diff options
Diffstat (limited to 'arch/x86/kvm/mmu.c')
-rw-r--r-- | arch/x86/kvm/mmu.c | 672 |
1 files changed, 567 insertions, 105 deletions
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e55af12e11b7..2ad6f5481671 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -27,11 +27,22 @@ #include <linux/highmem.h> #include <linux/module.h> #include <linux/swap.h> +#include <linux/hugetlb.h> +#include <linux/compiler.h> #include <asm/page.h> #include <asm/cmpxchg.h> #include <asm/io.h> +/* + * When setting this variable to true it enables Two-Dimensional-Paging + * where the hardware walks 2 page tables: + * 1. the guest-virtual to guest-physical + * 2. while doing 1. it walks guest-physical to host-physical + * If the hardware supports that we don't need to do shadow paging. + */ +bool tdp_enabled = false; + #undef MMU_DEBUG #undef AUDIT @@ -101,8 +112,6 @@ static int dbg = 1; #define PT_FIRST_AVAIL_BITS_SHIFT 9 #define PT64_SECOND_AVAIL_BITS_SHIFT 52 -#define PT_SHADOW_IO_MARK (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) - #define VALID_PAGE(x) ((x) != INVALID_PAGE) #define PT64_LEVEL_BITS 9 @@ -159,6 +168,13 @@ static int dbg = 1; #define ACC_USER_MASK PT_USER_MASK #define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK) +struct kvm_pv_mmu_op_buffer { + void *ptr; + unsigned len; + unsigned processed; + char buf[512] __aligned(sizeof(long)); +}; + struct kvm_rmap_desc { u64 *shadow_ptes[RMAP_EXT]; struct kvm_rmap_desc *more; @@ -200,11 +216,15 @@ static int is_present_pte(unsigned long pte) static int is_shadow_present_pte(u64 pte) { - pte &= ~PT_SHADOW_IO_MARK; return pte != shadow_trap_nonpresent_pte && pte != shadow_notrap_nonpresent_pte; } +static int is_large_pte(u64 pte) +{ + return pte & PT_PAGE_SIZE_MASK; +} + static int is_writeble_pte(unsigned long pte) { return pte & PT_WRITABLE_MASK; @@ -215,14 +235,14 @@ static int is_dirty_pte(unsigned long pte) return pte & PT_DIRTY_MASK; } -static int is_io_pte(unsigned long pte) +static int is_rmap_pte(u64 pte) { - return pte & PT_SHADOW_IO_MARK; + return is_shadow_present_pte(pte); } -static int is_rmap_pte(u64 pte) +static pfn_t spte_to_pfn(u64 pte) { - return is_shadow_present_pte(pte); + return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; } static gfn_t pse36_gfn_delta(u32 gpte) @@ -349,16 +369,100 @@ static void mmu_free_rmap_desc(struct kvm_rmap_desc *rd) } /* + * Return the pointer to the largepage write count for a given + * gfn, handling slots that are not large page aligned. + */ +static int *slot_largepage_idx(gfn_t gfn, struct kvm_memory_slot *slot) +{ + unsigned long idx; + + idx = (gfn / KVM_PAGES_PER_HPAGE) - + (slot->base_gfn / KVM_PAGES_PER_HPAGE); + return &slot->lpage_info[idx].write_count; +} + +static void account_shadowed(struct kvm *kvm, gfn_t gfn) +{ + int *write_count; + + write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn)); + *write_count += 1; + WARN_ON(*write_count > KVM_PAGES_PER_HPAGE); +} + +static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn) +{ + int *write_count; + + write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn)); + *write_count -= 1; + WARN_ON(*write_count < 0); +} + +static int has_wrprotected_page(struct kvm *kvm, gfn_t gfn) +{ + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + int *largepage_idx; + + if (slot) { + largepage_idx = slot_largepage_idx(gfn, slot); + return *largepage_idx; + } + + return 1; +} + +static int host_largepage_backed(struct kvm *kvm, gfn_t gfn) +{ + struct vm_area_struct *vma; + unsigned long addr; + + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) + return 0; + + vma = find_vma(current->mm, addr); + if (vma && is_vm_hugetlb_page(vma)) + return 1; + + return 