diff options
Diffstat (limited to 'arch/x86/kvm/mmu.c')
| -rw-r--r-- | arch/x86/kvm/mmu.c | 1639 |
1 files changed, 937 insertions, 702 deletions
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b1ed0a1a5913..908ea5464a51 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -7,6 +7,7 @@ * MMU support * * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affiliates. * * Authors: * Yaniv Kamay <yaniv@qumranet.com> @@ -32,6 +33,7 @@ #include <linux/compiler.h> #include <linux/srcu.h> #include <linux/slab.h> +#include <linux/uaccess.h> #include <asm/page.h> #include <asm/cmpxchg.h> @@ -47,15 +49,25 @@ */ bool tdp_enabled = false; -#undef MMU_DEBUG +enum { + AUDIT_PRE_PAGE_FAULT, + AUDIT_POST_PAGE_FAULT, + AUDIT_PRE_PTE_WRITE, + AUDIT_POST_PTE_WRITE, + AUDIT_PRE_SYNC, + AUDIT_POST_SYNC +}; -#undef AUDIT +char *audit_point_name[] = { + "pre page fault", + "post page fault", + "pre pte write", + "post pte write", + "pre sync", + "post sync" +}; -#ifdef AUDIT -static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg); -#else -static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) {} -#endif +#undef MMU_DEBUG #ifdef MMU_DEBUG @@ -69,7 +81,7 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) {} #endif -#if defined(MMU_DEBUG) || defined(AUDIT) +#ifdef MMU_DEBUG static int dbg = 0; module_param(dbg, bool, 0644); #endif @@ -87,11 +99,11 @@ module_param(oos_shadow, bool, 0644); } #endif +#define PTE_PREFETCH_NUM 8 + #define PT_FIRST_AVAIL_BITS_SHIFT 9 #define PT64_SECOND_AVAIL_BITS_SHIFT 52 -#define VALID_PAGE(x) ((x) != INVALID_PAGE) - #define PT64_LEVEL_BITS 9 #define PT64_LEVEL_SHIFT(level) \ @@ -173,11 +185,12 @@ struct kvm_shadow_walk_iterator { shadow_walk_okay(&(_walker)); \ shadow_walk_next(&(_walker))) -typedef int (*mmu_parent_walk_fn) (struct kvm_mmu_page *sp); +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 *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; @@ -281,13 +294,70 @@ static gfn_t pse36_gfn_delta(u32 gpte) static void __set_spte(u64 *sptep, u64 spte) { + set_64bit(sptep, spte); +} + +static u64 __xchg_spte(u64 *sptep, u64 new_spte) +{ #ifdef CONFIG_X86_64 - set_64bit((unsigned long *)sptep, spte); + return xchg(sptep, new_spte); #else - set_64bit((unsigned long long *)sptep, spte); + u64 old_spte; + + do { + old_spte = *sptep; + } while (cmpxchg64(sptep, old_spte, new_spte) != old_spte); + + return old_spte; #endif } +static bool spte_has_volatile_bits(u64 spte) +{ + if (!shadow_accessed_mask) + return false; + + if (!is_shadow_present_pte(spte)) + return false; + + if ((spte & shadow_accessed_mask) && + (!is_writable_pte(spte) || (spte & shadow_dirty_mask))) + return false; + + return true; +} + +static bool spte_is_bit_cleared(u64 old_spte, u64 new_spte, u64 bit_mask) +{ + return (old_spte & bit_mask) && !(new_spte & bit_mask); +} + +static void update_spte(u64 *sptep, u64 new_spte) +{ + u64 mask, old_spte = *sptep; + + WARN_ON(!is_rmap_spte(new_spte)); + + new_spte |= old_spte & shadow_dirty_mask; + + mask = shadow_accessed_mask; + if (is_writable_pte(old_spte)) + mask |= shadow_dirty_mask; + + if (!spte_has_volatile_bits(old_spte) || (new_spte & mask) == mask) + __set_spte(sptep, new_spte); + else + old_spte = __xchg_spte(sptep, new_spte); + + if (!shadow_accessed_mask) + return; + + if (spte_is_bit_cleared(old_spte, new_spte, shadow_accessed_mask)) + kvm_set_pfn_accessed(spte_to_pfn(old_spte)); + if (spte_is_bit_cleared(old_spte, new_spte, shadow_dirty_mask)) + kvm_set_pfn_dirty(spte_to_pfn(old_spte)); +} + static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, struct kmem_cache *base_cache, int min) { @@ -304,10 +374,11 @@ static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, return 0; } -static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc) +static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc, + struct kmem_cache *cache) { while (mc->nobjs) - kfree(mc->objects[--mc->nobjs]); + kmem_cache_free(cache, mc->objects[--mc->nobjs]); } static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, @@ -341,7 +412,7 @@ static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu) if (r) goto out; r = mmu_topup_memory_cache(&vcpu->arch.mmu_rmap_desc_cache, - rmap_desc_cache, 4); + rmap_desc_cache, 4 + PTE_PREFETCH_NUM); if (r) goto out; r = mmu_topup_memory_cache_page(&vcpu->arch.mmu_page_cache, 8); @@ -355,10 +426,11 @@ out: static void mmu_free_memory_caches(struct kvm_vcpu *vcpu) { - mmu_free_memory_cache(&vcpu->arch.mmu_pte_chain_cache); - mmu_free_memory_cache(&vcpu->arch.mmu_rmap_desc_cache); + 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_page(&vcpu->arch.mmu_page_cache); - mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache); + mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache, + mmu_page_header_cache); } static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc, @@ -379,7 +451,7 @@ static struct kvm_pte_chain *mmu_alloc_pte_chain(struct kvm_vcpu *vcpu) static void mmu_free_pte_chain(struct kvm_pte_chain *pc) { - kfree(pc); + kmem_cache_free(pte_chain_cache, pc); } static struct kvm_rmap_desc *mmu_alloc_rmap_desc(struct kvm_vcpu *vcpu) @@ -390,7 +462,23 @@ static struct kvm_rmap_desc *mmu_alloc_rmap_desc(struct kvm_vcpu *vcpu) static void mmu_free_rmap_desc(struct kvm_rmap_desc *rd) { - kfree(rd); + kmem_cache_free(rmap_desc_cache, rd); +} + +static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index) +{ + if (!sp->role.direct) + return sp->gfns[index]; + + return sp->gfn + (index << ((sp->role.level - 1) * PT64_LEVEL_BITS)); +} + +static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn) +{ + if (sp->role.direct) + BUG_ON(gfn != kvm_mmu_page_get_gfn(sp, index)); + else + sp->gfns[index] = gfn; } /* @@ -403,8 +491,8 @@ static int *slot_largepage_idx(gfn_t gfn, { unsigned long idx; - idx = (gfn / KVM_PAGES_PER_HPAGE(level)) - - (slot->base_gfn / KVM_PAGES_PER_HPAGE(level)); + idx = (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - + (slot->base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); return &slot->lpage_info[level - 2][idx].write_count; } @@ -414,9 +502,7 @@ static void account_shadowed(struct kvm *kvm, gfn_t gfn) int *write_count; int i; - gfn = unalias_gfn(kvm, gfn); - - slot = gfn_to_memslot_unaliased(kvm, gfn); + slot = gfn_to_memslot(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); @@ -430,8 +516,7 @@ static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn) int *write_count; int i; - gfn = unalias_gfn(kvm, gfn); - slot = gfn_to_memslot_unaliased(kvm, gfn); + slot = gfn_to_memslot(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); @@ -447,8 +532,7 @@ static int has_wrprotected_page(struct kvm *kvm, struct kvm_memory_slot *slot; int *largepage_idx; - gfn = unalias_gfn(kvm, gfn); - slot = gfn_to_memslot_unaliased(kvm, gfn); + slot = gfn_to_memslot(kvm, gfn); if (slot) { largepage_idx = slot_largepage_idx(gfn, slot, level); return *largepage_idx; @@ -501,7 +585,6 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) /* * 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, int level) @@ -513,8 +596,8 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level) if (likely(level == PT_PAGE_TABLE_LEVEL)) return &slot->rmap[gfn - slot->base_gfn]; - idx = (gfn / KVM_PAGES_PER_HPAGE(level)) - - (slot->base_gfn / KVM_PAGES_PER_HPAGE(level)); + idx = (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - + (slot->base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); return &slot->lpage_info[level - 2][idx].rmap_pde; } @@ -541,9 +624,8 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) if (!is_rmap_spte(*spte)) return count; - gfn = unalias_gfn(vcpu->kvm, gfn); sp = page_header(__pa(spte)); - sp->gfns[spte - sp->spt] = gfn; + 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); @@ -554,6 +636,7 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) desc->sptes[0] = (u64 *)*rmapp; desc->sptes[1] = spte; *rmapp = (unsigned long)desc | 1; + ++count; } else { rmap_printk("rmap_add: %p %llx many->many\n", spte, *spte); desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul); @@ -566,7 +649,7 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) desc = desc->more; } for (i = 0; desc->sptes[i]; ++i) - ; + ++count; desc->sptes[i] = spte; } return count; @@ -600,32 +683,25 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) struct kvm_rmap_desc *desc; struct kvm_rmap_desc *prev_desc; struct kvm_mmu_page *sp; - pfn_t pfn; + gfn_t gfn; unsigned long *rmapp; int i; - if (!is_rmap_spte(*spte)) - return; sp = page_header(__pa(spte)); - pfn = spte_to_pfn(*spte); - if (*spte & shadow_accessed_mask) - kvm_set_pfn_accessed(pfn); - if (is_writable_pte(*spte)) - kvm_set_pfn_dirty(pfn); - rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], sp->role.level); + 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 %llx 0->BUG\n", spte, *spte); + printk(KERN_ERR "rmap_remove: %p 0->BUG\n", spte); BUG(); } else if (!