diff options
Diffstat (limited to 'arch/x86/kvm/mmu/mmu.c')
| -rw-r--r-- | arch/x86/kvm/mmu/mmu.c | 1907 |
1 files changed, 1136 insertions, 771 deletions
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index db007a4dffa2..63bb77ee1bb1 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -179,7 +179,6 @@ struct kvm_shadow_walk_iterator { static struct kmem_cache *pte_list_desc_cache; struct kmem_cache *mmu_page_header_cache; -static struct percpu_counter kvm_total_used_mmu_pages; static void mmu_spte_set(u64 *sptep, u64 spte); @@ -336,16 +335,19 @@ static int is_cpuid_PSE36(void) #ifdef CONFIG_X86_64 static void __set_spte(u64 *sptep, u64 spte) { + KVM_MMU_WARN_ON(is_ept_ve_possible(spte)); WRITE_ONCE(*sptep, spte); } static void __update_clear_spte_fast(u64 *sptep, u64 spte) { + KVM_MMU_WARN_ON(is_ept_ve_possible(spte)); WRITE_ONCE(*sptep, spte); } static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) { + KVM_MMU_WARN_ON(is_ept_ve_possible(spte)); return xchg(sptep, spte); } @@ -432,8 +434,8 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) * The idea using the light way get the spte on x86_32 guest is from * gup_get_pte (mm/gup.c). * - * An spte tlb flush may be pending, because kvm_set_pte_rmap - * coalesces them and we are running out of the MMU lock. Therefore + * An spte tlb flush may be pending, because they are coalesced and + * we are running out of the MMU lock. Therefore * we need to protect against in-progress updates of the spte. * * Reading the spte while an update is in progress may get the old value @@ -482,11 +484,12 @@ static void mmu_spte_set(u64 *sptep, u64 new_spte) __set_spte(sptep, new_spte); } -/* - * Update the SPTE (excluding the PFN), but do not track changes in its - * accessed/dirty status. +/* Rules for using mmu_spte_update: + * Update the state bits, it means the mapped pfn is not changed. + * + * Returns true if the TLB needs to be flushed */ -static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte) +static bool mmu_spte_update(u64 *sptep, u64 new_spte) { u64 old_spte = *sptep; @@ -495,61 +498,18 @@ static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte) if (!is_shadow_present_pte(old_spte)) { mmu_spte_set(sptep, new_spte); - return old_spte; + return false; } - if (!spte_has_volatile_bits(old_spte)) + if (!spte_needs_atomic_update(old_spte)) __update_clear_spte_fast(sptep, new_spte); else old_spte = __update_clear_spte_slow(sptep, new_spte); - WARN_ON_ONCE(spte_to_pfn(old_spte) != spte_to_pfn(new_spte)); + WARN_ON_ONCE(!is_shadow_present_pte(old_spte) || + spte_to_pfn(old_spte) != spte_to_pfn(new_spte)); - return old_spte; -} - -/* Rules for using mmu_spte_update: - * Update the state bits, it means the mapped pfn is not changed. - * - * Whenever an MMU-writable SPTE is overwritten with a read-only SPTE, remote - * TLBs must be flushed. Otherwise rmap_write_protect will find a read-only - * spte, even though the writable spte might be cached on a CPU's TLB. - * - * Returns true if the TLB needs to be flushed - */ -static bool mmu_spte_update(u64 *sptep, u64 new_spte) -{ - bool flush = false; - u64 old_spte = mmu_spte_update_no_track(sptep, new_spte); - - if (!is_shadow_present_pte(old_spte)) - return false; - - /* - * For the spte updated out of mmu-lock is safe, since - * we always atomically update it, see the comments in - * spte_has_volatile_bits(). - */ - if (is_mmu_writable_spte(old_spte) && - !is_writable_pte(new_spte)) - flush = true; - - /* - * Flush TLB when accessed/dirty states are changed in the page tables, - * to guarantee consistency between TLB and page tables. - */ - - if (is_accessed_spte(old_spte) && !is_accessed_spte(new_spte)) { - flush = true; - kvm_set_pfn_accessed(spte_to_pfn(old_spte)); - } - - if (is_dirty_spte(old_spte) && !is_dirty_spte(new_spte)) { - flush = true; - kvm_set_pfn_dirty(spte_to_pfn(old_spte)); - } - - return flush; + return leaf_spte_change_needs_tlb_flush(old_spte, new_spte); } /* @@ -560,39 +520,19 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) */ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) { - kvm_pfn_t pfn; u64 old_spte = *sptep; int level = sptep_to_sp(sptep)->role.level; - struct page *page; if (!is_shadow_present_pte(old_spte) || - !spte_has_volatile_bits(old_spte)) - __update_clear_spte_fast(sptep, 0ull); + !spte_needs_atomic_update(old_spte)) + __update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE); else - old_spte = __update_clear_spte_slow(sptep, 0ull); + old_spte = __update_clear_spte_slow(sptep, SHADOW_NONPRESENT_VALUE); if (!is_shadow_present_pte(old_spte)) return old_spte; kvm_update_page_stats(kvm, level, -1); - - pfn = spte_to_pfn(old_spte); - - /* - * KVM doesn't hold a reference to any pages mapped into the guest, and - * instead uses the mmu_notifier to ensure that KVM unmaps any pages - * before they are reclaimed. Sanity check that, if the pfn is backed - * by a refcounted page, the refcount is elevated. - */ - page = kvm_pfn_to_refcounted_page(pfn); - WARN_ON_ONCE(page && !page_count(page)); - - if (is_accessed_spte(old_spte)) - kvm_set_pfn_accessed(pfn); - - if (is_dirty_spte(old_spte)) - kvm_set_pfn_dirty(pfn); - return old_spte; } @@ -603,7 +543,7 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) */ static void mmu_spte_clear_no_track(u64 *sptep) { - __update_clear_spte_fast(sptep, 0ull); + __update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE); } static u64 mmu_spte_get_lockless(u64 *sptep) @@ -611,32 +551,6 @@ static u64 mmu_spte_get_lockless(u64 *sptep) return __get_spte_lockless(sptep); } -/* Returns the Accessed status of the PTE and resets it at the same time. */ -static bool mmu_spte_age(u64 *sptep) -{ - u64 spte = mmu_spte_get_lockless(sptep); - - if (!is_accessed_spte(spte)) - return false; - - if (spte_ad_enabled(spte)) { - clear_bit((ffs(shadow_accessed_mask) - 1), - (unsigned long *)sptep); - } else { - /* - * Capture the dirty status of the page, so that it doesn't get - * lost when the SPTE is marked for access tracking. - */ - if (is_writable_pte(spte)) - kvm_set_pfn_dirty(spte_to_pfn(spte)); - - spte = mark_spte_for_access_track(spte); - mmu_spte_update_no_track(sptep, spte); - } - - return true; -} - static inline bool is_tdp_mmu_active(struct kvm_vcpu *vcpu) { return tdp_mmu_enabled && vcpu->arch.mmu->root_role.direct; @@ -685,6 +599,12 @@ static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect) 1 + PT64_ROOT_MAX_LEVEL + PTE_PREFETCH_NUM); if (r) return r; + if (kvm_has_mirrored_tdp(vcpu->kvm)) { + r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_external_spt_cache, + PT64_ROOT_MAX_LEVEL); + if (r) + return r; + } r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadow_page_cache, PT64_ROOT_MAX_LEVEL); if (r) @@ -704,6 +624,7 @@ static void mmu_free_memory_caches(struct kvm_vcpu *vcpu) kvm_mmu_free_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadow_page_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadowed_info_cache); + kvm_mmu_free_memory_cache(&vcpu->arch.mmu_external_spt_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache); } @@ -719,7 +640,7 @@ static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index) if (sp->role.passthrough) return sp->gfn; - if (!sp->role.direct) + if (sp->shadowed_translation) return sp->shadowed_translation[index] >> PAGE_SHIFT; return sp->gfn + (index << ((sp->role.level - 1) * SPTE_LEVEL_BITS)); @@ -733,7 +654,7 @@ static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index) */ static u32 kvm_mmu_page_get_access(struct kvm_mmu_page *sp, int index) { - if (sp_has_gptes(sp)) + if (sp->shadowed_translation) return sp->shadowed_translation[index] & ACC_ALL; /* @@ -754,7 +675,7 @@ static u32 kvm_mmu_page_get_access(struct kvm_mmu_page *sp, int index) static void kvm_mmu_page_set_translation(struct kvm_mmu_page *sp, int index, gfn_t gfn, unsigned int access) { - if (sp_has_gptes(sp)) { + if (sp->shadowed_translation) { sp->shadowed_translation[index] = (gfn << PAGE_SHIFT) | access; return; } @@ -831,6 +752,15 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) gfn_t gfn; kvm->arch.indirect_shadow_pages++; + /* + * Ensure indirect_shadow_pages is elevated prior to re-reading guest + * child PTEs in FNAME(gpte_changed), i.e. guarantee either in-flight + * emulated writes are visible before re-reading guest PTEs, or that + * an emulated write will see the elevated count and acquire mmu_lock + * to update SPTEs. Pairs with the smp_mb() in kvm_mmu_track_write(). + */ + smp_mb(); + gfn = sp->gfn; slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); @@ -923,31 +853,173 @@ static struct kvm_memory_slot *gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu * About rmap_head encoding: * * If the bit zero of rmap_head->val is clear, then it points to the only spte - * in this rmap chain. Otherwise, (rmap_head->val & ~1) points to a struct + * in this rmap chain. Otherwise, (rmap_head->val & ~3) points to a struct * pte_list_desc containing more mappings. */ +#define KVM_RMAP_MANY BIT(0) + +/* + * rmaps and PTE lists are mostly protected by mmu_lock (the shadow MMU always + * operates with mmu_lock held for write), but rmaps can be walked without + * holding mmu_lock so long as the caller can tolerate SPTEs in the rmap chain + * being zapped/dropped _while the rmap is locked_. + * + * Other than the KVM_RMAP_LOCKED flag, modifications to rmap entries must be + * done while holding mmu_lock for write. This allows a task walking rmaps + * without holding mmu_lock to concurrently walk the same entries as a task + * that is holding mmu_lock but _not_ the rmap lock. Neither task will modify + * the rmaps, thus the walks are stable. + * + * As alluded to above, SPTEs in rmaps are _not_ protected by KVM_RMAP_LOCKED, + * only the rmap chains themselves are protected. E.g. holding an rmap's lock + * ensures all "struct pte_list_desc" fields are stable. + */ +#define KVM_RMAP_LOCKED BIT(1) + +static unsigned long __kvm_rmap_lock(struct kvm_rmap_head *rmap_head) +{ + unsigned long old_val, new_val; + + lockdep_assert_preemption_disabled(); + + /* + * Elide the lock if the rmap is empty, as lockless walkers (read-only + * mode) don't need to (and can't) walk an empty rmap, nor can they add + * entries to the rmap. I.e. the only paths that process empty rmaps + * do so while holding mmu_lock for write, and are mutually exclusive. + */ + old_val = atomic_long_read(&rmap_head->val); + if (!old_val) + return 0; + + do { + /* + * If the rmap is locked, wait for it to be unlocked before + * trying acquire the lock, e.g. to avoid bouncing the cache + * line. + */ + while (old_val & KVM_RMAP_LOCKED) { + cpu_relax(); + old_val = atomic_long_read(&rmap_head->val); + } + + /* + * Recheck