diff options
Diffstat (limited to 'arch/x86/kvm/mmu.c')
| -rw-r--r-- | arch/x86/kvm/mmu.c | 3428 |
1 files changed, 2179 insertions, 1249 deletions
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index fb8b376bf28..931467881da 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -18,9 +18,11 @@ * */ +#include "irq.h" #include "mmu.h" #include "x86.h" #include "kvm_cache_regs.h" +#include "cpuid.h" #include <linux/kvm_host.h> #include <linux/types.h> @@ -58,15 +60,6 @@ enum { AUDIT_POST_SYNC }; -char *audit_point_name[] = { - "pre page fault", - "post page fault", - "pre pte write", - "post pte write", - "pre sync", - "post sync" -}; - #undef MMU_DEBUG #ifdef MMU_DEBUG @@ -82,13 +75,10 @@ char *audit_point_name[] = { #endif #ifdef MMU_DEBUG -static int dbg = 0; +static bool dbg = 0; module_param(dbg, bool, 0644); #endif -static int oos_shadow = 1; -module_param(oos_shadow, bool, 0644); - #ifndef MMU_DEBUG #define ASSERT(x) do { } while (0) #else @@ -101,7 +91,7 @@ module_param(oos_shadow, bool, 0644); #define PTE_PREFETCH_NUM 8 -#define PT_FIRST_AVAIL_BITS_SHIFT 9 +#define PT_FIRST_AVAIL_BITS_SHIFT 10 #define PT64_SECOND_AVAIL_BITS_SHIFT 52 #define PT64_LEVEL_BITS 9 @@ -109,9 +99,6 @@ module_param(oos_shadow, bool, 0644); #define PT64_LEVEL_SHIFT(level) \ (PAGE_SHIFT + (level - 1) * PT64_LEVEL_BITS) -#define PT64_LEVEL_MASK(level) \ - (((1ULL << PT64_LEVEL_BITS) - 1) << PT64_LEVEL_SHIFT(level)) - #define PT64_INDEX(address, level)\ (((address) >> PT64_LEVEL_SHIFT(level)) & ((1 << PT64_LEVEL_BITS) - 1)) @@ -121,8 +108,6 @@ module_param(oos_shadow, bool, 0644); #define PT32_LEVEL_SHIFT(level) \ (PAGE_SHIFT + (level - 1) * PT32_LEVEL_BITS) -#define PT32_LEVEL_MASK(level) \ - (((1ULL << PT32_LEVEL_BITS) - 1) << PT32_LEVEL_SHIFT(level)) #define PT32_LVL_OFFSET_MASK(level) \ (PT32_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \ * PT32_LEVEL_BITS))) - 1)) @@ -148,10 +133,8 @@ module_param(oos_shadow, bool, 0644); (PAGE_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \ * PT32_LEVEL_BITS))) - 1)) -#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \ - | PT64_NX_MASK) - -#define RMAP_EXT 4 +#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \ + | shadow_x_mask | shadow_nx_mask) #define ACC_EXEC_MASK 1 #define ACC_WRITE_MASK PT_WRITABLE_MASK @@ -163,20 +146,24 @@ module_param(oos_shadow, bool, 0644); #define CREATE_TRACE_POINTS #include "mmutrace.h" -#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) +#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) +#define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1)) #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level) -struct kvm_rmap_desc { - u64 *sptes[RMAP_EXT]; - struct kvm_rmap_desc *more; +/* make pte_list_desc fit well in cache line */ +#define PTE_LIST_EXT 3 + +struct pte_list_desc { + u64 *sptes[PTE_LIST_EXT]; + struct pte_list_desc *more; }; struct kvm_shadow_walk_iterator { u64 addr; hpa_t shadow_addr; - int level; u64 *sptep; + int level; unsigned index; }; @@ -185,39 +172,134 @@ 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); +#define for_each_shadow_entry_lockless(_vcpu, _addr, _walker, spte) \ + for (shadow_walk_init(&(_walker), _vcpu, _addr); \ + shadow_walk_okay(&(_walker)) && \ + ({ spte = mmu_spte_get_lockless(_walker.sptep); 1; }); \ + __shadow_walk_next(&(_walker), 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_base_present_pte; static u64 __read_mostly shadow_nx_mask; static u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */ static u64 __read_mostly shadow_user_mask; static u64 __read_mostly shadow_accessed_mask; static u64 __read_mostly shadow_dirty_mask; +static u64 __read_mostly shadow_mmio_mask; -static inline u64 rsvd_bits(int s, int e) +static void mmu_spte_set(u64 *sptep, u64 spte); +static void mmu_free_roots(struct kvm_vcpu *vcpu); + +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask) { - return ((1ULL << (e - s + 1)) - 1) << s; + shadow_mmio_mask = mmio_mask; +} +EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); + +/* + * spte bits of bit 3 ~ bit 11 are used as low 9 bits of generation number, + * the bits of bits 52 ~ bit 61 are used as high 10 bits of generation + * number. + */ +#define MMIO_SPTE_GEN_LOW_SHIFT 3 +#define MMIO_SPTE_GEN_HIGH_SHIFT 52 + +#define MMIO_GEN_SHIFT 19 +#define MMIO_GEN_LOW_SHIFT 9 +#define MMIO_GEN_LOW_MASK ((1 << MMIO_GEN_LOW_SHIFT) - 1) +#define MMIO_GEN_MASK ((1 << MMIO_GEN_SHIFT) - 1) +#define MMIO_MAX_GEN ((1 << MMIO_GEN_SHIFT) - 1) + +static u64 generation_mmio_spte_mask(unsigned int gen) +{ + u64 mask; + + WARN_ON(gen > MMIO_MAX_GEN); + + mask = (gen & MMIO_GEN_LOW_MASK) << MMIO_SPTE_GEN_LOW_SHIFT; + mask |= ((u64)gen >> MMIO_GEN_LOW_SHIFT) << MMIO_SPTE_GEN_HIGH_SHIFT; + return mask; +} + +static unsigned int get_mmio_spte_generation(u64 spte) +{ + unsigned int gen; + + spte &= ~shadow_mmio_mask; + + gen = (spte >> MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_GEN_LOW_MASK; + gen |= (spte >> MMIO_SPTE_GEN_HIGH_SHIFT) << MMIO_GEN_LOW_SHIFT; + return gen; +} + +static unsigned int kvm_current_mmio_generation(struct kvm *kvm) +{ + /* + * Init kvm generation close to MMIO_MAX_GEN to easily test the + * code of handling generation number wrap-around. + */ + return (kvm_memslots(kvm)->generation + + MMIO_MAX_GEN - 150) & MMIO_GEN_MASK; +} + +static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn, + unsigned access) +{ + unsigned int gen = kvm_current_mmio_generation(kvm); + u64 mask = generation_mmio_spte_mask(gen); + + access &= ACC_WRITE_MASK | ACC_USER_MASK; + mask |= shadow_mmio_mask | access | gfn << PAGE_SHIFT; + + trace_mark_mmio_spte(sptep, gfn, access, gen); + mmu_spte_set(sptep, mask); +} + +static bool is_mmio_spte(u64 spte) +{ + return (spte & shadow_mmio_mask) == shadow_mmio_mask; +} + +static gfn_t get_mmio_spte_gfn(u64 spte) +{ + u64 mask = generation_mmio_spte_mask(MMIO_MAX_GEN) | shadow_mmio_mask; + return (spte & ~mask) >> PAGE_SHIFT; +} + +static unsigned get_mmio_spte_access(u64 spte) +{ + u64 mask = generation_mmio_spte_mask(MMIO_MAX_GEN) | shadow_mmio_mask; + return (spte & ~mask) & ~PAGE_MASK; +} + +static bool set_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, + pfn_t pfn, unsigned access) +{ + if (unlikely(is_noslot_pfn(pfn))) { + mark_mmio_spte(kvm, sptep, gfn, access); + return true; + } + + return false; } -void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte) +static bool check_mmio_spte(struct kvm *kvm, u64 spte) { - shadow_trap_nonpresent_pte = trap_pte; - shadow_notrap_nonpresent_pte = notrap_pte; + unsigned int kvm_gen, spte_gen; + + kvm_gen = kvm_current_mmio_generation(kvm); + spte_gen = get_mmio_spte_generation(spte); + + trace_check_mmio_spte(spte, kvm_gen, spte_gen); + return likely(kvm_gen == spte_gen); } -EXPORT_SYMBOL_GPL(kvm_mmu_set_nonpresent_ptes); -void kvm_mmu_set_base_ptes(u64 base_pte) +static inline u64 rsvd_bits(int s, int e) { - shadow_base_present_pte = base_pte; + return ((1ULL << (e - s + 1)) - 1) << s; } -EXPORT_SYMBOL_GPL(kvm_mmu_set_base_ptes); void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, u64 dirty_mask, u64 nx_mask, u64 x_mask) @@ -230,11 +312,6 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_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; @@ -247,8 +324,7 @@ static int is_nx(struct kvm_vcpu *vcpu) static int is_shadow_present_pte(u64 pte) { - return pte != shadow_trap_nonpresent_pte - && pte != shadow_notrap_nonpresent_pte; + return pte & PT_PRESENT_MASK && !is_mmio_spte(pte); } static int is_large_pte(u64 pte) @@ -256,16 +332,6 @@ 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; -} - static int is_rmap_spte(u64 pte) { return is_shadow_present_pte(pte); @@ -292,28 +358,183 @@ static gfn_t pse36_gfn_delta(u32 gpte) return (gpte & PT32_DIR_PSE36_MASK) << shift; } +#ifdef CONFIG_X86_64 static void __set_spte(u64 *sptep, u64 spte) { - set_64bit(sptep, spte); + *sptep = spte; } -static u64 __xchg_spte(u64 *sptep, u64 new_spte) +static void __update_clear_spte_fast(u64 *sptep, u64 spte) { -#ifdef CONFIG_X86_64 - return xchg(sptep, new_spte); + *sptep = spte; +} + +static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) +{ + return xchg(sptep, spte); +} + +static u64 __get_spte_lockless(u64 *sptep) +{ + return ACCESS_ONCE(*sptep); +} + +static bool __check_direct_spte_mmio_pf(u64 spte) +{ + /* It is valid if the spte is zapped. */ + return spte == 0ull; +} #else - u64 old_spte; +union split_spte { + struct { + u32 spte_low; + u32 spte_high; + }; + u64 spte; +}; - do { - old_spte = *sptep; - } while (cmpxchg64(sptep, old_spte, new_spte) != old_spte); +static void count_spte_clear(u64 *sptep, u64 spte) +{ + struct kvm_mmu_page *sp = page_header(__pa(sptep)); + + if (is_shadow_present_pte(spte)) + return; + + /* Ensure the spte is completely set before we increase the count */ + smp_wmb(); + sp->clear_spte_count++; +} + +static void __set_spte(u64 *sptep, u64 spte) +{ + union split_spte *ssptep, sspte; + + ssptep = (union split_spte *)sptep; + sspte = (union split_spte)spte; + + ssptep->spte_high = sspte.spte_high; + + /* + * If we map the spte from nonpresent to present, We should store + * the high bits firstly, then set present bit, so cpu can not + * fetch this spte while we are setting the spte. + */ + smp_wmb(); + + ssptep->spte_low = sspte.spte_low; +} + +static void __update_clear_spte_fast(u64 *sptep, u64 spte) +{ + union split_spte *ssptep, sspte; + + ssptep = (union split_spte *)sptep; + sspte = (union split_spte)spte; + + ssptep->spte_low = sspte.spte_low; + + /* + * If we map the spte from present to nonpresent, we should clear + * present bit firstly to avoid vcpu fetch the old high bits. + */ + smp_wmb(); + + ssptep->spte_high = sspte.spte_high; + count_spte_clear(sptep, spte); +} + +static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) +{ + union split_spte *ssptep, sspte, orig; + + ssptep = (union split_spte *)sptep; + sspte = (union split_spte)spte; + + /* xchg acts as a barrier before the setting of the high bits */ + orig.spte_low = xchg(&ssptep->spte_low, sspte.spte_low); + orig.spte_high = ssptep->spte_high; + ssptep->spte_high = sspte.spte_high; + count_spte_clear(sptep, spte); + + return orig.spte; +} + +/* + * The idea using the light way get the spte on x86_32 guest is from + * gup_get_pte(arch/x86/mm/gup.c). + * + * An spte tlb flush may be pending, because kvm_set_pte_rmapp + * coalesces them and we are running out of the MMU lock. Therefore + * we need to protect against in-progress updates of the spte. + * + * Reading the spte while an update is in progress may get the old value + * for the high part of the spte. The race is fine for a present->non-present + * change (because the high part of the spte is ignored for non-present spte), + * but for a present->present change we must reread the spte. + * + * All such changes are done in two steps (present->non-present and + * non-present->present), hence it is enough to count the number of + * present->non-present updates: if it changed while reading the spte, + * we might have hit the race. This is done using clear_spte_count. + */ +static u64 __get_spte_lockless(u64 *sptep) +{ + struct kvm_mmu_page *sp = page_header(__pa(sptep)); + union split_spte spte, *orig = (union split_spte *)sptep; + int count; + +retry: + count = sp->clear_spte_count; + smp_rmb(); - return old_spte; + spte.spte_low = orig->spte_low; + smp_rmb(); + + spte.spte_high = orig->spte_high; + smp_rmb(); + + if (unlikely(spte.spte_low != orig->spte_low || + count != sp->clear_spte_count)) + goto retry; + + return spte.spte; +} + +static bool __check_direct_spte_mmio_pf(u64 spte) +{ + union split_spte sspte = (union split_spte)spte; + u32 high_mmio_mask = shadow_mmio_mask >> 32; + + /* It is valid if the spte is zapped. */ + if (spte == 0ull) + return true; + + /* It is valid if the spte is being zapped. */ + if (sspte.spte_low == 0ull && + (sspte.spte_high & high_mmio_mask) == high_mmio_mask) + return true; + + return false; +} #endif + +static bool spte_is_locklessly_modifiable(u64 spte) +{ + return (spte & (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE)) == + (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE); } static bool spte_has_volatile_bits(u64 spte) { + /* + * Always atomicly update spte if it can be updated + * out of mmu-lock, it can ensure dirty bit is not lost, + * also, it can help us to get a stable is_writable_pte() + * to ensure tlb flush is not missed. + */ + if (spte_is_locklessly_modifiable(spte)) + return true; + if (!shadow_accessed_mask) return false; @@ -332,30 +553,138 @@ 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) +/* Rules for using mmu_spte_set: + * Set the sptep from nonpresent to present. + * Note: the sptep being assigned *must* be either not present + * or in a state where the hardware will not attempt to update + * the spte. + */ +static void mmu_spte_set(u64 *sptep, u64 new_spte) { - u64 mask, old_spte = *sptep; + WARN_ON(is_shadow_present_pte(*sptep)); + __set_spte(sptep, new_spte); +} - WARN_ON(!is_rmap_spte(new_spte)); +/* Rules for using mmu_spte_update: + * Update the state bits, it means the mapped pfn is not changged. + * + * Whenever we overwrite a writable spte with a read-only one we + * should flush remote TLBs. Otherwise rmap_write_protect + * will find a read-only spte, even though the writable spte + * might be cached on a CPU's TLB, the return value indicates this + * case. + */ +static bool mmu_spte_update(u64 *sptep, u64 new_spte) +{ + u64 old_spte = *sptep; + bool ret = false; - new_spte |= old_spte & shadow_dirty_mask; + WARN_ON(!is_rmap_spte(new_spte)); - mask = shadow_accessed_mask; - if (is_writable_pte(old_spte)) - mask |= shadow_dirty_mask; + if (!is_shadow_present_pte(old_spte)) { + mmu_spte_set(sptep, new_spte); + return ret; + } - if (!spte_has_volatile_bits(old_spte) || (new_spte & mask) == mask) - __set_spte(sptep, new_spte); + if (!spte_has_volatile_bits(old_spte)) + __update_clear_spte_fast(sptep, new_spte); else - old_spte = __xchg_spte(sptep, new_spte); + old_spte = __update_clear_spte_slow(sptep, new_spte); + + /* + * For the spte updated out of mmu-lock is safe, since + * we always atomicly update it, see the comments in + * spte_has_volatile_bits(). + */ + if (spte_is_locklessly_modifiable(old_spte) && + !is_writable_pte(new_spte)) + ret = true; if (!shadow_accessed_mask) - return; + return ret; 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)); + + return ret; +} + +/* + * Rules for using mmu_spte_clear_track_bits: + * It sets the sptep from present to nonpresent, and track the + * state bits, it is used to clear the last level sptep. + */ +static int mmu_spte_clear_track_bits(u64 *sptep) +{ + pfn_t pfn; + u64 old_spte = *sptep; + + if (!spte_has_volatile_bits(old_spte)) + __update_clear_spte_fast(sptep, 0ull); + else + old_spte = __update_clear_spte_slow(sptep, 0ull); + + if (!is_rmap_spte(old_spte)) + return 0; + + pfn = spte_to_pfn(old_spte); + + /* + * KVM does not hold the refcount of the page used by + * kvm mmu, before reclaiming the page, we should + * unmap it from mmu first. + */ + WARN_ON(!kvm_is_mmio_pfn(pfn) && !page_count(pfn_to_page(pfn))); + + 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); + return 1; +} + +/* + * Rules for using mmu_spte_clear_no_track: + * Directly clear spte without caring the state bits of sptep, + * it is used to set the upper level spte. + */ +static void mmu_spte_clear_no_track(u64 *sptep) +{ + __update_clear_spte_fast(sptep, 0ull); +} + +static u64 mmu_spte_get_lockless(u64 *sptep) +{ + return __get_spte_lockless(sptep); +} + +static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu) +{ + /* + * Prevent page table teardown by making any free-er wait during + * kvm_flush_remote_tlbs() IPI to all active vcpus. + */ + local_irq_disable(); + vcpu->mode = READING_SHADOW_PAGE_TABLES; + /* + * Make sure a following spte read is not reordered ahead of the write + * to vcpu->mode. + */ + smp_mb(); +} + +static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu) +{ + /* + * Make sure the write to vcpu->mode is not reordered in front of + * reads to sptes. If it does, kvm_commit_zap_page() can see us + * OUTSIDE_GUEST_MODE and proceed to free the shadow page table. + */ + smp_mb(); + vcpu->mode = OUTSIDE_GUEST_MODE; + local_irq_enable(); } static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, @@ -374,6 +703,11 @@ static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, return 0; } +static int mmu_memory_cache_free_objects(struct kvm_mmu_memory_cache *cache) +{ + return cache->nobjs; +} + static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc, struct kmem_cache *cache) { @@ -384,15 +718,15 @@ static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc, static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, int min) { - struct page *page; + void *page; if (cache->nobjs >= min) return 0; while (cache->nobjs < ARRAY_SIZE(cache->objects)) { - page = alloc_page(GFP_KERNEL); + page = (void *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; - cache->objects[cache->nobjs++] = page_address(page); + cache->objects[cache->nobjs++] = page; } return 0; } @@ -407,12 +741,8 @@ static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu) { 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); @@ -426,15 +756,14 @@ out: 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); } -static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc, - size_t size) +static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) { void *p; @@ -443,26 +772,14 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc, return p; } -static struct kvm_pte_chain *mmu_alloc_pte_chain(struct kvm_vcpu *vcpu) +static struct pte_list_desc *mmu_alloc_pte_list_desc(struct kvm_vcpu *vcpu) { - return mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_chain_cache, - sizeof(struct kvm_pte_chain)); + return mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_list_desc_cache); } -static void mmu_free_pte_chain(struct kvm_pte_chain *pc) +static void mmu_free_pte_list_desc(struct pte_list_desc *pte_list_desc) { - kmem_cache_free(pte_chain_cache, pc); -} - -static struct kvm_rmap_desc *mmu_alloc_rmap_desc(struct kvm_vcpu *vcpu) -{ - 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) @@ -482,47 +799,48 @@ static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn) } /* - * Return the pointer to the largepage write count for a given - * gfn, handling slots that are not large page aligned. + * Return the pointer to the large page information for a given gfn, + * handling slots that are not large page aligned. */ -static int *slot_largepage_idx(gfn_t gfn, - struct kvm_memory_slot *slot, - int level) +static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, + struct kvm_memory_slot *slot, + int level) { unsigned long idx; - idx = (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - - (slot->base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); - return &slot->lpage_info[level - 2][idx].write_count; + idx = gfn_to_index(gfn, slot->base_gfn, level); + return &slot->arch.lpage_info[level - 2][idx]; } static void account_shadowed(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *slot; - int *write_count; + struct kvm_lpage_info *linfo; int i; 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); - *write_count += 1; + 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) { struct kvm_memory_slot *slot; - int *write_count; + struct kvm_lpage_info *linfo; int i; 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); - *write_count -= 1; - WARN_ON(*write_count < 0); + linfo = lpage_info_slot(gfn, slot, i); + linfo->write_count -= 1; + WARN_ON(linfo->write_count < 0); } + kvm->arch.indirect_shadow_pages--; } static int has_wrprotected_page(struct kvm *kvm, @@ -530,12 +848,12 @@ static int has_wrprotected_page(struct kvm *kvm, int level) { struct kvm_memory_slot *slot; - int *largepage_idx; + struct kvm_lpage_info *linfo; slot = gfn_to_memslot(kvm, gfn); if (slot) { - largepage_idx = slot_largepage_idx(gfn, slot, level); - return *largepage_idx; + linfo = lpage_info_slot(gfn, slot, level); + return linfo->write_count; } return 1; @@ -559,22 +877,35 @@ static int host_mapping_level(struct kvm *kvm, gfn_t gfn) return ret; } -static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) +static struct kvm_memory_slot * +gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, + bool no_dirty_log) { struct kvm_memory_slot *slot; - int host_level, level, max_level; - slot = gfn_to_memslot(vcpu->kvm, large_gfn); - if (slot && slot->dirty_bitmap) - return PT_PAGE_TABLE_LEVEL; + 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 bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn) +{ + return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true); +} + +static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) +{ + int host_level, level, max_level; host_level = host_mapping_level(vcpu->kvm, large_gfn); if (host_level == PT_PAGE_TABLE_LEVEL) return host_level; - max_level = kvm_x86_ops->get_lpage_level() < host_level ? - kvm_x86_ops->get_lpage_level() : host_level; + max_level = min(kvm_x86_ops->get_lpage_level(), host_level); for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level) if (has_wrprotected_page(vcpu->kvm, large_gfn, level)) @@ -584,68 +915,42 @@ 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; - unsigned long idx; - - slot = gfn_to_memslot(kvm, gfn); - if (likely(level == PT_PAGE_TABLE_LEVEL)) - return &slot->rmap[gfn - slot->base_gfn]; - - idx = (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - - (slot->base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); - - return &slot->lpage_info[level - 2][idx].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) @@ -655,59 +960,52 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) 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 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; @@ -715,198 +1013,381 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) 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(); } } -static int set_spte_track_bits(u64 *sptep, u64 new_spte) +typedef void (*pte_list_walk_fn) (u64 *spte); +static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn) { - pfn_t pfn; - u64 old_spte = *sptep; + struct pte_list_desc *desc; + int i; - if (!spte_has_volatile_bits(old_spte)) - __set_spte(sptep, new_spte); - else - old_spte = __xchg_spte(sptep, new_spte); + if (!*pte_list) + return; - if (!is_rmap_spte(old_spte)) - return 0; + if (!(*pte_list & 1)) + return fn((u64 *)*pte_list); - 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); - return 1; + 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; + } } -static void drop_spte(struct kvm *kvm, u64 *sptep, u64 new_spte) +static unsigned long *__gfn_to_rmap(gfn_t gfn, int level, + struct kvm_memory_slot *slot) { - if (set_spte_track_bits(sptep, new_spte)) - rmap_remove(kvm, sptep); + unsigned long idx; + + idx = gfn_to_index(gfn, slot->base_gfn, level); + return &slot->arch.rmap[level - PT_PAGE_TABLE_LEVEL][idx]; } -static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte) +/* + * 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_rmap_desc *desc; - u64 *prev_spte; - int i; + struct kvm_memory_slot *slot; - if (!*rmapp) - return NULL; - else if (!(*rmapp & 1)) { - if (!spte) - return (u64 *)*rmapp; + slot = gfn_to_memslot(kvm, gfn); + return __gfn_to_rmap(gfn, level, slot); +} + +static bool rmap_can_add(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu_memory_cache *cache; + + cache = &vcpu->arch.mmu_pte_list_desc_cache; + return mmu_memory_cache_free_objects(cache); +} + +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 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); +} + +/* + * Used by the following functions to iterate through the sptes linked by a + * rmap. All fields are private and not assumed to be used outside. + */ +struct rmap_iterator { + /* private fields */ + struct pte_list_desc *desc; /* holds the sptep if not NULL */ + int pos; /* index of the sptep */ +}; + +/* + * Iteration must be started by this function. This should also be used after + * removing/dropping sptes from the rmap link because in such cases the + * information in the itererator may not be valid. + * + * Returns sptep if found, NULL otherwise. + */ +static u64 *rmap_get_first(unsigned long rmap, struct rmap_iterator *iter) +{ + if (!rmap) return NULL; + + if (!(rmap & 1)) { + iter->desc = NULL; + return (u64 *)rmap; } - 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]; + + iter->desc = (struct pte_list_desc *)(rmap & ~1ul); + iter->pos = 0; + return iter->desc->sptes[iter->pos]; +} + +/* + * Must be used with a valid iterator: e.g. after rmap_get_first(). + * + * Returns sptep if found, NULL otherwise. + */ +static u64 *rmap_get_next(struct rmap_iterator *iter) +{ + if (iter->desc) { + if (iter->pos < PTE_LIST_EXT - 1) { + u64 *sptep; + + ++iter->pos; + sptep = iter->desc->sptes[iter->pos]; + if (sptep) + return sptep; + } + + iter->desc = iter->desc->more; + + if (iter->desc) { + iter->pos = 0; + /* desc->sptes[0] cannot be NULL */ + return iter->desc->sptes[iter->pos]; } - desc = desc->more; } + return NULL; } -static int rmap_write_protect(struct kvm *kvm, u64 gfn) +static void drop_spte(struct kvm *kvm, u64 *sptep) +{ + if (mmu_spte_clear_track_bits(sptep)) + rmap_remove(kvm, sptep); +} + + +static bool __drop_large_spte(struct kvm *kvm, u64 *sptep) +{ + if (is_large_pte(*sptep)) { + WARN_ON(page_header(__pa(sptep))->role.level == + PT_PAGE_TABLE_LEVEL); + drop_spte(kvm, sptep); + --kvm->stat.lpages; + return true; + } + + return false; +} + +static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) +{ + if (__drop_large_spte(vcpu->kvm, sptep)) + kvm_flush_remote_tlbs(vcpu->kvm); +} + +/* + * Write-protect on the specified @sptep, @pt_protect indicates whether + * spte write-protection is caused by protecting shadow page table. + * + * Note: write protection is difference between drity logging and spte + * protection: + * - for dirty logging, the spte can be set to writable at anytime if + * its dirty bitmap is properly set. + * - for spte protection, the spte can be writable only after unsync-ing + * shadow page. + * + * Return true if tlb need be flushed. + */ +static bool spte_write_protect(struct kvm *kvm, u64 *sptep, bool pt_protect) +{ + u64 spte = *sptep; + + if (!is_writable_pte(spte) && + !(pt_protect && spte_is_locklessly_modifiable(spte))) + return false; + + rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep); + + if (pt_protect) + spte &= ~SPTE_MMU_WRITEABLE; + spte = spte & ~PT_WRITABLE_MASK; + + return mmu_spte_update(sptep, spte); +} + +static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, + bool pt_protect) +{ + u64 *sptep; + struct rmap_iterator iter; + bool flush = false; + + for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { + BUG_ON(!(*sptep & PT_PRESENT_MASK)); + + flush |= spte_write_protect(kvm, sptep, pt_protect); + sptep = rmap_get_next(&iter); + } + + return flush; +} + +/** + * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages + * @kvm: kvm instance + * @slot: slot to protect + * @gfn_offset: start of the BITS_PER_LONG pages we care about + * @mask: indicates which pages we should protect + * + * Used when we do not need to care about huge page mappings: e.g. during dirty + * logging we do not have any such mappings. + */ +void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn_offset, unsigned long mask) { unsigned long *rmapp; - u64 *spte; - int i, write_protected = 0; - - rmapp = gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL); - - spte = rmap_next(kvm, rmapp, NULL); - while (spte) { - BUG_ON(!spte); - BUG_ON(!