diff options
Diffstat (limited to 'arch/x86/kvm/mmu')
| -rw-r--r-- | arch/x86/kvm/mmu/mmu.c | 734 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/mmu_internal.h | 45 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/page_track.c | 252 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/page_track.h | 58 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/paging_tmpl.h | 43 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/spte.c | 6 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/spte.h | 21 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/tdp_iter.c | 13 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/tdp_mmu.c | 262 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/tdp_mmu.h | 8 |
10 files changed, 851 insertions, 591 deletions
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index ec169f5c7dce..2d6cdeab1f8a 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -25,6 +25,7 @@ #include "kvm_cache_regs.h" #include "smm.h" #include "kvm_emulate.h" +#include "page_track.h" #include "cpuid.h" #include "spte.h" @@ -53,7 +54,7 @@ #include <asm/io.h> #include <asm/set_memory.h> #include <asm/vmx.h> -#include <asm/kvm_page_track.h> + #include "trace.h" extern bool itlb_multihit_kvm_mitigation; @@ -115,11 +116,6 @@ static int max_huge_page_level __read_mostly; static int tdp_root_level __read_mostly; static int max_tdp_level __read_mostly; -#ifdef MMU_DEBUG -bool dbg = 0; -module_param(dbg, bool, 0644); -#endif - #define PTE_PREFETCH_NUM 8 #include <trace/events/kvm.h> @@ -275,19 +271,11 @@ static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, static inline bool kvm_available_flush_remote_tlbs_range(void) { +#if IS_ENABLED(CONFIG_HYPERV) return kvm_x86_ops.flush_remote_tlbs_range; -} - -void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn, - gfn_t nr_pages) -{ - int ret = -EOPNOTSUPP; - - if (kvm_x86_ops.flush_remote_tlbs_range) - ret = static_call(kvm_x86_flush_remote_tlbs_range)(kvm, start_gfn, - nr_pages); - if (ret) - kvm_flush_remote_tlbs(kvm); +#else + return false; +#endif } static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index); @@ -490,7 +478,7 @@ retry: */ static void mmu_spte_set(u64 *sptep, u64 new_spte) { - WARN_ON(is_shadow_present_pte(*sptep)); + WARN_ON_ONCE(is_shadow_present_pte(*sptep)); __set_spte(sptep, new_spte); } @@ -502,7 +490,7 @@ static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte) { u64 old_spte = *sptep; - WARN_ON(!is_shadow_present_pte(new_spte)); + WARN_ON_ONCE(!is_shadow_present_pte(new_spte)); check_spte_writable_invariants(new_spte); if (!is_shadow_present_pte(old_spte)) { @@ -515,7 +503,7 @@ static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte) else old_spte = __update_clear_spte_slow(sptep, new_spte); - WARN_ON(spte_to_pfn(old_spte) != spte_to_pfn(new_spte)); + WARN_ON_ONCE(spte_to_pfn(old_spte) != spte_to_pfn(new_spte)); return old_spte; } @@ -597,7 +585,7 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) * by a refcounted page, the refcount is elevated. */ page = kvm_pfn_to_refcounted_page(pfn); - WARN_ON(page && !page_count(page)); + WARN_ON_ONCE(page && !page_count(page)); if (is_accessed_spte(old_spte)) kvm_set_pfn_accessed(pfn); @@ -803,16 +791,26 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, return &slot->arch.lpage_info[level - 2][idx]; } +/* + * The most significant bit in disallow_lpage tracks whether or not memory + * attributes are mixed, i.e. not identical for all gfns at the current level. + * The lower order bits are used to refcount other cases where a hugepage is + * disallowed, e.g. if KVM has shadow a page table at the gfn. + */ +#define KVM_LPAGE_MIXED_FLAG BIT(31) + static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot, gfn_t gfn, int count) { struct kvm_lpage_info *linfo; - int i; + int old, i; for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); + + old = linfo->disallow_lpage; linfo->disallow_lpage += count; - WARN_ON(linfo->disallow_lpage < 0); + WARN_ON_ONCE((old ^ linfo->disallow_lpage) & KVM_LPAGE_MIXED_FLAG); } } @@ -839,8 +837,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) /* the non-leaf shadow pages are keeping readonly. */ if (sp->role.level > PG_LEVEL_4K) - return kvm_slot_page_track_add_page(kvm, slot, gfn, - KVM_PAGE_TRACK_WRITE); + return __kvm_write_track_add_gfn(kvm, slot, gfn); kvm_mmu_gfn_disallow_lpage(slot, gfn); @@ -886,8 +883,7 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); if (sp->role.level > PG_LEVEL_4K) - return kvm_slot_page_track_remove_page(kvm, slot, gfn, - KVM_PAGE_TRACK_WRITE); + return __kvm_write_track_remove_gfn(kvm, slot, gfn); kvm_mmu_gfn_allow_lpage(slot, gfn); } @@ -941,10 +937,8 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, int count = 0; if (!rmap_head->val) { - rmap_printk("%p %llx 0->1\n", spte, *spte); rmap_head->val = (unsigned long)spte; } else if (!(rmap_head->val & 1)) { - rmap_printk("%p %llx 1->many\n", spte, *spte); desc = kvm_mmu_memory_cache_alloc(cache); desc->sptes[0] = (u64 *)rmap_head->val; desc->sptes[1] = spte; @@ -953,7 +947,6 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, rmap_head->val = (unsigned long)desc | 1; ++count; } else { - rmap_printk("%p %llx many->many\n", spte, *spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); count = desc->tail_count + desc->spte_count; @@ -973,7 +966,8 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, return count; } -static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, +static void pte_list_desc_remove_entry(struct kvm *kvm, + struct kvm_rmap_head *rmap_head, struct pte_list_desc *desc, int i) { struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); @@ -984,7 +978,7 @@ static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, * when adding an entry and the previous head is full, and heads are * removed (this flow) when they become empty. */ - BUG_ON(j < 0); + KVM_BUG_ON_DATA_CORRUPTION(j < 0, kvm); /* * Replace the to-be-freed SPTE with the last valid entry from the head @@ -999,7 +993,7 @@ static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, /* * The head descriptor is empty. If there are no tail descriptors, - * nullify the rmap head to mark the list as emtpy, else point the rmap + * nullify the rmap head to mark the list as empty, else point the rmap * head at the next descriptor, i.e. the new head. */ if (!head_desc->more) @@ -1009,35 +1003,34 @@ static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, mmu_free_pte_list_desc(head_desc); } -static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head) +static void pte_list_remove(struct kvm *kvm, u64 *spte, + struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; int i; - if (!rmap_head->val) { - pr_err("%s: %p 0->BUG\n", __func__, spte); - BUG(); - } else if (!(rmap_head->val & 1)) { - rmap_printk("%p 1->0\n", spte); - if ((u64 *)rmap_head->val != spte) { - pr_err("%s: %p 1->BUG\n", __func__, spte); - BUG(); - } + if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_head->val, kvm)) + return; + + if (!(rmap_head->val & 1)) { + if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_head->val != spte, kvm)) + return; + rmap_head->val = 0; } else { - rmap_printk("%p many->many\n", spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); while (desc) { for (i = 0; i < desc->spte_count; ++i) { if (desc->sptes[i] == spte) { - pte_list_desc_remove_entry(rmap_head, desc, i); + pte_list_desc_remove_entry(kvm, rmap_head, + desc, i); return; } } desc = desc->more; } - pr_err("%s: %p many->many\n", __func__, spte); - BUG(); + + KVM_BUG_ON_DATA_CORRUPTION(true, kvm); } } @@ -1045,7 +1038,7 @@ static void kvm_zap_one_rmap_spte(struct kvm *kvm, struct kvm_rmap_head *rmap_head, u64 *sptep) { mmu_spte_clear_track_bits(kvm, sptep); - pte_list_remove(sptep, rmap_head); + pte_list_remove(kvm, sptep, rmap_head); } /* Return true if at least one SPTE was zapped, false otherwise */ @@ -1120,7 +1113,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) slot = __gfn_to_memslot(slots, gfn); rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); - pte_list_remove(spte, rmap_head); + pte_list_remove(kvm, spte, rmap_head); } /* @@ -1212,7 +1205,7 @@ static void drop_large_spte(struct kvm *kvm, u64 *sptep, bool flush) struct kvm_mmu_page *sp; sp = sptep_to_sp(sptep); - WARN_ON(sp->role.level == PG_LEVEL_4K); + WARN_ON_ONCE(sp->role.level == PG_LEVEL_4K); drop_spte(kvm, sptep); @@ -1241,8 +1234,6 @@ static bool spte_write_protect(u64 *sptep, bool pt_protect) !(pt_protect && is_mmu_writable_spte(spte))) return false; - rmap_printk("spte %p %llx\n", sptep, *sptep); - if (pt_protect) spte &= ~shadow_mmu_writable_mask; spte = spte & ~PT_WRITABLE_MASK; @@ -1267,9 +1258,7 @@ static bool spte_clear_dirty(u64 *sptep) { u64 spte = *sptep; - rmap_printk("spte %p %llx\n", sptep, *sptep); - - MMU_WARN_ON(!spte_ad_enabled(spte)); + KVM_MMU_WARN_ON(!spte_ad_enabled(spte)); spte &= ~shadow_dirty_mask; return mmu_spte_update(sptep, spte); } @@ -1399,7 +1388,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, gfn_t end = slot->base_gfn + gfn_offset + __fls(mask); if (READ_ONCE(eager_page_split)) - kvm_mmu_try_split_huge_pages(kvm, slot, start, end, PG_LEVEL_4K); + kvm_mmu_try_split_huge_pages(kvm, slot, start, end + 1, PG_LEVEL_4K); kvm_mmu_slot_gfn_write_protect(kvm, slot, start, PG_LEVEL_2M); @@ -1475,14 +1464,11 @@ static bool kvm_set_pte_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, u64 new_spte; kvm_pfn_t new_pfn; - WARN_ON(pte_huge(pte)); + WARN_ON_ONCE(pte_huge(pte)); new_pfn = pte_pfn(pte); restart: for_each_rmap_spte(rmap_head, &iter, sptep) { - rmap_printk("spte %p %llx gfn %llx (%d)\n", - sptep, *sptep, gfn, level); - need_flush = true; if (pte_write(pte)) { @@ -1588,7 +1574,7 @@ static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm, for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, range->start, range->end - 1, &iterator) ret |= handler(kvm, iterator.rmap, range->slot, iterator.gfn, - iterator.level, range->pte); + iterator.level, range->arg.pte); return ret; } @@ -1710,21 +1696,19 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) return young; } -#ifdef MMU_DEBUG -static int is_empty_shadow_page(u64 *spt) +static void kvm_mmu_check_sptes_at_free(struct kvm_mmu_page *sp) { - u64 *pos; - u64 *end; +#ifdef CONFIG_KVM_PROVE_MMU + int i; - for (pos = spt, end = pos + SPTE_ENT_PER_PAGE; pos != end; pos++) - if (is_shadow_present_pte(*pos)) { - printk(KERN_ERR "%s: %p %llx\n", __func__, - pos, *pos); - return 0; - } - return 1; -} + for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { + if (KVM_MMU_WARN_ON(is_shadow_present_pte(sp->spt[i]))) + pr_err_ratelimited("SPTE %llx (@ %p) for gfn %llx shadow-present at free", + sp->spt[i], &sp->spt[i], + kvm_mmu_page_get_gfn(sp, i)); + } #endif +} /* * This value is the sum of all of the kvm instances's @@ -1752,7 +1736,8 @@ static void kvm_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp) { - MMU_WARN_ON(!is_empty_shadow_page(sp->spt)); + kvm_mmu_check_sptes_at_free(sp); + hlist_del(&sp->hash_link); list_del(&sp->link); free_page((unsigned long)sp->spt); @@ -1775,16 +1760,16 @@ static void mmu_page_add_parent_pte(struct