpaging_update_pte;
context->new_cr3 = paging_new_cr3;
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->update_pte = paging64_update_pte;
context->page_fault = paging32_page_fault;
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->update_pte = paging32_update_pte;
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->update_pte = nonpaging_update_pte;
int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
{
int r;
+ bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
ASSERT(vcpu);
ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu);
vcpu->arch.mmu.base_role.cr0_wp = is_write_protection(vcpu);
+ vcpu->arch.mmu.base_role.smep_andnot_wp
+ = smep && !is_write_protection(vcpu);
return r;
}
}
EXPORT_SYMBOL_GPL(kvm_mmu_unload);
-static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu,
- struct kvm_mmu_page *sp,
- u64 *spte)
-{
- u64 pte;
- struct kvm_mmu_page *child;
-
- pte = *spte;
- if (is_shadow_present_pte(pte)) {
- if (is_last_spte(pte, sp->role.level))
- drop_spte(vcpu->kvm, spte, shadow_trap_nonpresent_pte);
- else {
- child = page_header(pte & PT64_BASE_ADDR_MASK);
- mmu_page_remove_parent_pte(child, spte);
- }
- }
- __set_spte(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,
struct kvm_mmu_page *sp, u64 *spte,
const void *new)
int level, npte, invlpg_counter, r, flooded = 0;
bool remote_flush, local_flush, zap_page;
+ /*
+ * If we don't have indirect shadow pages, it means no page is
+ * write-protected, so we can exit simply.
+ */
+ if (!ACCESS_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
+ return;
+
zap_page = remote_flush = local_flush = false;
offset = offset_in_page(gpa);
spte = &sp->spt[page_offset / sizeof(*spte)];
while (npte--) {
entry = *spte;
- mmu_pte_write_zap_pte(vcpu, sp, spte);
+ mmu_page_zap_pte(vcpu->kvm, sp, spte);
if (gentry &&
!((sp->role.word ^ vcpu->arch.mmu.base_role.word)
& mask.word))
sp = container_of(vcpu->kvm->arch.active_mmu_pages.prev,
struct kvm_mmu_page, link);
kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list);
- kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
++vcpu->kvm->stat.mmu_recycled;
}
+ kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
}
int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
continue;
if (is_large_pte(pt[i])) {
- drop_spte(kvm, &pt[i],
- shadow_trap_nonpresent_pte);
+ drop_spte(kvm, &pt[i]);
--kvm->stat.lpages;
continue;
}
static void mmu_destroy_caches(void)
{
- if (pte_chain_cache)
- kmem_cache_destroy(pte_chain_cache);
- if (rmap_desc_cache)
- kmem_cache_destroy(rmap_desc_cache);
+ if (pte_list_desc_cache)
+ kmem_cache_destroy(pte_list_desc_cache);
if (mmu_page_header_cache)
kmem_cache_destroy(mmu_page_header_cache);
}
int kvm_mmu_module_init(void)
{
- pte_chain_cache = kmem_cache_create("kvm_pte_chain",
- sizeof(struct kvm_pte_chain),
- 0, 0, NULL);
- if (!pte_chain_cache)
- goto nomem;
- rmap_desc_cache = kmem_cache_create("kvm_rmap_desc",
- sizeof(struct kvm_rmap_desc),
+ pte_list_desc_cache = kmem_cache_create("pte_list_desc",
+ sizeof(struct pte_list_desc),
0, 0, NULL);
- if (!rmap_desc_cache)
+ if (!pte_list_desc_cache)
goto nomem;
mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header",