(*rmapp & 1)) { - rmap_printk("rmap_remove: %p %llx 1->0\n", spte, *spte); + rmap_printk("rmap_remove: %p 1->0\n", spte); if ((u64 *)*rmapp != spte) { - printk(KERN_ERR "rmap_remove: %p %llx 1->BUG\n", - spte, *spte); + printk(KERN_ERR "rmap_remove: %p 1->BUG\n", spte); BUG(); } *rmapp = 0; } else { - rmap_printk("rmap_remove: %p %llx many->many\n", spte, *spte); + rmap_printk("rmap_remove: %p many->many\n", spte); desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul); prev_desc = NULL; while (desc) { @@ -639,11 +715,37 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) prev_desc = desc; desc = desc->more; } - pr_err("rmap_remove: %p %llx many->many\n", spte, *spte); + pr_err("rmap_remove: %p many->many\n", spte); BUG(); } } +static void set_spte_track_bits(u64 *sptep, u64 new_spte) +{ + pfn_t pfn; + u64 old_spte = *sptep; + + if (!spte_has_volatile_bits(old_spte)) + __set_spte(sptep, new_spte); + else + old_spte = __xchg_spte(sptep, new_spte); + + if (!is_rmap_spte(old_spte)) + return; + + pfn = spte_to_pfn(old_spte); + if (!shadow_accessed_mask || old_spte & shadow_accessed_mask) + kvm_set_pfn_accessed(pfn); + if (!shadow_dirty_mask || (old_spte & shadow_dirty_mask)) + kvm_set_pfn_dirty(pfn); +} + +static void drop_spte(struct kvm *kvm, u64 *sptep, u64 new_spte) +{ + set_spte_track_bits(sptep, new_spte); + rmap_remove(kvm, sptep); +} + static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte) { struct kvm_rmap_desc *desc; @@ -676,7 +778,6 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) u64 *spte; int i, write_protected = 0; - gfn = unalias_gfn(kvm, gfn); rmapp = gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL); spte = rmap_next(kvm, rmapp, NULL); @@ -685,18 +786,11 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) BUG_ON(!(*spte & PT_PRESENT_MASK)); rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte); if (is_writable_pte(*spte)) { - __set_spte(spte, *spte & ~PT_WRITABLE_MASK); + update_spte(spte, *spte & ~PT_WRITABLE_MASK); write_protected = 1; } spte = rmap_next(kvm, rmapp, spte); } - 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 */ for (i = PT_DIRECTORY_LEVEL; @@ -709,9 +803,9 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) 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); + drop_spte(kvm, spte, + shadow_trap_nonpresent_pte); --kvm->stat.lpages; - __set_spte(spte, shadow_trap_nonpresent_pte); spte = NULL; write_protected = 1; } @@ -731,8 +825,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, 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_spte(spte, shadow_trap_nonpresent_pte); + drop_spte(kvm, spte, shadow_trap_nonpresent_pte); need_tlb_flush = 1; } return need_tlb_flush; @@ -754,8 +847,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, 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); + drop_spte(kvm, spte, shadow_trap_nonpresent_pte); spte = rmap_next(kvm, rmapp, NULL); } else { new_spte = *spte &~ (PT64_BASE_ADDR_MASK); @@ -763,9 +855,8 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, 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); + new_spte &= ~shadow_accessed_mask; + set_spte_track_bits(spte, new_spte); spte = rmap_next(kvm, rmapp, spte); } } @@ -799,8 +890,12 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, 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); + unsigned long idx; + int sh; + + sh = KVM_HPAGE_GFN_SHIFT(PT_DIRECTORY_LEVEL+j); + idx = ((memslot->base_gfn+gfn_offset) >> sh) - + (memslot->base_gfn >> sh); ret |= handler(kvm, &memslot->lpage_info[j][idx].rmap_pde, data); @@ -863,7 +958,6 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) sp = page_header(__pa(spte)); - gfn = unalias_gfn(vcpu->kvm, gfn); rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); kvm_unmap_rmapp(vcpu->kvm, rmapp, 0); @@ -891,14 +985,28 @@ static int is_empty_shadow_page(u64 *spt) } #endif +/* + * This value is the sum of all of the kvm instances's + * kvm->arch.n_used_mmu_pages values. We need a global, + * aggregate version in order to make the slab shrinker + * faster + */ +static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr) +{ + kvm->arch.n_used_mmu_pages += nr; + percpu_counter_add(&kvm_total_used_mmu_pages, nr); +} + static void kvm_mmu_free_page(struct kvm *kvm, struct kvm_mmu_page *sp) { ASSERT(is_empty_shadow_page(sp->spt)); + hlist_del(&sp->hash_link); list_del(&sp->link); __free_page(virt_to_page(sp->spt)); - __free_page(virt_to_page(sp->gfns)); - kfree(sp); - ++kvm->arch.n_free_mmu_pages; + if (!sp->role.direct) + __free_page(virt_to_page(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) @@ -907,19 +1015,21 @@ static unsigned kvm_page_table_hashfn(gfn_t gfn) } static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, - u64 *parent_pte) + 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); - sp->gfns = 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; - --vcpu->kvm->arch.n_free_mmu_pages; + kvm_mod_used_mmu_pages(vcpu->kvm, +1); return sp; } @@ -998,7 +1108,6 @@ static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp, BUG(); } - static void mmu_parent_walk(struct kvm_mmu_page *sp, mmu_parent_walk_fn fn) { struct kvm_pte_chain *pte_chain; @@ -1008,63 +1117,37 @@ static void mmu_parent_walk(struct kvm_mmu_page *sp, mmu_parent_walk_fn fn) if (!sp->multimapped && sp->parent_pte) { parent_sp = page_header(__pa(sp->parent_pte)); - fn(parent_sp); - mmu_parent_walk(parent_sp, fn); + 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) { - if (!pte_chain->parent_ptes[i]) + u64 *spte = pte_chain->parent_ptes[i]; + + if (!spte) break; - parent_sp = page_header(__pa(pte_chain->parent_ptes[i])); - fn(parent_sp); - mmu_parent_walk(parent_sp, fn); + parent_sp = page_header(__pa(spte)); + fn(parent_sp, spte); } } -static void kvm_mmu_update_unsync_bitmap(u64 *spte) +static void mark_unsync(struct kvm_mmu_page *sp, u64 *spte); +static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp) { - 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); + mmu_parent_walk(sp, mark_unsync); } -static void kvm_mmu_update_parents_unsync(struct kvm_mmu_page *sp) +static void mark_unsync(struct kvm_mmu_page *sp, u64 *spte) { - struct kvm_pte_chain *pte_chain; - struct hlist_node *node; - int i; + unsigned int index; - if (!sp->parent_pte) + index = spte - sp->spt; + if (__test_and_set_bit(index, sp->unsync_child_bitmap)) return; - - if (!sp->multimapped) { - kvm_mmu_update_unsync_bitmap(sp->parent_pte); + if (sp->unsync_children++) 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_mmu_page *sp) -{ - kvm_mmu_update_parents_unsync(sp); - return 1; -} - -static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp) -{ - mmu_parent_walk(sp, unsync_walk_fn); - kvm_mmu_update_parents_unsync(sp); + kvm_mmu_mark_parents_unsync(sp); } static void nonpaging_prefetch_page(struct kvm_vcpu *vcpu, @@ -1077,7 +1160,7 @@ static void nonpaging_prefetch_page(struct kvm_vcpu *vcpu, } static int nonpaging_sync_page(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp) + struct kvm_mmu_page *sp, bool clear_unsync) { return 1; } @@ -1123,35 +1206,40 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp, int i, ret, nr_unsync_leaf = 0; for_each_unsync_children(sp->unsync_child_bitmap, i) { + struct kvm_mmu_page *child; 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 (!is_shadow_present_pte(ent) || is_large_pte(ent)) + goto clear_child_bitmap; + + 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) + goto clear_child_bitmap; + else if (ret > 0) + nr_unsync_leaf += ret; + else + return ret; + } else if (child->unsync) { + nr_unsync_leaf++; + if (mmu_pages_add(pvec, child, i)) + return -ENOSPC; + } else + goto clear_child_bitmap; - if (child->unsync) { - nr_unsync_leaf++; - if (mmu_pages_add(pvec, child, i)) - return -ENOSPC; - } - } + continue; + +clear_child_bitmap: + __clear_bit(i, sp->unsync_child_bitmap); + sp->unsync_children--; + WARN_ON((int)sp->unsync_children < 0); } - if (find_first_bit(sp->unsync_child_bitmap, 512) == 512) - sp->unsync_children = 0; return nr_unsync_leaf; } @@ -1166,26 +1254,6 @@ static int mmu_unsync_walk(struct kvm_mmu_page *sp, return __mmu_unsync_walk(sp, pvec); } -static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn) -{ - unsigned index; - struct hlist_head *bucket; - struct kvm_mmu_page *sp; - struct hlist_node *node; - - 