kvm_mmu_memory_cache *cache, pte_list_add(cache, parent_pte, &sp->parent_ptes); } -static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp, +static void mmu_page_remove_parent_pte(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *parent_pte) { - pte_list_remove(parent_pte, &sp->parent_ptes); + pte_list_remove(kvm, parent_pte, &sp->parent_ptes); } -static void drop_parent_pte(struct kvm_mmu_page *sp, +static void drop_parent_pte(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *parent_pte) { - mmu_page_remove_parent_pte(sp, parent_pte); + mmu_page_remove_parent_pte(kvm, sp, parent_pte); mmu_spte_clear_no_track(parent_pte); } @@ -1840,7 +1825,7 @@ static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp, static inline void clear_unsync_child_bit(struct kvm_mmu_page *sp, int idx) { --sp->unsync_children; - WARN_ON((int)sp->unsync_children < 0); + WARN_ON_ONCE((int)sp->unsync_children < 0); __clear_bit(idx, sp->unsync_child_bitmap); } @@ -1898,7 +1883,7 @@ static int mmu_unsync_walk(struct kvm_mmu_page *sp, static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) { - WARN_ON(!sp->unsync); + WARN_ON_ONCE(!sp->unsync); trace_kvm_mmu_sync_page(sp); sp->unsync = 0; --kvm->stat.mmu_unsync; @@ -2073,11 +2058,11 @@ static int mmu_pages_first(struct kvm_mmu_pages *pvec, if (pvec->nr == 0) return 0; - WARN_ON(pvec->page[0].idx != INVALID_INDEX); + WARN_ON_ONCE(pvec->page[0].idx != INVALID_INDEX); sp = pvec->page[0].sp; level = sp->role.level; - WARN_ON(level == PG_LEVEL_4K); + WARN_ON_ONCE(level == PG_LEVEL_4K); parents->parent[level-2] = sp; @@ -2099,7 +2084,7 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents) if (!sp) return; - WARN_ON(idx == INVALID_INDEX); + WARN_ON_ONCE(idx == INVALID_INDEX); clear_unsync_child_bit(sp, idx); level++; } while (!sp->unsync_children); @@ -2220,7 +2205,7 @@ static struct kvm_mmu_page *kvm_mmu_find_shadow_page(struct kvm *kvm, if (ret < 0) break; - WARN_ON(!list_empty(&invalid_list)); + WARN_ON_ONCE(!list_empty(&invalid_list)); if (ret > 0) kvm_flush_remote_tlbs(kvm); } @@ -2499,7 +2484,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (child->role.access == direct_access) return; - drop_parent_pte(child, sptep); + drop_parent_pte(vcpu->kvm, child, sptep); kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep); } } @@ -2517,7 +2502,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, drop_spte(kvm, spte); } else { child = spte_to_child_sp(pte); - drop_parent_pte(child, spte); + drop_parent_pte(kvm, child, spte); /* * Recursively zap nested TDP SPs, parentless SPs are @@ -2548,13 +2533,13 @@ static int kvm_mmu_page_unlink_children(struct kvm *kvm, return zapped; } -static void kvm_mmu_unlink_parents(struct kvm_mmu_page *sp) +static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) { u64 *sptep; struct rmap_iterator iter; while ((sptep = rmap_get_first(&sp->parent_ptes, &iter))) - drop_parent_pte(sp, sptep); + drop_parent_pte(kvm, sp, sptep); } static int mmu_zap_unsync_children(struct kvm *kvm, @@ -2593,7 +2578,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, ++kvm->stat.mmu_shadow_zapped; *nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list); *nr_zapped += kvm_mmu_page_unlink_children(kvm, sp, invalid_list); - kvm_mmu_unlink_parents(sp); + kvm_mmu_unlink_parents(kvm, sp); /* Zapping children means active_mmu_pages has become unstable. */ list_unstable = *nr_zapped; @@ -2675,7 +2660,7 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, kvm_flush_remote_tlbs(kvm); list_for_each_entry_safe(sp, nsp, invalid_list, link) { - WARN_ON(!sp->role.invalid || sp->root_count); + WARN_ON_ONCE(!sp->role.invalid || sp->root_count); kvm_mmu_free_shadow_page(sp); } } @@ -2775,12 +2760,9 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) LIST_HEAD(invalid_list); int r; - pgprintk("%s: looking for gfn %llx\n", __func__, gfn); r = 0; write_lock(&kvm->mmu_lock); for_each_gfn_valid_sp_with_gptes(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); } @@ -2831,7 +2813,7 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, * track machinery is used to write-protect upper-level shadow pages, * i.e. this guards the role.level == 4K assertion below! */ - if (kvm_slot_page_track_is_active(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_gfn_is_write_tracked(kvm, slot, gfn)) return -EPERM; /* @@ -2864,16 +2846,16 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, /* * Recheck after taking the spinlock, a different vCPU * may have since marked the page unsync. A false - * positive on the unprotected check above is not + * negative on the unprotected check above is not * possible as clearing sp->unsync _must_ hold mmu_lock - * for write, i.e. unsync cannot transition from 0->1 + * for write, i.e. unsync cannot transition from 1->0 * while this CPU holds mmu_lock for read (or write). */ if (READ_ONCE(sp->unsync)) continue; } - WARN_ON(sp->role.level != PG_LEVEL_4K); + WARN_ON_ONCE(sp->role.level != PG_LEVEL_4K); kvm_unsync_page(kvm, sp); } if (locked) @@ -2938,9 +2920,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, bool prefetch = !fault || fault->prefetch; bool write_fault = fault && fault->write; - pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__, - *sptep, write_fault, gfn); - if (unlikely(is_noslot_pfn(pfn))) { vcpu->stat.pf_mmio_spte_created++; mark_mmio_spte(vcpu, sptep, gfn, pte_access); @@ -2957,11 +2936,9 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, u64 pte = *sptep; child = spte_to_child_sp(pte); - drop_parent_pte(child, sptep); + drop_parent_pte(vcpu->kvm, child, sptep); flush = true; } else if (pfn != spte_to_pfn(*sptep)) { - pgprintk("hfn old %llx new %llx\n", - spte_to_pfn(*sptep), pfn); drop_spte(vcpu->kvm, sptep); flush = true; } else @@ -2986,8 +2963,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, if (flush) kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level); - pgprintk("%s: setting spte %llx\n", __func__, *sptep); - if (!was_rmapped) { WARN_ON_ONCE(ret == RET_PF_SPURIOUS); rmap_add(vcpu, slot, sptep, gfn, pte_access); @@ -3033,7 +3008,7 @@ static void __direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *spte, *start = NULL; int i; - WARN_ON(!sp->role.direct); + WARN_ON_ONCE(!sp->role.direct); i = spte_index(sptep) & ~(PTE_PREFETCH_NUM - 1); spte = sp->spt + i; @@ -3087,7 +3062,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) * * There are several ways to safely use this helper: * - * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before + * - Check mmu_invalidate_retry_gfn() after grabbing the mapping level, before * consuming it. In this case, mmu_lock doesn't need to be held during the * lookup, but it does need to be held while checking the MMU notifier. * @@ -3168,9 +3143,9 @@ out: return level; } -int kvm_mmu_max_mapping_level(struct kvm *kvm, - const struct kvm_memory_slot *slot, gfn_t gfn, - int max_level) +static int __kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, int max_level, bool is_private) { struct kvm_lpage_info *linfo; int host_level; @@ -3182,6 +3157,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, break; } + if (is_private) + return max_level; + if (max_level == PG_LEVEL_4K) return PG_LEVEL_4K; @@ -3189,6 +3167,16 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, return min(host_level, max_level); } +int kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, gfn_t gfn, + int max_level) +{ + bool is_private = kvm_slot_can_be_private(slot) && + kvm_mem_is_private(kvm, gfn); + + return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private); +} + void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; @@ -3209,8 +3197,9 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault * Enforce the iTLB multihit workaround after capturing the requested * level, which will be used to do precise, accurate accounting. */ - fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, - fault->gfn, fault->max_level); + fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot, + fault->gfn, fault->max_level, + fault->is_private); if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed) return; @@ -3456,8 +3445,8 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_mmu_page *sp; int ret = RET_PF_INVALID; - u64 spte = 0ull; - u64 *sptep = NULL; + u64 spte; + u64 *sptep; uint retry_count = 0; if (!page_fault_can_be_fast(fault)) @@ -3473,6 +3462,14 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) else sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte); + /* + * It's entirely possible for the mapping to have been zapped + * by a different task, but the root page should always be + * available as the vCPU holds a reference to its root(s). + */ + if (WARN_ON_ONCE(!sptep)) + spte = REMOVED_SPTE; + if (!is_shadow_present_pte(spte)) break; @@ -3574,16 +3571,12 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, if (!VALID_PAGE(*root_hpa)) return; - /* - * The "root" may be a special root, e.g. a PAE entry, treat it as a - * SPTE to ensure any non-PA bits are dropped. - */ - sp = spte_to_child_sp(*root_hpa); - if (WARN_ON(!sp)) + sp = root_to_sp(*root_hpa); + if (WARN_ON_ONCE(!sp)) return; if (is_tdp_mmu_page(sp)) - kvm_tdp_mmu_put_root(kvm, sp, false); + kvm_tdp_mmu_put_root(kvm, sp); else if (!--sp->root_count && sp->role.invalid) kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); @@ -3624,7 +3617,9 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, &invalid_list); if (free_active_root) { - if (to_shadow_page(mmu->root.hpa)) { + if (kvm_mmu_is_dummy_root(mmu->root.hpa)) { + /* Nothing to cleanup for dummy roots. */ + } else if (root_to_sp(mmu->root.hpa)) { mmu_free_root_page(kvm, &mmu->root.hpa, &invalid_list); } else if (mmu->pae_root) { for (i = 0; i < 4; ++i) { @@ -3648,6 +3643,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_free_roots); void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu) { unsigned long roots_to_free = 0; + struct kvm_mmu_page *sp; hpa_t root_hpa; int i; @@ -3662,8 +3658,8 @@ void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu) if (!VALID_PAGE(root_hpa)) continue; - if (!to_shadow_page(root_hpa) || - to_shadow_page(root_hpa)->role.guest_mode) + sp = root_to_sp(root_hpa); + if (!sp || sp->role.guest_mode) roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); } @@ -3671,19 +3667,6 @@ void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu) } EXPORT_SYMBOL_GPL(kvm_mmu_free_guest_mode_roots); - -static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn) -{ - int ret = 0; - - if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) { - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); - ret = 1; - } - - return ret; -} - static hpa_t mmu_alloc_root(struct kvm_vcpu *vcpu, gfn_t gfn, int quadrant, u8 level) { @@ -3776,7 +3759,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) kvm_page_track_write_tracking_enabled(kvm)) goto out_success; - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot(slot, bkt, slots) { /* @@ -3819,10 +3802,12 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) hpa_t root; root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu); - root_gfn = root_pgd >> PAGE_SHIFT; + root_gfn = (root_pgd & __PT_BASE_ADDR_MASK) >> PAGE_SHIFT; - if (mmu_check_root(vcpu, root_gfn)) - return 1; + if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) { + mmu->root.hpa = kvm_mmu_get_dummy_root(); + return 0; + } /* * On SVM, reading PDPTRs might access guest memory, which might fault @@ -3834,8 +3819,8 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) if (!