0; +} + +static int is_largepage_backed(struct kvm_vcpu *vcpu, gfn_t large_gfn) +{ + struct kvm_memory_slot *slot; + + if (has_wrprotected_page(vcpu->kvm, large_gfn)) + return 0; + + if (!host_largepage_backed(vcpu->kvm, large_gfn)) + return 0; + + slot = gfn_to_memslot(vcpu->kvm, large_gfn); + if (slot && slot->dirty_bitmap) + return 0; + + return 1; +} + +/* * Take gfn and return the reverse mapping to it. * Note: gfn must be unaliased before this function get called */ -static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn) +static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage) { struct kvm_memory_slot *slot; + unsigned long idx; slot = gfn_to_memslot(kvm, gfn); - return &slot->rmap[gfn - slot->base_gfn]; + if (!lpage) + return &slot->rmap[gfn - slot->base_gfn]; + + idx = (gfn / KVM_PAGES_PER_HPAGE) - + (slot->base_gfn / KVM_PAGES_PER_HPAGE); + + return &slot->lpage_info[idx].rmap_pde; } /* @@ -370,7 +474,7 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn) * If rmapp bit zero is one, (then rmap & ~1) points to a struct kvm_rmap_desc * containing more mappings. */ -static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) +static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage) { struct kvm_mmu_page *sp; struct kvm_rmap_desc *desc; @@ -382,7 +486,7 @@ static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) gfn = unalias_gfn(vcpu->kvm, gfn); sp = page_header(__pa(spte)); sp->gfns[spte - sp->spt] = gfn; - rmapp = gfn_to_rmap(vcpu->kvm, gfn); + rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage); if (!*rmapp) { rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte); *rmapp = (unsigned long)spte; @@ -435,20 +539,21 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) struct kvm_rmap_desc *desc; struct kvm_rmap_desc *prev_desc; struct kvm_mmu_page *sp; - struct page *page; + pfn_t pfn; unsigned long *rmapp; int i; if (!is_rmap_pte(*spte)) return; sp = page_header(__pa(spte)); - page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT); - mark_page_accessed(page); + pfn = spte_to_pfn(*spte); + if (*spte & PT_ACCESSED_MASK) + kvm_set_pfn_accessed(pfn); if (is_writeble_pte(*spte)) - kvm_release_page_dirty(page); + kvm_release_pfn_dirty(pfn); else - kvm_release_page_clean(page); - rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt]); + kvm_release_pfn_clean(pfn); + rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], is_large_pte(*spte)); if (!*rmapp) { printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte); BUG(); @@ -514,7 +619,7 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn) int write_protected = 0; gfn = unalias_gfn(kvm, gfn); - rmapp = gfn_to_rmap(kvm, gfn); + rmapp = gfn_to_rmap(kvm, gfn, 0); spte = rmap_next(kvm, rmapp, NULL); while (spte) { @@ -527,8 +632,35 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn) } spte = rmap_next(kvm, rmapp, spte); } + if (write_protected) { + pfn_t pfn; + + spte = rmap_next(kvm, rmapp, NULL); + pfn = spte_to_pfn(*spte); + kvm_set_pfn_dirty(pfn); + } + + /* check for huge page mappings */ + rmapp = gfn_to_rmap(kvm, gfn, 1); + spte = rmap_next(kvm, rmapp, NULL); + while (spte) { + BUG_ON(!spte); + BUG_ON(!