for an empty rmap, it may have been purged by the + * task that held the lock. + */ + if (!old_val) + return 0; + + new_val = old_val | KVM_RMAP_LOCKED; + /* + * Use try_cmpxchg_acquire() to prevent reads and writes to the rmap + * from being reordered outside of the critical section created by + * __kvm_rmap_lock(). + * + * Pairs with the atomic_long_set_release() in kvm_rmap_unlock(). + * + * For the !old_val case, no ordering is needed, as there is no rmap + * to walk. + */ + } while (!atomic_long_try_cmpxchg_acquire(&rmap_head->val, &old_val, new_val)); + + /* + * Return the old value, i.e. _without_ the LOCKED bit set. It's + * impossible for the return value to be 0 (see above), i.e. the read- + * only unlock flow can't get a false positive and fail to unlock. + */ + return old_val; +} + +static unsigned long kvm_rmap_lock(struct kvm *kvm, + struct kvm_rmap_head *rmap_head) +{ + lockdep_assert_held_write(&kvm->mmu_lock); + + return __kvm_rmap_lock(rmap_head); +} + +static void __kvm_rmap_unlock(struct kvm_rmap_head *rmap_head, + unsigned long val) +{ + KVM_MMU_WARN_ON(val & KVM_RMAP_LOCKED); + /* + * Ensure that all accesses to the rmap have completed before unlocking + * the rmap. + * + * Pairs with the atomic_long_try_cmpxchg_acquire() in __kvm_rmap_lock(). + */ + atomic_long_set_release(&rmap_head->val, val); +} + +static void kvm_rmap_unlock(struct kvm *kvm, + struct kvm_rmap_head *rmap_head, + unsigned long new_val) +{ + lockdep_assert_held_write(&kvm->mmu_lock); + + __kvm_rmap_unlock(rmap_head, new_val); +} + +static unsigned long kvm_rmap_get(struct kvm_rmap_head *rmap_head) +{ + return atomic_long_read(&rmap_head->val) & ~KVM_RMAP_LOCKED; +} + +/* + * If mmu_lock isn't held, rmaps can only be locked in read-only mode. The + * actual locking is the same, but the caller is disallowed from modifying the + * rmap, and so the unlock flow is a nop if the rmap is/was empty. + */ +static unsigned long kvm_rmap_lock_readonly(struct kvm_rmap_head *rmap_head) +{ + unsigned long rmap_val; + + preempt_disable(); + rmap_val = __kvm_rmap_lock(rmap_head); + + if (!rmap_val) + preempt_enable(); + + return rmap_val; +} + +static void kvm_rmap_unlock_readonly(struct kvm_rmap_head *rmap_head, + unsigned long old_val) +{ + if (!old_val) + return; + + KVM_MMU_WARN_ON(old_val != kvm_rmap_get(rmap_head)); + + __kvm_rmap_unlock(rmap_head, old_val); + preempt_enable(); +} /* * Returns the number of pointers in the rmap chain, not counting the new one. */ -static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, - struct kvm_rmap_head *rmap_head) +static int pte_list_add(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, + u64 *spte, struct kvm_rmap_head *rmap_head) { + unsigned long old_val, new_val; struct pte_list_desc *desc; int count = 0; - if (!rmap_head->val) { - rmap_head->val = (unsigned long)spte; - } else if (!(rmap_head->val & 1)) { + old_val = kvm_rmap_lock(kvm, rmap_head); + + if (!old_val) { + new_val = (unsigned long)spte; + } else if (!(old_val & KVM_RMAP_MANY)) { desc = kvm_mmu_memory_cache_alloc(cache); - desc->sptes[0] = (u64 *)rmap_head->val; + desc->sptes[0] = (u64 *)old_val; desc->sptes[1] = spte; desc->spte_count = 2; desc->tail_count = 0; - rmap_head->val = (unsigned long)desc | 1; + new_val = (unsigned long)desc | KVM_RMAP_MANY; ++count; } else { - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(old_val & ~KVM_RMAP_MANY); count = desc->tail_count + desc->spte_count; /* @@ -956,21 +1028,25 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, */ if (desc->spte_count == PTE_LIST_EXT) { desc = kvm_mmu_memory_cache_alloc(cache); - desc->more = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc->more = (struct pte_list_desc *)(old_val & ~KVM_RMAP_MANY); desc->spte_count = 0; desc->tail_count = count; - rmap_head->val = (unsigned long)desc | 1; + new_val = (unsigned long)desc | KVM_RMAP_MANY; + } else { + new_val = old_val; } desc->sptes[desc->spte_count++] = spte; } + + kvm_rmap_unlock(kvm, rmap_head, new_val); + return count; } -static void pte_list_desc_remove_entry(struct kvm *kvm, - struct kvm_rmap_head *rmap_head, +static void pte_list_desc_remove_entry(struct kvm *kvm, unsigned long *rmap_val, struct pte_list_desc *desc, int i) { - struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + struct pte_list_desc *head_desc = (struct pte_list_desc *)(*rmap_val & ~KVM_RMAP_MANY); int j = head_desc->spte_count - 1; /* @@ -997,9 +1073,9 @@ static void pte_list_desc_remove_entry(struct kvm *kvm, * head at the next descriptor, i.e. the new head. */ if (!head_desc->more) - rmap_head->val = 0; + *rmap_val = 0; else - rmap_head->val = (unsigned long)head_desc->more | 1; + *rmap_val = (unsigned long)head_desc->more | KVM_RMAP_MANY; mmu_free_pte_list_desc(head_desc); } @@ -1007,24 +1083,26 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte, struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; + unsigned long rmap_val; int i; - if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_head->val, kvm)) - return; + rmap_val = kvm_rmap_lock(kvm, rmap_head); + if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_val, kvm)) + goto out; - if (!(rmap_head->val & 1)) { - if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_head->val != spte, kvm)) - return; + if (!(rmap_val & KVM_RMAP_MANY)) { + if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_val != spte, kvm)) + goto out; - rmap_head->val = 0; + rmap_val = 0; } else { - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY); while (desc) { for (i = 0; i < desc->spte_count; ++i) { if (desc->sptes[i] == spte) { - pte_list_desc_remove_entry(kvm, rmap_head, + pte_list_desc_remove_entry(kvm, &rmap_val, desc, i); - return; + goto out; } } desc = desc->more; @@ -1032,6 +1110,9 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte, KVM_BUG_ON_DATA_CORRUPTION(true, kvm); } + +out: + kvm_rmap_unlock(kvm, rmap_head, rmap_val); } static void kvm_zap_one_rmap_spte(struct kvm *kvm, @@ -1046,17 +1127,19 @@ static bool kvm_zap_all_rmap_sptes(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc, *next; + unsigned long rmap_val; int i; - if (!rmap_head->val) + rmap_val = kvm_rmap_lock(kvm, rmap_head); + if (!rmap_val) return false; - if (!(rmap_head->val & 1)) { - mmu_spte_clear_track_bits(kvm, (u64 *)rmap_head->val); + if (!(rmap_val & KVM_RMAP_MANY)) { + mmu_spte_clear_track_bits(kvm, (u64 *)rmap_val); goto out; } - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY); for (; desc; desc = next) { for (i = 0; i < desc->spte_count; i++) @@ -1066,20 +1149,21 @@ static bool kvm_zap_all_rmap_sptes(struct kvm *kvm, } out: /* rmap_head is meaningless now, remember to reset it */ - rmap_head->val = 0; + kvm_rmap_unlock(kvm, rmap_head, 0); return true; } unsigned int pte_list_count(struct kvm_rmap_head *rmap_head) { + unsigned long rmap_val = kvm_rmap_get(rmap_head); struct pte_list_desc *desc; - if (!rmap_head->val) + if (!rmap_val) return 0; - else if (!(rmap_head->val & 1)) + else if (!(rmap_val & KVM_RMAP_MANY)) return 1; - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY); return desc->tail_count + desc->spte_count; } @@ -1122,6 +1206,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) */ struct rmap_iterator { /* private fields */ + struct rmap_head *head; struct pte_list_desc *desc; /* holds the sptep if not NULL */ int pos; /* index of the sptep */ }; @@ -1136,23 +1221,19 @@ struct rmap_iterator { static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head, struct rmap_iterator *iter) { - u64 *sptep; + unsigned long rmap_val = kvm_rmap_get(rmap_head); - if (!rmap_head->val) + if (!rmap_val) return NULL; - if (!(rmap_head->val & 1)) { + if (!(rmap_val & KVM_RMAP_MANY)) { iter->desc = NULL; - sptep = (u64 *)rmap_head->val; - goto out; + return (u64 *)rmap_val; } - iter->desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + iter->desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY); iter->pos = 0; - sptep = iter->desc->sptes[iter->pos]; -out: - BUG_ON(!is_shadow_present_pte(*sptep)); - return sptep; + return iter->desc->sptes[iter->pos]; } /* @@ -1162,14 +1243,11 @@ out: */ static u64 *rmap_get_next(struct rmap_iterator *iter) { - u64 *sptep; - if (iter->desc) { if (iter->pos < PTE_LIST_EXT - 1) { ++iter->pos; - sptep = iter->desc->sptes[iter->pos]; - if (sptep) - goto out; + if (iter->desc->sptes[iter->pos]) + return iter->desc->sptes[iter->pos]; } iter->desc = iter->desc->more; @@ -1177,20 +1255,24 @@ static u64 *rmap_get_next(struct rmap_iterator *iter) if (iter->desc) { iter->pos = 0; /* desc->sptes[0] cannot be NULL */ - sptep = iter->desc->sptes[iter->pos]; - goto out; + return iter->desc->sptes[iter->pos]; } } return NULL; -out: - BUG_ON(!is_shadow_present_pte(*sptep)); - return sptep; } -#define for_each_rmap_spte(_rmap_head_, _iter_, _spte_) \ - for (_spte_ = rmap_get_first(_rmap_head_, _iter_); \ - _spte_; _spte_ = rmap_get_next(_iter_)) +#define __for_each_rmap_spte(_rmap_head_, _iter_, _sptep_) \ + for (_sptep_ = rmap_get_first(_rmap_head_, _iter_); \ + _sptep_; _sptep_ = rmap_get_next(_iter_)) + +#define for_each_rmap_spte(_rmap_head_, _iter_, _sptep_) \ + __for_each_rmap_spte(_rmap_head_, _iter_, _sptep_) \ + if (!WARN_ON_ONCE(!is_shadow_present_pte(*(_sptep_)))) \ + +#define for_each_rmap_spte_lockless(_rmap_head_, _iter_, _sptep_, _spte_) \ + __for_each_rmap_spte(_rmap_head_, _iter_, _sptep_) \ + if (is_shadow_present_pte(_spte_ = mmu_spte_get_lockless(sptep))) static void drop_spte(struct kvm *kvm, u64 *sptep) { @@ -1263,16 +1345,6 @@ static bool spte_clear_dirty(u64 *sptep) return mmu_spte_update(sptep, spte); } -static bool spte_wrprot_for_clear_dirty(u64 *sptep) -{ - bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT, - (unsigned long *)sptep); - if (was_writable && !spte_ad_enabled(*sptep)) - kvm_set_pfn_dirty(spte_to_pfn(*sptep)); - - return was_writable; -} - /* * Gets the GFN ready for another round of dirty logging by clearing the * - D bit on ad-enabled SPTEs, and @@ -1286,24 +1358,17 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct rmap_iterator iter; bool flush = false; - for_each_rmap_spte(rmap_head, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) { if (spte_ad_need_write_protect(*sptep)) - flush |= spte_wrprot_for_clear_dirty(sptep); + flush |= test_and_clear_bit(PT_WRITABLE_SHIFT, + (unsigned long *)sptep); else flush |= spte_clear_dirty(sptep); + } return flush; } -/** - * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages - * @kvm: kvm instance - * @slot: slot to protect - * @gfn_offset: start of the BITS_PER_LONG pages we care about - * @mask: indicates which pages we should protect - * - * Used when we do not need to care about huge page mappings. - */ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) @@ -1327,16 +1392,6 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, } } -/** - * kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages, or write - * protect the page if the D-bit isn't supported. - * @kvm: kvm instance - * @slot: slot to clear D-bit - * @gfn_offset: start of the BITS_PER_LONG pages we care about - * @mask: indicates which pages we should clear D-bit - * - * Used for PML to re-log the dirty GPAs after userspace querying dirty_bitmap. - */ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) @@ -1360,24 +1415,16 @@ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, } } -/** - * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected - * PT level pages. - * - * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to - * enable dirty logging for them. - * - * We need to care about huge page mappings: e.g. during dirty logging we may - * have such mappings. - */ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { /* - * Huge pages are NOT write protected when we start dirty logging in - * initially-all-set mode; must write protect them here so that they - * are split to 4K on the first write. + * If the slot was assumed to be "initially all dirty", write-protect + * huge pages to ensure they are split to 4KiB on the first write (KVM + * dirty logs at 4KiB granularity). If eager page splitting is enabled, + * immediately try to split huge pages, e.g. so that vCPUs don't get + * saddled with the cost of splitting. * * The gfn_offset is guaranteed to be aligned to 64, but the base_gfn * of memslot has no such restriction, so the range can cross two large @@ -1399,7 +1446,16 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, PG_LEVEL_2M); } - /* Now handle 4K PTEs. */ + /* + * (Re)Enable dirty logging for all 4KiB SPTEs that map the GFNs in + * mask. If PML is enabled and the GFN doesn't need to be write- + * protected for other reasons, e.g. shadow paging, clear the Dirty bit. + * Otherwise clear the Writable bit. + * + * Note that kvm_mmu_clear_dirty_pt_masked() is called whenever PML is + * enabled but it chooses between clearing the Dirty bit and Writeable + * bit based on the context. + */ if (kvm_x86_ops.cpu_dirty_log_size) kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask); else @@ -1441,54 +1497,10 @@ static bool kvm_vcpu_write_protect_gfn(struct kvm_vcpu *vcpu, u64 gfn) return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn, PG_LEVEL_4K); } -static bool __kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - const struct kvm_memory_slot *slot) -{ - return kvm_zap_all_rmap_sptes(kvm, rmap_head); -} - static bool kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level, - pte_t unused) -{ - return __kvm_zap_rmap(kvm, rmap_head, slot); -} - -static bool kvm_set_pte_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level, - pte_t pte) + const struct kvm_memory_slot *slot) { - u64 *sptep; - struct rmap_iterator iter; - bool need_flush = false; - u64 new_spte; - kvm_pfn_t new_pfn; - - WARN_ON_ONCE(pte_huge(pte)); - new_pfn = pte_pfn(pte); - -restart: - for_each_rmap_spte(rmap_head, &iter, sptep) { - need_flush = true; - - if (pte_write(pte)) { - kvm_zap_one_rmap_spte(kvm, rmap_head, sptep); - goto restart; - } else { - new_spte = kvm_mmu_changed_pte_notifier_make_spte( - *sptep, new_pfn); - - mmu_spte_clear_track_bits(kvm, sptep); - mmu_spte_set(sptep, new_spte); - } - } - - if (need_flush && kvm_available_flush_remote_tlbs_range()) { - kvm_flush_remote_tlbs_gfn(kvm, gfn, level); - return false; - } - - return need_flush; + return kvm_zap_all_rmap_sptes(kvm, rmap_head); } struct slot_rmap_walk_iterator { @@ -1539,9 +1551,9 @@ static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator) static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) { while (++iterator->rmap <= iterator->end_rmap) { - iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level)); + iterator->gfn += KVM_PAGES_PER_HPAGE(iterator->level); - if (iterator->rmap->val) + if (atomic_long_read(&iterator->rmap->val)) return; } @@ -1560,80 +1572,101 @@ static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) slot_rmap_walk_okay(_iter_); \ slot_rmap_walk_next(_iter_)) -typedef bool (*rmap_handler_t)(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, - int level, pte_t pte); +/* The return value indicates if tlb flush on all vcpus is needed. */ +typedef bool (*slot_rmaps_handler) (struct kvm *kvm, + struct kvm_rmap_head *rmap_head, + const struct kvm_memory_slot *slot); -static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm, - struct kvm_gfn_range *range, - rmap_handler_t handler) +static __always_inline bool __walk_slot_rmaps(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + int start_level, int end_level, + gfn_t start_gfn, gfn_t end_gfn, + bool can_yield, bool flush_on_yield, + bool flush) { struct slot_rmap_walk_iterator iterator; - bool ret = false; - - 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->arg.pte); - - return ret; -} -bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) -{ - bool flush = false; + lockdep_assert_held_write(&kvm->mmu_lock); - if (kvm_memslots_have_rmaps(kvm)) - flush = kvm_handle_gfn_range(kvm, range, kvm_zap_rmap); + for_each_slot_rmap_range(slot, start_level, end_level, start_gfn, + end_gfn, &iterator) { + if (iterator.rmap) + flush |= fn(kvm, iterator.rmap, slot); - if (tdp_mmu_enabled) - flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); + if (!can_yield) + continue; - if (kvm_x86_ops.set_apic_access_page_addr && - range->slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) - kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); + if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { + if (flush && flush_on_yield) { + kvm_flush_remote_tlbs_range(kvm, start_gfn, + iterator.gfn - start_gfn + 1); + flush = false; + } + cond_resched_rwlock_write(&kvm->mmu_lock); + } + } return flush; } -bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) +static __always_inline bool walk_slot_rmaps(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + int start_level, int end_level, + bool flush_on_yield) { - bool flush = false; - - if (kvm_memslots_have_rmaps(kvm)) - flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmap); + return __walk_slot_rmaps(kvm, slot, fn, start_level, end_level, + slot->base_gfn, slot->base_gfn + slot->npages - 1, + true, flush_on_yield, false); +} - if (tdp_mmu_enabled) - flush |= kvm_tdp_mmu_set_spte_gfn(kvm, range); +static __always_inline bool walk_slot_rmaps_4k(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + bool flush_on_yield) +{ + return walk_slot_rmaps(kvm, slot, fn, PG_LEVEL_4K, PG_LEVEL_4K, flush_on_yield); +} - return flush; +static bool __kvm_rmap_zap_gfn_range(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t start, gfn_t end, bool can_yield, + bool flush) +{ + return __walk_slot_rmaps(kvm, slot, kvm_zap_rmap, + PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, + start, end - 1, can_yield, true, flush); } -static bool kvm_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level, - pte_t unused) +bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { - u64 *sptep; - struct rmap_iterator iter; - int young = 0; + bool flush = false; - for_each_rmap_spte(rmap_head, &iter, sptep) - young |= mmu_spte_age(sptep); + /* + * To prevent races with vCPUs faulting in a gfn using stale data, + * zapping a gfn range must be protected by mmu_invalidate_in_progress + * (and mmu_invalidate_seq). The only exception is memslot deletion; + * in that case, SRCU synchronization ensures that SPTEs are zapped + * after all vCPUs have unlocked SRCU, guaranteeing that vCPUs see the + * invalid slot. + */ + lockdep_assert_once(kvm->mmu_invalidate_in_progress || + lockdep_is_held(&kvm->slots_lock)); - return young; -} + if (kvm_memslots_have_rmaps(kvm)) + flush = __kvm_rmap_zap_gfn_range(kvm, range->slot, + range->start, range->end, + range->may_block, flush); -static bool kvm_test_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, - int level, pte_t unused) -{ - u64 *sptep; - struct rmap_iterator iter; + if (tdp_mmu_enabled) + flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); - for_each_rmap_spte(rmap_head, &iter, sptep) - if (is_accessed_spte(*sptep)) - return true; - return false; + if (kvm_x86_ops.set_apic_access_page_addr && + range->slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) + kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); + + return flush; } #define RMAP_RECYCLE_THRESHOLD 1000 @@ -1652,7 +1685,7 @@ static void __rmap_add(struct kvm *kvm, kvm_update_page_stats(kvm, sp->role.level, 1); rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); - rmap_count = pte_list_add(cache, spte, rmap_head); + rmap_count = pte_list_add(kvm, cache, spte, rmap_head); if (rmap_count > kvm->stat.max_mmu_rmap_size) kvm->stat.max_mmu_rmap_size = rmap_count; @@ -1670,15 +1703,68 @@ static void rmap_add(struct kvm_vcpu *vcpu, const struct kvm_memory_slot *slot, __rmap_add(vcpu->kvm, cache, slot, spte, gfn, access); } -bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) +static bool kvm_rmap_age_gfn_range(struct kvm *kvm, + struct kvm_gfn_range *range, + bool test_only) { + struct kvm_rmap_head *rmap_head; + struct rmap_iterator iter; + unsigned long rmap_val; bool young = false; + u64 *sptep; + gfn_t gfn; + int level; + u64 spte; - if (kvm_memslots_have_rmaps(kvm)) - young = kvm_handle_gfn_range(kvm, range, kvm_age_rmap); + for (level = PG_LEVEL_4K; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + for (gfn = range->start; gfn < range->end; + gfn += KVM_PAGES_PER_HPAGE(level)) { + rmap_head = gfn_to_rmap(gfn, level, range->slot); + rmap_val = kvm_rmap_lock_readonly(rmap_head); + + for_each_rmap_spte_lockless(rmap_head, &iter, sptep, spte) { + if (!is_accessed_spte(spte)) + continue; + + if (test_only) { + kvm_rmap_unlock_readonly(rmap_head, rmap_val); + return true; + } + + if (spte_ad_enabled(spte)) + clear_bit((ffs(shadow_accessed_mask) - 1), + (unsigned long *)sptep); + else + /* + * If the following cmpxchg fails, the + * spte is being concurrently modified + * and should most likely stay young. + */ + cmpxchg64(sptep, spte, + mark_spte_for_access_track(spte)); + young = true; + } + + kvm_rmap_unlock_readonly(rmap_head, rmap_val); + } + } + return young; +} + +static bool kvm_may_have_shadow_mmu_sptes(struct kvm *kvm) +{ + return !tdp_mmu_enabled || READ_ONCE(kvm->arch.indirect_shadow_pages); +} + +bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) +{ + bool young = false; if (tdp_mmu_enabled) - young |= kvm_tdp_mmu_age_gfn_range(kvm, range); + young = kvm_tdp_mmu_age_gfn_range(kvm, range); + + if (kvm_may_have_shadow_mmu_sptes(kvm)) + young |= kvm_rmap_age_gfn_range(kvm, range, false); return young; } @@ -1687,11 +1773,14 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { bool young = false; - if (kvm_memslots_have_rmaps(kvm)) - young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmap); - if (tdp_mmu_enabled) - young |= kvm_tdp_mmu_test_age_gfn(kvm, range); + young = kvm_tdp_mmu_test_age_gfn(kvm, range); + + if (young) + return young; + + if (kvm_may_have_shadow_mmu_sptes(kvm)) + young |= kvm_rmap_age_gfn_range(kvm, range, true); return young; } @@ -1710,27 +1799,15 @@ static void kvm_mmu_check_sptes_at_free(struct kvm_mmu_page *sp) #endif } -/* - * This value is the sum of all of the kvm instances's - * kvm->arch.n_used_mmu_pages values. We need a global, - * aggregate version in order to make the slab shrinker - * faster - */ -static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr) -{ - kvm->arch.n_used_mmu_pages += nr; - percpu_counter_add(&kvm_total_used_mmu_pages, nr); -} - static void kvm_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) { - kvm_mod_used_mmu_pages(kvm, +1); + kvm->arch.n_used_mmu_pages++; kvm_account_pgtable_pages((void *)sp->spt, +1); } static void kvm_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) { - kvm_mod_used_mmu_pages(kvm, -1); + kvm->arch.n_used_mmu_pages--; kvm_account_pgtable_pages((void *)sp->spt, -1); } @@ -1741,8 +1818,7 @@ static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp) hlist_del(&sp->hash_link); list_del(&sp->link); free_page((unsigned long)sp->spt); - if (!sp->role.direct) - free_page((unsigned long)sp->shadowed_translation); + free_page((unsigned long)sp->shadowed_translation); kmem_cache_free(mmu_page_header_cache, sp); } @@ -1751,13 +1827,14 @@ static unsigned kvm_page_table_hashfn(gfn_t gfn) return hash_64(gfn, KVM_MMU_HASH_SHIFT); } -static void mmu_page_add_parent_pte(struct kvm_mmu_memory_cache *cache, +static void mmu_page_add_parent_pte(struct kvm *kvm, + struct kvm_mmu_memory_cache *cache, struct kvm_mmu_page *sp, u64 *parent_pte) { if (!parent_pte) return; - pte_list_add(cache, parent_pte, &sp->parent_ptes); + pte_list_add(kvm, cache, parent_pte, &sp->parent_ptes); } static void mmu_page_remove_parent_pte(struct kvm *kvm, struct kvm_mmu_page *sp, @@ -1950,7 +2027,8 @@ static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) static int kvm_sync_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i) { - if (!sp->spt[i]) + /* sp->spt[i] has initial value of shadow page table allocation */ + if (sp->spt[i] == SHADOW_NONPRESENT_VALUE) return 0; return vcpu->arch.mmu->sync_spte(vcpu, sp, i); @@ -2243,7 +2321,7 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm, sp = kvm_mmu_memory_cache_alloc(caches->page_header_cache); sp->spt = kvm_mmu_memory_cache_alloc(caches->shadow_page_cache); - if (!role.direct) + if (!role.direct && role.level <= KVM_MAX_HUGEPAGE_LEVEL) sp->shadowed_translation = kvm_mmu_memory_cache_alloc(caches->shadowed_info_cache); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); @@ -2446,7 +2524,7 @@ static void __link_shadow_page(struct kvm *kvm, mmu_spte_set(sptep, spte); - mmu_page_add_parent_pte(cache, sp, sptep); + mmu_page_add_parent_pte(kvm, cache, sp, sptep); /* * The non-direct sub-pagetable must be updated before linking. For @@ -2510,11 +2588,12 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, * avoids retaining a large number of stale nested SPs. */ if (tdp_enabled && invalid_list && - child->role.guest_mode && !child->parent_ptes.val) + child->role.guest_mode && + !atomic_long_read(&child->parent_ptes.val)) return kvm_mmu_prepare_zap_page(kvm, child, invalid_list); } - } else if (is_mmio_spte(pte)) { + } else if (is_mmio_spte(kvm, pte)) { mmu_spte_clear_no_track(spte); } return 0; @@ -2754,36 +2833,49 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages) write_unlock(&kvm->mmu_lock); } -int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) +bool __kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + bool always_retry) { - struct kvm_mmu_page *sp; + struct kvm *kvm = vcpu->kvm; LIST_HEAD(invalid_list); - int r; + struct kvm_mmu_page *sp; + gpa_t gpa = cr2_or_gpa; + bool r = false; + + /* + * Bail early if there aren't any write-protected shadow pages to avoid + * unnecessarily taking mmu_lock lock, e.g. if the gfn is write-tracked + * by a third party. Reading indirect_shadow_pages without holding + * mmu_lock is safe, as this is purely an optimization, i.e. a false + * positive is benign, and a false negative will simply result in KVM + * skipping the unprotect+retry path, which is also an optimization. + */ + if (!READ_ONCE(kvm->arch.indirect_shadow_pages)) + goto out; + + if (!vcpu->arch.mmu->root_role.direct) { + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); + if (gpa == INVALID_GPA) + goto out; + } - r = 0; write_lock(&kvm->mmu_lock); - for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) { - r = 1; + for_each_gfn_valid_sp_with_gptes(kvm, sp, gpa_to_gfn(gpa)) kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); - } + + /* + * Snapshot the result before zapping, as zapping will remove all list + * entries, i.e. checking the list later would yield a false negative. + */ + r = !list_empty(&invalid_list); kvm_mmu_commit_zap_page(kvm, &invalid_list); write_unlock(&kvm->mmu_lock); - return r; -} - -static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) -{ - gpa_t gpa; - int r; - - if (vcpu->arch.mmu->root_role.direct) - return 0; - - gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); - - r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); - +out: + if (r || always_retry) { + vcpu->arch.last_retry_eip = kvm_rip_read(vcpu); + vcpu->arch.last_retry_addr = cr2_or_gpa; + } return r; } @@ -2803,7 +2895,7 @@ static void kvm_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) * be write-protected. */ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, - gfn_t gfn, bool can_unsync, bool prefetch) + gfn_t gfn, bool synchronizing, bool prefetch) { struct kvm_mmu_page *sp; bool locked = false; @@ -2818,12 +2910,12 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, /* * The page is not write-tracked, mark existing shadow pages unsync - * unless KVM is synchronizing an unsync SP (can_unsync = false). In - * that case, KVM must complete emulation of the guest TLB flush before - * allowing shadow pages to become unsync (writable by the guest). + * unless KVM is synchronizing an unsync SP. In that case, KVM must + * complete emulation of the guest TLB flush before allowing shadow + * pages to become unsync (writable by the guest). */ for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) { - if (!can_unsync) + if (synchronizing) return -EPERM; if (sp->unsync) @@ -2927,6 +3019,9 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, } if (is_shadow_present_pte(*sptep)) { + if (prefetch) + return RET_PF_SPURIOUS; + /* * If we overwrite a PTE page pointer with a 2MB PMD, unlink * the parent of the now unreachable PTE. @@ -2946,7 +3041,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, } wrprot = make_spte(vcpu, sp, slot, pte_access, gfn, pfn, *sptep, prefetch, - true, host_writable, &spte); + false, host_writable, &spte); if (*sptep == spte) { ret = RET_PF_SPURIOUS; @@ -2955,10 +3050,8 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, trace_kvm_mmu_set_spte(level, gfn, sptep); } - if (wrprot) { - if (write_fault) - ret = RET_PF_EMULATE; - } + if (wrprot && write_fault) + ret = RET_PF_WRITE_PROTECTED; if (flush) kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level); @@ -2974,32 +3067,51 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, return ret; } -static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp, - u64 *start, u64 *end) +static bool kvm_mmu_prefetch_sptes(struct kvm_vcpu *vcpu, gfn_t gfn, u64 *sptep, + int nr_pages, unsigned int access) { struct page *pages[PTE_PREFETCH_NUM]; struct kvm_memory_slot *slot; - unsigned int access = sp->role.access; - int i, ret; - gfn_t gfn; + int i; + + if (WARN_ON_ONCE(nr_pages > PTE_PREFETCH_NUM)) + return false; - gfn = kvm_mmu_page_get_gfn(sp, spte_index(start)); slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK); if (!slot) - return -1; + return false; - ret = gfn_to_page_many_atomic(slot, gfn, pages, end - start); - if (ret <= 0) - return -1; + nr_pages = kvm_prefetch_pages(slot, gfn, pages, nr_pages); + if (nr_pages <= 0) + return false; - for (i = 0; i < ret; i++, gfn++, start++) { - mmu_set_spte(vcpu, slot, start, access, gfn, + for (i = 0; i < nr_pages; i++, gfn++, sptep++) { + mmu_set_spte(vcpu, slot, sptep, access, gfn, page_to_pfn(pages[i]), NULL); - put_page(pages[i]); + + /* + * KVM always prefetches writable pages from the primary MMU, + * and KVM can make its SPTE writable in the fast page handler, + * without notifying the primary MMU. Mark pages/folios dirty + * now to ensure file data is written back if it ends up being + * written by the guest. Because KVM's prefetching GUPs + * writable PTEs, the probability of unnecessary writeback is + * extremely low. + */ + kvm_release_page_dirty(pages[i]); } - return 0; + return true; +} + +static bool direct_pte_prefetch_many(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp, + u64 *start, u64 *end) +{ + gfn_t gfn = kvm_mmu_page_get_gfn(sp, spte_index(start)); + unsigned int access = sp->role.access; + + return kvm_mmu_prefetch_sptes(vcpu, gfn, start, end - start, access); } static void __direct_pte_prefetch(struct kvm_vcpu *vcpu, @@ -3017,8 +3129,9 @@ static void __direct_pte_prefetch(struct kvm_vcpu *vcpu, if (is_shadow_present_pte(*spte) || spte == sptep) { if (!start) continue; - if (direct_pte_prefetch_many(vcpu, sp, start, spte) < 0) + if (!direct_pte_prefetch_many(vcpu, sp, start, spte)) return; + start = NULL; } else if (!start) start = spte; @@ -3168,13 +3281,12 @@ static int __kvm_mmu_max_mapping_level(struct kvm *kvm, } int kvm_mmu_max_mapping_level(struct kvm *kvm, - const struct kvm_memory_slot *slot, gfn_t gfn, - int max_level) + const struct kvm_memory_slot *slot, gfn_t gfn) { 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); + return __kvm_mmu_max_mapping_level(kvm, slot, gfn, PG_LEVEL_NUM, is_private); } void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) @@ -3314,9 +3426,18 @@ static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu, { gva_t gva = fault->is_tdp ? 