(pdptrs[i] & PT_PRESENT_MASK)) continue; - if (mmu_check_root(vcpu, pdptrs[i] >> PAGE_SHIFT)) - return 1; + if (!kvm_vcpu_is_visible_gfn(vcpu, pdptrs[i] >> PAGE_SHIFT)) + pdptrs[i] = 0; } } @@ -4002,7 +3987,7 @@ static bool is_unsync_root(hpa_t root) { struct kvm_mmu_page *sp; - if (!VALID_PAGE(root)) + if (!VALID_PAGE(root) || kvm_mmu_is_dummy_root(root)) return false; /* @@ -4018,7 +4003,7 @@ static bool is_unsync_root(hpa_t root) * requirement isn't satisfied. */ smp_rmb(); - sp = to_shadow_page(root); + sp = root_to_sp(root); /* * PAE roots (somewhat arbitrarily) aren't backed by shadow pages, the @@ -4048,11 +4033,12 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) if (vcpu->arch.mmu->cpu_role.base.level >= PT64_ROOT_4LEVEL) { hpa_t root = vcpu->arch.mmu->root.hpa; - sp = to_shadow_page(root); if (!is_unsync_root(root)) return; + sp = root_to_sp(root); + write_lock(&vcpu->kvm->mmu_lock); mmu_sync_children(vcpu, sp, true); write_unlock(&vcpu->kvm->mmu_lock); @@ -4194,7 +4180,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) return RET_PF_EMULATE; reserved = get_mmio_spte(vcpu, addr, &spte); - if (WARN_ON(reserved)) + if (WARN_ON_ONCE(reserved)) return -EINVAL; if (is_mmio_spte(spte)) { @@ -4232,7 +4218,7 @@ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu, * guest is writing the page which is write tracked which can * not be fixed by page fault handler. */ - if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_gfn_is_write_tracked(vcpu->kvm, fault->slot, fault->gfn)) return true; return false; @@ -4293,6 +4279,55 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL); } +static inline u8 kvm_max_level_for_order(int order) +{ + BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G); + + KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K)); + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G)) + return PG_LEVEL_1G; + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M)) + return PG_LEVEL_2M; + + return PG_LEVEL_4K; +} + +static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, + PAGE_SIZE, fault->write, fault->exec, + fault->is_private); +} + +static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + int max_order, r; + + if (!kvm_slot_can_be_private(fault->slot)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, + &max_order); + if (r) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return r; + } + + fault->max_level = min(kvm_max_level_for_order(max_order), + fault->max_level); + fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY); + + return RET_PF_CONTINUE; +} + static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; @@ -4325,6 +4360,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return RET_PF_EMULATE; } + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + if (fault->is_private) + return kvm_faultin_pfn_private(vcpu, fault); + async = false; fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async, fault->write, &fault->map_writable, @@ -4382,7 +4425,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, static bool is_page_fault_stale(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root.hpa); + struct kvm_mmu_page *sp = root_to_sp(vcpu->arch.mmu->root.hpa); /* Special roots, e.g. pae_root, are not backed by shadow pages. */ if (sp && is_obsolete_sp(vcpu->kvm, sp)) @@ -4400,13 +4443,17 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, return true; return fault->slot && - mmu_invalidate_retry_hva(vcpu->kvm, fault->mmu_seq, fault->hva); + mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn); } static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { int r; + /* Dummy roots are used only for shadowing bad guest roots. */ + if (WARN_ON_ONCE(kvm_mmu_is_dummy_root(vcpu->arch.mmu->root.hpa))) + return RET_PF_RETRY; + if (page_fault_handle_page_track(vcpu, fault)) return RET_PF_EMULATE; @@ -4443,8 +4490,6 @@ out_unlock: static int nonpaging_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - pgprintk("%s: gva %lx error %x\n", __func__, fault->addr, fault->error_code); - /* This path builds a PAE pagetable, we can map 2mb pages at maximum. */ fault->max_level = PG_LEVEL_2M; return direct_page_fault(vcpu, fault); @@ -4519,21 +4564,28 @@ out_unlock: } #endif -int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +bool __kvm_mmu_honors_guest_mtrrs(bool vm_has_noncoherent_dma) { /* - * If the guest's MTRRs may be used to compute the "real" memtype, - * restrict the mapping level to ensure KVM uses a consistent memtype - * across the entire mapping. If the host MTRRs are ignored by TDP - * (shadow_memtype_mask is non-zero), and the VM has non-coherent DMA - * (DMA doesn't snoop CPU caches), KVM's ABI is to honor the memtype - * from the guest's MTRRs so that guest accesses to memory that is - * DMA'd aren't cached against the guest's wishes. + * If host MTRRs are ignored (shadow_memtype_mask is non-zero), and the + * VM has non-coherent DMA (DMA doesn't snoop CPU caches), KVM's ABI is + * to honor the memtype from the guest's MTRRs so that guest accesses + * to memory that is DMA'd aren't cached against the guest's wishes. * * Note, KVM may still ultimately ignore guest MTRRs for certain PFNs, * e.g. KVM will force UC memtype for host MMIO. */ - if (shadow_memtype_mask && kvm_arch_has_noncoherent_dma(vcpu->kvm)) { + return vm_has_noncoherent_dma && shadow_memtype_mask; +} + +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +{ + /* + * If the guest's MTRRs may be used to compute the "real" memtype, + * restrict the mapping level to ensure KVM uses a consistent memtype + * across the entire mapping. + */ + if (kvm_mmu_honors_guest_mtrrs(vcpu->kvm)) { for ( ; fault->max_level > PG_LEVEL_4K; --fault->max_level) { int page_num = KVM_PAGES_PER_HPAGE(fault->max_level); gfn_t base = gfn_round_for_level(fault->gfn, @@ -4562,9 +4614,19 @@ static void nonpaging_init_context(struct kvm_mmu *context) static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t pgd, union kvm_mmu_page_role role) { - return (role.direct || pgd == root->pgd) && - VALID_PAGE(root->hpa) && - role.word == to_shadow_page(root->hpa)->role.word; + struct kvm_mmu_page *sp; + + if (!VALID_PAGE(root->hpa)) + return false; + + if (!role.direct && pgd != root->pgd) + return false; + + sp = root_to_sp(root->hpa); + if (WARN_ON_ONCE(!sp)) + return false; + + return role.word == sp->role.word; } /* @@ -4634,11 +4696,10 @@ static bool fast_pgd_switch(struct kvm *kvm, struct kvm_mmu *mmu, gpa_t new_pgd, union kvm_mmu_page_role new_role) { /* - * For now, limit the caching to 64-bit hosts+VMs in order to avoid - * having to deal with PDPTEs. We may add support for 32-bit hosts/VMs - * later if necessary. + * Limit reuse to 64-bit hosts+VMs without "special" roots in order to + * avoid having to deal with PDPTEs and other complexities. */ - if (VALID_PAGE(mmu->root.hpa) && !to_shadow_page(mmu->root.hpa)) + if (VALID_PAGE(mmu->root.hpa) && !root_to_sp(mmu->root.hpa)) kvm_mmu_free_roots(kvm, mmu, KVM_MMU_ROOT_CURRENT); if (VALID_PAGE(mmu->root.hpa)) @@ -4684,9 +4745,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd) * If this is a direct root page, it doesn't have a write flooding * count. Otherwise, clear the write flooding count. */ - if (!new_role.direct) - __clear_sp_write_flooding_count( - to_shadow_page(vcpu->arch.mmu->root.hpa)); + if (!new_role.direct) { + struct kvm_mmu_page *sp = root_to_sp(vcpu->arch.mmu->root.hpa); + + if (!WARN_ON_ONCE(!sp)) + __clear_sp_write_flooding_count(sp); + } } EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd); @@ -4808,28 +4872,13 @@ static void __reset_rsvds_bits_mask(struct rsvd_bits_validate *rsvd_check, } } -static bool guest_can_use_gbpages(struct kvm_vcpu *vcpu) -{ - /* - * If TDP is enabled, let the guest use GBPAGES if they're supported in - * hardware. The hardware page walker doesn't let KVM disable GBPAGES, - * i.e. won't treat them as reserved, and KVM doesn't redo the GVA->GPA - * walk for performance and complexity reasons. Not to mention KVM - * _can't_ solve the problem because GVA->GPA walks aren't visible to - * KVM once a TDP translation is installed. Mimic hardware behavior so - * that KVM's is at least consistent, i.e. doesn't randomly inject #PF. - */ - return tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) : - guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES); -} - static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { __reset_rsvds_bits_mask(&context->guest_rsvd_check, vcpu->arch.reserved_gpa_bits, context->cpu_role.base.level, is_efer_nx(context), - guest_can_use_gbpages(vcpu), + guest_can_use(vcpu, X86_FEATURE_GBPAGES), is_cr4_pse(context), guest_cpuid_is_amd_or_hygon(vcpu)); } @@ -4906,7 +4955,8 @@ static void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, __reset_rsvds_bits_mask(shadow_zero_check, reserved_hpa_bits(), context->root_role.level, context->root_role.efer_nx, - guest_can_use_gbpages(vcpu), is_pse, is_amd); + guest_can_use(vcpu, X86_FEATURE_GBPAGES), + is_pse, is_amd); if (!shadow_me_mask) return; @@ -5467,8 +5517,8 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) * physical address properties) in a single VM would require tracking * all relevant CPUID information in kvm_mmu_page_role. That is very * undesirable as it would increase the memory requirements for - * gfn_track (see struct kvm_mmu_page_role comments). For now that - * problem is swept under the rug; KVM's CPUID API is horrific and + * gfn_write_track (see struct kvm_mmu_page_role comments). For now + * that problem is swept under the rug; KVM's CPUID API is horrific and * it's all but impossible to solve it without introducing a new API. */ vcpu->arch.root_mmu.root_role.word = 0; @@ -5531,9 +5581,9 @@ void kvm_mmu_unload(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; kvm_mmu_free_roots(kvm, &vcpu->arch.root_mmu, KVM_MMU_ROOTS_ALL); - WARN_ON(VALID_PAGE(vcpu->arch.root_mmu.root.hpa)); + WARN_ON_ONCE(VALID_PAGE(vcpu->arch.root_mmu.root.hpa)); kvm_mmu_free_roots(kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL); - WARN_ON(VALID_PAGE(vcpu->arch.guest_mmu.root.hpa)); + WARN_ON_ONCE(VALID_PAGE(vcpu->arch.guest_mmu.root.hpa)); vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY); } @@ -5546,16 +5596,21 @@ static bool is_obsolete_root(struct kvm *kvm, hpa_t root_hpa) /* * When freeing obsolete roots, treat roots as obsolete if they don't - * have an associated shadow page. This does mean KVM will get false + * have an associated shadow page, as it's impossible to determine if + * such roots are fresh or stale. This does mean KVM will get false * positives and free roots that don't strictly need to be freed, but * such false positives are relatively rare: * - * (a) only PAE paging and nested NPT has roots without shadow pages + * (a) only PAE paging and nested NPT have roots without shadow pages + * (or any shadow paging flavor with a dummy root, see note below) * (b) remote reloads due to a memslot update obsoletes _all_ roots * (c) KVM doesn't track previous roots for PAE paging, and the guest * is unlikely to zap an in-use PGD. + * + * Note! Dummy roots are unique in that they are obsoleted by memslot + * _creation_! See also FNAME(fetch). */ - sp = to_shadow_page(root_hpa); + sp = root_to_sp(root_hpa); return !sp || is_obsolete_sp(kvm, sp); } @@ -5634,9 +5689,6 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, { unsigned offset, pte_size, misaligned; - pgprintk("misaligned: gpa %llx bytes %d role %x\n", - gpa, bytes, sp->role.word); - offset = offset_in_page(gpa); pte_size = sp->role.has_4_byte_gpte ? 