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.direct - && !sp->role.invalid) { - pgprintk("%s: found role %x\n", - __func__, sp->role.word); - return sp; - } - return NULL; -} - static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) { WARN_ON(!sp->unsync); @@ -1194,20 +1262,36 @@ static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) --kvm->stat.mmu_unsync; } -static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp); +static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, + struct list_head *invalid_list); +static void kvm_mmu_commit_zap_page(struct kvm *kvm, + struct list_head *invalid_list); + +#define for_each_gfn_sp(kvm, sp, gfn, pos) \ + hlist_for_each_entry(sp, pos, \ + &(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link) \ + if ((sp)->gfn != (gfn)) {} else -static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +#define for_each_gfn_indirect_valid_sp(kvm, sp, gfn, pos) \ + hlist_for_each_entry(sp, pos, \ + &(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link) \ + if ((sp)->gfn != (gfn) || (sp)->role.direct || \ + (sp)->role.invalid) {} else + +/* @sp->gfn should be write-protected at the call site */ +static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + struct list_head *invalid_list, bool clear_unsync) { if (sp->role.cr4_pae != !!is_pae(vcpu)) { - kvm_mmu_zap_page(vcpu->kvm, sp); + kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); 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); + if (clear_unsync) + kvm_unlink_unsync_page(vcpu->kvm, sp); + + if (vcpu->arch.mmu.sync_page(vcpu, sp, clear_unsync)) { + kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); return 1; } @@ -1215,6 +1299,52 @@ static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) return 0; } +static int kvm_sync_page_transient(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp) +{ + LIST_HEAD(invalid_list); + int ret; + + ret = __kvm_sync_page(vcpu, sp, &invalid_list, false); + if (ret) + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); + + return ret; +} + +static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + struct list_head *invalid_list) +{ + return __kvm_sync_page(vcpu, sp, invalid_list, true); +} + +/* @gfn should be write-protected at the call site */ +static void kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + struct kvm_mmu_page *s; + struct hlist_node *node; + LIST_HEAD(invalid_list); + bool flush = false; + + for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) { + if (!s->unsync) + continue; + + WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL); + if ((s->role.cr4_pae != !!is_pae(vcpu)) || + (vcpu->arch.mmu.sync_page(vcpu, s, true))) { + kvm_mmu_prepare_zap_page(vcpu->kvm, s, &invalid_list); + continue; + } + kvm_unlink_unsync_page(vcpu->kvm, s); + flush = true; + } + + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); + if (flush) + kvm_mmu_flush_tlb(vcpu); +} + struct mmu_page_path { struct kvm_mmu_page *parent[PT64_ROOT_LEVEL-1]; unsigned int idx[PT64_ROOT_LEVEL-1]; @@ -1281,6 +1411,7 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp; struct mmu_page_path parents; struct kvm_mmu_pages pages; + LIST_HEAD(invalid_list); kvm_mmu_pages_init(parent, &parents, &pages); while (mmu_unsync_walk(parent, &pages)) { @@ -1293,9 +1424,10 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, kvm_flush_remote_tlbs(vcpu->kvm); for_each_sp(pages, sp, parents, i) { - kvm_sync_page(vcpu, sp); + kvm_sync_page(vcpu, sp, &invalid_list); mmu_pages_clear_parents(&parents); } + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); cond_resched_lock(&vcpu->kvm->mmu_lock); kvm_mmu_pages_init(parent, &parents, &pages); } @@ -1310,11 +1442,10 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, u64 *parent_pte) { union kvm_mmu_page_role role; - unsigned index; unsigned quadrant; - struct hlist_head *bucket; struct kvm_mmu_page *sp; - struct hlist_node *node, *tmp; + struct hlist_node *node; + bool need_sync = false; role = vcpu->arch.mmu.base_role; role.level = level; @@ -1322,40 +1453,46 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, if (role.direct) role.cr4_pae = 0; role.access = access; - if (vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) { + if (!vcpu->arch.mmu.direct_map + && vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) { quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level)); quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; role.quadrant = quadrant; } - 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) - if (sp->gfn == gfn) { - if (sp->unsync) - if (kvm_sync_page(vcpu, sp)) - continue; + for_each_gfn_sp(vcpu->kvm, sp, gfn, node) { + if (!need_sync && sp->unsync) + need_sync = true; - if (sp->role.word != role.word) - continue; + if (sp->role.word != role.word) + continue; - mmu_page_add_parent_pte(vcpu, sp, parent_pte); - if (sp->unsync_children) { - set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests); - kvm_mmu_mark_parents_unsync(sp); - } - trace_kvm_mmu_get_page(sp, false); - return sp; - } + if (sp->unsync && kvm_sync_page_transient(vcpu, sp)) + break; + + mmu_page_add_parent_pte(vcpu, sp, parent_pte); + if (sp->unsync_children) { + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + kvm_mmu_mark_parents_unsync(sp); + } else if (sp->unsync) + kvm_mmu_mark_parents_unsync(sp); + + trace_kvm_mmu_get_page(sp, false); + return sp; + } ++vcpu->kvm->stat.mmu_cache_miss; - sp = kvm_mmu_alloc_page(vcpu, parent_pte); + sp = kvm_mmu_alloc_page(vcpu, parent_pte, direct); if (!sp) return sp; sp->gfn = gfn; sp->role = role; - hlist_add_head(&sp->hash_link, bucket); + hlist_add_head(&sp->hash_link, + &vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]); if (!direct) { if (rmap_write_protect(vcpu->kvm, gfn)) kvm_flush_remote_tlbs(vcpu->kvm); + if (level > PT_PAGE_TABLE_LEVEL && need_sync) + kvm_sync_pages(vcpu, gfn); + account_shadowed(vcpu->kvm, gfn); } if (shadow_trap_nonpresent_pte != shadow_notrap_nonpresent_pte) @@ -1372,6 +1509,12 @@ static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator, iterator->addr = addr; iterator->shadow_addr = vcpu->arch.mmu.root_hpa; iterator->level = vcpu->arch.mmu.shadow_root_level; + + if (iterator->level == PT64_ROOT_LEVEL && + vcpu->arch.mmu.root_level < PT64_ROOT_LEVEL && + !vcpu->arch.mmu.direct_map) + --iterator->level; + if (iterator->level == PT32E_ROOT_LEVEL) { iterator->shadow_addr = vcpu->arch.mmu.pae_root[(addr >> 30) & 3]; @@ -1402,6 +1545,47 @@ static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator) --iterator->level; } +static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp) +{ + u64 spte; + + spte = __pa(sp->spt) + | PT_PRESENT_MASK | PT_ACCESSED_MASK + | PT_WRITABLE_MASK | PT_USER_MASK; + __set_spte(sptep, spte); +} + +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); + kvm_flush_remote_tlbs(vcpu->kvm); + } +} + +static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, + unsigned direct_access) +{ + if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) { + struct kvm_mmu_page *child; + + /* + * For the direct sp, if the guest pte's dirty bit + * changed form clean to dirty, it will corrupt the + * sp's access: allow writable in the read-only sp, + * so we should update the spte at this point to get + * a new sp with the correct access. + */ + child = page_header(*sptep & PT64_BASE_ADDR_MASK); + if (child->role.access == direct_access) + return; + + mmu_page_remove_parent_pte(child, sptep); + __set_spte(sptep, shadow_trap_nonpresent_pte); + kvm_flush_remote_tlbs(vcpu->kvm); + } +} + static void kvm_mmu_page_unlink_children(struct kvm *kvm, struct kvm_mmu_page *sp) { @@ -1422,7 +1606,8 @@ static void kvm_mmu_page_unlink_children(struct kvm *kvm, } else { if (is_large_pte(ent)) --kvm->stat.lpages; - rmap_remove(kvm, &pt[i]); + drop_spte(kvm, &pt[i], + shadow_trap_nonpresent_pte); } } pt[i] = shadow_trap_nonpresent_pte; @@ -1464,7 +1649,8 @@ static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) } static int mmu_zap_unsync_children(struct kvm *kvm, - struct kvm_mmu_page *parent) + struct kvm_mmu_page *parent, + struct list_head *invalid_list) { int i, zapped = 0; struct mmu_page_path parents; @@ -1478,7 +1664,7 @@ static int mmu_zap_unsync_children(struct kvm *kvm, struct kvm_mmu_page *sp; for_each_sp(pages, sp, parents, i) { - kvm_mmu_zap_page(kvm, sp); + kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); mmu_pages_clear_parents(&parents); zapped++; } @@ -1488,112 +1674,113 @@ static int mmu_zap_unsync_children(struct kvm *kvm, return zapped; } -static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) +static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, + struct