(*spte & PT_PRESENT_MASK)); - rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte); - if (is_writable_pte(*spte)) { - update_spte(spte, *spte & ~PT_WRITABLE_MASK); - write_protected = 1; - } - spte = rmap_next(kvm, rmapp, spte); + + while (mask) { + rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), + PT_PAGE_TABLE_LEVEL, slot); + __rmap_write_protect(kvm, rmapp, false); + + /* clear the first set bit */ + mask &= mask - 1; } +} - /* check for huge page mappings */ - for (i = PT_DIRECTORY_LEVEL; +static bool rmap_write_protect(struct kvm *kvm, u64 gfn) +{ + struct kvm_memory_slot *slot; + unsigned long *rmapp; + int i; + bool write_protected = false; + + slot = gfn_to_memslot(kvm, gfn); + + for (i = PT_PAGE_TABLE_LEVEL; i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - rmapp = gfn_to_rmap(kvm, gfn, i); - spte = rmap_next(kvm, rmapp, NULL); - while (spte) { - BUG_ON(!spte); - BUG_ON(!(*spte & PT_PRESENT_MASK)); - BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)); - pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn); - if (is_writable_pte(*spte)) { - drop_spte(kvm, spte, - shadow_trap_nonpresent_pte); - --kvm->stat.lpages; - spte = NULL; - write_protected = 1; - } - spte = rmap_next(kvm, rmapp, spte); - } + rmapp = __gfn_to_rmap(gfn, i, slot); + write_protected |= __rmap_write_protect(kvm, rmapp, true); } return write_protected; } static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, - unsigned long data) + struct kvm_memory_slot *slot, unsigned long data) { - u64 *spte; + u64 *sptep; + struct rmap_iterator iter; int need_tlb_flush = 0; - while ((spte = rmap_next(kvm, rmapp, NULL))) { - BUG_ON(!(*spte & PT_PRESENT_MASK)); - rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", spte, *spte); - drop_spte(kvm, spte, shadow_trap_nonpresent_pte); + while ((sptep = rmap_get_first(*rmapp, &iter))) { + BUG_ON(!(*sptep & PT_PRESENT_MASK)); + rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", sptep, *sptep); + + drop_spte(kvm, sptep); need_tlb_flush = 1; } + return need_tlb_flush; } static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, - unsigned long data) + struct kvm_memory_slot *slot, unsigned long data) { + u64 *sptep; + struct rmap_iterator iter; int need_flush = 0; - u64 *spte, new_spte; + u64 new_spte; pte_t *ptep = (pte_t *)data; pfn_t new_pfn; WARN_ON(pte_huge(*ptep)); new_pfn = pte_pfn(*ptep); - spte = rmap_next(kvm, rmapp, NULL); - while (spte) { - BUG_ON(!is_shadow_present_pte(*spte)); - rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", spte, *spte); + + for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { + BUG_ON(!is_shadow_present_pte(*sptep)); + rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", sptep, *sptep); + need_flush = 1; + if (pte_write(*ptep)) { - drop_spte(kvm, spte, shadow_trap_nonpresent_pte); - spte = rmap_next(kvm, rmapp, NULL); + drop_spte(kvm, sptep); + sptep = rmap_get_first(*rmapp, &iter); } else { - new_spte = *spte &~ (PT64_BASE_ADDR_MASK); + new_spte = *sptep & ~PT64_BASE_ADDR_MASK; new_spte |= (u64)new_pfn << PAGE_SHIFT; new_spte &= ~PT_WRITABLE_MASK; new_spte &= ~SPTE_HOST_WRITEABLE; new_spte &= ~shadow_accessed_mask; - set_spte_track_bits(spte, new_spte); - spte = rmap_next(kvm, rmapp, spte); + + mmu_spte_clear_track_bits(sptep); + mmu_spte_set(sptep, new_spte); + sptep = rmap_get_next(&iter); } } + if (need_flush) kvm_flush_remote_tlbs(kvm); return 0; } -static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, - unsigned long data, - int (*handler)(struct kvm *kvm, unsigned long *rmapp, - unsigned long data)) +static int kvm_handle_hva_range(struct kvm *kvm, + unsigned long start, + unsigned long end, + unsigned long data, + int (*handler)(struct kvm *kvm, + unsigned long *rmapp, + struct kvm_memory_slot *slot, + unsigned long data)) { - int i, j; - int ret; - int retval = 0; + int j; + int ret = 0; struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; slots = kvm_memslots(kvm); - for (i = 0; i < slots->nmemslots; i++) { - struct kvm_memory_slot *memslot = &slots->memslots[i]; - unsigned long start = memslot->userspace_addr; - unsigned long end; + kvm_for_each_memslot(memslot, slots) { + unsigned long hva_start, hva_end; + gfn_t gfn_start, gfn_end; + + hva_start = max(start, memslot->userspace_addr); + hva_end = min(end, memslot->userspace_addr + + (memslot->npages << PAGE_SHIFT)); + if (hva_start >= hva_end) + continue; + /* + * {gfn(page) | page intersects with [hva_start, hva_end)} = + * {gfn_start, gfn_start+1, ..., gfn_end-1}. + */ + gfn_start = hva_to_gfn_memslot(hva_start, memslot); + gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); - end = start + (memslot->npages << PAGE_SHIFT); - if (hva >= start && hva < end) { - gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT; + for (j = PT_PAGE_TABLE_LEVEL; + j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) { + unsigned long idx, idx_end; + unsigned long *rmapp; - ret = handler(kvm, &memslot->rmap[gfn_offset], data); + /* + * {idx(page_j) | page_j intersects with + * [hva_start, hva_end)} = {idx, idx+1, ..., idx_end}. + */ + idx = gfn_to_index(gfn_start, memslot->base_gfn, j); + idx_end = gfn_to_index(gfn_end - 1, memslot->base_gfn, j); - for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) { - unsigned long idx; - int sh; + rmapp = __gfn_to_rmap(gfn_start, j, memslot); - 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); - } - trace_kvm_age_page(hva, memslot, ret); - retval |= ret; + for (; idx <= idx_end; ++idx) + ret |= handler(kvm, rmapp++, memslot, data); } } - return retval; + return ret; +} + +static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, + unsigned long data, + int (*handler)(struct kvm *kvm, unsigned long *rmapp, + struct kvm_memory_slot *slot, + unsigned long data)) +{ + return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler); } int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) @@ -914,39 +1395,77 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp); } +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +{ + return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); +} + void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) { kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp); } static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, - unsigned long data) + struct kvm_memory_slot *slot, unsigned long data) { - u64 *spte; + u64 *sptep; + struct rmap_iterator uninitialized_var(iter); int young = 0; /* - * Emulate the accessed bit for EPT, by checking if this page has + * In case of absence of EPT Access and Dirty Bits supports, + * emulate the accessed bit for EPT, by checking if this page has * an EPT mapping, and clearing it if it does. On the next access, * a new EPT mapping will be established. * This has some overhead, but not as much as the cost of swapping * out actively used pages or breaking up actively used hugepages. */ + if (!shadow_accessed_mask) { + young = kvm_unmap_rmapp(kvm, rmapp, slot, data); + goto out; + } + + for (sptep = rmap_get_first(*rmapp, &iter); sptep; + sptep = rmap_get_next(&iter)) { + BUG_ON(!is_shadow_present_pte(*sptep)); + + if (*sptep & shadow_accessed_mask) { + young = 1; + clear_bit((ffs(shadow_accessed_mask) - 1), + (unsigned long *)sptep); + } + } +out: + /* @data has hva passed to kvm_age_hva(). */ + trace_kvm_age_page(data, slot, young); + return young; +} + +static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, + struct kvm_memory_slot *slot, unsigned long data) +{ + u64 *sptep; + struct rmap_iterator iter; + int young = 0; + + /* + * If there's no access bit in the secondary pte set by the + * hardware it's up to gup-fast/gup to set the access bit in + * the primary pte or in the page structure. + */ if (!shadow_accessed_mask) - return kvm_unmap_rmapp(kvm, rmapp, data); - - spte = rmap_next(kvm, rmapp, NULL); - while (spte) { - int _young; - u64 _spte = *spte; - BUG_ON(!(_spte & PT_PRESENT_MASK)); - _young = _spte & PT_ACCESSED_MASK; - if (_young) { + goto out; + + for (sptep = rmap_get_first(*rmapp, &iter); sptep; + sptep = rmap_get_next(&iter)) { + BUG_ON(!is_shadow_present_pte(*sptep)); + + if (*sptep & shadow_accessed_mask) { young = 1; - clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte); + break; } - spte = rmap_next(kvm, rmapp, spte); } +out: return young; } @@ -961,13 +1480,18 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); - kvm_unmap_rmapp(vcpu->kvm, rmapp, 0); + kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, 0); kvm_flush_remote_tlbs(vcpu->kvm); } int kvm_age_hva(struct kvm *kvm, unsigned long hva) { - return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp); + return kvm_handle_hva(kvm, hva, hva, kvm_age_rmapp); +} + +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) +{ + return kvm_handle_hva(kvm, hva, 0, kvm_test_age_rmapp); } #ifdef MMU_DEBUG @@ -998,16 +1522,15 @@ static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr) percpu_counter_add(&kvm_total_used_mmu_pages, nr); } -static void kvm_mmu_free_page(struct kvm *kvm, struct kvm_mmu_page *sp) +static void kvm_mmu_free_page(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((unsigned long)sp->spt); if (!sp->role.direct) - __free_page(virt_to_page(sp->gfns)); + 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) @@ -1015,134 +1538,63 @@ static unsigned kvm_page_table_hashfn(gfn_t gfn) return gfn & ((1 << KVM_MMU_HASH_SHIFT) - 1); } -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->multimapped = 0; - sp->parent_pte = parent_pte; - kvm_mod_used_mmu_pages(vcpu->kvm, +1); - return sp; -} - 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; + mmu_page_remove_parent_pte(sp, parent_pte); + mmu_spte_clear_no_track(parent_pte); +} - if (!sp->multimapped && sp->parent_pte) { - parent_sp = page_header(__pa(sp->parent_pte)); - fn(parent_sp, sp->parent_pte); - return; - } +static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, + u64 *parent_pte, int direct) +{ + struct kvm_mmu_page *sp; - 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]; + sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache); + sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache); + if (!direct) + sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache); + set_page_private(virt_to_page(sp->spt), (unsigned long)sp); - if (!spte) - break; - parent_sp = page_header(__pa(spte)); - fn(parent_sp, spte); - } + /* + * The active_mmu_pages list is the FIFO list, do not move the + * page until it is zapped. kvm_zap_obsolete_pages depends on + * this feature. See the comments in kvm_zap_obsolete_pages(). + */ + list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); + 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; @@ -1151,17 +1603,8 @@ static void mark_unsync(struct kvm_mmu_page *sp, u64 *spte) 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, bool clear_unsync) + struct kvm_mmu_page *sp) { return 1; } @@ -1170,6 +1613,13 @@ static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { } +static void nonpaging_update_pte(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp, u64 *spte, + const void *pte) +{ + WARN_ON(1); +} + #define KVM_PAGE_ARRAY_NR 16 struct kvm_mmu_pages { @@ -1180,11 +1630,6 @@ struct kvm_mmu_pages { unsigned int nr; }; -#define for_each_unsync_children(bitmap, idx) \ - for (idx = find_first_bit(bitmap, 512); \ - idx < 512; \ - idx = find_next_bit(bitmap, 512, idx+1)) - static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp, int idx) { @@ -1206,7 +1651,7 @@ 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) { + for_each_set_bit(i, sp->unsync_child_bitmap, 512) { struct kvm_mmu_page *child; u64 ent = sp->spt[i]; @@ -1268,16 +1713,24 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, 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 +/* + * NOTE: we should pay more attention on the zapped-obsolete page + * (is_obsolete_sp(sp) && sp->role.invalid) when you do hash list walk + * since it has been deleted from active_mmu_pages but still can be found + * at hast list. + * + * for_each_gfn_indirect_valid_sp has skipped that kind of page and + * kvm_mmu_get_page(), the only user of for_each_gfn_sp(), has skipped + * all the obsolete pages. + */ +#define for_each_gfn_sp(_kvm, _sp, _gfn) \ + hlist_for_each_entry(_sp, \ + &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \ + if ((_sp)->gfn != (_gfn)) {} else -#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 +#define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn) \ + for_each_gfn_sp(_kvm, _sp, _gfn) \ + if ((_sp)->role.direct || (_sp)->role.invalid) {} else /* @sp->gfn should be write-protected at the call site */ static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, @@ -1291,7 +1744,7 @@ static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (clear_unsync) kvm_unlink_unsync_page(vcpu->kvm, sp); - if (vcpu->arch.mmu.sync_page(vcpu, sp, clear_unsync)) { + if (vcpu->arch.mmu.sync_page(vcpu, sp)) { kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); return 1; } @@ -1313,6 +1766,13 @@ static int kvm_sync_page_transient(struct kvm_vcpu *vcpu, return ret; } +#ifdef CONFIG_KVM_MMU_AUDIT +#include "mmu_audit.c" +#else +static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { } +static void mmu_audit_disable(void) { } +#endif + static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { @@ -1323,21 +1783,20 @@ static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, 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) { + for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) { if (!s->unsync) continue; WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL); + kvm_unlink_unsync_page(vcpu->kvm, s); if ((s->role.cr4_pae != !!is_pae(vcpu)) || - (vcpu->arch.mmu.sync_page(vcpu, s, true))) { + (vcpu->arch.mmu.sync_page(vcpu, s))) { kvm_mmu_prepare_zap_page(vcpu->kvm, s, &invalid_list); continue; } - kvm_unlink_unsync_page(vcpu->kvm, s); flush = true; } @@ -1416,7 +1875,7 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, kvm_mmu_pages_init(parent, &parents, &pages); while (mmu_unsync_walk(parent, &pages)) { - int protected = 0; + bool protected = false; for_each_sp(pages, sp, parents, i) protected |= rmap_write_protect(vcpu->kvm, sp->gfn); @@ -1434,6 +1893,31 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, } } +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 void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp) +{ + sp->write_flooding_count = 0; +} + +static void clear_sp_write_flooding_count(u64 *spte) +{ + struct kvm_mmu_page *sp = page_header(__pa(spte)); + + __clear_sp_write_flooding_count(sp); +} + +static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); +} + static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gaddr, @@ -1445,7 +1929,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, union kvm_mmu_page_role role; unsigned quadrant; struct kvm_mmu_page *sp; - struct hlist_node *node; bool need_sync = false; role = vcpu->arch.mmu.base_role; @@ -1460,7 +1943,10 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; role.quadrant = quadrant; } - for_each_gfn_sp(vcpu->kvm, sp, gfn, node) { + for_each_gfn_sp(vcpu->kvm, sp, gfn) { + if (is_obsolete_sp(vcpu->kvm, sp)) + continue; + if (!need_sync && sp->unsync) need_sync = true; @@ -1477,6 +1963,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, } else if (sp->unsync) kvm_mmu_mark_parents_unsync(sp); + __clear_sp_write_flooding_count(sp); trace_kvm_mmu_get_page(sp, false); return sp; } @@ -1496,10 +1983,8 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, 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); + sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; + init_shadow_page_table(sp); trace_kvm_mmu_get_page(sp, true); return sp; } @@ -1531,37 +2016,42 @@ static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator) 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) +static void __shadow_walk_next(struct kvm_shadow_walk_iterator *iterator, + u64 spte) { - iterator->shadow_addr = *iterator->sptep & PT64_BASE_ADDR_MASK; + if (is_last_spte(spte, iterator->level)) { + iterator->level = 0; + return; + } + + iterator->shadow_addr = spte & PT64_BASE_ADDR_MASK; --iterator->level; } -static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp) +static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator) { - u64 spte; - - spte = __pa(sp->spt) - | PT_PRESENT_MASK | PT_ACCESSED_MASK - | PT_WRITABLE_MASK | PT_USER_MASK; - __set_spte(sptep, spte); + return __shadow_walk_next(iterator, *iterator->sptep); } -static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) +static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp, bool accessed) { - if (is_large_pte(*sptep)) { - drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte); - kvm_flush_remote_tlbs(vcpu->kvm); - } + u64 spte; + + BUILD_BUG_ON(VMX_EPT_READABLE_MASK != PT_PRESENT_MASK || + VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); + + spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK | + shadow_user_mask | shadow_x_mask; + + if (accessed) + spte |= shadow_accessed_mask; + + mmu_spte_set(sptep, spte); } static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, @@ -1581,72 +2071,57 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, 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 kvm_mmu_page_unlink_children(struct kvm *kvm, - struct kvm_mmu_page *sp) +static bool mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, + u64 *spte) { - 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); - } + 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); + if (is_large_pte(pte)) + --kvm->stat.lpages; + } else { + child = page_header(pte & PT64_BASE_ADDR_MASK); + drop_parent_pte(child, spte); } - pt[i] = shadow_trap_nonpresent_pte; + return true; } + + if (is_mmio_spte(pte)) + mmu_spte_clear_no_track(spte); + + return false; } -static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte) +static void kvm_mmu_page_unlink_children(struct kvm *kvm, + struct kvm_mmu_page *sp) { - mmu_page_remove_parent_pte(sp, parent_pte); + unsigned i; + + for (i = 0; i < PT64_ENT_PER_PAGE; ++i) + mmu_page_zap_pte(kvm, sp, sp->spt + i); } -static void kvm_mmu_reset_last_pte_updated(struct kvm *kvm) +static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte) { - int i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) - vcpu->arch.last_pte_updated = NULL; + mmu_page_remove_parent_pte(sp, parent_pte); } static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) { - u64 *parent_pte; - - while (sp->multimapped || sp->parent_pte) { - if (!sp->multimapped) - parent_pte = sp->parent_pte; - else { - struct kvm_pte_chain *chain; + u64 *sptep; + struct rmap_iterator iter; - 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 ((sptep = rmap_get_first(sp->parent_ptes, &iter))) + drop_parent_pte(sp, sptep); } static int mmu_zap_unsync_children(struct kvm *kvm, @@ -1685,40 +2160,71 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, ret = mmu_zap_unsync_children(kvm, sp, invalid_list); kvm_mmu_page_unlink_children(kvm, sp); kvm_mmu_unlink_parents(kvm, sp); + 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) { /* 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); + + /* + * The obsolete pages can not be used on any vcpus. + * See the comments in kvm_mmu_invalidate_zap_all_pages(). + */ + if (!sp->role.invalid && !is_obsolete_sp(kvm, sp)) + 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; + struct kvm_mmu_page *sp, *nsp; if (list_empty(invalid_list)) return; + /* + * wmb: make sure everyone sees our modifications to the page tables + * rmb: make sure we see changes to vcpu->mode + */ + smp_mb(); + + /* + * Wait for all vcpus to exit guest mode and/or lockless shadow + * page table walks. + */ kvm_flush_remote_tlbs(kvm); - do { - sp = list_first_entry(invalid_list, struct kvm_mmu_page, link); + list_for_each_entry_safe(sp, nsp, invalid_list, link) { WARN_ON(!sp->role.invalid || sp->root_count); - kvm_mmu_free_page(kvm, sp); - } while (!list_empty(invalid_list)); + kvm_mmu_free_page(sp); + } +} + +static bool prepare_zap_oldest_mmu_page(struct kvm *kvm, + struct list_head *invalid_list) +{ + struct kvm_mmu_page *sp; + if (list_empty(&kvm->arch.active_mmu_pages)) + return false; + + sp = list_entry(kvm->arch.active_mmu_pages.prev, + struct kvm_mmu_page, link); + kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); + + return true; } /* @@ -1728,83 +2234,45 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_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 - */ + + spin_lock(&kvm->mmu_lock); 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); - kvm_mmu_prepare_zap_page(kvm, page, &invalid_list); - kvm_mmu_commit_zap_page(kvm, &invalid_list); - } + /* Need to free some mmu pages to achieve the goal. */ + while (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) + if (!prepare_zap_oldest_mmu_page(kvm, &invalid_list)) + break; + + kvm_mmu_commit_zap_page(kvm, &invalid_list); goal_nr_mmu_pages = kvm->arch.n_used_mmu_pages; } kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages; + + spin_unlock(&kvm->mmu_lock); } -static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) +int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) { struct kvm_mmu_page *sp; - struct hlist_node *node; LIST_HEAD(invalid_list); int r; pgprintk("%s: looking for gfn %llx\n", __func__, gfn); r = 0; - - for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) { + spin_lock(&kvm->mmu_lock); + for_each_gfn_indirect_valid_sp(kvm, sp, gfn) { 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) -{ - struct kvm_mmu_page *sp; - struct hlist_node *node; - LIST_HEAD(invalid_list); - - 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) -{ - int slot = memslot_id(kvm, gfn); - struct kvm_mmu_page *sp = page_header(__pa(pte)); - - __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; + spin_unlock(&kvm->mmu_lock); - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { - if (pt[i] == shadow_notrap_nonpresent_pte) - __set_spte(&pt[i], shadow_trap_nonpresent_pte); - } + return r; } +EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page); /* * The function is based on mtrr_type_lookup() in @@ -1918,15 +2386,13 @@ static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) 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) { struct kvm_mmu_page *s; - struct hlist_node *node; - for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) { + for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) { if (s->unsync) continue; WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL); @@ -1938,21 +2404,17 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) { struct kvm_mmu_page *s; - struct hlist_node *node; bool need_unsync = false; - for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) { + for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) { if (!can_unsync) return 1; if (s->role.level != PT_PAGE_TABLE_LEVEL) return 1; - if (!need_unsync && !s->unsync) { - if (!oos_shadow) - return 1; + if (!s->unsync) need_unsync = true; - } } if (need_unsync) kvm_unsync_pages(vcpu, gfn); @@ -1960,57 +2422,54 @@ static int mmu_need_write_protect(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, + unsigned pte_access, int level, gfn_t gfn, pfn_t pfn, bool speculative, - bool can_unsync, bool reset_host_protection) + bool can_unsync, bool host_writable) { u64 spte; int ret = 0; - /* - * We don't set the accessed bit, since we sometimes want to see - * whether the guest actually used the pte (in order to detect - * demand paging). - */ - spte = shadow_base_present_pte; + if (set_mmio_spte(vcpu->kvm, sptep, gfn, pfn, pte_access)) + return 0; + + 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 spte |= shadow_nx_mask; + if (pte_access & ACC_USER_MASK) spte |= shadow_user_mask; + if (level > PT_PAGE_TABLE_LEVEL) spte |= PT_PAGE_SIZE_MASK; if (tdp_enabled) spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn, kvm_is_mmio_pfn(pfn)); - if (reset_host_protection) + if (host_writable) spte |= SPTE_HOST_WRITEABLE; + else + pte_access &= ~ACC_WRITE_MASK; spte |= (u64)pfn << PAGE_SHIFT; - if ((pte_access & ACC_WRITE_MASK) - || (!vcpu->arch.mmu.direct_map && write_fault - && !is_write_protection(vcpu) && !user_fault)) { + if (pte_access & ACC_WRITE_MASK) { + /* + * Other vcpu creates new sp in the window between + * mapping_level() and acquiring mmu-lock. We can + * allow guest to retry the access, the mapping can + * be fixed if guest refault. + */ if (level > PT_PAGE_TABLE_LEVEL && - has_wrprotected_page(vcpu->kvm, gfn, level)) { - ret = 1; - drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte); + has_wrprotected_page(vcpu->kvm, gfn, level)) goto done; - } - spte |= PT_WRITABLE_MASK; - - if (!vcpu->arch.mmu.direct_map - && !(pte_access & ACC_WRITE_MASK)) - spte &= ~PT_USER_MASK; + spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE; /* * Optimization: for pte sync, if spte was writable the hash @@ -2026,8 +2485,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, __func__, gfn); ret = 1; pte_access &= ~ACC_WRITE_MASK; - if (is_writable_pte(spte)) - spte &= ~PT_WRITABLE_MASK; + spte &= ~(PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE); } } @@ -2035,25 +2493,22 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, mark_page_dirty(vcpu->kvm, gfn); set_pte: - update_spte(sptep, spte); + if (mmu_spte_update(sptep, spte)) + kvm_flush_remote_tlbs(vcpu->kvm); done: return ret; } 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, - pfn_t pfn, bool speculative, - bool reset_host_protection) + unsigned pte_access, int write_fault, int *emulate, + int level, gfn_t gfn, pfn_t pfn, bool speculative, + bool host_writable) { int was_rmapped = 0; int rmap_count; - pgprintk("%s: spte %llx access %x write_fault %d" - " user_fault %d gfn %llx\n", - __func__, *sptep, pt_access, - write_fault, user_fault, gfn); + pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__, + *sptep, write_fault, gfn); if (is_rmap_spte(*sptep)) { /* @@ -2066,26 +2521,27 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, 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, - reset_host_protection)) { + if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative, + true, host_writable)) { if (write_fault) - *ptwrite = 1; + *emulate = 1; kvm_mmu_flush_tlb(vcpu); } + if (unlikely(is_mmio_spte(*sptep) && emulate)) + *emulate = 1; + pgprintk("%s: setting spte %llx\n", __func__, *sptep); pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n", is_large_pte(*sptep)? "2MB" : "4kB", @@ -2094,51 +2550,27 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (!was_rmapped && is_large_pte(*sptep)) ++vcpu->kvm->stat.lpages; - page_header_update_slot(vcpu->kvm, sptep, gfn); - if (!was_rmapped) { - rmap_count = rmap_add(vcpu, sptep, gfn); - if (rmap_count > RMAP_RECYCLE_THRESHOLD) - rmap_recycle(vcpu, sptep, gfn); - } - kvm_release_pfn_clean(pfn); - if (speculative) { - vcpu->arch.last_pte_updated = sptep; - vcpu->arch.last_pte_gfn = gfn; + if (is_shadow_present_pte(*sptep)) { + if (!was_rmapped) { + rmap_count = rmap_add(vcpu, sptep, gfn); + if (rmap_count > RMAP_RECYCLE_THRESHOLD) + rmap_recycle(vcpu, sptep, gfn); + } } -} -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; + kvm_release_pfn_clean(pfn); } 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); - } + slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, no_dirty_log); + if (!slot) + return KVM_PFN_ERR_FAULT; - hva = gfn_to_hva_memslot(slot, gfn); - - return hva_to_pfn_atomic(vcpu->kvm, hva); + return gfn_to_pfn_memslot_atomic(slot, gfn); } static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, @@ -2151,7 +2583,7 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, 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)) + if (!gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK)) return -1; ret = gfn_to_page_many_atomic(vcpu->kvm, gfn, pages, end - start); @@ -2159,10 +2591,9 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, 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); + mmu_set_spte(vcpu, start, access, 0, NULL, + sp->role.level, gfn, page_to_pfn(pages[i]), + true, true); return 0; } @@ -2179,7 +2610,7 @@ static void __direct_pte_prefetch(struct kvm_vcpu *vcpu, 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) @@ -2211,24 +2642,29 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) } static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, - int level, gfn_t gfn, pfn_t pfn) + int map_writable, int level, gfn_t gfn, pfn_t pfn, + bool prefault) { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; - int pt_write = 0; + int emulate = 0; gfn_t pseudo_gfn; + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + return 0; + for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) { if (iterator.level == level) { - mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL, - 0, write, 1, &pt_write, - level, gfn, pfn, false, true); + mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, + 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) { + drop_large_spte(vcpu, iterator.sptep); + if (!is_shadow_present_pte(*iterator.sptep)) { u64 base_addr = iterator.addr; base_addr &= PT64_LVL_ADDR_MASK(iterator.level); @@ -2236,20 +2672,11 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr, iterator.level - 1, 1, ACC_ALL, iterator.sptep); - if (!sp) { - pgprintk("nonpaging_map: ENOMEM\n"); - kvm_release_pfn_clean(pfn); - return -ENOMEM; - } - __set_spte(iterator.sptep, - __pa(sp->spt) - | PT_PRESENT_MASK | PT_WRITABLE_MASK - | shadow_user_mask | shadow_x_mask - | shadow_accessed_mask); + link_shadow_page(iterator.sptep, sp, true); } } - return pt_write; + return emulate; } static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk) @@ -2265,49 +2692,257 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct * 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, 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); + /* + * Do not cache the mmio info caused by writing the readonly gfn + * into the spte otherwise read access on readonly gfn also can + * caused mmio page fault and treat it as mmio access. + * Return 1 to tell kvm to emulate it. + */ + if (pfn == KVM_PFN_ERR_RO_FAULT) + return 1; + + if (pfn == KVM_PFN_ERR_HWPOISON) { + kvm_send_hwpoison_signal(gfn_to_hva(vcpu->kvm, gfn), current); return 0; - } else if (is_fault_pfn(pfn)) - return -EFAULT; + } - return 1; + return -EFAULT; +} + +static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, + gfn_t *gfnp, pfn_t *pfnp, int *levelp) +{ + pfn_t pfn = *pfnp; + gfn_t gfn = *gfnp; + int level = *levelp; + + /* + * Check if it's a transparent hugepage. If this would be an + * hugetlbfs page, level wouldn't be set to + * PT_PAGE_TABLE_LEVEL and there would be no adjustment done + * here. + */ + if (!is_error_noslot_pfn(pfn) && !kvm_is_mmio_pfn(pfn) && + level == PT_PAGE_TABLE_LEVEL && + PageTransCompound(pfn_to_page(pfn)) && + !has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) { + unsigned long mask; + /* + * mmu_notifier_retry was successful and we hold the + * mmu_lock here, so the pmd can't become splitting + * from under us, and in turn + * __split_huge_page_refcount() can't run from under + * us and we can safely transfer the refcount from + * PG_tail to PG_head as we switch the pfn to tail to + * head. + */ + *levelp = level = PT_DIRECTORY_LEVEL; + mask = KVM_PAGES_PER_HPAGE(level) - 1; + VM_BUG_ON((gfn & mask) != (pfn & mask)); + if (pfn & mask) { + gfn &= ~mask; + *gfnp = gfn; + kvm_release_pfn_clean(pfn); + pfn &= ~mask; + kvm_get_pfn(pfn); + *pfnp = pfn; + } + } } -static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) +static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, + pfn_t pfn, unsigned access, int *ret_val) +{ + bool ret = true; + + /* The pfn is invalid, report the error! */ + if (unlikely(is_error_pfn(pfn))) { + *ret_val = kvm_handle_bad_page(vcpu, gfn, pfn); + goto exit; + } + + if (unlikely(is_noslot_pfn(pfn))) + vcpu_cache_mmio_info(vcpu, gva, gfn, access); + + ret = false; +exit: + return ret; +} + +static bool page_fault_can_be_fast(u32 error_code) +{ + /* + * Do not fix the mmio spte with invalid generation number which + * need to be updated by slow page fault path. + */ + if (unlikely(error_code & PFERR_RSVD_MASK)) + return false; + + /* + * #PF can be fast only if the shadow page table is present and it + * is caused by write-protect, that means we just need change the + * W bit of the spte which can be done out of mmu-lock. + */ + if (!(error_code & PFERR_PRESENT_MASK) || + !(error_code & PFERR_WRITE_MASK)) + return false; + + return true; +} + +static bool +fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + u64 *sptep, u64 spte) +{ + gfn_t gfn; + + WARN_ON(!sp->role.direct); + + /* + * The gfn of direct spte is stable since it is calculated + * by sp->gfn. + */ + gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt); + + if (cmpxchg64(sptep, spte, spte | PT_WRITABLE_MASK) == spte) + mark_page_dirty(vcpu->kvm, gfn); + + return true; +} + +/* + * Return value: + * - true: let the vcpu to access on the same address again. + * - false: let the real page fault path to fix it. + */ +static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, + u32 error_code) +{ + struct kvm_shadow_walk_iterator iterator; + struct kvm_mmu_page *sp; + bool ret = false; + u64 spte = 0ull; + + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + return false; + + if (!page_fault_can_be_fast(error_code)) + return false; + + walk_shadow_page_lockless_begin(vcpu); + for_each_shadow_entry_lockless(vcpu, gva, iterator, spte) + if (!is_shadow_present_pte(spte) || iterator.level < level) + break; + + /* + * If the mapping has been changed, let the vcpu fault on the + * same address again. + */ + if (!is_rmap_spte(spte)) { + ret = true; + goto exit; + } + + sp = page_header(__pa(iterator.sptep)); + if (!is_last_spte(spte, sp->role.level)) + goto exit; + + /* + * Check if it is a spurious fault caused by TLB lazily flushed. + * + * Need not check the access of upper level table entries since + * they are always ACC_ALL. + */ + if (is_writable_pte(spte)) { + ret = true; + goto exit; + } + + /* + * Currently, to simplify the code, only the spte write-protected + * by dirty-log can be fast fixed. + */ + if (!spte_is_locklessly_modifiable(spte)) + goto exit; + + /* + * Do not fix write-permission on the large spte since we only dirty + * the first page into the dirty-bitmap in fast_pf_fix_direct_spte() + * that means other pages are missed if its slot is dirty-logged. + * + * Instead, we let the slow page fault path create a normal spte to + * fix the access. + * + * See the comments in kvm_arch_commit_memory_region(). + */ + if (sp->role.level > PT_PAGE_TABLE_LEVEL) + goto exit; + + /* + * Currently, fast page fault only works for direct mapping since + * the gfn is not stable for indirect shadow page. + * See Documentation/virtual/kvm/locking.txt to get more detail. + */ + ret = fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte); +exit: + trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep, + spte, ret); + walk_shadow_page_lockless_end(vcpu); + + return ret; +} + +static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, + gva_t gva, pfn_t *pfn, bool write, bool *writable); +static void make_mmu_pages_available(struct kvm_vcpu *vcpu); + +static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, + gfn_t gfn, bool prefault) { int r; int level; + int force_pt_level; pfn_t pfn; unsigned long mmu_seq; + bool map_writable, write = error_code & PFERR_WRITE_MASK; - level = mapping_level(vcpu, gfn); + force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn); + if (likely(!force_pt_level)) { + level = mapping_level(vcpu, gfn); + /* + * This path builds a PAE pagetable - so we can map + * 2mb pages at maximum. Therefore check if the level + * is larger than that. + */ + if (level > PT_DIRECTORY_LEVEL) + level = PT_DIRECTORY_LEVEL; - /* - * This path builds a PAE pagetable - so we can map 2mb pages at - * maximum. Therefore check if the level is larger than that. - */ - if (level > PT_DIRECTORY_LEVEL) - level = PT_DIRECTORY_LEVEL; + gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); + } else + level = PT_PAGE_TABLE_LEVEL; - gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); + if (fast_page_fault(vcpu, v, level, error_code)) + return 0; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - pfn = gfn_to_pfn(vcpu->kvm, gfn); - /* mmio */ - if (is_error_pfn(pfn)) - return kvm_handle_bad_page(vcpu->kvm, gfn, pfn); + if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable)) + return 0; + + if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r)) + return r; spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu, mmu_seq)) + if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; - kvm_mmu_free_some_pages(vcpu); - r = __direct_map(vcpu, v, write, level, gfn, pfn); + make_mmu_pages_available(vcpu); + if (likely(!force_pt_level)) + transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); + r = __direct_map(vcpu, v, write, map_writable, level, gfn, pfn, + prefault); spin_unlock(&vcpu->kvm->mmu_lock); @@ -2328,22 +2963,25 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) 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 && (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL || vcpu->arch.mmu.direct_map)) { hpa_t root = vcpu->arch.mmu.root_hpa; + spin_lock(&vcpu->kvm->mmu_lock); sp = page_header(root); --sp->root_count; 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); + vcpu->arch.mmu.root_hpa = INVALID_PAGE; return; } + + spin_lock(&vcpu->kvm->mmu_lock); for (i = 0; i < 4; ++i) { hpa_t root = vcpu->arch.mmu.pae_root[i]; @@ -2381,7 +3019,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { spin_lock(&vcpu->kvm->mmu_lock); - kvm_mmu_free_some_pages(vcpu); + make_mmu_pages_available(vcpu); sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL, 1, ACC_ALL, NULL); ++sp->root_count; @@ -2393,8 +3031,9 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) 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, + make_mmu_pages_available(vcpu); + sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT), + i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL, NULL); root = __pa(sp->spt); @@ -2431,7 +3070,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); spin_lock(&vcpu->kvm->mmu_lock); - kvm_mmu_free_some_pages(vcpu); + make_mmu_pages_available(vcpu); sp = kvm_mmu_get_page(vcpu, root_gfn, 0, PT64_ROOT_LEVEL, 0, ACC_ALL, NULL); root = __pa(sp->spt); @@ -2455,7 +3094,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) { - pdptr = kvm_pdptr_read_mmu(vcpu, &vcpu->arch.mmu, i); + pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i); if (!is_present_gpte(pdptr)) { vcpu->arch.mmu.pae_root[i] = 0; continue; @@ -2465,7 +3104,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) return 1; } spin_lock(&vcpu->kvm->mmu_lock); - kvm_mmu_free_some_pages(vcpu); + make_mmu_pages_available(vcpu); sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL, 0, ACC_ALL, NULL); @@ -2524,11 +3163,13 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu) if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; - trace_kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); + vcpu_clear_mmio_info(vcpu, ~0ul); + 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); + kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); return; } for (i = 0; i < 4; ++i) { @@ -2540,7 +3181,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu) mmu_sync_children(vcpu, sp); } } - trace_kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); + kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); } void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) @@ -2549,30 +3190,129 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) mmu_sync_roots(vcpu); spin_unlock(&vcpu->kvm->mmu_lock); } +EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots); static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, - u32 access, u32 *error) + u32 access, struct x86_exception *exception) { - if (error) - *error = 0; + if (exception) + exception->error_code = 0; return vaddr; } static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, - u32 access, u32 *error) + u32 access, + struct x86_exception *exception) { - if (error) - *error = 0; + if (exception) + exception->error_code = 0; return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access); } +static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct) +{ + if (direct) + return vcpu_match_mmio_gpa(vcpu, addr); + + return vcpu_match_mmio_gva(vcpu, addr); +} + + +/* + * On direct hosts, the last spte is only allows two states + * for mmio page fault: + * - It is the mmio spte + * - It is zapped or it is being zapped. + * + * This function completely checks the spte when the last spte + * is not the mmio spte. + */ +static bool check_direct_spte_mmio_pf(u64 spte) +{ + return __check_direct_spte_mmio_pf(spte); +} + +static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr) +{ + struct kvm_shadow_walk_iterator iterator; + u64 spte = 0ull; + + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + return spte; + + walk_shadow_page_lockless_begin(vcpu); + for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) + if (!is_shadow_present_pte(spte)) + break; + walk_shadow_page_lockless_end(vcpu); + + return spte; +} + +int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) +{ + u64 spte; + + if (quickly_check_mmio_pf(vcpu, addr, direct)) + return RET_MMIO_PF_EMULATE; + + spte = walk_shadow_page_get_mmio_spte(vcpu, addr); + + if (is_mmio_spte(spte)) { + gfn_t gfn = get_mmio_spte_gfn(spte); + unsigned