4 : 8; @@ -5684,9 +5736,8 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) return spte; } -static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes, - struct kvm_page_track_notifier_node *node) +void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, + int bytes) { gfn_t gfn = gpa >> PAGE_SHIFT; struct kvm_mmu_page *sp; @@ -5702,8 +5753,6 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) return; - pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); - write_lock(&vcpu->kvm->mmu_lock); gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes); @@ -5742,7 +5791,18 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err int r, emulation_type = EMULTYPE_PF; bool direct = vcpu->arch.mmu->root_role.direct; - if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) + /* + * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP + * checks when emulating instructions that triggers implicit access. + * WARN if hardware generates a fault with an error code that collides + * with the KVM-defined value. Clear the flag and continue on, i.e. + * don't terminate the VM, as KVM can't possibly be relying on a flag + * that KVM doesn't know about. + */ + if (WARN_ON_ONCE(error_code & PFERR_IMPLICIT_ACCESS)) + error_code &= ~PFERR_IMPLICIT_ACCESS; + + if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) return RET_PF_RETRY; r = RET_PF_INVALID; @@ -6099,7 +6159,7 @@ restart: * pages. Skip the bogus page, otherwise we'll get stuck in an * infinite loop if the page gets put back on the list (again). */ - if (WARN_ON(sp->role.invalid)) + if (WARN_ON_ONCE(sp->role.invalid)) continue; /* @@ -6199,32 +6259,15 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); } -static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot, - struct kvm_page_track_notifier_node *node) +void kvm_mmu_init_vm(struct kvm *kvm) { - kvm_mmu_zap_all_fast(kvm); -} - -int kvm_mmu_init_vm(struct kvm *kvm) -{ - struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; - int r; - INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); - if (tdp_mmu_enabled) { - r = kvm_mmu_init_tdp_mmu(kvm); - if (r < 0) - return r; - } - - node->track_write = kvm_mmu_pte_write; - node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot; - kvm_page_track_register_notifier(kvm, node); + if (tdp_mmu_enabled) + kvm_mmu_init_tdp_mmu(kvm); kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache; kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO; @@ -6233,8 +6276,6 @@ int kvm_mmu_init_vm(struct kvm *kvm) kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache; kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO; - - return 0; } static void mmu_free_vm_memory_caches(struct kvm *kvm) @@ -6246,10 +6287,6 @@ static void mmu_free_vm_memory_caches(struct kvm *kvm) void kvm_mmu_uninit_vm(struct kvm *kvm) { - struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; - - kvm_page_track_unregister_notifier(kvm, node); - if (tdp_mmu_enabled) kvm_mmu_uninit_tdp_mmu(kvm); @@ -6268,7 +6305,7 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e if (!kvm_memslots_have_rmaps(kvm)) return flush; - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) { @@ -6294,27 +6331,25 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { bool flush; - int i; if (WARN_ON_ONCE(gfn_end <= gfn_start)) return; write_lock(&kvm->mmu_lock); - kvm_mmu_invalidate_begin(kvm, 0, -1ul); + kvm_mmu_invalidate_begin(kvm); + + kvm_mmu_invalidate_range_add(kvm, gfn_start, gfn_end); flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); - if (tdp_mmu_enabled) { - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start, - gfn_end, true, flush); - } + if (tdp_mmu_enabled) + flush = kvm_tdp_mmu_zap_leafs(kvm, gfn_start, gfn_end, flush); if (flush) kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start); - kvm_mmu_invalidate_end(kvm, 0, -1ul); + kvm_mmu_invalidate_end(kvm); write_unlock(&kvm->mmu_lock); } @@ -6588,7 +6623,7 @@ void kvm_mmu_try_split_huge_pages(struct kvm *kvm, kvm_tdp_mmu_try_split_huge_pages(kvm, memslot, start, end, target_level, false); /* - * A TLB flush is unnecessary at this point for the same resons as in + * A TLB flush is unnecessary at this point for the same reasons as in * kvm_mmu_slot_try_split_huge_pages(). */ } @@ -6670,7 +6705,7 @@ static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm, */ if (walk_slot_rmaps(kvm, slot, kvm_mmu_zap_collapsible_spte, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL - 1, true)) - kvm_arch_flush_remote_tlbs_memslot(kvm, slot); + kvm_flush_remote_tlbs_memslot(kvm, slot); } void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, @@ -6689,20 +6724,6 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, } } -void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, - const struct kvm_memory_slot *memslot) -{ - /* - * All current use cases for flushing the TLBs for a specific memslot - * related to dirty logging, and many do the TLB flush out of mmu_lock. - * The interaction between the various operations on memslot must be - * serialized by slots_locks to ensure the TLB flush from one operation - * is observed by any other operation on the same memslot. - */ - lockdep_assert_held(&kvm->slots_lock); - kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages); -} - void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, const struct kvm_memory_slot *memslot) { @@ -6732,7 +6753,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, */ } -void kvm_mmu_zap_all(struct kvm *kvm) +static void kvm_mmu_zap_all(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; LIST_HEAD(invalid_list); @@ -6741,7 +6762,7 @@ void kvm_mmu_zap_all(struct kvm *kvm) write_lock(&kvm->mmu_lock); restart: list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) { - if (WARN_ON(sp->role.invalid)) + if (WARN_ON_ONCE(sp->role.invalid)) continue; if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign)) goto restart; @@ -6757,9 +6778,20 @@ restart: write_unlock(&kvm->mmu_lock); } +void kvm_arch_flush_shadow_all(struct kvm *kvm) +{ + kvm_mmu_zap_all(kvm); +} + +void kvm_arch_flush_shadow_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + kvm_mmu_zap_all_fast(kvm); +} + void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) { - WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); + WARN_ON_ONCE(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); gen &= MMIO_SPTE_GEN_MASK; @@ -6770,7 +6802,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) * modifier prior to checking for a wrap of the MMIO generation so * that a wrap in any address space is detected. */ - gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1); + gen &= ~((u64)kvm_arch_nr_memslot_as_ids(kvm) - 1); /* * The very rare case: if the MMIO generation number has wrapped, @@ -6847,11 +6879,7 @@ static unsigned long mmu_shrink_count(struct shrinker *shrink, return percpu_counter_read_positive(&kvm_total_used_mmu_pages); } -static struct shrinker mmu_shrinker = { - .count_objects = mmu_shrink_count, - .scan_objects = mmu_shrink_scan, - .seeks = DEFAULT_SEEKS * 10, -}; +static struct shrinker *mmu_shrinker; static void mmu_destroy_caches(void) { @@ -6862,7 +6890,7 @@ static void mmu_destroy_caches(void) static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp) { if (nx_hugepage_mitigation_hard_disabled) - return sprintf(buffer, "never\n"); + return sysfs_emit(buffer, "never\n"); return param_get_bool(buffer, kp); } @@ -6984,10 +7012,16 @@ int kvm_mmu_vendor_module_init(void) if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL)) goto out; - ret = register_shrinker(&mmu_shrinker, "x86-mmu"); - if (ret) + mmu_shrinker = shrinker_alloc(0, "x86-mmu"); + if (!mmu_shrinker) goto out_shrinker; + mmu_shrinker->count_objects = mmu_shrink_count; + mmu_shrinker->scan_objects = mmu_shrink_scan; + mmu_shrinker->seeks = DEFAULT_SEEKS * 10; + + shrinker_register(mmu_shrinker); + return 0; out_shrinker: @@ -7009,7 +7043,7 @@ void kvm_mmu_vendor_module_exit(void) { mmu_destroy_caches(); percpu_counter_destroy(&kvm_total_used_mmu_pages); - unregister_shrinker(&mmu_shrinker); + shrinker_free(mmu_shrinker); } /* @@ -7221,3 +7255,163 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm) if (kvm->arch.nx_huge_page_recovery_thread) kthread_stop(kvm->arch.nx_huge_page_recovery_thread); } + +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + /* + * Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only + * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM + * can simply ignore such slots. But if userspace is making memory + * PRIVATE, then KVM must prevent the guest from accessing the memory + * as shared. And if userspace is making memory SHARED and this point + * is reached, then at least one page within the range was previously + * PRIVATE, i.e. the slot's possible hugepage ranges are changing. + * Zapping SPTEs in this case ensures KVM will reassess whether or not + * a hugepage can be used for affected ranges. + */ + if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) + return false; + + return kvm_unmap_gfn_range(kvm, range); +} + +static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG; +} + +static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, int level, unsigned long attrs) +{ + const unsigned long start = gfn; + const unsigned long end = start + KVM_PAGES_PER_HPAGE(level); + + if (level == PG_LEVEL_2M) + return kvm_range_has_memory_attributes(kvm, start, end, attrs); + + for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) { + if (hugepage_test_mixed(slot, gfn, level - 1) || + attrs != kvm_get_memory_attributes(kvm, gfn)) + return false; + } + return true; +} + +bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + unsigned long attrs = range->arg.attributes; + struct kvm_memory_slot *slot = range->slot; + int level; + + lockdep_assert_held_write(&kvm->mmu_lock); + lockdep_assert_held(&kvm->slots_lock); + + /* + * Calculate which ranges can be mapped with hugepages even if the slot + * can't map memory PRIVATE. KVM mustn't create a SHARED hugepage over + * a range that has PRIVATE GFNs, and conversely converting a range to + * SHARED may now allow hugepages. + */ + if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) + return false; + + /* + * The sequence matters here: upper levels consume the result of lower + * level's scanning. + */ + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + gfn_t gfn = gfn_round_for_level(range->start, level); + + /* Process the head