0 : fault->addr; + if (fault->is_private) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + vcpu_cache_mmio_info(vcpu, gva, fault->gfn, access & shadow_mmio_access_mask); + fault->slot = NULL; + fault->pfn = KVM_PFN_NOSLOT; + fault->map_writable = false; + /* * If MMIO caching is disabled, emulate immediately without * touching the shadow page tables as attempting to install an @@ -3338,7 +3459,7 @@ static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu, return RET_PF_CONTINUE; } -static bool page_fault_can_be_fast(struct kvm_page_fault *fault) +static bool page_fault_can_be_fast(struct kvm *kvm, struct kvm_page_fault *fault) { /* * Page faults with reserved bits set, i.e. faults on MMIO SPTEs, only @@ -3350,6 +3471,26 @@ static bool page_fault_can_be_fast(struct kvm_page_fault *fault) return false; /* + * For hardware-protected VMs, certain conditions like attempting to + * perform a write to a page which is not in the state that the guest + * expects it to be in can result in a nested/extended #PF. In this + * case, the below code might misconstrue this situation as being the + * result of a write-protected access, and treat it as a spurious case + * rather than taking any action to satisfy the real source of the #PF + * such as generating a KVM_EXIT_MEMORY_FAULT. This can lead to the + * guest spinning on a #PF indefinitely, so don't attempt the fast path + * in this case. + * + * Note that the kvm_mem_is_private() check might race with an + * attribute update, but this will either result in the guest spinning + * on RET_PF_SPURIOUS until the update completes, or an actual spurious + * case might go down the slow path. Either case will resolve itself. + */ + if (kvm->arch.has_private_mem && + fault->is_private != kvm_mem_is_private(kvm, fault->gfn)) + return false; + + /* * #PF can be fast if: * * 1. The shadow page table entry is not present and A/D bits are @@ -3365,7 +3506,7 @@ static bool page_fault_can_be_fast(struct kvm_page_fault *fault) * by setting the Writable bit, which can be done out of mmu_lock. */ if (!fault->present) - return !kvm_ad_enabled(); + return !kvm_ad_enabled; /* * Note, instruction fetches and writes are mutually exclusive, ignore @@ -3392,7 +3533,7 @@ static bool fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, * harm. This also avoids the TLB flush needed after setting dirty bit * so non-PML cases won't be impacted. * - * Compare with set_spte where instead shadow_dirty_mask is set. + * Compare with make_spte() where instead shadow_dirty_mask is set. */ if (!try_cmpxchg64(sptep, &old_spte, new_spte)) return false; @@ -3403,18 +3544,6 @@ static bool fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, return true; } -static bool is_access_allowed(struct kvm_page_fault *fault, u64 spte) -{ - if (fault->exec) - return is_executable_pte(spte); - - if (fault->write) - return is_writable_pte(spte); - - /* Fault was on Read access */ - return spte & PT_PRESENT_MASK; -} - /* * Returns the last level spte pointer of the shadow page walk for the given * gpa, and sets *spte to the spte value. This spte may be non-preset. If no @@ -3449,7 +3578,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) u64 *sptep; uint retry_count = 0; - if (!page_fault_can_be_fast(fault)) + if (!page_fault_can_be_fast(vcpu->kvm, fault)) return ret; walk_shadow_page_lockless_begin(vcpu); @@ -3458,7 +3587,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) u64 new_spte; if (tdp_mmu_enabled) - sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, fault->addr, &spte); + sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, fault->gfn, &spte); else sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte); @@ -3468,7 +3597,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) * available as the vCPU holds a reference to its root(s). */ if (WARN_ON_ONCE(!sptep)) - spte = REMOVED_SPTE; + spte = FROZEN_SPTE; if (!is_shadow_present_pte(spte)) break; @@ -3500,8 +3629,9 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) * uses A/D bits for non-nested MMUs. Thus, if A/D bits are * enabled, the SPTE can't be an access-tracked SPTE. */ - if (unlikely(!kvm_ad_enabled()) && is_access_track_spte(spte)) - new_spte = restore_acc_track_spte(new_spte); + if (unlikely(!kvm_ad_enabled) && is_access_track_spte(spte)) + new_spte = restore_acc_track_spte(new_spte) | + shadow_accessed_mask; /* * To keep things simple, only SPTEs that are MMU-writable can @@ -3706,8 +3836,13 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) unsigned i; int r; - if (tdp_mmu_enabled) - return kvm_tdp_mmu_alloc_root(vcpu); + if (tdp_mmu_enabled) { + if (kvm_has_mirrored_tdp(vcpu->kvm) && + !VALID_PAGE(mmu->mirror_root_hpa)) + kvm_tdp_mmu_alloc_root(vcpu, true); + kvm_tdp_mmu_alloc_root(vcpu, false); + return 0; + } write_lock(&vcpu->kvm->mmu_lock); r = make_mmu_pages_available(vcpu); @@ -4134,23 +4269,31 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level return leaf; } -/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */ -static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) +static int get_sptes_lockless(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, + int *root_level) { - u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; - struct rsvd_bits_validate *rsvd_check; - int root, leaf, level; - bool reserved = false; + int leaf; walk_shadow_page_lockless_begin(vcpu); if (is_tdp_mmu_active(vcpu)) - leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root); + leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, root_level); else - leaf = get_walk(vcpu, addr, sptes, &root); + leaf = get_walk(vcpu, addr, sptes, root_level); walk_shadow_page_lockless_end(vcpu); + return leaf; +} + +/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */ +static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) +{ + u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; + struct rsvd_bits_validate *rsvd_check; + int root, leaf, level; + bool reserved = false; + leaf = get_sptes_lockless(vcpu, addr, sptes, &root); if (unlikely(leaf < 0)) { *sptep = 0ull; return reserved; @@ -4196,7 +4339,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) if (WARN_ON_ONCE(reserved)) return -EINVAL; - if (is_mmio_spte(spte)) { + if (is_mmio_spte(vcpu->kvm, spte)) { gfn_t gfn = get_mmio_spte_gfn(spte); unsigned int access = get_mmio_spte_access(spte); @@ -4259,24 +4402,28 @@ static u32 alloc_apf_token(struct kvm_vcpu *vcpu) return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; } -static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - gfn_t gfn) +static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) { struct kvm_arch_async_pf arch; arch.token = alloc_apf_token(vcpu); - arch.gfn = gfn; + arch.gfn = fault->gfn; + arch.error_code = fault->error_code; arch.direct_map = vcpu->arch.mmu->root_role.direct; arch.cr3 = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu); - return kvm_setup_async_pf(vcpu, cr2_or_gpa, - kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); + return kvm_setup_async_pf(vcpu, fault->addr, + kvm_vcpu_gfn_to_hva(vcpu, fault->gfn), &arch); } void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { int r; + if (WARN_ON_ONCE(work->arch.error_code & PFERR_PRIVATE_ACCESS)) + return; + if ((vcpu->arch.mmu->root_role.direct != work->arch.direct_map) || work->wakeup_all) return; @@ -4289,7 +4436,16 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu)) return; - kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL); + r = kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, work->arch.error_code, + true, NULL, NULL); + + /* + * Account fixed page faults, otherwise they'll never be counted, but + * ignore stats for all other return times. Page-ready "faults" aren't + * truly spurious and never trigger emulation + */ + if (r == RET_PF_FIXED) + vcpu->stat.pf_fixed++; } static inline u8 kvm_max_level_for_order(int order) @@ -4309,16 +4465,34 @@ static inline u8 kvm_max_level_for_order(int order) return PG_LEVEL_4K; } -static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, - struct kvm_page_fault *fault) +static u8 kvm_max_private_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, + u8 max_level, int gmem_order) { - kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, - PAGE_SIZE, fault->write, fault->exec, - fault->is_private); + u8 req_max_level; + + if (max_level == PG_LEVEL_4K) + return PG_LEVEL_4K; + + max_level = min(kvm_max_level_for_order(gmem_order), max_level); + if (max_level == PG_LEVEL_4K) + return PG_LEVEL_4K; + + req_max_level = kvm_x86_call(private_max_mapping_level)(kvm, pfn); + if (req_max_level) + max_level = min(max_level, req_max_level); + + return max_level; +} + +static void kvm_mmu_finish_page_fault(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault, int r) +{ + kvm_release_faultin_page(vcpu->kvm, fault->refcounted_page, + r == RET_PF_RETRY, fault->map_writable); } -static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, - struct kvm_page_fault *fault) +static int kvm_mmu_faultin_pfn_private(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) { int max_order, r; @@ -4328,65 +4502,39 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, } r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, - &max_order); + &fault->refcounted_page, &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); + fault->max_level = kvm_max_private_mapping_level(vcpu->kvm, fault->pfn, + fault->max_level, max_order); return RET_PF_CONTINUE; } -static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +static int __kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) { - struct kvm_memory_slot *slot = fault->slot; - bool async; - - /* - * Retry the page fault if the gfn hit a memslot that is being deleted - * or moved. This ensures any existing SPTEs for the old memslot will - * be zapped before KVM inserts a new MMIO SPTE for the gfn. - */ - if (slot && (slot->flags & KVM_MEMSLOT_INVALID)) - return RET_PF_RETRY; - - if (!kvm_is_visible_memslot(slot)) { - /* Don't expose private memslots to L2. */ - if (is_guest_mode(vcpu)) { - fault->slot = NULL; - fault->pfn = KVM_PFN_NOSLOT; - fault->map_writable = false; - return RET_PF_CONTINUE; - } - /* - * If the APIC access page exists but is disabled, go directly - * to emulation without caching the MMIO access or creating a - * MMIO SPTE. That way the cache doesn't need to be purged - * when the AVIC is re-enabled. - */ - if (slot && slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT && - !kvm_apicv_activated(vcpu->kvm)) - 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; - } + unsigned int foll = fault->write ? FOLL_WRITE : 0; if (fault->is_private) - return kvm_faultin_pfn_private(vcpu, fault); + return kvm_mmu_faultin_pfn_private(vcpu, fault); - async = false; - fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async, - fault->write, &fault->map_writable, - &fault->hva); - if (!async) - return RET_PF_CONTINUE; /* *pfn has correct page already */ + foll |= FOLL_NOWAIT; + fault->pfn = __kvm_faultin_pfn(fault->slot, fault->gfn, foll, + &fault->map_writable, &fault->refcounted_page); + + /* + * If