access = get_mmio_spte_access(spte); + + if (!check_mmio_spte(vcpu->kvm, spte)) + return RET_MMIO_PF_INVALID; + + if (direct) + addr = 0; + + trace_handle_mmio_page_fault(addr, gfn, access); + vcpu_cache_mmio_info(vcpu, addr, gfn, access); + return RET_MMIO_PF_EMULATE; + } + + /* + * It's ok if the gva is remapped by other cpus on shadow guest, + * it's a BUG if the gfn is not a mmio page. + */ + if (direct && !check_direct_spte_mmio_pf(spte)) + return RET_MMIO_PF_BUG; + + /* + * If the page table is zapped by other cpus, let CPU fault again on + * the address. + */ + return RET_MMIO_PF_RETRY; +} +EXPORT_SYMBOL_GPL(handle_mmio_page_fault_common); + +static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, + u32 error_code, bool direct) +{ + int ret; + + ret = handle_mmio_page_fault_common(vcpu, addr, direct); + WARN_ON(ret == RET_MMIO_PF_BUG); + return ret; +} + static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, - u32 error_code) + u32 error_code, bool prefault) { gfn_t gfn; int r; pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); + + if (unlikely(error_code & PFERR_RSVD_MASK)) { + r = handle_mmio_page_fault(vcpu, gva, error_code, true); + + if (likely(r != RET_MMIO_PF_INVALID)) + return r; + } + r = mmu_topup_memory_caches(vcpu); if (r) return r; @@ -2583,40 +3323,108 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, gfn = gva >> PAGE_SHIFT; return nonpaging_map(vcpu, gva & PAGE_MASK, - error_code & PFERR_WRITE_MASK, gfn); + error_code, gfn, prefault); +} + +static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) +{ + struct kvm_arch_async_pf arch; + + arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; + arch.gfn = gfn; + arch.direct_map = vcpu->arch.mmu.direct_map; + arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu); + + return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch); +} + +static bool can_do_async_pf(struct kvm_vcpu *vcpu) +{ + if (unlikely(!irqchip_in_kernel(vcpu->kvm) || + kvm_event_needs_reinjection(vcpu))) + return false; + + return kvm_x86_ops->interrupt_allowed(vcpu); +} + +static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, + gva_t gva, pfn_t *pfn, bool write, bool *writable) +{ + bool async; + + *pfn = gfn_to_pfn_async(vcpu->kvm, gfn, &async, write, writable); + + if (!async) + return false; /* *pfn has correct page already */ + + if (!prefault && can_do_async_pf(vcpu)) { + trace_kvm_try_async_get_page(gva, gfn); + if (kvm_find_async_pf_gfn(vcpu, gfn)) { + trace_kvm_async_pf_doublefault(gva, gfn); + kvm_make_request(KVM_REQ_APF_HALT, vcpu); + return true; + } else if (kvm_arch_setup_async_pf(vcpu, gva, gfn)) + return true; + } + + *pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write, writable); + + return false; } -static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, - u32 error_code) +static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, + bool prefault) { pfn_t pfn; int r; int level; + int force_pt_level; gfn_t gfn = gpa >> PAGE_SHIFT; unsigned long mmu_seq; + int write = error_code & PFERR_WRITE_MASK; + bool map_writable; ASSERT(vcpu); ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa)); + if (unlikely(error_code & PFERR_RSVD_MASK)) { + r = handle_mmio_page_fault(vcpu, gpa, error_code, true); + + if (likely(r != RET_MMIO_PF_INVALID)) + return r; + } + r = mmu_topup_memory_caches(vcpu); if (r) return r; - level = mapping_level(vcpu, gfn); + force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn); + if (likely(!force_pt_level)) { + level = mapping_level(vcpu, gfn); + gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); + } else + level = PT_PAGE_TABLE_LEVEL; - gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); + if (fast_page_fault(vcpu, gpa, level, error_code)) + return 0; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - pfn = gfn_to_pfn(vcpu->kvm, gfn); - if (is_error_pfn(pfn)) - return kvm_handle_bad_page(vcpu->kvm, gfn, pfn); + + if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) + return 0; + + if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r)) + return r; + spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu, mmu_seq)) + if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; - kvm_mmu_free_some_pages(vcpu); - r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK, - level, gfn, pfn); + make_mmu_pages_available(vcpu); + if (likely(!force_pt_level)) + transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); + r = __direct_map(vcpu, gpa, write, map_writable, + level, gfn, pfn, prefault); spin_unlock(&vcpu->kvm->mmu_lock); return r; @@ -2627,27 +3435,19 @@ out_unlock: return 0; } -static void nonpaging_free(struct kvm_vcpu *vcpu) +static void nonpaging_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - mmu_free_roots(vcpu); -} - -static int nonpaging_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) -{ - context->new_cr3 = nonpaging_new_cr3; 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->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) @@ -2655,36 +3455,55 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) ++vcpu->stat.tlb_flush; kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } +EXPORT_SYMBOL_GPL(kvm_mmu_flush_tlb); -static void paging_new_cr3(struct kvm_vcpu *vcpu) +void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu) { - pgprintk("%s: cr3 %lx\n", __func__, vcpu->arch.cr3); mmu_free_roots(vcpu); } static unsigned long get_cr3(struct kvm_vcpu *vcpu) { - return vcpu->arch.cr3; + return kvm_read_cr3(vcpu); } -static void inject_page_fault(struct kvm_vcpu *vcpu) +static void inject_page_fault(struct kvm_vcpu *vcpu, + struct x86_exception *fault) { - vcpu->arch.mmu.inject_page_fault(vcpu); + vcpu->arch.mmu.inject_page_fault(vcpu, fault); } -static void paging_free(struct kvm_vcpu *vcpu) +static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, + unsigned access, int *nr_present) { - nonpaging_free(vcpu); + if (unlikely(is_mmio_spte(*sptep))) { + if (gfn != get_mmio_spte_gfn(*sptep)) { + mmu_spte_clear_no_track(sptep); + return true; + } + + (*nr_present)++; + mark_mmio_spte(kvm, sptep, gfn, access); + return true; + } + + return false; } -static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level) +static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte) { - int bit7; + unsigned index; - bit7 = (gpte >> 7) & 1; - return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0; + index = level - 1; + index |= (gpte & PT_PAGE_SIZE_MASK) >> (PT_PAGE_SIZE_SHIFT - 2); + return mmu->last_pte_bitmap & (1 << index); } +#define PTTYPE_EPT 18 /* arbitrary */ +#define PTTYPE PTTYPE_EPT +#include "paging_tmpl.h" +#undef PTTYPE + #define PTTYPE 64 #include "paging_tmpl.h" #undef PTTYPE @@ -2694,15 +3513,19 @@ static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level) #undef PTTYPE static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, - int level) + struct kvm_mmu *context) { int maxphyaddr = cpuid_maxphyaddr(vcpu); u64 exb_bit_rsvd = 0; + u64 gbpages_bit_rsvd = 0; + + context->bad_mt_xwr = 0; if (!context->nx) exb_bit_rsvd = rsvd_bits(63, 63); - switch (level) { + if (!guest_cpuid_has_gbpages(vcpu)) + gbpages_bit_rsvd = rsvd_bits(7, 7); + switch (context->root_level) { case PT32_ROOT_LEVEL: /* no rsvd bits for 2 level 4K page table entries */ context->rsvd_bits_mask[0][1] = 0; @@ -2724,7 +3547,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, case PT32E_ROOT_LEVEL: context->rsvd_bits_mask[0][2] = rsvd_bits(maxphyaddr, 63) | - rsvd_bits(7, 8) | rsvd_bits(1, 2); /* PDPTE */ + rsvd_bits(5, 8) | rsvd_bits(1, 2); /* PDPTE */ context->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62); /* PDE */ context->rsvd_bits_mask[0][0] = exb_bit_rsvd | @@ -2736,16 +3559,16 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, break; case PT64_ROOT_LEVEL: context->rsvd_bits_mask[0][3] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8); + rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 7); context->rsvd_bits_mask[0][2] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8); + gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); context->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); context->rsvd_bits_mask[0][0] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3]; context->rsvd_bits_mask[1][2] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51) | + gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 29); context->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51) | @@ -2755,79 +3578,191 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, } } -static int paging64_init_context_common(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, - int level) +static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, + struct kvm_mmu *context, bool execonly) +{ + int maxphyaddr = cpuid_maxphyaddr(vcpu); + int pte; + + context->rsvd_bits_mask[0][3] = + rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7); + context->rsvd_bits_mask[0][2] = + rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); + context->rsvd_bits_mask[0][1] = + rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); + context->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51); + + /* large page */ + context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3]; + context->rsvd_bits_mask[1][2] = + rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29); + context->rsvd_bits_mask[1][1] = + rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20); + context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + + for (pte = 0; pte < 64; pte++) { + int rwx_bits = pte & 7; + int mt = pte >> 3; + if (mt == 0x2 || mt == 0x3 || mt == 0x7 || + rwx_bits == 0x2 || rwx_bits == 0x6 || + (rwx_bits == 0x4 && !execonly)) + context->bad_mt_xwr |= (1ull << pte); + } +} + +void update_permission_bitmask(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu, bool ept) +{ + unsigned bit, byte, pfec; + u8 map; + bool fault, x, w, u, wf, uf, ff, smapf, cr4_smap, cr4_smep, smap = 0; + + cr4_smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP); + cr4_smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); + for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) { + pfec = byte << 1; + map = 0; + wf = pfec & PFERR_WRITE_MASK; + uf = pfec & PFERR_USER_MASK; + ff = pfec & PFERR_FETCH_MASK; + /* + * PFERR_RSVD_MASK bit is set in PFEC if the access is not + * subject to SMAP restrictions, and cleared otherwise. The + * bit is only meaningful if the SMAP bit is set in CR4. + */ + smapf = !(pfec & PFERR_RSVD_MASK); + for (bit = 0; bit < 8; ++bit) { + x = bit & ACC_EXEC_MASK; + w = bit & ACC_WRITE_MASK; + u = bit & ACC_USER_MASK; + + if (!ept) { + /* Not really needed: !nx will cause pte.nx to fault */ + x |= !mmu->nx; + /* Allow supervisor writes if !cr0.wp */ + w |= !is_write_protection(vcpu) && !uf; + /* Disallow supervisor fetches of user code if cr4.smep */ + x &= !(cr4_smep && u && !uf); + + /* + * SMAP:kernel-mode data accesses from user-mode + * mappings should fault. A fault is considered + * as a SMAP violation if all of the following + * conditions are ture: + * - X86_CR4_SMAP is set in CR4 + * - An user page is accessed + * - Page fault in kernel mode + * - if CPL = 3 or X86_EFLAGS_AC is clear + * + * Here, we cover the first three conditions. + * The fourth is computed dynamically in + * permission_fault() and is in smapf. + * + * Also, SMAP does not affect instruction + * fetches, add the !ff check here to make it + * clearer. + */ + smap = cr4_smap && u && !uf && !ff; + } else + /* Not really needed: no U/S accesses on ept */ + u = 1; + + fault = (ff && !x) || (uf && !u) || (wf && !w) || + (smapf && smap); + map |= fault << bit; + } + mmu->permissions[byte] = map; + } +} + +static void update_last_pte_bitmap(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) +{ + u8 map; + unsigned level, root_level = mmu->root_level; + const unsigned ps_set_index = 1 << 2; /* bit 2 of index: ps */ + + if (root_level == PT32E_ROOT_LEVEL) + --root_level; + /* PT_PAGE_TABLE_LEVEL always terminates */ + map = 1 | (1 << ps_set_index); + for (level = PT_DIRECTORY_LEVEL; level <= root_level; ++level) { + if (level <= PT_PDPE_LEVEL + && (mmu->root_level >= PT32E_ROOT_LEVEL || is_pse(vcpu))) + map |= 1 << (ps_set_index | (level - 1)); + } + mmu->last_pte_bitmap = map; +} + +static void paging64_init_context_common(struct kvm_vcpu *vcpu, + struct kvm_mmu *context, + int level) { context->nx = is_nx(vcpu); + context->root_level = level; - reset_rsvds_bits_mask(vcpu, context, level); + reset_rsvds_bits_mask(vcpu, context); + update_permission_bitmask(vcpu, context, false); + update_last_pte_bitmap(vcpu, context); ASSERT(is_pae(vcpu)); - 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->free = paging_free; - context->root_level = level; + context->update_pte = paging64_update_pte; 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, - struct kvm_mmu *context) +static void paging64_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - return paging64_init_context_common(vcpu, context, PT64_ROOT_LEVEL); + paging64_init_context_common(vcpu, context, PT64_ROOT_LEVEL); } -static int paging32_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void paging32_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { context->nx = false; + context->root_level = PT32_ROOT_LEVEL; - reset_rsvds_bits_mask(vcpu, context, PT32_ROOT_LEVEL); + reset_rsvds_bits_mask(vcpu, context); + update_permission_bitmask(vcpu, context, false); + update_last_pte_bitmap(vcpu, context); - context->new_cr3 = paging_new_cr3; 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->root_level = PT32_ROOT_LEVEL; + context->update_pte = paging32_update_pte; 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, - struct kvm_mmu *context) +static void paging32E_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - return paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL); + paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL); } -static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) +static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) { struct kvm_mmu *context = vcpu->arch.walk_mmu; - context->new_cr3 = nonpaging_new_cr3; + context->base_role.word = 0; 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; 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->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; - context->nx = is_nx(vcpu); if (!is_paging(vcpu)) { context->nx = false; @@ -2835,62 +3770,86 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->root_level = 0; } else if (is_long_mode(vcpu)) { 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; + reset_rsvds_bits_mask(vcpu, context); + context->gva_to_gpa = paging64_gva_to_gpa; } else if (is_pae(vcpu)) { 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; + reset_rsvds_bits_mask(vcpu, context); + context->gva_to_gpa = paging64_gva_to_gpa; } else { 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; + reset_rsvds_bits_mask(vcpu, context); + context->gva_to_gpa = paging32_gva_to_gpa; } - return 0; + update_permission_bitmask(vcpu, context, false); + update_last_pte_bitmap(vcpu, context); } -int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context) +void 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)); if (!is_paging(vcpu)) - r = nonpaging_init_context(vcpu, context); + nonpaging_init_context(vcpu, context); else if (is_long_mode(vcpu)) - r = paging64_init_context(vcpu, context); + paging64_init_context(vcpu, context); else if (is_pae(vcpu)) - r = paging32E_init_context(vcpu, context); + paging32E_init_context(vcpu, context); else - r = paging32_init_context(vcpu, context); + paging32_init_context(vcpu, context); + vcpu->arch.mmu.base_role.nxe = is_nx(vcpu); vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu); vcpu->arch.mmu.base_role.cr0_wp = is_write_protection(vcpu); - - return r; + vcpu->arch.mmu.base_role.smep_andnot_wp + = smep && !is_write_protection(vcpu); } EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); -static int init_kvm_softmmu(struct kvm_vcpu *vcpu) +void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, + bool execonly) { - int r = kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu); + ASSERT(vcpu); + ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); + + context->shadow_root_level = kvm_x86_ops->get_tdp_level(); + + context->nx = true; + context->page_fault = ept_page_fault; + context->gva_to_gpa = ept_gva_to_gpa; + context->sync_page = ept_sync_page; + context->invlpg = ept_invlpg; + context->update_pte = ept_update_pte; + context->root_level = context->shadow_root_level; + context->root_hpa = INVALID_PAGE; + context->direct_map = false; + + update_permission_bitmask(vcpu, context, true); + reset_rsvds_bits_mask_ept(vcpu, context, execonly); +} +EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu); +static void init_kvm_softmmu(struct kvm_vcpu *vcpu) +{ + 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->get_pdptr = kvm_pdptr_read; vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; - - return r; } -static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) +static void 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->get_pdptr = kvm_pdptr_read; g_context->inject_page_fault = kvm_inject_page_fault; /* @@ -2905,28 +3864,27 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) 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; + reset_rsvds_bits_mask(vcpu, g_context); 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; + reset_rsvds_bits_mask(vcpu, g_context); 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; + reset_rsvds_bits_mask(vcpu, g_context); g_context->gva_to_gpa = paging32_gva_to_gpa_nested; } - return 0; + update_permission_bitmask(vcpu, g_context, false); + update_last_pte_bitmap(vcpu, g_context); } -static int init_kvm_mmu(struct kvm_vcpu *vcpu) +static void init_kvm_mmu(struct kvm_vcpu *vcpu) { - vcpu->arch.update_pte.pfn = bad_pfn; - if (mmu_is_nested(vcpu)) return init_kvm_nested_mmu(vcpu); else if (tdp_enabled) @@ -2935,18 +3893,12 @@ static int init_kvm_mmu(struct kvm_vcpu *vcpu) return init_kvm_softmmu(vcpu); } -static void destroy_kvm_mmu(struct kvm_vcpu *vcpu) +void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) { ASSERT(vcpu); - if (VALID_PAGE(vcpu->arch.mmu.root_hpa)) - /* mmu.free() should set root_hpa = INVALID_PAGE */ - vcpu->arch.mmu.free(vcpu); -} -int kvm_mmu_reset_context(struct kvm_vcpu *vcpu) -{ - destroy_kvm_mmu(vcpu); - return init_kvm_mmu(vcpu); + kvm_mmu_unload(vcpu); + init_kvm_mmu(vcpu); } EXPORT_SYMBOL_GPL(kvm_mmu_reset_context); @@ -2958,9 +3910,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) if (r) goto out; r = mmu_alloc_roots(vcpu); - spin_lock(&vcpu->kvm->mmu_lock); - mmu_sync_roots(vcpu); - spin_unlock(&vcpu->kvm->mmu_lock); + kvm_mmu_sync_roots(vcpu); if (r) goto out; /* set_cr3() should ensure TLB has been flushed */ @@ -2973,33 +3923,12 @@ EXPORT_SYMBOL_GPL(kvm_mmu_load); void kvm_mmu_unload(struct kvm_vcpu *vcpu) { mmu_free_roots(vcpu); + WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa)); } 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, + struct kvm_mmu_page *sp, u64 *spte, const void *new) { if (sp->role.level != PT_PAGE_TABLE_LEVEL) { @@ -3007,14 +3936,8 @@ 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); - else - paging64_update_pte(vcpu, sp, spte, new); + vcpu->arch.mmu.update_pte(vcpu, sp, spte, new); } static bool need_remote_flush(u64 old, u64 new) @@ -3025,8 +3948,8 @@ static bool need_remote_flush(u64 old, u64 new) return true; if ((old ^ new) & PT64_BASE_ADDR_MASK) return true; - old ^= PT64_NX_MASK; - new ^= PT64_NX_MASK; + old ^= shadow_nx_mask; + new ^= shadow_nx_mask; return (old & ~new & PT64_PERM_MASK) != 0; } @@ -3042,192 +3965,183 @@ static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page, kvm_mmu_flush_tlb(vcpu); } -static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu) +static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, + const u8 *new, int *bytes) { - u64 *spte = vcpu->arch.last_pte_updated; + u64 gentry; + int r; - return !!(spte && (*spte & shadow_accessed_mask)); + /* + * Assume that the pte write on a page table of the same type + * as the current vcpu paging mode since we update the sptes only + * when they have the same mode. + */ + if (is_pae(vcpu) && *bytes == 4) { + /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ + *gpa &= ~(gpa_t)7; + *bytes = 8; + r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, 8); + if (r) + gentry = 0; + new = (const u8 *)&gentry; + } + + switch (*bytes) { + case 4: + gentry = *(const u32 *)new; + break; + case 8: + gentry = *(const u64 *)new; + break; + default: + gentry = 0; + break; + } + + return gentry; } -static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - u64 gpte) +/* + * If we're seeing too many writes to a page, it may no longer be a page table, + * or we may be forking, in which case it is better to unmap the page. + */ +static bool detect_write_flooding(struct kvm_mmu_page *sp) { - gfn_t gfn; - pfn_t pfn; + /* + * Skip write-flooding detected for the sp whose level is 1, because + * it can become unsync, then the guest page is not write-protected. + */ + if (sp->role.level == PT_PAGE_TABLE_LEVEL) + return false; - if (!is_present_gpte(gpte)) - return; - gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; + return ++sp->write_flooding_count >= 3; +} - vcpu->arch.update_pte.mmu_seq = vcpu->kvm->mmu_notifier_seq; - smp_rmb(); - pfn = gfn_to_pfn(vcpu->kvm, gfn); +/* + * Misaligned accesses are too much trouble to fix up; also, they usually + * indicate a page is not used as a page table. + */ +static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, + int bytes) +{ + unsigned offset, pte_size, misaligned; - if (is_error_pfn(pfn)) { - kvm_release_pfn_clean(pfn); - return; - } - vcpu->arch.update_pte.gfn = gfn; - vcpu->arch.update_pte.pfn = pfn; + pgprintk("misaligned: gpa %llx bytes %d role %x\n", + gpa, bytes, sp->role.word); + + offset = offset_in_page(gpa); + pte_size = sp->role.cr4_pae ? 8 : 4; + + /* + * Sometimes, the OS only writes the last one bytes to update status + * bits, for example, in linux, andb instruction is used in clear_bit(). + */ + if (!(offset & (pte_size - 1)) && bytes == 1) + return false; + + misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); + misaligned |= bytes < 4; + + return misaligned; } -static void kvm_mmu_access_page(struct kvm_vcpu *vcpu, gfn_t gfn) +static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) { - u64 *spte = vcpu->arch.last_pte_updated; + unsigned page_offset, quadrant; + u64 *spte; + int level; + + page_offset = offset_in_page(gpa); + level = sp->role.level; + *nspte = 1; + if (!sp->role.cr4_pae) { + page_offset <<= 1; /* 32->64 */ + /* + * A 32-bit pde maps 4MB while the shadow pdes map + * only 2MB. So we need to double the offset again + * and zap two pdes instead of one. + */ + if (level == PT32_ROOT_LEVEL) { + page_offset &= ~7; /* kill rounding error */ + page_offset <<= 1; + *nspte = 2; + } + quadrant = page_offset >> PAGE_SHIFT; + page_offset &= ~PAGE_MASK; + if (quadrant != sp->role.quadrant) + return NULL; + } - if (spte - && vcpu->arch.last_pte_gfn == gfn - && shadow_accessed_mask - && !(*spte & shadow_accessed_mask) - && is_shadow_present_pte(*spte)) - set_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte); + spte = &sp->spt[page_offset / sizeof(*spte)]; + return spte; } void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes, - bool guest_initiated) + const u8 *new, int bytes) { gfn_t gfn = gpa >> PAGE_SHIFT; union kvm_mmu_page_role mask = { .word = 0 }; struct kvm_mmu_page *sp; - struct hlist_node *node; LIST_HEAD(invalid_list); - u64 entry, gentry; - u64 *spte; - unsigned offset = offset_in_page(gpa); - unsigned pte_size; - unsigned page_offset; - unsigned misaligned; - unsigned quadrant; - int level; - int flooded = 0; + u64 entry, gentry, *spte; int npte; - int r; - int invlpg_counter; 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; pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); - invlpg_counter = atomic_read(&vcpu->kvm->arch.invlpg_counter); + gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, new, &bytes); /* - * Assume that the pte write on a page table of the same type - * as the current vcpu paging mode. This is nearly always true - * (might be false while changing modes). Note it is verified later - * by update_pte(). + * No need to care whether allocation memory is successful + * or not since pte prefetch is skiped if it does not have + * enough objects in the cache. */ - if ((is_pae(vcpu) && bytes == 4) || !new) { - /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ - if (is_pae(vcpu)) { - gpa &= ~(gpa_t)7; - bytes = 8; - } - r = kvm_read_guest(vcpu->kvm, gpa, &gentry, min(bytes, 8)); - if (r) - gentry = 0; - new = (const u8 *)&gentry; - } + mmu_topup_memory_caches(vcpu); - switch (bytes) { - case 4: - gentry = *(const u32 *)new; - break; - case 8: - gentry = *(const u64 *)new; - break; - default: - gentry = 0; - break; - } - - mmu_guess_page_from_pte_write(vcpu, gpa, gentry); spin_lock(&vcpu->kvm->mmu_lock); - if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter) - gentry = 0; - kvm_mmu_access_page(vcpu, gfn); - kvm_mmu_free_some_pages(vcpu); ++vcpu->kvm->stat.mmu_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)) { - ++vcpu->arch.last_pt_write_count; - if (vcpu->arch.last_pt_write_count >= 3) - flooded = 1; - } else { - vcpu->arch.last_pt_write_gfn = gfn; - vcpu->arch.last_pt_write_count = 1; - vcpu->arch.last_pte_updated = NULL; - } - } + kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); 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; - if (misaligned || flooded) { - /* - * Misaligned accesses are too much trouble to fix - * up; also, they usually indicate a page is not used - * as a page table. - * - * If we're seeing too many writes to a page, - * it may no longer be a page table, or we may be - * forking, in which case it is better to unmap the - * page. - */ - pgprintk("misaligned: gpa %llx bytes %d role %x\n", - gpa, bytes, sp->role.word); + for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { + if (detect_write_misaligned(sp, gpa, bytes) || + detect_write_flooding(sp)) { zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); ++vcpu->kvm->stat.mmu_flooded; continue; } - page_offset = offset; - level = sp->role.level; - npte = 1; - if (!sp->role.cr4_pae) { - page_offset <<= 1; /* 32->64 */ - /* - * A 32-bit pde maps 4MB while the shadow pdes map - * only 2MB. So we need to double the offset again - * and zap two pdes instead of one. - */ - if (level == PT32_ROOT_LEVEL) { - page_offset &= ~7; /* kill rounding error */ - page_offset <<= 1; - npte = 2; - } - quadrant = page_offset >> PAGE_SHIFT; - page_offset &= ~PAGE_MASK; - if (quadrant != sp->role.quadrant) - continue; - } + + spte = get_written_sptes(sp, gpa, &npte); + if (!spte) + continue; + local_flush = true; - 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)) + & mask.word) && rmap_can_add(vcpu)) mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); - if (!remote_flush && need_remote_flush(entry, *spte)) + if (need_remote_flush(entry, *spte)) remote_flush = true; ++spte; } } 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); + 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); - vcpu->arch.update_pte.pfn = bad_pfn; - } } int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) @@ -3240,35 +4154,43 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); - spin_lock(&vcpu->kvm->mmu_lock); r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); - spin_unlock(&vcpu->kvm->mmu_lock); + return r; } EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); -void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) +static