page if it straddles the range. */ + if (gfn != range->start || gfn + nr_pages > range->end) { + /* + * Skip mixed tracking if the aligned gfn isn't covered + * by the memslot, KVM can't use a hugepage due to the + * misaligned address regardless of memory attributes. + */ + if (gfn >= slot->base_gfn) { + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + gfn += nr_pages; + } + + /* + * Pages entirely covered by the range are guaranteed to have + * only the attributes which were just set. + */ + for ( ; gfn + nr_pages <= range->end; gfn += nr_pages) + hugepage_clear_mixed(slot, gfn, level); + + /* + * Process the last tail page if it straddles the range and is + * contained by the memslot. Like the head page, KVM can't + * create a hugepage if the slot size is misaligned. + */ + if (gfn < range->end && + (gfn + nr_pages) <= (slot->base_gfn + slot->npages)) { + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + } + return false; +} + +void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + int level; + + if (!kvm_arch_has_private_mem(kvm)) + return; + + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + /* + * Don't bother tracking mixed attributes for pages that can't + * be huge due to alignment, i.e. process only pages that are + * entirely contained by the memslot. + */ + gfn_t end = gfn_round_for_level(slot->base_gfn + slot->npages, level); + gfn_t start = gfn_round_for_level(slot->base_gfn, level); + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + gfn_t gfn; + + if (start < slot->base_gfn) + start += nr_pages; + + /* + * Unlike setting attributes, every potential hugepage needs to + * be manually checked as the attributes may already be mixed. + */ + for (gfn = start; gfn < end; gfn += nr_pages) { + unsigned long attrs = kvm_get_memory_attributes(kvm, gfn); + + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + } +} +#endif diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index d39af5639ce9..0669a8a668ca 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -6,21 +6,14 @@ #include <linux/kvm_host.h> #include <asm/kvm_host.h> -#undef MMU_DEBUG - -#ifdef MMU_DEBUG -extern bool dbg; - -#define pgprintk(x...) do { if (dbg) printk(x); } while (0) -#define rmap_printk(fmt, args...) do { if (dbg) printk("%s: " fmt, __func__, ## args); } while (0) -#define MMU_WARN_ON(x) WARN_ON(x) +#ifdef CONFIG_KVM_PROVE_MMU +#define KVM_MMU_WARN_ON(x) WARN_ON_ONCE(x) #else -#define pgprintk(x...) do { } while (0) -#define rmap_printk(x...) do { } while (0) -#define MMU_WARN_ON(x) do { } while (0) +#define KVM_MMU_WARN_ON(x) BUILD_BUG_ON_INVALID(x) #endif /* Page table builder macros common to shadow (host) PTEs and guest PTEs. */ +#define __PT_BASE_ADDR_MASK GENMASK_ULL(51, 12) #define __PT_LEVEL_SHIFT(level, bits_per_level) \ (PAGE_SHIFT + ((level) - 1) * (bits_per_level)) #define __PT_INDEX(address, level, bits_per_level) \ @@ -44,6 +37,16 @@ extern bool dbg; #define INVALID_PAE_ROOT 0 #define IS_VALID_PAE_ROOT(x) (!!(x)) +static inline hpa_t kvm_mmu_get_dummy_root(void) +{ + return my_zero_pfn(0) << PAGE_SHIFT; +} + +static inline bool kvm_mmu_is_dummy_root(hpa_t shadow_page) +{ + return is_zero_pfn(shadow_page >> PAGE_SHIFT); +} + typedef u64 __rcu *tdp_ptep_t; struct kvm_mmu_page { @@ -56,7 +59,12 @@ struct kvm_mmu_page { bool tdp_mmu_page; bool unsync; - u8 mmu_valid_gen; + union { + u8 mmu_valid_gen; + + /* Only accessed under slots_lock. */ + bool tdp_mmu_scheduled_root_to_zap; + }; /* * The shadow page can't be replaced by an equivalent huge page @@ -98,13 +106,7 @@ struct kvm_mmu_page { struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ tdp_ptep_t ptep; }; - union { - DECLARE_BITMAP(unsync_child_bitmap, 512); - struct { - struct work_struct tdp_mmu_async_work; - void *tdp_mmu_async_data; - }; - }; + DECLARE_BITMAP(unsync_child_bitmap, 512); /* * Tracks shadow pages that, if zapped, would allow KVM to create an NX @@ -170,9 +172,6 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn, int min_level); -void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn, - gfn_t nr_pages); - /* Flush the given page (huge or not) of guest memory. */ static inline void kvm_flush_remote_tlbs_gfn(struct kvm *kvm, gfn_t gfn, int level) { @@ -203,6 +202,7 @@ struct kvm_page_fault { /* Derived from mmu and global state. */ const bool is_tdp; + const bool is_private; const bool nx_huge_page_workaround_enabled; /* @@ -298,6 +298,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, .max_level = KVM_MAX_HUGEPAGE_LEVEL, .req_level = PG_LEVEL_4K, .goal_level = PG_LEVEL_4K, + .is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT), }; int r; diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 0a2ac438d647..c87da11f3a04 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -12,13 +12,13 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/lockdep.h> #include <linux/kvm_host.h> #include <linux/rculist.h> -#include <asm/kvm_page_track.h> - #include "mmu.h" #include "mmu_internal.h" +#include "page_track.h" bool kvm_page_track_write_tracking_enabled(struct kvm *kvm) { @@ -28,103 +28,64 @@ bool kvm_page_track_write_tracking_enabled(struct kvm *kvm) void kvm_page_track_free_memslot(struct kvm_memory_slot *slot) { - int i; - - for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) { - kvfree(slot->arch.gfn_track[i]); - slot->arch.gfn_track[i] = NULL; - } + kvfree(slot->arch.gfn_write_track); + slot->arch.gfn_write_track = NULL; } -int kvm_page_track_create_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot, - unsigned long npages) +static int __kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot, + unsigned long npages) { - int i; - - for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) { - if (i == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(kvm)) - continue; - - slot->arch.gfn_track[i] = - __vcalloc(npages, sizeof(*slot->arch.gfn_track[i]), - GFP_KERNEL_ACCOUNT); - if (!slot->arch.gfn_track[i]) - goto track_free; - } + const size_t size = sizeof(*slot->arch.gfn_write_track); - return 0; + if (!slot->arch.gfn_write_track) + slot->arch.gfn_write_track = __vcalloc(npages, size, + GFP_KERNEL_ACCOUNT); -track_free: - kvm_page_track_free_memslot(slot); - return -ENOMEM; + return slot->arch.gfn_write_track ? 0 : -ENOMEM; } -static inline bool page_track_mode_is_valid(enum kvm_page_track_mode mode) +int kvm_page_track_create_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot, + unsigned long npages) { - if (mode < 0 || mode >= KVM_PAGE_TRACK_MAX) - return false; + if (!kvm_page_track_write_tracking_enabled(kvm)) + return 0; - return true; + return __kvm_page_track_write_tracking_alloc(slot, npages); } int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot) { - unsigned short *gfn_track; - - if (slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE]) - return 0; - - gfn_track = __vcalloc(slot->npages, sizeof(*gfn_track), - GFP_KERNEL_ACCOUNT); - if (gfn_track == NULL) - return -ENOMEM; - - slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE] = gfn_track; - return 0; + return __kvm_page_track_write_tracking_alloc(slot, slot->npages); } -static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode, short count) +static void update_gfn_write_track(struct kvm_memory_slot *slot, gfn_t gfn, + short count) { int index, val; index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); - val = slot->arch.gfn_track[mode][index]; + val = slot->arch.gfn_write_track[index]; - if (WARN_ON(val + count < 0 || val + count > USHRT_MAX)) + if (WARN_ON_ONCE(val + count < 0 || val + count > USHRT_MAX)) return; - slot->arch.gfn_track[mode][index] += count; + slot->arch.gfn_write_track[index] += count; } -/* - * add guest page to the tracking pool so that corresponding access on that - * page will be intercepted. - * - * It should be called under the protection both of mmu-lock and kvm->srcu - * or kvm->slots_lock. - * - * @kvm: the guest instance we are interested in. - * @slot: the @gfn belongs to. - * @gfn: the guest page. - * @mode: tracking mode, currently only write track is supported. - */ -void kvm_slot_page_track_add_page(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode) +void __kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn) { + lockdep_assert_held_write(&kvm->mmu_lock); - if (WARN_ON(!page_track_mode_is_valid(mode))) - return; + lockdep_assert_once(lockdep_is_held(&kvm->slots_lock) || + srcu_read_lock_held(&kvm->srcu)); - if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(kvm))) + if (KVM_BUG_ON(!kvm_page_track_write_tracking_enabled(kvm), kvm)) return; - update_gfn_track(slot, gfn, mode, 1); + update_gfn_write_track(slot, gfn, 1); /* * new track stops large page mapping for the @@ -132,37 +93,22 @@ void kvm_slot_page_track_add_page(struct kvm *kvm, */ kvm_mmu_gfn_disallow_lpage(slot, gfn); - if (mode == KVM_PAGE_TRACK_WRITE) - if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K)) - kvm_flush_remote_tlbs(kvm); + if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K)) + kvm_flush_remote_tlbs(kvm); } -EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page); -/* - * remove the guest page from the tracking pool which stops the interception - * of corresponding access on that page. It is the opposed operation of - * kvm_slot_page_track_add_page(). - * - * It should be called under the protection both of mmu-lock and kvm->srcu - * or kvm->slots_lock. - * - * @kvm: the guest instance we are interested in. - * @slot: the @gfn belongs to. - * @gfn: the guest page. - * @mode: tracking mode, currently only write track is supported. - */ -void kvm_slot_page_track_remove_page(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode) +void __kvm_write_track_remove_gfn(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn) { - if (WARN_ON(!page_track_mode_is_valid(mode))) - return; + lockdep_assert_held_write(&kvm->mmu_lock); - if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(kvm))) + lockdep_assert_once(lockdep_is_held(&kvm->slots_lock) || + srcu_read_lock_held(&kvm->srcu)); + + if (KVM_BUG_ON(!kvm_page_track_write_tracking_enabled(kvm), kvm)) return; - update_gfn_track(slot, gfn, mode, -1); + update_gfn_write_track(slot, gfn, -1); /* * allow large page mapping for the tracked page @@ -170,31 +116,26 @@ void kvm_slot_page_track_remove_page(struct kvm *kvm, */ kvm_mmu_gfn_allow_lpage(slot, gfn); } -EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page); /* * check if the corresponding access on the specified guest page is tracked. */ -bool kvm_slot_page_track_is_active(struct kvm *kvm, - const struct kvm_memory_slot *slot, - gfn_t gfn, enum kvm_page_track_mode mode) +bool kvm_gfn_is_write_tracked(struct kvm *kvm, + const struct kvm_memory_slot *slot, gfn_t gfn) { int index; - if (WARN_ON(!page_track_mode_is_valid(mode))) - return false; - if (!slot) return false; - if (mode == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(kvm)) + if (!kvm_page_track_write_tracking_enabled(kvm)) return false; index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); - return !!READ_ONCE(slot->arch.gfn_track[mode][index]); + return !!READ_ONCE(slot->arch.gfn_write_track[index]); } +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING void kvm_page_track_cleanup(struct kvm *kvm) { struct kvm_page_track_notifier_head *head; @@ -216,17 +157,22 @@ int kvm_page_track_init(struct kvm *kvm) * register the notifier so that event interception for the tracked guest * pages can be received. */ -void -kvm_page_track_register_notifier(struct kvm *kvm, - struct kvm_page_track_notifier_node *n) +int kvm_page_track_register_notifier(struct kvm *kvm, + struct kvm_page_track_notifier_node *n) { struct kvm_page_track_notifier_head *head; + if (!kvm || kvm->mm != current->mm) + return -ESRCH; + + kvm_get_kvm(kvm); + head = &kvm->arch.track_notifier_head; write_lock(&kvm->mmu_lock); hlist_add_head_rcu(&n->node, &head->track_notifier_list); write_unlock(&kvm->mmu_lock); + return 0; } EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier); @@ -234,9 +180,8 @@ EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier); * stop receiving the event interception. It is the opposed operation of * kvm_page_track_register_notifier(). */ -void -kvm_page_track_unregister_notifier(struct kvm *kvm, - struct kvm_page_track_notifier_node *n) +void kvm_page_track_unregister_notifier(struct kvm *kvm, + struct kvm_page_track_notifier_node *n) { struct kvm_page_track_notifier_head *head; @@ -246,6 +191,8 @@ kvm_page_track_unregister_notifier(struct kvm *kvm, hlist_del_rcu(&n->node); write_unlock(&kvm->mmu_lock); synchronize_srcu(&head->track_srcu); + + kvm_put_kvm(kvm); } EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier); @@ -256,34 +203,30 @@ EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier); * The node should figure out if the written page is the one that node is * interested in by itself. */ -void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, - int bytes) +void __kvm_page_track_write(struct kvm *kvm, gpa_t gpa, const u8 *new, int bytes) { struct kvm_page_track_notifier_head *head; struct kvm_page_track_notifier_node *n; int idx; - head = &vcpu->kvm->arch.track_notifier_head; + head = &kvm->arch.track_notifier_head; if (hlist_empty(&head->track_notifier_list)) return; idx = srcu_read_lock(&head->track_srcu); hlist_for_each_entry_srcu(n, &head->track_notifier_list, node, - srcu_read_lock_held(&head->track_srcu)) + srcu_read_lock_held(&head->track_srcu)) if (n->track_write) - n->track_write(vcpu, gpa, new, bytes, n); + n->track_write(gpa, new, bytes, n); srcu_read_unlock(&head->track_srcu, idx); } /* - * Notify the node that memory slot is being removed or moved so that it can - * drop write-protection for the pages in the memory slot. - * - * The node should figure out it has any write-protected pages in this slot - * by itself. + * Notify external page track nodes that a memory region is being removed from + * the VM, e.g. so that users can free any associated metadata. */ -void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot) +void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot) { struct kvm_page_track_notifier_head *head; struct kvm_page_track_notifier_node *n; @@ -296,8 +239,69 @@ void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot) idx = srcu_read_lock(&head->track_srcu); hlist_for_each_entry_srcu(n, &head->track_notifier_list, node, - srcu_read_lock_held(&head->track_srcu)) - if (n->track_flush_slot) - n->track_flush_slot(kvm, slot, n); + srcu_read_lock_held(&head->track_srcu)) + if (n->track_remove_region) + n->track_remove_region(slot->base_gfn, slot->npages, n); srcu_read_unlock(&head->track_srcu, idx); } + +/* + * add guest page to the tracking pool so that corresponding access on that + * page will be intercepted. + * + * @kvm: the guest instance we are interested in. + * @gfn: the guest page. + */ +int kvm_write_track_add_gfn(struct kvm *kvm, gfn_t gfn) +{ + struct kvm_memory_slot *slot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + + slot = gfn_to_memslot(kvm, gfn); + if (!slot) { + srcu_read_unlock(&kvm->srcu, idx); + return -EINVAL; + } + + write_lock(&kvm->mmu_lock); + __kvm_write_track_add_gfn(kvm, slot, gfn); + write_unlock(&kvm->mmu_lock); + + srcu_read_unlock(&kvm->srcu, idx); + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_write_track_add_gfn); + +/* + * remove the guest page from the tracking pool which stops the interception + * of corresponding access on that page. + * + * @kvm: the guest instance we are interested in. + * @gfn: the guest page. + */ +int kvm_write_track_remove_gfn(struct kvm *kvm, gfn_t gfn) +{ + struct kvm_memory_slot *slot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + + slot = gfn_to_memslot(kvm, gfn); + if (!slot) { + srcu_read_unlock(&kvm->srcu, idx); + return -EINVAL; + } + + write_lock(&kvm->mmu_lock); + __kvm_write_track_remove_gfn(kvm, slot, gfn); + write_unlock(&kvm->mmu_lock); + + srcu_read_unlock(&kvm->srcu, idx); + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_write_track_remove_gfn); +#endif diff --git a/arch/x86/kvm/mmu/page_track.h b/arch/x86/kvm/mmu/page_track.h new file mode 100644 index 000000000000..d4d72ed999b1 --- /dev/null +++ b/arch/x86/kvm/mmu/page_track.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_PAGE_TRACK_H +#define __KVM_X86_PAGE_TRACK_H + +#include <linux/kvm_host.h> + +#include <asm/kvm_page_track.h> + + +bool kvm_page_track_write_tracking_enabled(struct kvm *kvm); +int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot); + +void kvm_page_track_free_memslot(struct kvm_memory_slot *slot); +int kvm_page_track_create_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot, + unsigned long npages); + +void __kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn); +void __kvm_write_track_remove_gfn(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn); + +bool kvm_gfn_is_write_tracked(struct kvm *kvm, + const struct kvm_memory_slot *slot, gfn_t gfn); + +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING +int kvm_page_track_init(struct kvm *kvm); +void kvm_page_track_cleanup(struct kvm *kvm); + +void __kvm_page_track_write(struct kvm *kvm, gpa_t gpa, const u8 *new, int bytes); +void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot); + +static inline bool kvm_page_track_has_external_user(struct kvm *kvm) +{ + return !hlist_empty(&kvm->arch.track_notifier_head.track_notifier_list); +} +#else +static inline int kvm_page_track_init(struct kvm *kvm) { return 0; } +static inline void kvm_page_track_cleanup(struct kvm *kvm) { } + +static inline void __kvm_page_track_write(struct kvm *kvm, gpa_t gpa, + const u8 *new, int bytes) { } +static inline void kvm_page_track_delete_slot(struct kvm *kvm, + struct kvm_memory_slot *slot) { } + +static inline bool kvm_page_track_has_external_user(struct kvm *kvm) { return false; } + +#endif /* CONFIG_KVM_EXTERNAL_WRITE_TRACKING */ + +static inline void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, + const u8 *new, int bytes) +{ + __kvm_page_track_write(vcpu->kvm, gpa, new, bytes); + + kvm_mmu_track_write(vcpu, gpa, new, bytes); +} + +#endif /* __KVM_X86_PAGE_TRACK_H */ diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 0662e0278e70..4d4e98fe4f35 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -62,7 +62,7 @@ #endif /* Common logic, but per-type values. These also need to be undefined. */ -#define PT_BASE_ADDR_MASK ((pt_element_t)(((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))) +#define PT_BASE_ADDR_MASK ((pt_element_t)__PT_BASE_ADDR_MASK) #define PT_LVL_ADDR_MASK(lvl) __PT_LVL_ADDR_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS) #define PT_LVL_OFFSET_MASK(lvl) __PT_LVL_OFFSET_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS) #define PT_INDEX(addr, lvl) __PT_INDEX(addr, lvl, PT_LEVEL_BITS) @@ -338,7 +338,6 @@ retry_walk: } #endif walker->max_level = walker->level; - ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu))); /* * FIXME: on Intel processors, loads of the PDPTE registers for PAE paging @@ -348,9 +347,21 @@ retry_walk: nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK; pte_access = ~0; + + /* + * Queue a page fault for injection if this assertion fails, as callers + * assume that walker.fault contains sane info on a walk failure. I.e. + * avoid making the situation worse by inducing even worse badness + * between when the assertion fails and when KVM kicks the vCPU out to + * userspace (because the VM is bugged). + */ + if (KVM_BUG_ON(is_long_mode(vcpu) && !is_pae(vcpu), vcpu->kvm)) + goto error; + ++walker->level; do { + struct kvm_memory_slot *slot; unsigned long host_addr; pt_access = pte_access; @@ -381,7 +392,11 @@ retry_walk: if (unlikely(real_gpa == INVALID_GPA)) return 0; - host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa), + slot = kvm_vcpu_gfn_to_memslot(vcpu, gpa_to_gfn(real_gpa)); + if (!kvm_is_visible_memslot(slot)) + goto error; + + host_addr = gfn_to_hva_memslot_prot(slot, gpa_to_gfn(real_gpa), &walker->pte_writable[walker->level - 1]); if (unlikely(kvm_is_error_hva(host_addr))) goto error; @@ -456,9 +471,6 @@ retry_walk: goto retry_walk; } - pgprintk("%s: pte %llx pte_access %x pt_access %x\n", - __func__, (u64)pte, walker->pte_access, - walker->pt_access[walker->level - 1]); return 1; error: @@ -529,8 +541,6 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte)) return false; - pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte); - gfn = gpte_to_gfn(gpte); pte_access = sp->role.access & FNAME(gpte_access)(gpte); FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte); @@ -638,8 +648,19 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (FNAME(gpte_changed)(vcpu, gw, top_level)) goto out_gpte_changed; - if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) + if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) + goto out_gpte_changed; + + /* + * Load a new root and retry the faulting instruction in the extremely + * unlikely scenario that the guest root gfn became visible between + * loading a dummy root and handling the resulting page fault, e.g. if + * userspace create a memslot in the interim. + */ + if (unlikely(kvm_mmu_is_dummy_root(vcpu->arch.mmu->root.hpa))) { + kvm_make_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu); goto out_gpte_changed; + } for_each_shadow_entry(vcpu, fault->addr, it) { gfn_t table_gfn; @@ -758,7 +779,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault struct guest_walker walker; int r; - pgprintk("%s: addr %lx err %x\n", __func__, fault->addr, fault->error_code); WARN_ON_ONCE(fault->is_tdp); /* @@ -773,7 +793,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault * The page is not mapped by the guest. Let the guest handle it. */ if (!r) { - pgprintk("%s: guest page fault\n", __func__); if (!fault->prefetch) kvm_inject_emulated_page_fault(vcpu, &walker.fault); @@ -837,7 +856,7 @@ static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) { int offset = 0; - WARN_ON(sp->role.level != PG_LEVEL_4K); + WARN_ON_ONCE(sp->role.level != PG_LEVEL_4K); if (PTTYPE == 32) offset = sp->role.quadrant << SPTE_LEVEL_BITS; diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index cf2c6426a6fc..4a599130e9c9 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -61,7 +61,7 @@ static u64 generation_mmio_spte_mask(u64 gen) { u64 mask; - WARN_ON(gen & ~MMIO_SPTE_GEN_MASK); + WARN_ON_ONCE(gen & ~MMIO_SPTE_GEN_MASK); mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK; mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK; @@ -221,8 +221,6 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * shadow pages and unsync'ing pages is not allowed. */ if (mmu_try_to_unsync_pages(vcpu->kvm, slot, gfn, can_unsync, prefetch)) { - pgprintk("%s: found shadow page for %llx, marking ro\n", - __func__, gfn); wrprot = true; pte_access &= ~ACC_WRITE_MASK; spte &= ~(PT_WRITABLE_MASK | shadow_mmu_writable_mask); @@ -242,7 +240,7 @@ out: if ((spte & PT_WRITABLE_MASK) && kvm_slot_dirty_track_enabled(slot)) { /* Enforced by kvm_mmu_hugepage_adjust. */ - WARN_ON(level > PG_LEVEL_4K); + WARN_ON_ONCE(level > PG_LEVEL_4K); mark_page_dirty_in_slot(vcpu->kvm, slot, gfn); } diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 1279db2eab44..a129951c9a88 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -3,6 +3,7 @@ #ifndef KVM_X86_MMU_SPTE_H #define KVM_X86_MMU_SPTE_H +#include "mmu.h" #include "mmu_internal.h" /* @@ -236,6 +237,18 @@ static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep) return to_shadow_page(__pa(sptep)); } +static inline struct kvm_mmu_page *root_to_sp(hpa_t root) +{ + if (kvm_mmu_is_dummy_root(root)) + return NULL; + + /* + * The "root" may be a special root, e.g. a PAE entry, treat it as a + * SPTE to ensure any non-PA bits are dropped. + */ + return spte_to_child_sp(root); +} + static inline bool is_mmio_spte(u64 spte) { return (spte & shadow_mmio_mask) == shadow_mmio_value && @@ -265,13 +278,13 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) static inline bool spte_ad_enabled(u64 spte) { - MMU_WARN_ON(!is_shadow_present_pte(spte)); + KVM_MMU_WARN_ON(!is_shadow_present_pte(spte)); return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_DISABLED; } static inline bool spte_ad_need_write_protect(u64 spte) { - MMU_WARN_ON(!is_shadow_present_pte(spte)); + KVM_MMU_WARN_ON(!is_shadow_present_pte(spte)); /* * This is benign for non-TDP SPTEs as SPTE_TDP_AD_ENABLED is '0', * and non-TDP SPTEs will never set these bits. Optimize for 64-bit @@ -282,13 +295,13 @@ static inline bool spte_ad_need_write_protect(u64 spte) static inline u64 spte_shadow_accessed_mask(u64 spte) { - MMU_WARN_ON(!is_shadow_present_pte(spte)); + KVM_MMU_WARN_ON(!is_shadow_present_pte(spte)); return spte_ad_enabled(spte) ? shadow_accessed_mask : 0; } static inline u64 spte_shadow_dirty_mask(u64 spte) { - MMU_WARN_ON(!is_shadow_present_pte(spte)); + KVM_MMU_WARN_ON(!is_shadow_present_pte(spte)); return spte_ad_enabled(spte) ? shadow_dirty_mask : 0; } diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index d2eb0d4f8710..04c247bfe318 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -39,13 +39,14 @@ void tdp_iter_restart(struct tdp_iter *iter) void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root, int min_level, gfn_t next_last_level_gfn) { - int root_level = root->role.level; - - WARN_ON(root_level < 1); - WARN_ON(root_level > PT64_ROOT_MAX_LEVEL); + if (WARN_ON_ONCE(!root || (root->role.level < 1) || + (root->role.level > PT64_ROOT_MAX_LEVEL))) { + iter->valid = false; + return; + } iter->next_last_level_gfn = next_last_level_gfn; - iter->root_level = root_level; + iter->root_level = root->role.level; iter->min_level = min_level; iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root->spt; iter->as_id = kvm_mmu_page_as_id(root); @@ -145,7 +146,7 @@ static bool try_step_up(struct tdp_iter *iter) * Step to the next SPTE in a pre-order traversal of the paging structure. * To get to the next SPTE, the iterator either steps down towards the goal * GFN, if at a present, non-last-level SPTE, or over to a SPTE mapping a - * highter GFN. + * higher GFN. * * The basic algorithm is as follows: * 1. If the current SPTE is a non-last-level SPTE, step down into the page diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 512163d52194..6ae19b4ee5b1 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -12,18 +12,10 @@ #include <trace/events/kvm.h> /* Initializes the TDP MMU for the VM, if enabled. */ -int kvm_mmu_init_tdp_mmu(struct kvm *kvm) +void kvm_mmu_init_tdp_mmu(struct kvm *kvm) { - struct workqueue_struct *wq; - - wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0); - if (!wq) - return -ENOMEM; - INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); - kvm->arch.tdp_mmu_zap_wq = wq; - return 1; } /* Arbitrarily returns true so that this may be used in if statements. */ @@ -46,20 +38,15 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) * ultimately frees all roots. */ kvm_tdp_mmu_invalidate_all_roots(kvm); - - /* - * Destroying a workqueue also first flushes the workqueue, i.e. no - * need to invoke kvm_tdp_mmu_zap_invalidated_roots(). - */ - destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); + kvm_tdp_mmu_zap_invalidated_roots(kvm); WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); /* * Ensure that all the outstanding RCU callbacks to free shadow pages - * can run before the VM is torn down. Work items on tdp_mmu_zap_wq - * can call kvm_tdp_mmu_put_root and create new callbacks. + * can run before the VM is torn down. Putting the last reference to + * zapped roots will create new callbacks. */ rcu_barrier(); } @@ -86,51 +73,8 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head) tdp_mmu_free_sp(sp); } -static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared); - -static void tdp_mmu_zap_root_work(struct work_struct *work) +void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) { - struct kvm_mmu_page *root = container_of(work, struct kvm_mmu_page, - tdp_mmu_async_work); - struct kvm *kvm = root->tdp_mmu_async_data; - - read_lock(&kvm->mmu_lock); - - /* - * A TLB flush is not necessary as KVM performs a local TLB flush when - * allocating a new root (see kvm_mmu_load()), and when migrating vCPU - * to a different pCPU. Note, the local TLB flush on reuse also - * invalidates any paging-structure-cache entries, i.e. TLB entries for - * intermediate paging structures, that may be zapped, as such entries - * are associated with the ASID on both VMX and SVM. - */ - tdp_mmu_zap_root(kvm, root, true); - - /* - * Drop the refcount using kvm_tdp_mmu_put_root() to test its logic for - * avoiding an infinite loop. By design, the root is reachable while - * it's being asynchronously zapped, thus a different task can put its - * last reference, i.e. flowing through kvm_tdp_mmu_put_root() for an - * asynchronously zapped root is unavoidable. - */ - kvm_tdp_mmu_put_root(kvm, root, true); - - read_unlock(&kvm->mmu_lock); -} - -static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root) -{ - root->tdp_mmu_async_data = kvm; - INIT_WORK(&root->tdp_mmu_async_work, tdp_mmu_zap_root_work); - queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work); -} - -void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared) -{ - kvm_lockdep_assert_mmu_lock_held(kvm, shared); - if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) return; @@ -159,10 +103,16 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, */ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, struct kvm_mmu_page *prev_root, - bool shared, bool only_valid) + bool only_valid) { struct kvm_mmu_page *next_root; + /* + * While the roots themselves are RCU-protected, fields such as + * role.invalid are protected by mmu_lock. + */ + lockdep_assert_held(&kvm->mmu_lock); + rcu_read_lock(); if (prev_root) @@ -185,7 +135,7 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, rcu_read_unlock(); if (prev_root) - kvm_tdp_mmu_put_root(kvm, prev_root, shared); + kvm_tdp_mmu_put_root(kvm, prev_root); return next_root; } @@ -197,22 +147,22 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * recent root. (Unless keeping a live reference is desirable.) * * If shared is set, this function is operating under the MMU lock in read - * mode. In the unlikely event that this thread must free a root, the lock - * will be temporarily dropped and reacquired in write mode. + * mode. */ -#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, _only_valid)\ - for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, _only_valid); \ - _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _shared, _only_valid)) \ - if (kvm_lockdep_assert_mmu_lock_held(_kvm, _shared) && \ - kvm_mmu_page_as_id(_root) != _as_id) { \ +#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid)\ + for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid); \ + ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ + _root = tdp_mmu_next_root(_kvm, _root, _only_valid)) \ + if (kvm_mmu_page_as_id(_root) != _as_id) { \ } else -#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \ - __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true) +#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ + __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, true) -#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, false, false) +#define for_each_tdp_mmu_root_yield_safe(_kvm, _root) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, false); \ + ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ + _root = tdp_mmu_next_root(_kvm, _root, false)) /* * Iterate over all TDP MMU roots. Requires that mmu_lock be held for write, @@ -292,7 +242,7 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) * by a memslot update or by the destruction of the VM. Initialize the * refcount to two; one reference for the vCPU, and one reference for * the TDP MMU itself, which is held until the root is invalidated and - * is ultimately put by tdp_mmu_zap_root_work(). + * is ultimately put by kvm_tdp_mmu_zap_invalidated_roots(). */ refcount_set(&root->tdp_mmu_root_count, 2); @@ -325,28 +275,18 @@ static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) * * @kvm: kvm instance * @sp: the page to be removed - * @shared: This operation may not be running under the exclusive use of - * the MMU lock and the operation must synchronize with other - * threads that might be adding or removing pages. */ -static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp, - bool shared) +static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp) { tdp_unaccount_mmu_page(kvm, sp); if (!sp->nx_huge_page_disallowed) return; - if (shared) - spin_lock(&kvm->arch.tdp_mmu_pages_lock); - else - lockdep_assert_held_write(&kvm->mmu_lock); - + spin_lock(&kvm->arch.tdp_mmu_pages_lock); sp->nx_huge_page_disallowed = false; untrack_possible_nx_huge_page(kvm, sp); - - if (shared) - spin_unlock(&kvm->arch.tdp_mmu_pages_lock); + spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } /** @@ -375,7 +315,7 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) trace_kvm_mmu_prepare_zap_page(sp); - tdp_mmu_unlink_sp(kvm, sp, shared); + tdp_mmu_unlink_sp(kvm, sp); for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { tdp_ptep_t sptep = pt + i; @@ -475,9 +415,9 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, bool is_leaf = is_present && is_last_spte(new_spte, level); bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte); - WARN_ON(level > PT64_ROOT_MAX_LEVEL); - WARN_ON(level < PG_LEVEL_4K); - WARN_ON(gfn & (KVM_PAGES_PER_HPAGE(level) - 