resolving the page failed because I/O is needed to fault-in the + * page, then either set up an asynchronous #PF to do the I/O, or if + * doing an async #PF isn't possible, retry with I/O allowed. All + * other failures are terminal, i.e. retrying won't help. + */ + if (fault->pfn != KVM_PFN_ERR_NEEDS_IO) + return RET_PF_CONTINUE; if (!fault->prefetch && kvm_can_do_async_pf(vcpu)) { trace_kvm_try_async_get_page(fault->addr, fault->gfn); @@ -4394,7 +4542,7 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault trace_kvm_async_pf_repeated_fault(fault->addr, fault->gfn); kvm_make_request(KVM_REQ_APF_HALT, vcpu); return RET_PF_RETRY; - } else if (kvm_arch_setup_async_pf(vcpu, fault->addr, fault->gfn)) { + } else if (kvm_arch_setup_async_pf(vcpu, fault)) { return RET_PF_RETRY; } } @@ -4404,21 +4552,79 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault * to wait for IO. Note, gup always bails if it is unable to quickly * get a page and a fatal signal, i.e. SIGKILL, is pending. */ - fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL, - fault->write, &fault->map_writable, - &fault->hva); + foll |= FOLL_INTERRUPTIBLE; + foll &= ~FOLL_NOWAIT; + fault->pfn = __kvm_faultin_pfn(fault->slot, fault->gfn, foll, + &fault->map_writable, &fault->refcounted_page); + return RET_PF_CONTINUE; } -static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, - unsigned int access) +static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault, unsigned int access) { + struct kvm_memory_slot *slot = fault->slot; + struct kvm *kvm = vcpu->kvm; int ret; + if (KVM_BUG_ON(kvm_is_gfn_alias(kvm, fault->gfn), kvm)) + return -EFAULT; + + /* + * Note that the mmu_invalidate_seq also serves to detect a concurrent + * change in attributes. is_page_fault_stale() will detect an + * invalidation relate to fault->fn and resume the guest without + * installing a mapping in the page tables. + */ fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); /* + * Now that we have a snapshot of mmu_invalidate_seq we can check for a + * private vs. shared mismatch. + */ + if (fault->is_private != kvm_mem_is_private(kvm, fault->gfn)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + if (unlikely(!slot)) + return kvm_handle_noslot_fault(vcpu, fault, access); + + /* + * Retry the page fault if the gfn hit a memslot that is being deleted + * or moved. This ensures any existing SPTEs for the old memslot will + * be zapped before KVM inserts a new MMIO SPTE for the gfn. + */ + if (slot->flags & KVM_MEMSLOT_INVALID) + return RET_PF_RETRY; + + if (slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) { + /* + * Don't map L1's APIC access page into L2, KVM doesn't support + * using APICv/AVIC to accelerate L2 accesses to L1's APIC, + * i.e. the access needs to be emulated. Emulating access to + * L1's APIC is also correct if L1 is accelerating L2's own + * virtual APIC, but for some reason L1 also maps _L1's_ APIC + * into L2. Note, vcpu_is_mmio_gpa() always treats access to + * the APIC as MMIO. Allow an MMIO SPTE to be created, as KVM + * uses different roots for L1 vs. L2, i.e. there is no danger + * of breaking APICv/AVIC for L1. + */ + if (is_guest_mode(vcpu)) + return kvm_handle_noslot_fault(vcpu, fault, access); + + /* + * If the APIC access page exists but is disabled, go directly + * to emulation without caching the MMIO access or creating a + * MMIO SPTE. That way the cache doesn't need to be purged + * when the AVIC is re-enabled. + */ + if (!kvm_apicv_activated(vcpu->kvm)) + return RET_PF_EMULATE; + } + + /* * Check for a relevant mmu_notifier invalidation event before getting * the pfn from the primary MMU, and before acquiring mmu_lock. * @@ -4439,18 +4645,17 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held * to detect retry guarantees the worst case latency for the vCPU. */ - if (fault->slot && - mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) + if (mmu_invalidate_retry_gfn_unsafe(kvm, fault->mmu_seq, fault->gfn)) return RET_PF_RETRY; - ret = __kvm_faultin_pfn(vcpu, fault); + ret = __kvm_mmu_faultin_pfn(vcpu, fault); if (ret != RET_PF_CONTINUE) return ret; if (unlikely(is_error_pfn(fault->pfn))) return kvm_handle_error_pfn(vcpu, fault); - if (unlikely(!fault->slot)) + if (WARN_ON_ONCE(!fault->slot || is_noslot_pfn(fault->pfn))) return kvm_handle_noslot_fault(vcpu, fault, access); /* @@ -4460,8 +4665,8 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, * overall cost of failing to detect the invalidation until after * mmu_lock is acquired. */ - if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) { - kvm_release_pfn_clean(fault->pfn); + if (mmu_invalidate_retry_gfn_unsafe(kvm, fault->mmu_seq, fault->gfn)) { + kvm_mmu_finish_page_fault(vcpu, fault, RET_PF_RETRY); return RET_PF_RETRY; } @@ -4510,7 +4715,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return RET_PF_RETRY; if (page_fault_handle_page_track(vcpu, fault)) - return RET_PF_EMULATE; + return RET_PF_WRITE_PROTECTED; r = fast_page_fault(vcpu, fault); if (r != RET_PF_INVALID) @@ -4520,7 +4725,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (r) return r; - r = kvm_faultin_pfn(vcpu, fault, ACC_ALL); + r = kvm_mmu_faultin_pfn(vcpu, fault, ACC_ALL); if (r != RET_PF_CONTINUE) return r; @@ -4537,8 +4742,8 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault r = direct_map(vcpu, fault); out_unlock: + kvm_mmu_finish_page_fault(vcpu, fault, r); write_unlock(&vcpu->kvm->mmu_lock); - kvm_release_pfn_clean(fault->pfn); return r; } @@ -4561,13 +4766,24 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, if (WARN_ON_ONCE(fault_address >> 32)) return -EFAULT; #endif + /* + * Legacy #PF exception only have a 32-bit error code. Simply drop the + * upper bits as KVM doesn't use them for #PF (because they are never + * set), and to ensure there are no collisions with KVM-defined bits. + */ + if (WARN_ON_ONCE(error_code >> 32)) + error_code = lower_32_bits(error_code); + + /* + * Restrict KVM-defined flags to bits 63:32 so that it's impossible for + * them to conflict with #PF error codes, which are limited to 32 bits. + */ + BUILD_BUG_ON(lower_32_bits(PFERR_SYNTHETIC_MASK)); vcpu->arch.l1tf_flush_l1d = true; if (!flags) { trace_kvm_page_fault(vcpu, fault_address, error_code); - if (kvm_event_needs_reinjection(vcpu)) - kvm_mmu_unprotect_page_virt(vcpu, fault_address); r = kvm_mmu_page_fault(vcpu, fault_address, error_code, insn, insn_len); } else if (flags & KVM_PV_REASON_PAGE_NOT_PRESENT) { @@ -4590,7 +4806,7 @@ static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu, int r; if (page_fault_handle_page_track(vcpu, fault)) - return RET_PF_EMULATE; + return RET_PF_WRITE_PROTECTED; r = fast_page_fault(vcpu, fault); if (r != RET_PF_INVALID) @@ -4600,7 +4816,7 @@ static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu, if (r) return r; - r = kvm_faultin_pfn(vcpu, fault, ACC_ALL); + r = kvm_mmu_faultin_pfn(vcpu, fault, ACC_ALL); if (r != RET_PF_CONTINUE) return r; @@ -4613,44 +4829,27 @@ static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu, r = kvm_tdp_mmu_map(vcpu, fault); out_unlock: + kvm_mmu_finish_page_fault(vcpu, fault, r); read_unlock(&vcpu->kvm->mmu_lock); - kvm_release_pfn_clean(fault->pfn); return r; } #endif -bool __kvm_mmu_honors_guest_mtrrs(bool vm_has_noncoherent_dma) +bool kvm_mmu_may_ignore_guest_pat(void) { /* - * 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. + * When EPT is enabled (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 PAT so that guest accesses to + * memory that is DMA'd aren't cached against the guest's wishes. As a + * result, KVM _may_ ignore guest PAT, whereas without non-coherent DMA, + * KVM _always_ ignores guest PAT (when EPT is enabled). */ - return vm_has_noncoherent_dma && shadow_memtype_mask; + return 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, - fault->max_level); - - if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num)) - break; - } - } - #ifdef CONFIG_X86_64 if (tdp_mmu_enabled) return kvm_tdp_mmu_page_fault(vcpu, fault); @@ -4659,6 +4858,85 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) return direct_page_fault(vcpu, fault); } +static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, + u8 *level) +{ + int r; + + /* + * Restrict to TDP page fault, since that's the only case where the MMU + * is indexed by GPA. + */ + if (vcpu->arch.mmu->page_fault != kvm_tdp_page_fault) + return -EOPNOTSUPP; + + do { + if (signal_pending(current)) + return -EINTR; + cond_resched(); + r = kvm_mmu_do_page_fault(vcpu, gpa, error_code, true, NULL, level); + } while (r == RET_PF_RETRY); + + if (r < 0) + return r; + + switch (r) { + case RET_PF_FIXED: + case RET_PF_SPURIOUS: + case RET_PF_WRITE_PROTECTED: + return 0; + + case RET_PF_EMULATE: + return -ENOENT; + + case RET_PF_RETRY: + case RET_PF_CONTINUE: + case RET_PF_INVALID: + default: + WARN_ONCE(1, "could not fix page fault during prefault"); + return -EIO; + } +} + +long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range) +{ + u64 error_code = PFERR_GUEST_FINAL_MASK; + u8 level = PG_LEVEL_4K; + u64 end; + int r; + + if (!vcpu->kvm->arch.pre_fault_allowed) + return -EOPNOTSUPP; + + /* + * reload is efficient when called repeatedly, so we can do it on + * every iteration. + */ + r = kvm_mmu_reload(vcpu); + if (r) + return r; + + if (kvm_arch_has_private_mem(vcpu->kvm) && + kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(range->gpa))) + error_code |= PFERR_PRIVATE_ACCESS; + + /* + * Shadow paging uses GVA for kvm page fault, so restrict to + * two-dimensional paging. + */ + r = kvm_tdp_map_page(vcpu, range->gpa, error_code, &level); + if (r < 0) + return r; + + /* + * If the mapping that covers range->gpa can use a huge page, it + * may start below it or end after range->gpa + range->size. + */ + end = (range->gpa & KVM_HPAGE_MASK(level)) + KVM_HPAGE_SIZE(level); + return min(range->size, end - range->gpa); +} + static void nonpaging_init_context(struct kvm_mmu *context) { context->page_fault = nonpaging_page_fault; @@ -4812,7 +5090,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd); static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, unsigned int access) { - if (unlikely(is_mmio_spte(*sptep))) { + if (unlikely(is_mmio_spte(vcpu->kvm, *sptep))) { if (gfn != get_mmio_spte_gfn(*sptep)) { mmu_spte_clear_no_track(sptep); return true; @@ -4933,7 +5211,7 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, __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(vcpu, X86_FEATURE_GBPAGES), + guest_cpu_cap_has(vcpu, X86_FEATURE_GBPAGES), is_cr4_pse(context), guest_cpuid_is_amd_compatible(vcpu)); } @@ -4986,7 +5264,7 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, static