(*spte & PT_PRESENT_MASK)); + BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)); + pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn); + if (is_writeble_pte(*spte)) { + rmap_remove(kvm, spte); + --kvm->stat.lpages; + set_shadow_pte(spte, shadow_trap_nonpresent_pte); + write_protected = 1; + } + spte = rmap_next(kvm, rmapp, spte); + } + if (write_protected) kvm_flush_remote_tlbs(kvm); + + account_shadowed(kvm, gfn); } #ifdef MMU_DEBUG @@ -538,8 +670,8 @@ static int is_empty_shadow_page(u64 *spt) u64 *end; for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++) - if ((*pos & ~PT_SHADOW_IO_MARK) != shadow_trap_nonpresent_pte) { - printk(KERN_ERR "%s: %p %llx\n", __FUNCTION__, + if (*pos != shadow_trap_nonpresent_pte) { + printk(KERN_ERR "%s: %p %llx\n", __func__, pos, *pos); return 0; } @@ -559,7 +691,7 @@ static void kvm_mmu_free_page(struct kvm *kvm, struct kvm_mmu_page *sp) static unsigned kvm_page_table_hashfn(gfn_t gfn) { - return gfn; + return gfn & ((1 << KVM_MMU_HASH_SHIFT) - 1); } static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, @@ -662,13 +794,14 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn) struct kvm_mmu_page *sp; struct hlist_node *node; - pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn); - index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; + pgprintk("%s: looking for gfn %lx\n", __func__, gfn); + index = kvm_page_table_hashfn(gfn); bucket = &kvm->arch.mmu_page_hash[index]; hlist_for_each_entry(sp, node, bucket, hash_link) - if (sp->gfn == gfn && !sp->role.metaphysical) { + if (sp->gfn == gfn && !sp->role.metaphysical + && !sp->role.invalid) { pgprintk("%s: found role %x\n", - __FUNCTION__, sp->role.word); + __func__, sp->role.word); return sp; } return NULL; @@ -699,27 +832,27 @@ 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; } - pgprintk("%s: looking gfn %lx role %x\n", __FUNCTION__, + pgprintk("%s: looking gfn %lx role %x\n", __func__, gfn, role.word); - index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; + index = kvm_page_table_hashfn(gfn); bucket = &vcpu->kvm->arch.mmu_page_hash[index]; hlist_for_each_entry(sp, node, bucket, hash_link) if (sp->gfn == gfn && sp->role.word == role.word) { mmu_page_add_parent_pte(vcpu, sp, parent_pte); - pgprintk("%s: found\n", __FUNCTION__); + pgprintk("%s: found\n", __func__); return sp; } ++vcpu->kvm->stat.mmu_cache_miss; sp = kvm_mmu_alloc_page(vcpu, parent_pte); if (!sp) return sp; - pgprintk("%s: adding gfn %lx role %x\n", __FUNCTION__, gfn, role.word); + pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word); sp->gfn = gfn; sp->role = role; hlist_add_head(&sp->hash_link, bucket); - vcpu->arch.mmu.prefetch_page(vcpu, sp); if (!metaphysical) rmap_write_protect(vcpu->kvm, gfn); + vcpu->arch.mmu.prefetch_page(vcpu, sp); return sp; } @@ -745,11 +878,17 @@ static void kvm_mmu_page_unlink_children(struct kvm *kvm, for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { ent = pt[i]; + if (is_shadow_present_pte(ent)) { + if (!is_large_pte(ent)) { + ent &= PT64_BASE_ADDR_MASK; + mmu_page_remove_parent_pte(page_header(ent), + &pt[i]); + } else { + --kvm->stat.lpages; + rmap_remove(kvm, &pt[i]); + } + } pt[i] = shadow_trap_nonpresent_pte; - if (!is_shadow_present_pte(ent)) - continue; - ent &= PT64_BASE_ADDR_MASK; - mmu_page_remove_parent_pte(page_header(ent), &pt[i]); } kvm_flush_remote_tlbs(kvm); } @@ -789,10 +928,15 @@ static void kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) } kvm_mmu_page_unlink_children(kvm, sp); if (!sp->root_count) { + if (!sp->role.metaphysical) + unaccount_shadowed(kvm, sp->gfn); hlist_del(&sp->hash_link); kvm_mmu_free_page(kvm, sp); - } else + } else { list_move(&sp->link, &kvm->arch.active_mmu_pages); + sp->role.invalid = 1; + kvm_reload_remote_mmus(kvm); + } kvm_mmu_reset_last_pte_updated(kvm); } @@ -838,13 +982,13 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) struct hlist_node *node, *n; int r; - pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn); + pgprintk("%s: looking for gfn %lx\n", __func__, gfn); r = 0; - index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; + index = kvm_page_table_hashfn(gfn); bucket = &kvm->arch.mmu_page_hash[index]; hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) if (sp->gfn == gfn && !sp->role.metaphysical) { - pgprintk("%s: gfn %lx role %x\n", __FUNCTION__, gfn, + pgprintk("%s: gfn %lx role %x\n", __func__, gfn, sp->role.word); kvm_mmu_zap_page(kvm, sp); r = 1; @@ -857,7 +1001,7 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) struct kvm_mmu_page *sp; while ((sp = kvm_mmu_lookup_page(kvm, gfn)) != NULL) { - pgprintk("%s: zap %lx %x\n", __FUNCTION__, gfn, sp->role.word); + pgprintk("%s: zap %lx %x\n", __func__, gfn, sp->role.word); kvm_mmu_zap_page(kvm, sp); } } @@ -889,26 +1033,39 @@ struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva) static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, unsigned pt_access, unsigned pte_access, int user_fault, int write_fault, int dirty, - int *ptwrite, gfn_t gfn, struct page *page) + int *ptwrite, int largepage, gfn_t gfn, + pfn_t pfn, bool speculative) { u64 spte; int was_rmapped = 0; int was_writeble = is_writeble_pte(*shadow_pte); - hfn_t host_pfn = (*shadow_pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; pgprintk("%s: spte %llx access %x write_fault %d" " user_fault %d gfn %lx\n", - __FUNCTION__, *shadow_pte, pt_access, + __func__, *shadow_pte, pt_access, write_fault, user_fault, gfn); if (is_rmap_pte(*shadow_pte)) { - if (host_pfn != page_to_pfn(page)) { + /* + * If we overwrite a PTE page pointer with a 2MB PMD, unlink + * the parent of the now unreachable PTE. + */ + if (largepage && !is_large_pte(*shadow_pte)) { + struct kvm_mmu_page *child; + u64 pte = *shadow_pte; + + child = page_header(pte & PT64_BASE_ADDR_MASK); + mmu_page_remove_parent_pte(child, shadow_pte); + } else if (pfn != spte_to_pfn(*shadow_pte)) { pgprintk("hfn old %lx new %lx\n", - host_pfn, page_to_pfn(page)); + spte_to_pfn(*shadow_pte), pfn); rmap_remove(vcpu->kvm, shadow_pte); + } else { + if (largepage) + was_rmapped = is_large_pte(*shadow_pte); + else + was_rmapped = 1; } - else - was_rmapped = 1; } /* @@ -917,6 +1074,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, * demand paging). */ spte = PT_PRESENT_MASK | PT_DIRTY_MASK; + if (!speculative) + pte_access |= PT_ACCESSED_MASK; if (!dirty) pte_access &= ~ACC_WRITE_MASK; if (!(pte_access & ACC_EXEC_MASK)) @@ -925,15 +1084,10 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, spte |= PT_PRESENT_MASK; if (pte_access & ACC_USER_MASK) spte |= PT_USER_MASK; + if (largepage) + spte |= PT_PAGE_SIZE_MASK; - if (is_error_page(page)) { - set_shadow_pte(shadow_pte, - shadow_trap_nonpresent_pte | PT_SHADOW_IO_MARK); - kvm_release_page_clean(page); - return; - } - - spte |= page_to_phys(page); + spte |= (u64)pfn << PAGE_SHIFT; if ((pte_access & ACC_WRITE_MASK) || (write_fault && !is_write_protection(vcpu) && !user_fault)) { @@ -946,9 +1100,10 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, } shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn); - if (shadow) { + if (shadow || + (largepage && has_wrprotected_page(vcpu->kvm, gfn))) { pgprintk("%s: found shadow page for %lx, marking ro\n", - __FUNCTION__, gfn); + __func__, gfn); pte_access &= ~ACC_WRITE_MASK; if (is_writeble_pte(spte)) { spte &= ~PT_WRITABLE_MASK; @@ -964,18 +1119,25 @@ unshadowed: if (pte_access & ACC_WRITE_MASK) mark_page_dirty(vcpu->kvm, gfn); - pgprintk("%s: setting spte %llx\n", __FUNCTION__, spte); + pgprintk("%s: setting spte %llx\n", __func__, spte); + pgprintk("instantiating %s PTE (%s) at %d (%llx) addr %llx\n", + (spte&PT_PAGE_SIZE_MASK)? "2MB" : "4kB", + (spte&PT_WRITABLE_MASK)?"RW":"R", gfn, spte, shadow_pte); set_shadow_pte(shadow_pte, spte); + if (!was_rmapped && (spte & PT_PAGE_SIZE_MASK) + && (spte & PT_PRESENT_MASK)) + ++vcpu->kvm->stat.lpages; + page_header_update_slot(vcpu->kvm, shadow_pte, gfn); if (!was_rmapped) { - rmap_add(vcpu, shadow_pte, gfn); + rmap_add(vcpu, shadow_pte, gfn, largepage); if (!is_rmap_pte(*shadow_pte)) - kvm_release_page_clean(page); + kvm_release_pfn_clean(pfn); } else { if (was_writeble) - kvm_release_page_dirty(page); + kvm_release_pfn_dirty(pfn); else - kvm_release_page_clean(page); + kvm_release_pfn_clean(pfn); } if (!ptwrite || !