void make_mmu_pages_available(struct kvm_vcpu *vcpu) { 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; + if (likely(kvm_mmu_available_pages(vcpu->kvm) >= KVM_MIN_FREE_MMU_PAGES)) + return; + + while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES) { + if (!prepare_zap_oldest_mmu_page(vcpu->kvm, &invalid_list)) + break; - 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) +static bool is_mmio_page_fault(struct kvm_vcpu *vcpu, gva_t addr) { - int r; + if (vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu)) + return vcpu_match_mmio_gpa(vcpu, addr); + + return vcpu_match_mmio_gva(vcpu, addr); +} + +int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code, + void *insn, int insn_len) +{ + int r, emulation_type = EMULTYPE_RETRY; enum emulation_result er; - r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code); + r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false); if (r < 0) goto out; @@ -3277,16 +4199,15 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code) goto out; } - r = mmu_topup_memory_caches(vcpu); - if (r) - goto out; + if (is_mmio_page_fault(vcpu, cr2)) + emulation_type = 0; - er = emulate_instruction(vcpu, cr2, error_code, 0); + er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); switch (er) { case EMULATE_DONE: return 1; - case EMULATE_DO_MMIO: + case EMULATE_USER_EXIT: ++vcpu->stat.mmio_exits; /* fall through */ case EMULATE_FAIL: @@ -3352,134 +4273,259 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu) int kvm_mmu_create(struct kvm_vcpu *vcpu) { ASSERT(vcpu); - ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); + + vcpu->arch.walk_mmu = &vcpu->arch.mmu; + vcpu->arch.mmu.root_hpa = INVALID_PAGE; + vcpu->arch.mmu.translate_gpa = translate_gpa; + vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; return alloc_mmu_pages(vcpu); } -int kvm_mmu_setup(struct kvm_vcpu *vcpu) +void kvm_mmu_setup(struct kvm_vcpu *vcpu) { ASSERT(vcpu); ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); - return init_kvm_mmu(vcpu); + init_kvm_mmu(vcpu); } void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) { - struct kvm_mmu_page *sp; + struct kvm_memory_slot *memslot; + gfn_t last_gfn; + int i; - list_for_each_entry(sp, &kvm->arch.active_mmu_pages, link) { - int i; - u64 *pt; + memslot = id_to_memslot(kvm->memslots, slot); + last_gfn = memslot->base_gfn + memslot->npages - 1; - if (!test_bit(slot, sp->slot_bitmap)) - continue; + spin_lock(&kvm->mmu_lock); + + for (i = PT_PAGE_TABLE_LEVEL; + i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + unsigned long *rmapp; + unsigned long last_index, index; + + rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL]; + last_index = gfn_to_index(last_gfn, memslot->base_gfn, i); + + for (index = 0; index <= last_index; ++index, ++rmapp) { + if (*rmapp) + __rmap_write_protect(kvm, rmapp, false); - pt = sp->spt; - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) - /* avoid RMW */ - if (is_writable_pte(pt[i])) - pt[i] &= ~PT_WRITABLE_MASK; + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) + cond_resched_lock(&kvm->mmu_lock); + } } + + spin_unlock(&kvm->mmu_lock); + + /* + * kvm_mmu_slot_remove_write_access() and kvm_vm_ioctl_get_dirty_log() + * which do tlb flush out of mmu-lock should be serialized by + * kvm->slots_lock otherwise tlb flush would be missed. + */ + lockdep_assert_held(&kvm->slots_lock); + + /* + * We can flush all the TLBs out of the mmu lock without TLB + * corruption since we just change the spte from writable to + * readonly so that we only need to care the case of changing + * spte from present to present (changing the spte from present + * to nonpresent will flush all the TLBs immediately), in other + * words, the only case we care is mmu_spte_update() where we + * haved checked SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE + * instead of PT_WRITABLE_MASK, that means it does not depend + * on PT_WRITABLE_MASK anymore. + */ kvm_flush_remote_tlbs(kvm); } -void kvm_mmu_zap_all(struct kvm *kvm) +#define BATCH_ZAP_PAGES 10 +static void kvm_zap_obsolete_pages(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; - LIST_HEAD(invalid_list); + int batch = 0; - spin_lock(&kvm->mmu_lock); restart: - list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) - if (kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list)) + list_for_each_entry_safe_reverse(sp, node, + &kvm->arch.active_mmu_pages, link) { + int ret; + + /* + * No obsolete page exists before new created page since + * active_mmu_pages is the FIFO list. + */ + if (!is_obsolete_sp(kvm, sp)) + break; + + /* + * Since we are reversely walking the list and the invalid + * list will be moved to the head, skip the invalid page + * can help us to avoid the infinity list walking. + */ + if (sp->role.invalid) + continue; + + /* + * Need not flush tlb since we only zap the sp with invalid + * generation number. + */ + if (batch >= BATCH_ZAP_PAGES && + cond_resched_lock(&kvm->mmu_lock)) { + batch = 0; goto restart; + } - kvm_mmu_commit_zap_page(kvm, &invalid_list); + ret = kvm_mmu_prepare_zap_page(kvm, sp, + &kvm->arch.zapped_obsolete_pages); + batch += ret; + + if (ret) + goto restart; + } + + /* + * Should flush tlb before free page tables since lockless-walking + * may use the pages. + */ + kvm_mmu_commit_zap_page(kvm, &kvm->arch.zapped_obsolete_pages); +} + +/* + * Fast invalidate all shadow pages and use lock-break technique + * to zap obsolete pages. + * + * It's required when memslot is being deleted or VM is being + * destroyed, in these cases, we should ensure that KVM MMU does + * not use any resource of the being-deleted slot or all slots + * after calling the function. + */ +void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm) +{ + spin_lock(&kvm->mmu_lock); + trace_kvm_mmu_invalidate_zap_all_pages(kvm); + kvm->arch.mmu_valid_gen++; + + /* + * Notify all vcpus to reload its shadow page table + * and flush TLB. Then all vcpus will switch to new + * shadow page table with the new mmu_valid_gen. + * + * Note: we should do this under the protection of + * mmu-lock, otherwise, vcpu would purge shadow page + * but miss tlb flush. + */ + kvm_reload_remote_mmus(kvm); + + kvm_zap_obsolete_pages(kvm); spin_unlock(&kvm->mmu_lock); } -static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm, - struct list_head *invalid_list) +static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) { - struct kvm_mmu_page *page; + return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); +} - page = container_of(kvm->arch.active_mmu_pages.prev, - struct kvm_mmu_page, link); - return kvm_mmu_prepare_zap_page(kvm, page, invalid_list); +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm) +{ + /* + * The very rare case: if the generation-number is round, + * zap all shadow pages. + */ + if (unlikely(kvm_current_mmio_generation(kvm) >= MMIO_MAX_GEN)) { + printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n"); + kvm_mmu_invalidate_zap_all_pages(kvm); + } } -static int mmu_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) +static unsigned long +mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { struct kvm *kvm; - struct kvm *kvm_freed = NULL; - - if (nr_to_scan == 0) - goto out; + int nr_to_scan = sc->nr_to_scan; + unsigned long freed = 0; spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { - int idx, freed_pages; + int idx; LIST_HEAD(invalid_list); + /* + * Never scan more than sc->nr_to_scan VM instances. + * Will not hit this condition practically since we do not try + * to shrink more than one VM and it is very unlikely to see + * !n_used_mmu_pages so many times. + */ + if (!nr_to_scan--) + break; + /* + * n_used_mmu_pages is accessed without holding kvm->mmu_lock + * here. We may skip a VM instance errorneosly, but we do not + * want to shrink a VM that only started to populate its MMU + * anyway. + */ + if (!kvm->arch.n_used_mmu_pages && + !kvm_has_zapped_obsolete_pages(kvm)) + continue; + idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); - 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; + + if (kvm_has_zapped_obsolete_pages(kvm)) { + kvm_mmu_commit_zap_page(kvm, + &kvm->arch.zapped_obsolete_pages); + goto unlock; } - nr_to_scan--; + if (prepare_zap_oldest_mmu_page(kvm, &invalid_list)) + freed++; kvm_mmu_commit_zap_page(kvm, &invalid_list); + +unlock: spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); + + /* + * unfair on small ones + * per-vm shrinkers cry out + * sadness comes quickly + */ + list_move_tail(&kvm->vm_list, &vm_list); + break; } - if (kvm_freed) - list_move_tail(&kvm_freed->vm_list, &vm_list); spin_unlock(&kvm_lock); + return freed; +} -out: +static unsigned long +mmu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +{ return percpu_counter_read_positive(&kvm_total_used_mmu_pages); } static struct shrinker mmu_shrinker = { - .shrink = mmu_shrink, + .count_objects = mmu_shrink_count, + .scan_objects = mmu_shrink_scan, .seeks = DEFAULT_SEEKS * 10, }; 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); } -void kvm_mmu_module_exit(void) -{ - mmu_destroy_caches(); - percpu_counter_destroy(&kvm_total_used_mmu_pages); - unregister_shrinker(&mmu_shrinker); -} - int kvm_mmu_module_init(void) { - pte_chain_cache = kmem_cache_create("kvm_pte_chain", - sizeof(struct kvm_pte_chain), + pte_list_desc_cache = kmem_cache_create("pte_list_desc", + sizeof(struct pte_list_desc), 0, 0, NULL); - if (!pte_chain_cache) - goto nomem; - rmap_desc_cache = kmem_cache_create("kvm_rmap_desc", - sizeof(struct kvm_rmap_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", @@ -3505,15 +4551,15 @@ nomem: */ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) { - int i; unsigned int nr_mmu_pages; unsigned int nr_pages = 0; struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; slots = kvm_memslots(kvm); - for (i = 0; i < slots->nmemslots; i++) - nr_pages += slots->memslots[i].npages; + kvm_for_each_memslot(memslot, slots) + nr_pages += memslot->npages; nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; nr_mmu_pages = max(nr_mmu_pages, @@ -3522,157 +4568,41 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) return nr_mmu_pages; } -static void *pv_mmu_peek_buffer(struct kvm_pv_mmu_op_buffer *buffer, - unsigned len) -{ - if (len > buffer->len) - return NULL; - return buffer->ptr; -} - -static void *pv_mmu_read_buffer(struct kvm_pv_mmu_op_buffer *buffer, - unsigned len) -{ - void *ret; - - ret = pv_mmu_peek_buffer(buffer, len); - if (!ret) - return ret; - buffer->ptr += len; - buffer->len -= len; - buffer->processed += len; - return ret; -} - -static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu, - gpa_t addr, gpa_t value) -{ - int bytes = 8; - int r; - - if (!is_long_mode(vcpu) && !is_pae(vcpu)) - bytes = 4; - - r = mmu_topup_memory_caches(vcpu); - if (r) - return r; - - if (!emulator_write_phys(vcpu, addr, &value, bytes)) - return -EFAULT; - - return 1; -} - -static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu) -{ - (void)kvm_set_cr3(vcpu, vcpu->arch.cr3); - return 1; -} - -static int kvm_pv_mmu_release_pt(struct kvm_vcpu *vcpu, gpa_t addr) -{ - spin_lock(&vcpu->kvm->mmu_lock); - mmu_unshadow(vcpu->kvm, addr >> PAGE_SHIFT); - spin_unlock(&vcpu->kvm->mmu_lock); - return 1; -} - -static int kvm_pv_mmu_op_one(struct kvm_vcpu *vcpu, - struct kvm_pv_mmu_op_buffer *buffer) -{ - struct kvm_mmu_op_header *header; - - header = pv_mmu_peek_buffer(buffer, sizeof *header); - if (!header) - return 0; - switch (header->op) { - case KVM_MMU_OP_WRITE_PTE: { - struct kvm_mmu_op_write_pte *wpte; - - wpte = pv_mmu_read_buffer(buffer, sizeof *wpte); - if (!wpte) - return 0; - return kvm_pv_mmu_write(vcpu, wpte->pte_phys, - wpte->pte_val); - } - case KVM_MMU_OP_FLUSH_TLB: { - struct kvm_mmu_op_flush_tlb *ftlb; - - ftlb = pv_mmu_read_buffer(buffer, sizeof *ftlb); - if (!ftlb) - return 0; - return kvm_pv_mmu_flush_tlb(vcpu); - } - case KVM_MMU_OP_RELEASE_PT: { - struct kvm_mmu_op_release_pt *rpt; - - rpt = pv_mmu_read_buffer(buffer, sizeof *rpt); - if (!rpt) - return 0; - return kvm_pv_mmu_release_pt(vcpu, rpt->pt_phys); - } - default: return 0; - } -} - -int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes, - gpa_t addr, unsigned long *ret) -{ - int r; - struct kvm_pv_mmu_op_buffer *buffer = &vcpu->arch.mmu_op_buffer; - - buffer->ptr = buffer->buf; - buffer->len = min_t(unsigned long, bytes, sizeof buffer->buf); - buffer->processed = 0; - - r = kvm_read_guest(vcpu->kvm, addr, buffer->buf, buffer->len); - if (r) - goto out; - - while (buffer->len) { - r = kvm_pv_mmu_op_one(vcpu, buffer); - if (r < 0) - goto out; - if (r == 0) - break; - } - - r = 1; -out: - *ret = buffer->processed; - return r; -} - int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]) { struct kvm_shadow_walk_iterator iterator; + u64 spte; int nr_sptes = 0; - spin_lock(&vcpu->kvm->mmu_lock); - for_each_shadow_entry(vcpu, addr, iterator) { - sptes[iterator.level-1] = *iterator.sptep; + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + return nr_sptes; + + walk_shadow_page_lockless_begin(vcpu); + for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) { + sptes[iterator.level-1] = spte; nr_sptes++; - if (!is_shadow_present_pte(*iterator.sptep)) + if (!is_shadow_present_pte(spte)) break; } - spin_unlock(&vcpu->kvm->mmu_lock); + walk_shadow_page_lockless_end(vcpu); return nr_sptes; } EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy); -#ifdef CONFIG_KVM_MMU_AUDIT -#include "mmu_audit.c" -#else -static void mmu_audit_disable(void) { } -#endif - void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { ASSERT(vcpu); - destroy_kvm_mmu(vcpu); + kvm_mmu_unload(vcpu); free_mmu_pages(vcpu); mmu_free_memory_caches(vcpu); +} + +void kvm_mmu_module_exit(void) +{ + mmu_destroy_caches(); + percpu_counter_destroy(&kvm_total_used_mmu_pages); + unregister_shrinker(&mmu_shrinker); mmu_audit_disable(); } |