inline u64 reserved_hpa_bits(void) { - return rsvd_bits(shadow_phys_bits, 63); + return rsvd_bits(kvm_host.maxphyaddr, 63); } /* @@ -5010,7 +5288,7 @@ 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(vcpu, X86_FEATURE_GBPAGES), + guest_cpu_cap_has(vcpu, X86_FEATURE_GBPAGES), is_pse, is_amd); if (!shadow_me_mask) @@ -5322,6 +5600,11 @@ static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu) return max_tdp_level; } +u8 kvm_mmu_get_max_tdp_level(void) +{ + return tdp_root_level ? tdp_root_level : max_tdp_level; +} + static union kvm_mmu_page_role kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, union kvm_cpu_role cpu_role) @@ -5333,7 +5616,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, role.efer_nx = true; role.smm = cpu_role.base.smm; role.guest_mode = cpu_role.base.guest_mode; - role.ad_disabled = !kvm_ad_enabled(); + role.ad_disabled = !kvm_ad_enabled; role.level = kvm_mmu_get_tdp_level(vcpu); role.direct = true; role.has_4_byte_gpte = false; @@ -5430,7 +5713,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, union kvm_mmu_page_role root_role; /* NPT requires CR0.PG=1. */ - WARN_ON_ONCE(cpu_role.base.direct); + WARN_ON_ONCE(cpu_role.base.direct || !cpu_role.base.guest_mode); root_role = cpu_role.base; root_role.level = kvm_mmu_get_tdp_level(vcpu); @@ -5626,7 +5909,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) * stale entries. Flushing on alloc also allows KVM to skip the TLB * flush when freeing a root (see kvm_tdp_mmu_put_root()). */ - static_call(kvm_x86_flush_tlb_current)(vcpu); + kvm_x86_call(flush_tlb_current)(vcpu); out: return r; } @@ -5802,10 +6085,15 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, bool flush = false; /* - * If we don't have indirect shadow pages, it means no page is - * write-protected, so we can exit simply. + * When emulating guest writes, ensure the written value is visible to + * any task that is handling page faults before checking whether or not + * KVM is shadowing a guest PTE. This ensures either KVM will create + * the correct SPTE in the page fault handler, or this task will see + * a non-zero indirect_shadow_pages. Pairs with the smp_mb() in + * account_shadowed(). */ - if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) + smp_mb(); + if (!vcpu->kvm->arch.indirect_shadow_pages) return; write_lock(&vcpu->kvm->mmu_lock); @@ -5840,78 +6128,195 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, write_unlock(&vcpu->kvm->mmu_lock); } -int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, - void *insn, int insn_len) +static bool is_write_to_guest_page_table(u64 error_code) +{ + const u64 mask = PFERR_GUEST_PAGE_MASK | PFERR_WRITE_MASK | PFERR_PRESENT_MASK; + + return (error_code & mask) == mask; +} + +static int kvm_mmu_write_protect_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + u64 error_code, int *emulation_type) { - int r, emulation_type = EMULTYPE_PF; bool direct = vcpu->arch.mmu->root_role.direct; /* - * 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. + * Do not try to unprotect and retry if the vCPU re-faulted on the same + * RIP with the same address that was previously unprotected, as doing + * so will likely put the vCPU into an infinite. E.g. if the vCPU uses + * a non-page-table modifying instruction on the PDE that points to the + * instruction, then unprotecting the gfn will unmap the instruction's + * code, i.e. make it impossible for the instruction to ever complete. + */ + if (vcpu->arch.last_retry_eip == kvm_rip_read(vcpu) && + vcpu->arch.last_retry_addr == cr2_or_gpa) + return RET_PF_EMULATE; + + /* + * Reset the unprotect+retry values that guard against infinite loops. + * The values will be refreshed if KVM explicitly unprotects a gfn and + * retries, in all other cases it's safe to retry in the future even if + * the next page fault happens on the same RIP+address. + */ + vcpu->arch.last_retry_eip = 0; + vcpu->arch.last_retry_addr = 0; + + /* + * It should be impossible to reach this point with an MMIO cache hit, + * as RET_PF_WRITE_PROTECTED is returned if and only if there's a valid, + * writable memslot, and creating a memslot should invalidate the MMIO + * cache by way of changing the memslot generation. WARN and disallow + * retry if MMIO is detected, as retrying MMIO emulation is pointless + * and could put the vCPU into an infinite loop because the processor + * will keep faulting on the non-existent MMIO address. */ - if (WARN_ON_ONCE(error_code & PFERR_IMPLICIT_ACCESS)) - error_code &= ~PFERR_IMPLICIT_ACCESS; + if (WARN_ON_ONCE(mmio_info_in_cache(vcpu, cr2_or_gpa, direct))) + return RET_PF_EMULATE; + + /* + * Before emulating the instruction, check to see if the access was due + * to a read-only violation while the CPU was walking non-nested NPT + * page tables, i.e. for a direct MMU, for _guest_ page tables in L1. + * If L1 is sharing (a subset of) its page tables with L2, e.g. by + * having nCR3 share lower level page tables with hCR3, then when KVM + * (L0) write-protects the nested NPTs, i.e. npt12 entries, KVM is also + * unknowingly write-protecting L1's guest page tables, which KVM isn't + * shadowing. + * + * Because the CPU (by default) walks NPT page tables using a write + * access (to ensure the CPU can do A/D updates), page walks in L1 can + * trigger write faults for the above case even when L1 isn't modifying + * PTEs. As a result, KVM will unnecessarily emulate (or at least, try + * to emulate) an excessive number of L1 instructions; because L1's MMU + * isn't shadowed by KVM, there is no need to write-protect L1's gPTEs + * and thus no need to emulate in order to guarantee forward progress. + * + * Try to unprotect the gfn, i.e. zap any shadow pages, so that L1 can + * proceed without triggering emulation. If one or more shadow pages + * was zapped, skip emulation and resume L1 to let it natively execute + * the instruction. If no shadow pages were zapped, then the write- + * fault is due to something else entirely, i.e. KVM needs to emulate, + * as resuming the guest will put it into an infinite loop. + * + * Note, this code also applies to Intel CPUs, even though it is *very* + * unlikely that an L1 will share its page tables (IA32/PAE/paging64 + * format) with L2's page tables (EPT format). + * + * For indirect MMUs, i.e. if KVM is shadowing the current MMU, try to + * unprotect the gfn and retry if an event is awaiting reinjection. If + * KVM emulates multiple instructions before completing event injection, + * the event could be delayed beyond what is architecturally allowed, + * e.g. KVM could inject an IRQ after the TPR has been raised. + */ + if (((direct && is_write_to_guest_page_table(error_code)) || + (!direct && kvm_event_needs_reinjection(vcpu))) && + kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa)) + return RET_PF_RETRY; + + /* + * The gfn is write-protected, but if KVM detects its emulating an + * instruction that is unlikely to be used to modify page tables, or if + * emulation fails, KVM can try to unprotect the gfn and let the CPU + * re-execute the instruction that caused the page fault. Do not allow + * retrying an instruction from a nested guest as KVM is only explicitly + * shadowing L1's page tables, i.e. unprotecting something for L1 isn't + * going to magically fix whatever issue caused L2 to fail. + */ + if (!is_guest_mode(vcpu)) + *emulation_type |= EMULTYPE_ALLOW_RETRY_PF; + + return RET_PF_EMULATE; +} + +int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, + void *insn, int insn_len) +{ + int r, emulation_type = EMULTYPE_PF; + bool direct = vcpu->arch.mmu->root_role.direct; if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) return RET_PF_RETRY; + /* + * Except for reserved faults (emulated MMIO is shared-only), set the + * PFERR_PRIVATE_ACCESS flag for software-protected VMs based on the gfn's + * current attributes, which are the source of truth for such VMs. Note, + * this wrong for nested MMUs as the GPA is an L2 GPA, but KVM doesn't + * currently supported nested virtualization (among many other things) + * for software-protected VMs. + */ + if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && + !(error_code & PFERR_RSVD_MASK) && + vcpu->kvm->arch.vm_type == KVM_X86_SW_PROTECTED_VM && + kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(cr2_or_gpa))) + error_code |= PFERR_PRIVATE_ACCESS; + r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { + if (WARN_ON_ONCE(error_code & PFERR_PRIVATE_ACCESS)) + return -EFAULT; + r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct); if (r == RET_PF_EMULATE) goto emulate; } if (r == RET_PF_INVALID) { - r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, - lower_32_bits(error_code), false, - &emulation_type); + vcpu->stat.pf_taken++; + + r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, error_code, false, + &emulation_type, NULL); if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm)) return -EIO; } if (r < 0) return r; - if (r != RET_PF_EMULATE) - return 1; + + if (r == RET_PF_WRITE_PROTECTED) + r = kvm_mmu_write_protect_fault(vcpu, cr2_or_gpa, error_code, + &emulation_type); + + if (r == RET_PF_FIXED) + vcpu->stat.pf_fixed++; + else if (r == RET_PF_EMULATE) + vcpu->stat.pf_emulate++; + else if (r == RET_PF_SPURIOUS) + vcpu->stat.pf_spurious++; /* - * Before emulating the instruction, check if the error code - * was due to a RO violation while translating the guest page. - * This can occur when using nested virtualization with nested - * paging in both guests. If true, we simply unprotect the page - * and resume the guest. + * None of handle_mmio_page_fault(), kvm_mmu_do_page_fault(), or + * kvm_mmu_write_protect_fault() return RET_PF_CONTINUE. + * kvm_mmu_do_page_fault() only uses RET_PF_CONTINUE internally to + * indicate continuing the page fault handling until to the final + * page table mapping phase. */ - if (vcpu->arch.mmu->root_role.direct && - (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) { - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa)); - return 1; - } + WARN_ON_ONCE(r == RET_PF_CONTINUE); + if (r != RET_PF_EMULATE) + return r; - /* - * vcpu->arch.mmu.page_fault returned RET_PF_EMULATE, but we can still - * optimistically try to just unprotect the page and let the processor - * re-execute the instruction that caused the page fault. Do not allow - * retrying MMIO emulation, as it's not only pointless but could also - * cause us to enter an infinite loop because the processor will keep - * faulting on the non-existent MMIO address. Retrying an instruction - * from a nested guest is also pointless and dangerous as we are only - * explicitly shadowing L1's page tables, i.e. unprotecting something - * for L1 isn't going to magically fix