*ptwrite) vcpu->arch.last_pte_updated = shadow_pte; @@ -985,10 +1147,10 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) { } -static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, - gfn_t gfn, struct page *page) +static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, + int largepage, gfn_t gfn, pfn_t pfn, + int level) { - int level = PT32E_ROOT_LEVEL; hpa_t table_addr = vcpu->arch.mmu.root_hpa; int pt_write = 0; @@ -1001,8 +1163,14 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, if (level == 1) { mmu_set_spte(vcpu, &table[index], ACC_ALL, ACC_ALL, - 0, write, 1, &pt_write, gfn, page); - return pt_write || is_io_pte(table[index]); + 0, write, 1, &pt_write, 0, gfn, pfn, false); + return pt_write; + } + + if (largepage && level == 2) { + mmu_set_spte(vcpu, &table[index], ACC_ALL, ACC_ALL, + 0, write, 1, &pt_write, 1, gfn, pfn, false); + return pt_write; } if (table[index] == shadow_trap_nonpresent_pte) { @@ -1016,7 +1184,7 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, 1, ACC_ALL, &table[index]); if (!new_table) { pgprintk("nonpaging_map: ENOMEM\n"); - kvm_release_page_clean(page); + kvm_release_pfn_clean(pfn); return -ENOMEM; } @@ -1030,21 +1198,30 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) { int r; - - struct page *page; - - down_read(&vcpu->kvm->slots_lock); + int largepage = 0; + pfn_t pfn; down_read(¤t->mm->mmap_sem); - page = gfn_to_page(vcpu->kvm, gfn); + if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) { + gfn &= ~(KVM_PAGES_PER_HPAGE-1); + largepage = 1; + } + + pfn = gfn_to_pfn(vcpu->kvm, gfn); up_read(¤t->mm->mmap_sem); + /* mmio */ + if (is_error_pfn(pfn)) { + kvm_release_pfn_clean(pfn); + return 1; + } + spin_lock(&vcpu->kvm->mmu_lock); kvm_mmu_free_some_pages(vcpu); - r = __nonpaging_map(vcpu, v, write, gfn, page); + r = __direct_map(vcpu, v, write, largepage, gfn, pfn, + PT32E_ROOT_LEVEL); spin_unlock(&vcpu->kvm->mmu_lock); - up_read(&vcpu->kvm->slots_lock); return r; } @@ -1073,6 +1250,8 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) sp = page_header(root); --sp->root_count; + if (!sp->root_count && sp->role.invalid) + kvm_mmu_zap_page(vcpu->kvm, sp); vcpu->arch.mmu.root_hpa = INVALID_PAGE; spin_unlock(&vcpu->kvm->mmu_lock); return; @@ -1085,6 +1264,8 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) root &= PT64_BASE_ADDR_MASK; sp = page_header(root); --sp->root_count; + if (!sp->root_count && sp->role.invalid) + kvm_mmu_zap_page(vcpu->kvm, sp); } vcpu->arch.mmu.pae_root[i] = INVALID_PAGE; } @@ -1097,6 +1278,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) int i; gfn_t root_gfn; struct kvm_mmu_page *sp; + int metaphysical = 0; root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT; @@ -1105,14 +1287,20 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) hpa_t root = vcpu->arch.mmu.root_hpa; ASSERT(!VALID_PAGE(root)); + if (tdp_enabled) + metaphysical = 1; sp = kvm_mmu_get_page(vcpu, root_gfn, 0, - PT64_ROOT_LEVEL, 0, ACC_ALL, NULL); + PT64_ROOT_LEVEL, metaphysical, + ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; vcpu->arch.mmu.root_hpa = root; return; } #endif + metaphysical = !is_paging(vcpu); + if (tdp_enabled) + metaphysical = 1; for (i = 0; i < 4; ++i) { hpa_t root = vcpu->arch.mmu.pae_root[i]; @@ -1126,7 +1314,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) } else if (vcpu->arch.mmu.root_level == 0) root_gfn = 0; sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, - PT32_ROOT_LEVEL, !is_paging(vcpu), + PT32_ROOT_LEVEL, metaphysical, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; @@ -1146,7 +1334,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn; int r; - pgprintk("%s: gva %lx error %x\n", __FUNCTION__, gva, error_code); + pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); r = mmu_topup_memory_caches(vcpu); if (r) return r; @@ -1160,6 +1348,41 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, error_code & PFERR_WRITE_MASK, gfn); } +static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, + u32 error_code) +{ + pfn_t pfn; + int r; + int largepage = 0; + gfn_t gfn = gpa >> PAGE_SHIFT; + + ASSERT(vcpu); + ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa)); + + r = mmu_topup_memory_caches(vcpu); + if (r) + return r; + + down_read(¤t->mm->mmap_sem); + if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) { + gfn &= ~(KVM_PAGES_PER_HPAGE-1); + largepage = 1; + } + pfn = gfn_to_pfn(vcpu->kvm, gfn); + up_read(¤t->mm->mmap_sem); + if (is_error_pfn(pfn)) { + kvm_release_pfn_clean(pfn); + return 1; + } + spin_lock(&vcpu->kvm->mmu_lock); + kvm_mmu_free_some_pages(vcpu); + r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK, + largepage, gfn, pfn, TDP_ROOT_LEVEL); + spin_unlock(&vcpu->kvm->mmu_lock); + + return r; +} + static void nonpaging_free(struct kvm_vcpu *vcpu) { mmu_free_roots(vcpu); @@ -1188,7 +1411,7 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) static void paging_new_cr3(struct kvm_vcpu *vcpu) { - pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->arch.cr3); + pgprintk("%s: cr3 %lx\n", __func__, vcpu->arch.cr3); mmu_free_roots(vcpu); } @@ -1253,7 +1476,35 @@ static int paging32E_init_context(struct kvm_vcpu *vcpu) return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL); } -static int init_kvm_mmu(struct kvm_vcpu *vcpu) +static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu *context = &vcpu->arch.mmu; + + context->new_cr3 = nonpaging_new_cr3; + context->page_fault = tdp_page_fault; + context->free = nonpaging_free; + context->prefetch_page = nonpaging_prefetch_page; + context->shadow_root_level = TDP_ROOT_LEVEL; + context->root_hpa = INVALID_PAGE; + + if (!is_paging(vcpu)) { + context->gva_to_gpa = nonpaging_gva_to_gpa; + context->root_level = 0; + } else if (is_long_mode(vcpu)) { + context->gva_to_gpa = paging64_gva_to_gpa; + context->root_level = PT64_ROOT_LEVEL; + } else if (is_pae(vcpu)) { + context->gva_to_gpa = paging64_gva_to_gpa; + context->root_level = PT32E_ROOT_LEVEL; + } else { + context->gva_to_gpa = paging32_gva_to_gpa; + context->root_level = PT32_ROOT_LEVEL; + } + + return 0; +} + +static int init_kvm_softmmu(struct kvm_vcpu *vcpu) { ASSERT(vcpu); ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); @@ -1268,6 +1519,16 @@ static int init_kvm_mmu(struct kvm_vcpu *vcpu) return paging32_init_context(vcpu); } +static int init_kvm_mmu(struct kvm_vcpu *vcpu) +{ + vcpu->arch.update_pte.pfn = bad_pfn; + + if (tdp_enabled) + return init_kvm_tdp_mmu(vcpu); + else + return init_kvm_softmmu(vcpu); +} + static void destroy_kvm_mmu(struct kvm_vcpu *vcpu) { ASSERT(vcpu); @@ -1316,7 +1577,8 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu, pte = *spte; if (is_shadow_present_pte(pte)) { - if (sp->role.level == PT_PAGE_TABLE_LEVEL) + if (sp->role.level == PT_PAGE_TABLE_LEVEL || + is_large_pte(pte)) rmap_remove(vcpu->kvm, spte); else { child = page_header(pte & PT64_BASE_ADDR_MASK); @@ -1324,24 +1586,26 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu, } } set_shadow_pte(spte, shadow_trap_nonpresent_pte); + if (is_large_pte(pte)) + --vcpu->kvm->stat.lpages; } static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, - const void *new, int bytes, - int offset_in_pte) + const void *new) { - if (sp->role.level != PT_PAGE_TABLE_LEVEL) { + if ((sp->role.level != PT_PAGE_TABLE_LEVEL) + && !vcpu->arch.update_pte.largepage) { ++vcpu->kvm->stat.mmu_pde_zapped; return; } ++vcpu->kvm->stat.mmu_pte_updated; if (sp->role.glevels == PT32_ROOT_LEVEL) - paging32_update_pte(vcpu, sp, spte, new, bytes, offset_in_pte); + paging32_update_pte(vcpu, sp, spte, new); else - paging64_update_pte(vcpu, sp, spte, new, bytes, offset_in_pte); + paging64_update_pte(vcpu, sp, spte, new); } static bool need_remote_flush(u64 old, u64 new) @@ -1378,7 +1642,9 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, gfn_t gfn; int r; u64 gpte = 0; - struct page *page; + pfn_t pfn; + + vcpu->arch.update_pte.largepage = 0; if (bytes != 4 && bytes != 8) return; @@ -1408,11 +1674,19 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; down_read(¤t->mm->mmap_sem); - page = gfn_to_page(vcpu->kvm, gfn); + if (is_large_pte(gpte) && is_largepage_backed(vcpu, gfn)) { + gfn &= ~(KVM_PAGES_PER_HPAGE-1); + vcpu->arch.update_pte.largepage = 1; + } + pfn = gfn_to_pfn(vcpu->kvm, gfn); up_read(¤t->mm->mmap_sem); + if (is_error_pfn(pfn)) { + kvm_release_pfn_clean(pfn); + return; + } vcpu->arch.update_pte.gfn = gfn; - vcpu->arch.update_pte.page = page; + vcpu->arch.update_pte.pfn = pfn; } void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, @@ -1423,7 +1697,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, struct hlist_node *node, *n; struct hlist_head *bucket; unsigned index; - u64 entry; + u64 entry, gentry; u64 *spte; unsigned offset = offset_in_page(gpa); unsigned pte_size; @@ -1433,8 +1707,9 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, int level; int flooded = 0; int npte; + int r; - pgprintk("%s: gpa %llx bytes %d\n", __FUNCTION__, gpa, bytes); + pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes); spin_lock(&vcpu->kvm->mmu_lock); kvm_mmu_free_some_pages(vcpu); @@ -1450,7 +1725,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, vcpu->arch.last_pt_write_count = 1; vcpu->arch.last_pte_updated = NULL; } - index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; + index = kvm_page_table_hashfn(gfn); bucket = &vcpu->kvm->arch.mmu_page_hash[index]; hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) { if (sp->gfn != gfn || sp->role.metaphysical) @@ -1496,20 +1771,29 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, continue; } spte = &sp->spt[page_offset / sizeof(*spte)]; + if ((gpa & (pte_size - 1)) || (bytes < pte_size)) { + gentry = 0; + r = kvm_read_guest_atomic(vcpu->kvm, + gpa & ~(u64)(pte_size - 1), + &gentry, pte_size); + new = (const void *)&gentry; + if (r < 0) + new = NULL; + } while (npte--) { entry = *spte; mmu_pte_write_zap_pte(vcpu, sp, spte); - mmu_pte_write_new_pte(vcpu, sp, spte, new, bytes, - page_offset & (pte_size - 1)); + if (new) + mmu_pte_write_new_pte(vcpu, sp, spte, new); mmu_pte_write_flush_tlb(vcpu, entry, *spte); ++spte; } } kvm_mmu_audit(vcpu, "post pte write"); spin_unlock(&vcpu->kvm->mmu_lock); - if (vcpu->arch.update_pte.page) { - kvm_release_page_clean(vcpu->arch.update_pte.page); - vcpu->arch.update_pte.page = NULL; + if (!is_error_pfn(vcpu->arch.update_pte.pfn)) { + kvm_release_pfn_clean(vcpu->arch.update_pte.pfn); + vcpu->arch.update_pte.pfn = bad_pfn; } } @@ -1518,9 +1802,7 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) gpa_t gpa; int r; - down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva); - up_read(&vcpu->kvm->slots_lock); spin_lock(&vcpu->kvm->mmu_lock); r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); @@ -1577,6 +1859,12 @@ out: } EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); +void kvm_enable_tdp(void) +{ + tdp_enabled = true; +} +EXPORT_SYMBOL_GPL(kvm_enable_tdp); + static void free_mmu_pages(struct kvm_vcpu *vcpu) { struct kvm_mmu_page *sp; @@ -1677,7 +1965,53 @@ void kvm_mmu_zap_all(struct kvm *kvm) kvm_flush_remote_tlbs(kvm); } -void kvm_mmu_module_exit(void) +void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm) +{ + struct kvm_mmu_page *page; + + page = container_of(kvm->arch.active_mmu_pages.prev, + struct kvm_mmu_page, link); + kvm_mmu_zap_page(kvm, page); +} + +static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask) +{ + struct kvm *kvm; + struct kvm *kvm_freed = NULL; + int cache_count = 0; + + spin_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) { + int npages; + + spin_lock(&kvm->mmu_lock); + npages = kvm->arch.n_alloc_mmu_pages - + kvm->arch.n_free_mmu_pages; + cache_count += npages; + if (!kvm_freed && nr_to_scan > 0 && npages > 0) { + kvm_mmu_remove_one_alloc_mmu_page(kvm); + cache_count--; + kvm_freed = kvm; + } + nr_to_scan--; + + spin_unlock(&kvm->mmu_lock); + } + if (kvm_freed) + list_move_tail(&kvm_freed->vm_list, &vm_list); + + spin_unlock(&kvm_lock); + + return cache_count; +} + +static struct shrinker mmu_shrinker = { + .shrink = mmu_shrink, + .seeks = DEFAULT_SEEKS * 10, +}; + +void mmu_destroy_caches(void) { if (pte_chain_cache) kmem_cache_destroy(pte_chain_cache); @@ -1687,6 +2021,12 @@ void kvm_mmu_module_exit(void) kmem_cache_destroy(mmu_page_header_cache); } +void kvm_mmu_module_exit(void) +{ + mmu_destroy_caches(); + unregister_shrinker(&mmu_shrinker); +} + int kvm_mmu_module_init(void) { pte_chain_cache = kmem_cache_create("kvm_pte_chain", @@ -1706,10 +2046,12 @@ int kvm_mmu_module_init(void) if (!mmu_page_header_cache) goto nomem; + register_shrinker(&mmu_shrinker); + return 0; nomem: - kvm_mmu_module_exit(); + mmu_destroy_caches(); return -ENOMEM; } @@ -1732,6 +2074,127 @@ 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) +{ + kvm_x86_ops->tlb_flush(vcpu); + 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; + + buffer.ptr = buffer.buf; + buffer.len = min_t(unsigned long, bytes, sizeof buffer.buf); + buffer.processed = 0; + + r = kvm_read_guest(vcpu->kvm, addr, buffer.buf, buffer.len); + if (r) + goto out; + + while (buffer.len) { + r = kvm_pv_mmu_op_one(vcpu, &buffer); + if (r < 0) + goto out; + if (r == 0) + break; + } + + r = 1; +out: + *ret = buffer.processed; + return r; +} + #ifdef AUDIT static const char *audit_msg; @@ -1768,8 +2231,7 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte, audit_mappings_page(vcpu, ent, va, level - 1); } else { gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, va); - struct page *page = gpa_to_page(vcpu, gpa); - hpa_t hpa = page_to_phys(page); + hpa_t hpa = (hpa_t)gpa_to_pfn(vcpu, gpa) << PAGE_SHIFT; if (is_shadow_present_pte(ent) && (ent & PT64_BASE_ADDR_MASK) != hpa) @@ -1782,7 +2244,7 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte, && !is_error_hpa(hpa)) printk(KERN_ERR "audit: (%s) notrap shadow," " valid guest gva %lx\n", audit_msg, va); - kvm_release_page_clean(page); + kvm_release_pfn_clean(pfn); } } @@ -1867,7 +2329,7 @@ static void audit_rmap(struct kvm_vcpu *vcpu) if (n_rmap != n_actual) printk(KERN_ERR "%s: (%s) rmap %d actual %d\n", - __FUNCTION__, audit_msg, n_rmap, n_actual); + __func__, audit_msg, n_rmap, n_actual); } static void audit_write_protection(struct kvm_vcpu *vcpu) @@ -1887,7 +2349,7 @@ static void audit_write_protection(struct kvm_vcpu *vcpu) if (*rmapp) printk(KERN_ERR "%s: (%s) shadow page has writable" " mappings: gfn %lx role %x\n", - __FUNCTION__, audit_msg, sp->gfn, + __func__, audit_msg, sp->gfn, sp->role.word); } } |