1)); + WARN_ON_ONCE(level > PT64_ROOT_MAX_LEVEL); + WARN_ON_ONCE(level < PG_LEVEL_4K); + WARN_ON_ONCE(gfn & (KVM_PAGES_PER_HPAGE(level) - 1)); /* * If this warning were to trigger it would indicate that there was a @@ -522,9 +462,9 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, * impact the guest since both the former and current SPTEs * are nonpresent. */ - if (WARN_ON(!is_mmio_spte(old_spte) && - !is_mmio_spte(new_spte) && - !is_removed_spte(new_spte))) + if (WARN_ON_ONCE(!is_mmio_spte(old_spte) && + !is_mmio_spte(new_spte) && + !is_removed_spte(new_spte))) pr_err("Unexpected SPTE change! Nonpresent SPTEs\n" "should not be replaced with another,\n" "different nonpresent SPTE, unless one or both\n" @@ -661,7 +601,7 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, * should be used. If operating under the MMU lock in write mode, the * use of the removed SPTE should not be necessary. */ - WARN_ON(is_removed_spte(old_spte) || is_removed_spte(new_spte)); + WARN_ON_ONCE(is_removed_spte(old_spte) || is_removed_spte(new_spte)); old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level); @@ -689,7 +629,7 @@ static inline void tdp_mmu_iter_set_spte(struct kvm *kvm, struct tdp_iter *iter, else #define tdp_mmu_for_each_pte(_iter, _mmu, _start, _end) \ - for_each_tdp_pte(_iter, to_shadow_page(_mmu->root.hpa), _start, _end) + for_each_tdp_pte(_iter, root_to_sp(_mmu->root.hpa), _start, _end) /* * Yield if the MMU lock is contended or this thread needs to return control @@ -709,7 +649,7 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm, struct tdp_iter *iter, bool flush, bool shared) { - WARN_ON(iter->yielded); + WARN_ON_ONCE(iter->yielded); /* Ensure forward progress has been made before yielding. */ if (iter->next_last_level_gfn == iter->yielded_gfn) @@ -728,7 +668,7 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm, rcu_read_lock(); - WARN_ON(iter->gfn > iter->next_last_level_gfn); + WARN_ON_ONCE(iter->gfn > iter->next_last_level_gfn); iter->yielded = true; } @@ -877,13 +817,13 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, * true if a TLB flush is needed before releasing the MMU lock, i.e. if one or * more SPTEs were zapped since the MMU lock was last acquired. */ -bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, - bool can_yield, bool flush) +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush) { struct kvm_mmu_page *root; - for_each_tdp_mmu_root_yield_safe(kvm, root, as_id) - flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, flush); + lockdep_assert_held_write(&kvm->mmu_lock); + for_each_tdp_mmu_root_yield_safe(kvm, root) + flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush); return flush; } @@ -891,7 +831,6 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, void kvm_tdp_mmu_zap_all(struct kvm *kvm) { struct kvm_mmu_page *root; - int i; /* * Zap all roots, including invalid roots, as all SPTEs must be dropped @@ -905,10 +844,9 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) * is being destroyed or the userspace VMM has exited. In both cases, * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request. */ - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - for_each_tdp_mmu_root_yield_safe(kvm, root, i) - tdp_mmu_zap_root(kvm, root, false); - } + lockdep_assert_held_write(&kvm->mmu_lock); + for_each_tdp_mmu_root_yield_safe(kvm, root) + tdp_mmu_zap_root(kvm, root, false); } /* @@ -917,18 +855,47 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) */ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) { - flush_workqueue(kvm->arch.tdp_mmu_zap_wq); + struct kvm_mmu_page *root; + + read_lock(&kvm->mmu_lock); + + for_each_tdp_mmu_root_yield_safe(kvm, root) { + if (!root->tdp_mmu_scheduled_root_to_zap) + continue; + + root->tdp_mmu_scheduled_root_to_zap = false; + KVM_BUG_ON(!root->role.invalid, kvm); + + /* + * A TLB flush is not necessary as KVM performs a local TLB + * flush when allocating a new root (see kvm_mmu_load()), and + * when migrating a vCPU to a different pCPU. Note, the local + * TLB flush on reuse also invalidates paging-structure-cache + * entries, i.e. TLB entries for intermediate paging structures, + * that may be zapped, as such entries are associated with the + * ASID on both VMX and SVM. + */ + tdp_mmu_zap_root(kvm, root, true); + + /* + * The referenced needs to be put *after* zapping the root, as + * the root must be reachable by mmu_notifiers while it's being + * zapped + */ + kvm_tdp_mmu_put_root(kvm, root); + } + + read_unlock(&kvm->mmu_lock); } /* * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that * is about to be zapped, e.g. in response to a memslots update. The actual - * zapping is performed asynchronously. Using a separate workqueue makes it - * easy to ensure that the destruction is performed before the "fast zap" - * completes, without keeping a separate list of invalidated roots; the list is - * effectively the list of work items in the workqueue. + * zapping is done separately so that it happens with mmu_lock with read, + * whereas invalidating roots must be done with mmu_lock held for write (unless + * the VM is being destroyed). * - * Note, the asynchronous worker is gifted the TDP MMU's reference. + * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference. * See kvm_tdp_mmu_get_vcpu_root_hpa(). */ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) @@ -953,19 +920,20 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) /* * As above, mmu_lock isn't held when destroying the VM! There can't * be other references to @kvm, i.e. nothing else can invalidate roots - * or be consuming roots, but walking the list of roots does need to be - * guarded against roots being deleted by the asynchronous zap worker. + * or get/put references to roots. */ - rcu_read_lock(); - - list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) { + list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { + /* + * Note, invalid roots can outlive a memslot update! Invalid + * roots must be *zapped* before the memslot update completes, + * but a different task can acquire a reference and keep the + * root alive after its been zapped. + */ if (!root->role.invalid) { + root->tdp_mmu_scheduled_root_to_zap = true; root->role.invalid = true; - tdp_mmu_schedule_zap_root(kvm, root); } } - - rcu_read_unlock(); } /* @@ -1146,8 +1114,13 @@ retry: bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool flush) { - return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start, - range->end, range->may_block, flush); + struct kvm_mmu_page *root; + + __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false) + flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, + range->may_block, flush); + + return flush; } typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter, @@ -1241,7 +1214,7 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte; /* Huge pages aren't expected to be modified without first being zapped. */ - WARN_ON(pte_huge(range->pte) || range->start + 1 != range->end); + WARN_ON_ONCE(pte_huge(range->arg.pte) || range->start + 1 != range->end); if (iter->level != PG_LEVEL_4K || !is_shadow_present_pte(iter->old_spte)) @@ -1255,9 +1228,9 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter, */ tdp_mmu_iter_set_spte(kvm, iter, 0); - if (!pte_write(range->pte)) { + if (!pte_write(range->arg.pte)) { new_spte = kvm_mmu_changed_pte_notifier_make_spte(iter->old_spte, - pte_pfn(range->pte)); + pte_pfn(range->arg.pte)); tdp_mmu_iter_set_spte(kvm, iter, new_spte); } @@ -1332,7 +1305,7 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, lockdep_assert_held_read(&kvm->mmu_lock); - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages, min_level); @@ -1364,6 +1337,8 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm, { struct kvm_mmu_page *sp; + kvm_lockdep_assert_mmu_lock_held(kvm, shared); + /* * Since we are allocating while under the MMU lock we have to be * careful about GFP flags. Use GFP_NOWAIT to avoid blocking on direct @@ -1514,11 +1489,10 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, int r = 0; kvm_lockdep_assert_mmu_lock_held(kvm, shared); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, shared) { + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) { r = tdp_mmu_split_huge_pages_root(kvm, root, start, end, target_level, shared); if (r) { - kvm_tdp_mmu_put_root(kvm, root, shared); + kvm_tdp_mmu_put_root(kvm, root); break; } } @@ -1540,16 +1514,17 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - tdp_root_for_each_leaf_pte(iter, root, start, end) { + tdp_root_for_each_pte(iter, root, start, end) { retry: - if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) + if (!is_shadow_present_pte(iter.old_spte) || + !is_last_spte(iter.old_spte, iter.level)) continue; - if (!is_shadow_present_pte(iter.old_spte)) + if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; - MMU_WARN_ON(kvm_ad_enabled() && - spte_ad_need_write_protect(iter.old_spte)); + KVM_MMU_WARN_ON(kvm_ad_enabled() && + spte_ad_need_write_protect(iter.old_spte)); if (!(iter.old_spte & dbit)) continue; @@ -1578,8 +1553,7 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, bool spte_set = false; lockdep_assert_held_read(&kvm->mmu_lock); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); @@ -1600,6 +1574,8 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, shadow_dirty_mask; struct tdp_iter iter; + lockdep_assert_held_write(&kvm->mmu_lock); + rcu_read_lock(); tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask), @@ -1607,8 +1583,8 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, if (!mask) break; - MMU_WARN_ON(kvm_ad_enabled() && - spte_ad_need_write_protect(iter.old_spte)); + KVM_MMU_WARN_ON(kvm_ad_enabled() && + spte_ad_need_write_protect(iter.old_spte)); if (iter.level > PG_LEVEL_4K || !(mask & (1UL << (iter.gfn - gfn)))) @@ -1646,7 +1622,6 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, { struct kvm_mmu_page *root; - lockdep_assert_held_write(&kvm->mmu_lock); for_each_tdp_mmu_root(kvm, root, slot->as_id) clear_dirty_pt_masked(kvm, root, gfn, mask, wrprot); } @@ -1712,8 +1687,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, struct kvm_mmu_page *root; lockdep_assert_held_read(&kvm->mmu_lock); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) zap_collapsible_spte_range(kvm, root, slot); } diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 0a63b1afabd3..20d97aa46c49 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -7,7 +7,7 @@ #include "spte.h" -int kvm_mmu_init_tdp_mmu(struct kvm *kvm); +void kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); @@ -17,11 +17,9 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) return refcount_inc_not_zero(&root->tdp_mmu_root_count); } -void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared); +void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root); -bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, - gfn_t end, bool can_yield, bool flush); +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush); bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); void kvm_tdp_mmu_zap_all(struct kvm *kvm); void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm); |