list_head *invalid_list) { int ret; - trace_kvm_mmu_zap_page(sp); + trace_kvm_mmu_prepare_zap_page(sp); ++kvm->stat.mmu_shadow_zapped; - ret = mmu_zap_unsync_children(kvm, sp); + ret = mmu_zap_unsync_children(kvm, sp, invalid_list); kvm_mmu_page_unlink_children(kvm, sp); kvm_mmu_unlink_parents(kvm, sp); - kvm_flush_remote_tlbs(kvm); if (!sp->role.invalid && !sp->role.direct) 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); + /* Count self */ + ret++; + list_move(&sp->link, invalid_list); } else { - sp->role.invalid = 1; list_move(&sp->link, &kvm->arch.active_mmu_pages); kvm_reload_remote_mmus(kvm); } + + sp->role.invalid = 1; kvm_mmu_reset_last_pte_updated(kvm); return ret; } +static void kvm_mmu_commit_zap_page(struct kvm *kvm, + struct list_head *invalid_list) +{ + struct kvm_mmu_page *sp; + + if (list_empty(invalid_list)) + return; + + kvm_flush_remote_tlbs(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); + } while (!list_empty(invalid_list)); + +} + /* * Changing the number of mmu pages allocated to the vm - * Note: if kvm_nr_mmu_pages is too small, you will get dead lock + * Note: if goal_nr_mmu_pages is too small, you will get dead lock */ -void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages) +void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages) { - int used_pages; - - used_pages = kvm->arch.n_alloc_mmu_pages - kvm->arch.n_free_mmu_pages; - used_pages = max(0, used_pages); - + LIST_HEAD(invalid_list); /* * If we set the number of mmu pages to be smaller be than the * number of actived pages , we must to free some mmu pages before we * change the value */ - if (used_pages > kvm_nr_mmu_pages) { - while (used_pages > kvm_nr_mmu_pages && + if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) { + while (kvm->arch.n_used_mmu_pages > goal_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); - used_pages -= kvm_mmu_zap_page(kvm, page); - used_pages--; + kvm_mmu_prepare_zap_page(kvm, page, &invalid_list); + kvm_mmu_commit_zap_page(kvm, &invalid_list); } - kvm_nr_mmu_pages = used_pages; - kvm->arch.n_free_mmu_pages = 0; + goal_nr_mmu_pages = kvm->arch.n_used_mmu_pages; } - else - kvm->arch.n_free_mmu_pages += kvm_nr_mmu_pages - - kvm->arch.n_alloc_mmu_pages; - kvm->arch.n_alloc_mmu_pages = kvm_nr_mmu_pages; + kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages; } static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) { - unsigned index; - struct hlist_head *bucket; struct kvm_mmu_page *sp; - struct hlist_node *node, *n; + struct hlist_node *node; + LIST_HEAD(invalid_list); int r; - pgprintk("%s: looking for gfn %lx\n", __func__, gfn); + pgprintk("%s: looking for gfn %llx\n", __func__, gfn); r = 0; - index = kvm_page_table_hashfn(gfn); - bucket = &kvm->arch.mmu_page_hash[index]; -restart: - hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) - if (sp->gfn == gfn && !sp->role.direct) { - pgprintk("%s: gfn %lx role %x\n", __func__, gfn, - sp->role.word); - r = 1; - if (kvm_mmu_zap_page(kvm, sp)) - goto restart; - } + + for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) { + pgprintk("%s: gfn %llx role %x\n", __func__, gfn, + sp->role.word); + r = 1; + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + } + kvm_mmu_commit_zap_page(kvm, &invalid_list); return r; } static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) { - unsigned index; - struct hlist_head *bucket; struct kvm_mmu_page *sp; - struct hlist_node *node, *nn; + struct hlist_node *node; + LIST_HEAD(invalid_list); - index = kvm_page_table_hashfn(gfn); - bucket = &kvm->arch.mmu_page_hash[index]; -restart: - hlist_for_each_entry_safe(sp, node, nn, bucket, hash_link) { - if (sp->gfn == gfn && !sp->role.direct - && !sp->role.invalid) { - pgprintk("%s: zap %lx %x\n", - __func__, gfn, sp->role.word); - if (kvm_mmu_zap_page(kvm, sp)) - goto restart; - } + for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) { + pgprintk("%s: zap %llx %x\n", + __func__, gfn, sp->role.word); + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); } + kvm_mmu_commit_zap_page(kvm, &invalid_list); } static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn) @@ -1723,47 +1910,51 @@ u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) } EXPORT_SYMBOL_GPL(kvm_get_guest_memory_type); -static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { - 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.direct) - continue; - if (s->role.word != sp->role.word) - return 1; - } trace_kvm_mmu_unsync_page(sp); ++vcpu->kvm->stat.mmu_unsync; sp->unsync = 1; kvm_mmu_mark_parents_unsync(sp); - mmu_convert_notrap(sp); - return 0; +} + +static void kvm_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + struct kvm_mmu_page *s; + struct hlist_node *node; + + for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) { + if (s->unsync) + continue; + WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL); + __kvm_unsync_page(vcpu, s); + } } static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) { - struct kvm_mmu_page *shadow; + struct kvm_mmu_page *s; + struct hlist_node *node; + bool need_unsync = false; - shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn); - if (shadow) { - if (shadow->role.level != PT_PAGE_TABLE_LEVEL) + for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) { + if (!can_unsync) return 1; - if (shadow->unsync) - return 0; - if (can_unsync && oos_shadow) - return kvm_unsync_page(vcpu, shadow); - return 1; + + if (s->role.level != PT_PAGE_TABLE_LEVEL) + return 1; + + if (!need_unsync && !s->unsync) { + if (!oos_shadow) + return 1; + need_unsync = true; + } } + if (need_unsync) + kvm_unsync_pages(vcpu, gfn); return 0; } @@ -1781,7 +1972,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, * whether the guest actually used the pte (in order to detect * demand paging). */ - spte = shadow_base_present_pte | shadow_dirty_mask; + spte = shadow_base_present_pte; if (!speculative) spte |= shadow_accessed_mask; if (!dirty) @@ -1804,18 +1995,20 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= (u64)pfn << PAGE_SHIFT; if ((pte_access & ACC_WRITE_MASK) - || (write_fault && !is_write_protection(vcpu) && !user_fault)) { + || (!vcpu->arch.mmu.direct_map && write_fault + && !is_write_protection(vcpu) && !user_fault)) { if (level > PT_PAGE_TABLE_LEVEL && has_wrprotected_page(vcpu->kvm, gfn, level)) { ret = 1; - spte = shadow_trap_nonpresent_pte; - goto set_pte; + drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte); + goto done; } spte |= PT_WRITABLE_MASK; - if (!tdp_enabled && !(pte_access & ACC_WRITE_MASK)) + if (!vcpu->arch.mmu.direct_map + && !(pte_access & ACC_WRITE_MASK)) spte &= ~PT_USER_MASK; /* @@ -1828,7 +2021,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, goto set_pte; if (mmu_need_write_protect(vcpu, gfn, can_unsync)) { - pgprintk("%s: found shadow page for %lx, marking ro\n", + pgprintk("%s: found shadow page for %llx, marking ro\n", __func__, gfn); ret = 1; pte_access &= ~ACC_WRITE_MASK; @@ -1841,7 +2034,8 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, mark_page_dirty(vcpu->kvm, gfn); set_pte: - __set_spte(sptep, spte); + update_spte(sptep, spte); +done: return ret; } @@ -1853,11 +2047,10 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, bool reset_host_protection) { int was_rmapped = 0; - int was_writable = is_writable_pte(*sptep); int rmap_count; pgprintk("%s: spte %llx access %x write_fault %d" - " user_fault %d gfn %lx\n", + " user_fault %d gfn %llx\n", __func__, *sptep, pt_access, write_fault, user_fault, gfn); @@ -1876,10 +2069,9 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, __set_spte(sptep, shadow_trap_nonpresent_pte); kvm_flush_remote_tlbs(vcpu->kvm); } else if (pfn != spte_to_pfn(*sptep)) { - pgprintk("hfn old %lx new %lx\n", + pgprintk("hfn old %llx new %llx\n", spte_to_pfn(*sptep), pfn); - rmap_remove(vcpu->kvm, sptep); - __set_spte(sptep, shadow_trap_nonpresent_pte); + drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte); kvm_flush_remote_tlbs(vcpu->kvm); } else was_rmapped = 1; @@ -1890,11 +2082,11 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, reset_host_protection)) { if (write_fault) *ptwrite = 1; - kvm_x86_ops->tlb_flush(vcpu); + kvm_mmu_flush_tlb(vcpu); } pgprintk("%s: setting spte %llx\n", __func__, *sptep); - pgprintk("instantiating %s PTE (%s) at %ld (%llx) addr %p\n", + pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n", is_large_pte(*sptep)? "2MB" : "4kB", *sptep & PT_PRESENT_MASK ?"RW":"R", gfn, *sptep, sptep); @@ -1904,15 +2096,10 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, page_header_update_slot(vcpu->kvm, sptep, gfn); if (!was_rmapped) { rmap_count = rmap_add(vcpu, sptep, gfn); - kvm_release_pfn_clean(pfn); if (rmap_count > RMAP_RECYCLE_THRESHOLD) rmap_recycle(vcpu, sptep, gfn); - } else { - if (was_writable) - kvm_release_pfn_dirty(pfn); - else - kvm_release_pfn_clean(pfn); } + kvm_release_pfn_clean(pfn); if (speculative) { vcpu->arch.last_pte_updated = sptep; vcpu->arch.last_pte_gfn = gfn; @@ -1923,6 +2110,105 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) { } +static struct kvm_memory_slot * +pte_prefetch_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) +{ + struct kvm_memory_slot *slot; + + slot = gfn_to_memslot(vcpu->kvm, gfn); + if (!slot || slot->flags & KVM_MEMSLOT_INVALID || + (no_dirty_log && slot->dirty_bitmap)) + slot = NULL; + + return slot; +} + +static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, + bool no_dirty_log) +{ + struct kvm_memory_slot *slot; + unsigned long hva; + + slot = pte_prefetch_gfn_to_memslot(vcpu, gfn, no_dirty_log); + if (!slot) { + get_page(bad_page); + return page_to_pfn(bad_page); + } + + hva = gfn_to_hva_memslot(slot, gfn); + + return hva_to_pfn_atomic(vcpu->kvm, hva); +} + +static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp, + u64 *start, u64 *end) +{ + struct page *pages[PTE_PREFETCH_NUM]; + unsigned access = sp->role.access; + int i, ret; + gfn_t gfn; + + gfn = kvm_mmu_page_get_gfn(sp, start - sp->spt); + if (!pte_prefetch_gfn_to_memslot(vcpu, gfn, access & ACC_WRITE_MASK)) + return -1; + + ret = gfn_to_page_many_atomic(vcpu->kvm, gfn, pages, end - start); + if (ret <= 0) + return -1; + + for (i = 0; i < ret; i++, gfn++, start++) + mmu_set_spte(vcpu, start, ACC_ALL, + access, 0, 0, 1, NULL, + sp->role.level, gfn, + page_to_pfn(pages[i]), true, true); + + return 0; +} + +static void __direct_pte_prefetch(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp, u64 *sptep) +{ + u64 *spte, *start = NULL; + int i; + + WARN_ON(!sp->role.direct); + + i = (sptep - sp->spt) & ~(PTE_PREFETCH_NUM - 1); + spte = sp->spt + i; + + for (i = 0; i < PTE_PREFETCH_NUM; i++, spte++) { + if (*spte != shadow_trap_nonpresent_pte || spte == sptep) { + if (!start) + continue; + if (direct_pte_prefetch_many(vcpu, sp, start, spte) < 0) + break; + start = NULL; + } else if (!start) + start = spte; + } +} + +static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) +{ + struct kvm_mmu_page *sp; + + /* + * Since it's no accessed bit on EPT, it's no way to + * distinguish between actually accessed translations + * and prefetched, so disable pte prefetch if EPT is + * enabled. + */ + if (!shadow_accessed_mask) + return; + + sp = page_header(__pa(sptep)); + if (sp->role.level > PT_PAGE_TABLE_LEVEL) + return; + + __direct_pte_prefetch(vcpu, sp, sptep); +} + static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, int level, gfn_t gfn, pfn_t pfn) { @@ -1936,12 +2222,16 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL, 0, write, 1, &pt_write, level, gfn, pfn, false, true); + direct_pte_prefetch(vcpu, iterator.sptep); ++vcpu->stat.pf_fixed; break; } if (*iterator.sptep == shadow_trap_nonpresent_pte) { - pseudo_gfn = (iterator.addr & PT64_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT; + u64 base_addr = iterator.addr; + + base_addr &= PT64_LVL_ADDR_MASK(iterator.level); + pseudo_gfn = base_addr >> PAGE_SHIFT; sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr, iterator.level - 1, 1, ACC_ALL, iterator.sptep); @@ -1954,12 +2244,38 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, __set_spte(iterator.sptep, __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK - | shadow_user_mask | shadow_x_mask); + | shadow_user_mask | shadow_x_mask + | shadow_accessed_mask); } } return pt_write; } +static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk) +{ + siginfo_t info; + + info.si_signo = SIGBUS; + info.si_errno = 0; + info.si_code = BUS_MCEERR_AR; + info.si_addr = (void __user *)address; + info.si_addr_lsb = PAGE_SHIFT; + + send_sig_info(SIGBUS, &info, tsk); +} + +static int kvm_handle_bad_page(struct kvm *kvm, 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); + return 0; + } else if (is_fault_pfn(pfn)) + return -EFAULT; + + return 1; +} + static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) { int r; @@ -1983,10 +2299,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) pfn = gfn_to_pfn(vcpu->kvm, gfn); /* mmio */ - if (is_error_pfn(pfn)) { - kvm_release_pfn_clean(pfn); - return 1; - } + if (is_error_pfn(pfn)) + return kvm_handle_bad_page(vcpu->kvm, gfn, pfn); spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu, mmu_seq)) @@ -2009,17 +2323,22 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) { int i; struct kvm_mmu_page *sp; + LIST_HEAD(invalid_list); if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; spin_lock(&vcpu->kvm->mmu_lock); - if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { + if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL && + (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL || + vcpu->arch.mmu.direct_map)) { 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); + if (!sp->root_count && sp->role.invalid) { + kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); + } vcpu->arch.mmu.root_hpa = INVALID_PAGE; spin_unlock(&vcpu->kvm->mmu_lock); return; @@ -2032,10 +2351,12 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) sp = page_header(root); --sp->root_count; if (!sp->root_count && sp->role.invalid) - kvm_mmu_zap_page(vcpu->kvm, sp); + kvm_mmu_prepare_zap_page(vcpu->kvm, sp, + &invalid_list); } vcpu->arch.mmu.pae_root[i] = INVALID_PAGE; } + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); spin_unlock(&vcpu->kvm->mmu_lock); vcpu->arch.mmu.root_hpa = INVALID_PAGE; } @@ -2045,85 +2366,165 @@ static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn) int ret = 0; if (!kvm_is_visible_gfn(vcpu->kvm, root_gfn)) { - set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests); + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); ret = 1; } return ret; } -static int mmu_alloc_roots(struct kvm_vcpu *vcpu) +static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) { - int i; - gfn_t root_gfn; struct kvm_mmu_page *sp; - int direct = 0; - u64 pdptr; - - root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT; + unsigned i; if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { + spin_lock(&vcpu->kvm->mmu_lock); + kvm_mmu_free_some_pages(vcpu); + sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL, + 1, ACC_ALL, NULL); + ++sp->root_count; + spin_unlock(&vcpu->kvm->mmu_lock); + vcpu->arch.mmu.root_hpa = __pa(sp->spt); + } else if (vcpu->arch.mmu.shadow_root_level == PT32E_ROOT_LEVEL) { + for (i = 0; i < 4; ++i) { + hpa_t root = vcpu->arch.mmu.pae_root[i]; + + ASSERT(!VALID_PAGE(root)); + spin_lock(&vcpu->kvm->mmu_lock); + kvm_mmu_free_some_pages(vcpu); + sp = kvm_mmu_get_page(vcpu, i << 30, i << 30, + PT32_ROOT_LEVEL, 1, ACC_ALL, + NULL); + root = __pa(sp->spt); + ++sp->root_count; + spin_unlock(&vcpu->kvm->mmu_lock); + vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK; + } + vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root); + } else + BUG(); + + return 0; +} + +static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu_page *sp; + u64 pdptr, pm_mask; + gfn_t root_gfn; + int i; + + root_gfn = vcpu->arch.mmu.get_cr3(vcpu) >> PAGE_SHIFT; + + if (mmu_check_root(vcpu, root_gfn)) + return 1; + + /* + * Do we shadow a long mode page table? If so we need to + * write-protect the guests page table root. + */ + if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) { hpa_t root = vcpu->arch.mmu.root_hpa; ASSERT(!VALID_PAGE(root)); - if (mmu_check_root(vcpu, root_gfn)) - return 1; - if (tdp_enabled) { - direct = 1; - root_gfn = 0; - } + spin_lock(&vcpu->kvm->mmu_lock); - sp = kvm_mmu_get_page(vcpu, root_gfn, 0, - PT64_ROOT_LEVEL, direct, - ACC_ALL, NULL); + kvm_mmu_free_some_pages(vcpu); + sp = kvm_mmu_get_page(vcpu, root_gfn, 0, PT64_ROOT_LEVEL, + 0, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); vcpu->arch.mmu.root_hpa = root; return 0; } - direct = !is_paging(vcpu); + + /* + * We shadow a 32 bit page table. This may be a legacy 2-level + * or a PAE 3-level page table. In either case we need to be aware that + * the shadow page table may be a PAE or a long mode page table. + */ + pm_mask = PT_PRESENT_MASK; + if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) + pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK; + for (i = 0; i < 4; ++i) { hpa_t root = vcpu->arch.mmu.pae_root[i]; ASSERT(!VALID_PAGE(root)); if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) { - pdptr = kvm_pdptr_read(vcpu, i); + pdptr = kvm_pdptr_read_mmu(vcpu, &vcpu->arch.mmu, i); if (!is_present_gpte(pdptr)) { vcpu->arch.mmu.pae_root[i] = 0; continue; } root_gfn = pdptr >> PAGE_SHIFT; - } else if (vcpu->arch.mmu.root_level == 0) - root_gfn = 0; - if (mmu_check_root(vcpu, root_gfn)) - return 1; - if (tdp_enabled) { - direct = 1; - root_gfn = i << 30; + if (mmu_check_root(vcpu, root_gfn)) + return 1; } spin_lock(&vcpu->kvm->mmu_lock); + kvm_mmu_free_some_pages(vcpu); sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, - PT32_ROOT_LEVEL, direct, + PT32_ROOT_LEVEL, 0, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); - vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK; + vcpu->arch.mmu.pae_root[i] = root | pm_mask; } vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root); + + /* + * If we shadow a 32 bit page table with a long mode page + * table we enter this path. + */ + if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { + if (vcpu->arch.mmu.lm_root == NULL) { + /* + * The additional page necessary for this is only + * allocated on demand. + */ + + u64 *lm_root; + + lm_root = (void*)get_zeroed_page(GFP_KERNEL); + if (lm_root == NULL) + return 1; + + lm_root[0] = __pa(vcpu->arch.mmu.pae_root) | pm_mask; + + vcpu->arch.mmu.lm_root = lm_root; + } + + vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.lm_root); + } + return 0; } +static int mmu_alloc_roots(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.mmu.direct_map) + return mmu_alloc_direct_roots(vcpu); + else + return mmu_alloc_shadow_roots(vcpu); +} + static void mmu_sync_roots(struct kvm_vcpu *vcpu) { int i; struct kvm_mmu_page *sp; + if (vcpu->arch.mmu.direct_map) + return; + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; - if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { + + 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; sp = page_header(root); mmu_sync_children(vcpu, sp); @@ -2138,6 +2539,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu) mmu_sync_children(vcpu, sp); } } + trace_kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); } void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) @@ -2155,6 +2557,14 @@ static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, return vaddr; } +static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, + u32 access, u32 *error) +{ + if (error) + *error = 0; + return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access); +} + static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code) { @@ -2198,10 +2608,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, 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; - } + if (is_error_pfn(pfn)) + return kvm_handle_bad_page(vcpu->kvm, gfn, pfn); spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu, mmu_seq)) goto out_unlock; @@ -2223,10 +2631,9 @@ static void nonpaging_free(struct kvm_vcpu *vcpu) mmu_free_roots(vcpu); } -static int nonpaging_init_context(struct kvm_vcpu *vcpu) +static int nonpaging_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - struct kvm_mmu *context = &vcpu->arch.mmu; - context->new_cr3 = nonpaging_new_cr3; context->page_fault = nonpaging_page_fault; context->gva_to_gpa = nonpaging_gva_to_gpa; @@ -2237,13 +2644,15 @@ static int nonpaging_init_context(struct kvm_vcpu *vcpu) context->root_level = 0; context->shadow_root_level = PT32E_ROOT_LEVEL; context->root_hpa = INVALID_PAGE; + context->direct_map = true; + context->nx = false; return 0; } void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; - kvm_x86_ops->tlb_flush(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } static void paging_new_cr3(struct kvm_vcpu *vcpu) @@ -2252,11 +2661,14 @@ static void paging_new_cr3(struct kvm_vcpu *vcpu) mmu_free_roots(vcpu); } -static void inject_page_fault(struct kvm_vcpu *vcpu, - u64 addr, - u32 err_code) +static unsigned long get_cr3(struct kvm_vcpu *vcpu) { - kvm_inject_page_fault(vcpu, addr, err_code); + return vcpu->arch.cr3; +} + +static void inject_page_fault(struct kvm_vcpu *vcpu) +{ + vcpu->arch.mmu.inject_page_fault(vcpu); } static void paging_free(struct kvm_vcpu *vcpu) @@ -2264,12 +2676,12 @@ static void paging_free(struct kvm_vcpu *vcpu) nonpaging_free(vcpu); } -static bool is_rsvd_bits_set(struct kvm_vcpu *vcpu, u64 gpte, int level) +static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level) { int bit7; bit7 = (gpte >> 7) & 1; - return (gpte & vcpu->arch.mmu.rsvd_bits_mask[bit7][level-1]) != 0; + return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0; } #define PTTYPE 64 @@ -2280,13 +2692,14 @@ static bool is_rsvd_bits_set(struct kvm_vcpu *vcpu, u64 gpte, int level) #include "paging_tmpl.h" #undef PTTYPE -static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level) +static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, + struct kvm_mmu *context, + int level) { - struct kvm_mmu *context = &vcpu->arch.mmu; int maxphyaddr = cpuid_maxphyaddr(vcpu); u64 exb_bit_rsvd = 0; - if (!is_nx(vcpu)) + if (!context->nx) exb_bit_rsvd = rsvd_bits(63, 63); switch (level) { case PT32_ROOT_LEVEL: @@ -2341,9 +2754,13 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level) } } -static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level) +static int paging64_init_context_common(struct kvm_vcpu *vcpu, + struct kvm_mmu *context, + int level) { - struct kvm_mmu *context = &vcpu->arch.mmu; + context->nx = is_nx(vcpu); + + reset_rsvds_bits_mask(vcpu, context, level); ASSERT(is_pae(vcpu)); context->new_cr3 = paging_new_cr3; @@ -2356,20 +2773,23 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level) context->root_level = level; context->shadow_root_level = level; context->root_hpa = INVALID_PAGE; + context->direct_map = false; return 0; } -static int paging64_init_context(struct kvm_vcpu *vcpu) +static int paging64_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - reset_rsvds_bits_mask(vcpu, PT64_ROOT_LEVEL); - return paging64_init_context_common(vcpu, PT64_ROOT_LEVEL); + return paging64_init_context_common(vcpu, context, PT64_ROOT_LEVEL); } -static int paging32_init_context(struct kvm_vcpu *vcpu) +static int paging32_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - struct kvm_mmu *context = &vcpu->arch.mmu; + context->nx = false; + + reset_rsvds_bits_mask(vcpu, context, PT32_ROOT_LEVEL); - reset_rsvds_bits_mask(vcpu, PT32_ROOT_LEVEL); context->new_cr3 = paging_new_cr3; context->page_fault = paging32_page_fault; context->gva_to_gpa = paging32_gva_to_gpa; @@ -2380,18 +2800,19 @@ static int paging32_init_context(struct kvm_vcpu *vcpu) context->root_level = PT32_ROOT_LEVEL; context->shadow_root_level = PT32E_ROOT_LEVEL; context->root_hpa = INVALID_PAGE; + context->direct_map = false; return 0; } -static int paging32E_init_context(struct kvm_vcpu *vcpu) +static int paging32E_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - reset_rsvds_bits_mask(vcpu, PT32E_ROOT_LEVEL); - return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL); + return paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL); } static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) { - struct kvm_mmu *context = &vcpu->arch.mmu; + struct kvm_mmu *context = vcpu->arch.walk_mmu; context->new_cr3 = nonpaging_new_cr3; context->page_fault = tdp_page_fault; @@ -2401,20 +2822,29 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->invlpg = nonpaging_invlpg; context->shadow_root_level = kvm_x86_ops->get_tdp_level(); context->root_hpa = INVALID_PAGE; + context->direct_map = true; + context->set_cr3 = kvm_x86_ops->set_tdp_cr3; + context->get_cr3 = get_cr3; + context->inject_page_fault = kvm_inject_page_fault; + context->nx = is_nx(vcpu); if (!is_paging(vcpu)) { + context->nx = false; context->gva_to_gpa = nonpaging_gva_to_gpa; context->root_level = 0; } else if (is_long_mode(vcpu)) { - reset_rsvds_bits_mask(vcpu, PT64_ROOT_LEVEL); + context->nx = is_nx(vcpu); + reset_rsvds_bits_mask(vcpu, context, PT64_ROOT_LEVEL); context->gva_to_gpa = paging64_gva_to_gpa; context->root_level = PT64_ROOT_LEVEL; } else if (is_pae(vcpu)) { - reset_rsvds_bits_mask(vcpu, PT32E_ROOT_LEVEL); + context->nx = is_nx(vcpu); + reset_rsvds_bits_mask(vcpu, context, PT32E_ROOT_LEVEL); context->gva_to_gpa = paging64_gva_to_gpa; context->root_level = PT32E_ROOT_LEVEL; } else { - reset_rsvds_bits_mask(vcpu, PT32_ROOT_LEVEL); + context->nx = false; + reset_rsvds_bits_mask(vcpu, context, PT32_ROOT_LEVEL); context->gva_to_gpa = paging32_gva_to_gpa; context->root_level = PT32_ROOT_LEVEL; } @@ -2422,33 +2852,83 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) return 0; } -static int init_kvm_softmmu(struct kvm_vcpu *vcpu) +int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { int r; - ASSERT(vcpu); ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); if (!is_paging(vcpu)) - r = nonpaging_init_context(vcpu); + r = nonpaging_init_context(vcpu, context); else if (is_long_mode(vcpu)) - r = paging64_init_context(vcpu); + r = paging64_init_context(vcpu, context); else if (is_pae(vcpu)) - r = paging32E_init_context(vcpu); + r = paging32E_init_context(vcpu, context); else - r = paging32_init_context(vcpu); + r = paging32_init_context(vcpu, context); 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.cr0_wp = is_write_protection(vcpu); + + return r; +} +EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); + +static int init_kvm_softmmu(struct kvm_vcpu *vcpu) +{ + int r = kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu); + + vcpu->arch.walk_mmu->set_cr3 = kvm_x86_ops->set_cr3; + vcpu->arch.walk_mmu->get_cr3 = get_cr3; + vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; return r; } +static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu *g_context = &vcpu->arch.nested_mmu; + + g_context->get_cr3 = get_cr3; + g_context->inject_page_fault = kvm_inject_page_fault; + + /* + * Note that arch.mmu.gva_to_gpa translates l2_gva to l1_gpa. The + * translation of l2_gpa to l1_gpa addresses is done using the + * arch.nested_mmu.gva_to_gpa function. Basically the gva_to_gpa + * functions between mmu and nested_mmu are swapped. + */ + if (!is_paging(vcpu)) { + g_context->nx = false; + g_context->root_level = 0; + g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested; + } else if (is_long_mode(vcpu)) { + g_context->nx = is_nx(vcpu); + reset_rsvds_bits_mask(vcpu, g_context, PT64_ROOT_LEVEL); + g_context->root_level = PT64_ROOT_LEVEL; + g_context->gva_to_gpa = paging64_gva_to_gpa_nested; + } else if (is_pae(vcpu)) { + g_context->nx = is_nx(vcpu); + reset_rsvds_bits_mask(vcpu, g_context, PT32E_ROOT_LEVEL); + g_context->root_level = PT32E_ROOT_LEVEL; + g_context->gva_to_gpa = paging64_gva_to_gpa_nested; + } else { + g_context->nx = false; + reset_rsvds_bits_mask(vcpu, g_context, PT32_ROOT_LEVEL); + g_context->root_level = PT32_ROOT_LEVEL; + g_context->gva_to_gpa = paging32_gva_to_gpa_nested; + } + + return 0; +} + static int init_kvm_mmu(struct kvm_vcpu *vcpu) { vcpu->arch.update_pte.pfn = bad_pfn; - if (tdp_enabled) + if (mmu_is_nested(vcpu)) + return init_kvm_nested_mmu(vcpu); + else if (tdp_enabled) return init_kvm_tdp_mmu(vcpu); else return init_kvm_softmmu(vcpu); @@ -2457,10 +2937,9 @@ static int init_kvm_mmu(struct kvm_vcpu *vcpu) static void destroy_kvm_mmu(struct kvm_vcpu *vcpu) { ASSERT(vcpu); - if (VALID_PAGE(vcpu->arch.mmu.root_hpa)) { + if (VALID_PAGE(vcpu->arch.mmu.root_hpa)) + /* mmu.free() should set root_hpa = INVALID_PAGE */ vcpu->arch.mmu.free(vcpu); - vcpu->arch.mmu.root_hpa = INVALID_PAGE; - } } int kvm_mmu_reset_context(struct kvm_vcpu *vcpu) @@ -2477,9 +2956,6 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) r = mmu_topup_memory_caches(vcpu); if (r) goto out; - spin_lock(&vcpu->kvm->mmu_lock); - kvm_mmu_free_some_pages(vcpu); - spin_unlock(&vcpu->kvm->mmu_lock); r = mmu_alloc_roots(vcpu); spin_lock(&vcpu->kvm->mmu_lock); mmu_sync_roots(vcpu); @@ -2487,7 +2963,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) if (r) goto out; /* set_cr3() should ensure TLB has been flushed */ - kvm_x86_ops->set_cr3(vcpu, vcpu->arch.mmu.root_hpa); + vcpu->arch.mmu.set_cr3(vcpu, vcpu->arch.mmu.root_hpa); out: return r; } @@ -2497,6 +2973,7 @@ void kvm_mmu_unload(struct kvm_vcpu *vcpu) { mmu_free_roots(vcpu); } +EXPORT_SYMBOL_GPL(kvm_mmu_unload); static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, @@ -2508,7 +2985,7 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu, pte = *spte; if (is_shadow_present_pte(pte)) { if (is_last_spte(pte, sp->role.level)) - rmap_remove(vcpu->kvm, spte); + 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); @@ -2529,6 +3006,9 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, return; } + if (is_rsvd_bits_set(&vcpu->arch.mmu, *(u64 *)new, PT_PAGE_TABLE_LEVEL)) + return; + ++vcpu->kvm->stat.mmu_pte_updated; if (!sp->role.cr4_pae) paging32_update_pte(vcpu, sp, spte, new); @@ -2549,11 +3029,15 @@ static bool need_remote_flush(u64 old, u64 new) return (old & ~new & PT64_PERM_MASK) != 0; } -static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, u64 old, u64 new) +static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page, + bool remote_flush, bool local_flush) { - if (need_remote_flush(old, new)) + if (zap_page) + return; + + if (remote_flush) kvm_flush_remote_tlbs(vcpu->kvm); - else + else if (local_flush) kvm_mmu_flush_tlb(vcpu); } @@ -2603,10 +3087,10 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, bool guest_initiated) { gfn_t gfn = gpa >> PAGE_SHIFT; + union kvm_mmu_page_role mask = { .word = 0 }; struct kvm_mmu_page *sp; - struct hlist_node *node, *n; - struct hlist_head *bucket; - unsigned index; + struct hlist_node *node; + LIST_HEAD(invalid_list); u64 entry, gentry; u64 *spte; unsigned offset = offset_in_page(gpa); @@ -2619,6 +3103,9 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, int npte; int r; int invlpg_counter; + bool remote_flush, local_flush, zap_page; + + zap_page = remote_flush = local_flush = false; pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); @@ -2661,7 +3148,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, 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"); + trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); if (guest_initiated) { if (gfn == vcpu->arch.last_pt_write_gfn && !last_updated_pte_accessed(vcpu)) { @@ -2674,13 +3161,9 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, vcpu->arch.last_pte_updated = NULL; } } - index = kvm_page_table_hashfn(gfn); - bucket = &vcpu->kvm->arch.mmu_page_hash[index]; -restart: - hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) { - if (sp->gfn != gfn || sp->role.direct || sp->role.invalid) - continue; + mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; + for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) { pte_size = sp->role.cr4_pae ? 8 : 4; misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); misaligned |= bytes < 4; @@ -2697,8 +3180,8 @@ restart: */ pgprintk("misaligned: gpa %llx bytes %d role %x\n", gpa, bytes, sp->role.word); - if (kvm_mmu_zap_page(vcpu->kvm, sp)) - goto restart; + zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp, + &invalid_list); ++vcpu->kvm->stat.mmu_flooded; continue; } @@ -2722,17 +3205,23 @@ restart: if (quadrant != sp->role.quadrant) continue; } + local_flush = true; spte = &sp->spt[page_offset / sizeof(*spte)]; while (npte--) { entry = *spte; mmu_pte_write_zap_pte(vcpu, sp, spte); - if (gentry) + if (gentry && + !((sp->role.word ^ vcpu->arch.mmu.base_role.word) + & mask.word)) mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); - mmu_pte_write_flush_tlb(vcpu, entry, *spte); + if (!remote_flush && need_remote_flush(entry, *spte)) + remote_flush = true; ++spte; } } - kvm_mmu_audit(vcpu, "post pte write"); + mmu_pte_write_flush_tlb(vcpu, zap_page, remote_flush, local_flush); + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); + trace_kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE); spin_unlock(&vcpu->kvm->mmu_lock); if (!is_error_pfn(vcpu->arch.update_pte.pfn)) { kvm_release_pfn_clean(vcpu->arch.update_pte.pfn); @@ -2745,7 +3234,7 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) gpa_t gpa; int r; - if (tdp_enabled) + if (vcpu->arch.mmu.direct_map) return 0; gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); @@ -2759,13 +3248,16 @@ EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) { - while (vcpu->kvm->arch.n_free_mmu_pages < KVM_REFILL_PAGES && + LIST_HEAD(invalid_list); + + while (kvm_mmu_available_pages(vcpu->kvm) < 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, struct kvm_mmu_page, link); - kvm_mmu_zap_page(vcpu->kvm, sp); + kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); ++vcpu->kvm->stat.mmu_recycled; } } @@ -2795,11 +3287,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code) return 1; case EMULATE_DO_MMIO: ++vcpu->stat.mmio_exits; - return 0; + /* fall through */ 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(); @@ -2832,6 +3321,8 @@ EXPORT_SYMBOL_GPL(kvm_disable_tdp); static void free_mmu_pages(struct kvm_vcpu *vcpu) { free_page((unsigned long)vcpu->arch.mmu.pae_root); + if (vcpu->arch.mmu.lm_root != NULL) + free_page((unsigned long)vcpu->arch.mmu.lm_root); } static int alloc_mmu_pages(struct kvm_vcpu *vcpu) @@ -2873,15 +3364,6 @@ int kvm_mmu_setup(struct kvm_vcpu *vcpu) return init_kvm_mmu(vcpu); } -void kvm_mmu_destroy(struct kvm_vcpu *vcpu) -{ - ASSERT(vcpu); - - destroy_kvm_mmu(vcpu); - free_mmu_pages(vcpu); - mmu_free_memory_caches(vcpu); -} - void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) { struct kvm_mmu_page *sp; @@ -2896,7 +3378,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) pt = sp->spt; for (i = 0; i < PT64_ENT_PER_PAGE; ++i) /* avoid RMW */ - if (pt[i] & PT_WRITABLE_MASK) + if (is_writable_pte(pt[i])) pt[i] &= ~PT_WRITABLE_MASK; } kvm_flush_remote_tlbs(kvm); @@ -2905,50 +3387,53 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) void kvm_mmu_zap_all(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; + LIST_HEAD(invalid_list); spin_lock(&kvm->mmu_lock); restart: list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) - if (kvm_mmu_zap_page(kvm, sp)) + if (kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list)) goto restart; + kvm_mmu_commit_zap_page(kvm, &invalid_list); spin_unlock(&kvm->mmu_lock); - - kvm_flush_remote_tlbs(kvm); } -static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm) +static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm, + struct list_head *invalid_list) { struct kvm_mmu_page *page; page = container_of(kvm->arch.active_mmu_pages.prev, struct kvm_mmu_page, link); - return kvm_mmu_zap_page(kvm, page) + 1; + return kvm_mmu_prepare_zap_page(kvm, page, invalid_list); } static int mmu_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) { struct kvm *kvm; struct kvm *kvm_freed = NULL; - int cache_count = 0; + + if (nr_to_scan == 0) + goto out; spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { - int npages, idx, freed_pages; + int idx, freed_pages; + LIST_HEAD(invalid_list); idx = srcu_read_lock(&kvm->srcu); 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) { - freed_pages = kvm_mmu_remove_some_alloc_mmu_pages(kvm); - cache_count -= freed_pages; + if (!kvm_freed && nr_to_scan > 0 && + kvm->arch.n_used_mmu_pages > 0) { + freed_pages = kvm_mmu_remove_some_alloc_mmu_pages(kvm, + &invalid_list); kvm_freed = kvm; } nr_to_scan--; + kvm_mmu_commit_zap_page(kvm, &invalid_list); spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); } @@ -2957,7 +3442,8 @@ static int mmu_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) spin_unlock(&kvm_lock); - return cache_count; +out: + return percpu_counter_read_positive(&kvm_total_used_mmu_pages); } static struct shrinker mmu_shrinker = { @@ -2978,6 +3464,7 @@ static void mmu_destroy_caches(void) void kvm_mmu_module_exit(void) { mmu_destroy_caches(); + percpu_counter_destroy(&kvm_total_used_mmu_pages); unregister_shrinker(&mmu_shrinker); } @@ -3000,6 +3487,9 @@ int kvm_mmu_module_init(void) if (!mmu_page_header_cache) goto nomem; + if (percpu_counter_init(&kvm_total_used_mmu_pages, 0)) + goto nomem; + register_shrinker(&mmu_shrinker); return 0; @@ -3074,7 +3564,7 @@ static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu, static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu) { - kvm_set_cr3(vcpu, vcpu->arch.cr3); + (void)kvm_set_cr3(vcpu, vcpu->arch.cr3); return 1; } @@ -3170,273 +3660,18 @@ int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]) } EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy); -#ifdef AUDIT - -static const char *audit_msg; - -static gva_t canonicalize(gva_t gva) -{ -#ifdef CONFIG_X86_64 - gva = (long long)(gva << 16) >> 16; +#ifdef CONFIG_KVM_MMU_AUDIT +#include "mmu_audit.c" +#else +static void mmu_audit_disable(void) { } #endif - return gva; -} - - -typedef void (*inspect_spte_fn) (struct kvm *kvm, u64 *sptep); - -static void __mmu_spte_walk(struct kvm *kvm, struct kvm_mmu_page *sp, - inspect_spte_fn fn) -{ - int i; - - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { - u64 ent = sp->spt[i]; - - if (is_shadow_present_pte(ent)) { - if (!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); - } else - fn(kvm, &sp->spt[i]); - } - } -} - -static void mmu_spte_walk(struct kvm_vcpu *vcpu, inspect_spte_fn fn) -{ - int i; - struct kvm_mmu_page *sp; - - if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) - return; - if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { - hpa_t root = vcpu->arch.mmu.root_hpa; - sp = page_header(root); - __mmu_spte_walk(vcpu->kvm, sp, fn); - return; - } - for (i = 0; i < 4; ++i) { - hpa_t root = vcpu->arch.mmu.pae_root[i]; - - if (root && VALID_PAGE(root)) { - root &= PT64_BASE_ADDR_MASK; - sp = page_header(root); - __mmu_spte_walk(vcpu->kvm, sp, fn); - } - } - return; -} - -static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte, - gva_t va, int level) -{ - u64 *pt = __va(page_pte & PT64_BASE_ADDR_MASK); - int i; - gva_t va_delta = 1ul << (PAGE_SHIFT + 9 * (level - 1)); - - for (i = 0; i < PT64_ENT_PER_PAGE; ++i, va += va_delta) { - u64 ent = pt[i]; - - if (ent == shadow_trap_nonpresent_pte) - continue; - - va = canonicalize(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" - " gva %lx gpa %llx hpa %llx ent %llx %d\n", - audit_msg, vcpu->arch.mmu.root_level, - va, gpa, hpa, ent, - is_shadow_present_pte(ent)); - else if (ent == shadow_notrap_nonpresent_pte - && !is_error_hpa(hpa)) - printk(KERN_ERR "audit: (%s) notrap shadow," - " valid guest gva %lx\n", audit_msg, va); - kvm_release_pfn_clean(pfn); - - } - } -} - -static void audit_mappings(struct kvm_vcpu *vcpu) -{ - unsigned i; - - if (vcpu->arch.mmu.root_level == 4) - audit_mappings_page(vcpu, vcpu->arch.mmu.root_hpa, 0, 4); - else - for (i = 0; i < 4; ++i) - if (vcpu->arch.mmu.pae_root[i] & PT_PRESENT_MASK) - audit_mappings_page(vcpu, - vcpu->arch.mmu.pae_root[i], - i << 30, - 2); -} - -static int count_rmaps(struct kvm_vcpu *vcpu) -{ - struct kvm *kvm = vcpu->kvm; - struct kvm_memslots *slots; - int nmaps = 0; - int i, j, k, idx; - - idx = srcu_read_lock(&kvm->srcu); - slots = kvm_memslots(kvm); - for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { - struct kvm_memory_slot *m = &slots->memslots[i]; - struct kvm_rmap_desc *d; - - for (j = 0; j < m->npages; ++j) { - unsigned long *rmapp = &m->rmap[j]; - - if (!*rmapp) - continue; - if (!(*rmapp & 1)) { - ++nmaps; - continue; - } - d = (struct kvm_rmap_desc *)(*rmapp & ~1ul); - while (d) { - for (k = 0; k < RMAP_EXT; ++k) - if (d->sptes[k]) - ++nmaps; - else - break; - d = d->more; - } - } - } - srcu_read_unlock(&kvm->srcu, idx); - return nmaps; -} - -void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) -{ - unsigned long *rmapp; - struct kvm_mmu_page *rev_sp; - gfn_t gfn; - - if (*sptep & PT_WRITABLE_MASK) { - rev_sp = page_header(__pa(sptep)); - gfn = rev_sp->gfns[sptep - rev_sp->spt]; - - if (!gfn_to_memslot(kvm, gfn)) { - if (!printk_ratelimit()) - return; - printk(KERN_ERR "%s: no memslot for gfn %ld\n", - audit_msg, gfn); - printk(KERN_ERR "%s: index %ld of sp (gfn=%lx)\n", - audit_msg, (long int)(sptep - rev_sp->spt), - rev_sp->gfn); - dump_stack(); - return; - } - - rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt], - rev_sp->role.level); - if (!*rmapp) { - if (!printk_ratelimit()) - return; - printk(KERN_ERR "%s: no rmap for writable spte %llx\n", - audit_msg, *sptep); - dump_stack(); - } - } - -} - -void audit_writable_sptes_have_rmaps(struct kvm_vcpu *vcpu) -{ - mmu_spte_walk(vcpu, inspect_spte_has_rmap); -} - -static void check_writable_mappings_rmap(struct kvm_vcpu *vcpu) -{ - struct kvm_mmu_page *sp; - int i; - list_for_each_entry(sp, &vcpu->kvm->arch.active_mmu_pages, link) { - u64 *pt = sp->spt; - - if (sp->role.level != PT_PAGE_TABLE_LEVEL) - continue; - - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { - u64 ent = pt[i]; - - if (!(ent & PT_PRESENT_MASK)) - continue; - if (!(ent & PT_WRITABLE_MASK)) - continue; - inspect_spte_has_rmap(vcpu->kvm, &pt[i]); - } - } - return; -} - -static void audit_rmap(struct kvm_vcpu *vcpu) -{ - check_writable_mappings_rmap(vcpu); - count_rmaps(vcpu); -} - -static void audit_write_protection(struct kvm_vcpu *vcpu) -{ - struct kvm_mmu_page *sp; - struct kvm_memory_slot *slot; - unsigned long *rmapp; - u64 *spte; - gfn_t gfn; - - list_for_each_entry(sp, &vcpu->kvm->arch.active_mmu_pages, link) { - if (sp->role.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]; - - 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); - } - } -} - -static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) +void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { - int olddbg = dbg; + ASSERT(vcpu); - dbg = 0; - audit_msg = msg; - audit_rmap(vcpu); - audit_write_protection(vcpu); - if (strcmp("pre pte write", audit_msg) != 0) - audit_mappings(vcpu); - audit_writable_sptes_have_rmaps(vcpu); - dbg = olddbg; + destroy_kvm_mmu(vcpu); + free_mmu_pages(vcpu); + mmu_free_memory_caches(vcpu); + mmu_audit_disable(); } - -#endif |