whatever issue cause L2 to fail. - */ - if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu)) - emulation_type |= EMULTYPE_ALLOW_RETRY_PF; emulate: return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, insn_len); } EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); +void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg) +{ + u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; + int root_level, leaf, level; + + leaf = get_sptes_lockless(vcpu, gpa, sptes, &root_level); + if (unlikely(leaf < 0)) + return; + + pr_err("%s %llx", msg, gpa); + for (level = root_level; level >= leaf; level--) + pr_cont(", spte[%d] = 0x%llx", level, sptes[level]); + pr_cont("\n"); +} +EXPORT_SYMBOL_GPL(kvm_mmu_print_sptes); + static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, u64 addr, hpa_t root_hpa) { @@ -5959,10 +6364,10 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, /* It's actually a GPA for vcpu->arch.guest_mmu. */ if (mmu != &vcpu->arch.guest_mmu) { /* INVLPG on a non-canonical address is a NOP according to the SDM. */ - if (is_noncanonical_address(addr, vcpu)) + if (is_noncanonical_invlpg_address(addr, vcpu)) return; - static_call(kvm_x86_flush_tlb_gva)(vcpu, addr); + kvm_x86_call(flush_tlb_gva)(vcpu, addr); } if (!mmu->sync_spte) @@ -6048,59 +6453,6 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, } EXPORT_SYMBOL_GPL(kvm_configure_mmu); -/* The return value indicates if tlb flush on all vcpus is needed. */ -typedef bool (*slot_rmaps_handler) (struct kvm *kvm, - struct kvm_rmap_head *rmap_head, - const struct kvm_memory_slot *slot); - -static __always_inline bool __walk_slot_rmaps(struct kvm *kvm, - const struct kvm_memory_slot *slot, - slot_rmaps_handler fn, - int start_level, int end_level, - gfn_t start_gfn, gfn_t end_gfn, - bool flush_on_yield, bool flush) -{ - struct slot_rmap_walk_iterator iterator; - - lockdep_assert_held_write(&kvm->mmu_lock); - - for_each_slot_rmap_range(slot, start_level, end_level, start_gfn, - end_gfn, &iterator) { - if (iterator.rmap) - flush |= fn(kvm, iterator.rmap, slot); - - if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { - if (flush && flush_on_yield) { - kvm_flush_remote_tlbs_range(kvm, start_gfn, - iterator.gfn - start_gfn + 1); - flush = false; - } - cond_resched_rwlock_write(&kvm->mmu_lock); - } - } - - return flush; -} - -static __always_inline bool walk_slot_rmaps(struct kvm *kvm, - const struct kvm_memory_slot *slot, - slot_rmaps_handler fn, - int start_level, int end_level, - bool flush_on_yield) -{ - return __walk_slot_rmaps(kvm, slot, fn, start_level, end_level, - slot->base_gfn, slot->base_gfn + slot->npages - 1, - flush_on_yield, false); -} - -static __always_inline bool walk_slot_rmaps_4k(struct kvm *kvm, - const struct kvm_memory_slot *slot, - slot_rmaps_handler fn, - bool flush_on_yield) -{ - return walk_slot_rmaps(kvm, slot, fn, PG_LEVEL_4K, PG_LEVEL_4K, flush_on_yield); -} - static void free_mmu_pages(struct kvm_mmu *mmu) { if (!tdp_enabled && mmu->pae_root) @@ -6117,6 +6469,7 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) mmu->root.hpa = INVALID_PAGE; mmu->root.pgd = 0; + mmu->mirror_root_hpa = INVALID_PAGE; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; @@ -6173,7 +6526,10 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) vcpu->arch.mmu_page_header_cache.kmem_cache = mmu_page_header_cache; vcpu->arch.mmu_page_header_cache.gfp_zero = __GFP_ZERO; - vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO; + vcpu->arch.mmu_shadow_page_cache.init_value = + SHADOW_NONPRESENT_VALUE; + if (!vcpu->arch.mmu_shadow_page_cache.init_value) + vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO; vcpu->arch.mmu = &vcpu->arch.root_mmu; vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; @@ -6197,8 +6553,11 @@ static void kvm_zap_obsolete_pages(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; int nr_zapped, batch = 0; + LIST_HEAD(invalid_list); bool unstable; + lockdep_assert_held(&kvm->slots_lock); + restart: list_for_each_entry_safe_reverse(sp, node, &kvm->arch.active_mmu_pages, link) { @@ -6230,7 +6589,7 @@ restart: } unstable = __kvm_mmu_prepare_zap_page(kvm, sp, - &kvm->arch.zapped_obsolete_pages, &nr_zapped); + &invalid_list, &nr_zapped); batch += nr_zapped; if (unstable) @@ -6246,7 +6605,7 @@ restart: * kvm_mmu_load()), and the reload in the caller ensure no vCPUs are * running with an obsolete MMU. */ - kvm_mmu_commit_zap_page(kvm, &kvm->arch.zapped_obsolete_pages); + kvm_mmu_commit_zap_page(kvm, &invalid_list); } /* @@ -6280,8 +6639,13 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * write and in the same critical section as making the reload request, * e.g. before kvm_zap_obsolete_pages() could drop mmu_lock and yield. */ - if (tdp_mmu_enabled) - kvm_tdp_mmu_invalidate_all_roots(kvm); + if (tdp_mmu_enabled) { + /* + * External page tables don't support fast zapping, therefore + * their mirrors must be invalidated separately by the caller. + */ + kvm_tdp_mmu_invalidate_roots(kvm, KVM_DIRECT_ROOTS); + } /* * Notify all vcpus to reload its shadow page table and flush TLB. @@ -6306,18 +6670,13 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * lead to use-after-free. */ if (tdp_mmu_enabled) - kvm_tdp_mmu_zap_invalidated_roots(kvm); -} - -static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) -{ - return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); + kvm_tdp_mmu_zap_invalidated_roots(kvm, true); } void kvm_mmu_init_vm(struct kvm *kvm) { + kvm->arch.shadow_mmio_value = shadow_mmio_value; 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); @@ -6370,9 +6729,8 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e if (WARN_ON_ONCE(start >= end)) continue; - flush = __walk_slot_rmaps(kvm, memslot, __kvm_zap_rmap, - PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, - start, end - 1, true, flush); + flush = __kvm_rmap_zap_gfn_range(kvm, memslot, start, + end, true, flush); } } @@ -6552,7 +6910,7 @@ static void shadow_mmu_split_huge_page(struct kvm *kvm, continue; } - spte = make_huge_page_split_spte(kvm, huge_spte, sp->role, index); + spte = make_small_spte(kvm, huge_spte, sp->role, index); mmu_spte_set(sptep, spte); __rmap_add(kvm, cache, slot, sptep, gfn, sp->role.access); } @@ -6660,7 +7018,7 @@ static void kvm_shadow_mmu_try_split_huge_pages(struct kvm *kvm, */ for (level = KVM_MAX_HUGEPAGE_LEVEL; level > target_level; level--) __walk_slot_rmaps(kvm, slot, shadow_mmu_try_split_huge_pages, - level, level, start, end - 1, true, false); + level, level, start, end - 1, true, true, false); } /* Must be called with the mmu_lock held in write-mode. */ @@ -6735,8 +7093,7 @@ restart: * mapping if the indirect sp has level = 1. */ if (sp->role.direct && - sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn, - PG_LEVEL_NUM)) { + sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn)) { kvm_zap_one_rmap_spte(kvm, rmap_head, sptep); if (kvm_available_flush_remote_tlbs_range()) @@ -6750,6 +7107,7 @@ restart: return need_tlb_flush; } +EXPORT_SYMBOL_GPL(kvm_zap_gfn_range); static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *slot) @@ -6763,8 +7121,8 @@ static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm, kvm_flush_remote_tlbs_memslot(kvm, slot); } -void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *slot) +void kvm_mmu_recover_huge_pages(struct kvm *kvm, + const struct kvm_memory_slot *slot) { if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); @@ -6774,7 +7132,7 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, if (tdp_mmu_enabled) { read_lock(&kvm->mmu_lock); - kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot); + kvm_tdp_mmu_recover_huge_pages(kvm, slot); read_unlock(&kvm->mmu_lock); } } @@ -6838,10 +7196,70 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) kvm_mmu_zap_all(kvm); } +static void kvm_mmu_zap_memslot_pages_and_flush(struct kvm *kvm, + struct kvm_memory_slot *slot, + bool flush) +{ + LIST_HEAD(invalid_list); + unsigned long i; + + if (list_empty(&kvm->arch.active_mmu_pages)) + goto out_flush; + + /* + * Since accounting information is stored in struct kvm_arch_memory_slot, + * all MMU pages that are shadowing guest PTEs must be zapped before the + * memslot is deleted, as freeing such pages after the memslot is freed + * will result in use-after-free, e.g. in unaccount_shadowed(). + */ + for (i = 0; i < slot->npages; i++) { + struct kvm_mmu_page *sp; + gfn_t gfn = slot->base_gfn + i; + + for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + + if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); + flush = false; + cond_resched_rwlock_write(&kvm->mmu_lock); + } + } + +out_flush: + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); +} + +static void kvm_mmu_zap_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + struct kvm_gfn_range range = { + .slot = slot, + .start = slot->base_gfn, + .end = slot->base_gfn + slot->npages, + .may_block = true, + }; + bool flush; + + write_lock(&kvm->mmu_lock); + flush = kvm_unmap_gfn_range(kvm, &range); + kvm_mmu_zap_memslot_pages_and_flush(kvm, slot, flush); + write_unlock(&kvm->mmu_lock); +} + +static inline bool kvm_memslot_flush_zap_all(struct kvm *kvm) +{ + return kvm->arch.vm_type == KVM_X86_DEFAULT_VM && + kvm_check_has_quirk(kvm, KVM_X86_QUIRK_SLOT_ZAP_ALL); +} + void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - kvm_mmu_zap_all_fast(kvm); + if (kvm_memslot_flush_zap_all(kvm)) + kvm_mmu_zap_all_fast(kvm); + else + kvm_mmu_zap_memslot(kvm, slot); } void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) @@ -6869,77 +7287,23 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) } } -static unsigned long mmu_shrink_scan(struct shrinker *shrink, - struct shrink_control *sc) +static void mmu_destroy_caches(void) { - struct kvm *kvm; - int nr_to_scan = sc->nr_to_scan; - unsigned long freed = 0; - - mutex_lock(&kvm_lock); - - list_for_each_entry(kvm, &vm_list, vm_list) { - int idx; - LIST_HEAD(invalid_list); - - /* - * Never scan more than sc->nr_to_scan VM instances. - * Will not hit this condition practically since we do not try - * to shrink more than one VM and it is very unlikely to see - * !n_used_mmu_pages so many times. - */ - if (!nr_to_scan--) - break; - /* - * n_used_mmu_pages is accessed without holding kvm->mmu_lock - * here. We may skip a VM instance errorneosly, but we do not - * want to shrink a VM that only started to populate its MMU - * anyway. - */ - if (!kvm->arch.n_used_mmu_pages && - !kvm_has_zapped_obsolete_pages(kvm)) - continue; - - idx = srcu_read_lock(&kvm->srcu); - write_lock(&kvm->mmu_lock); - - if (kvm_has_zapped_obsolete_pages(kvm)) { - kvm_mmu_commit_zap_page(kvm, - &kvm->arch.zapped_obsolete_pages); - goto unlock; - } - - freed = kvm_mmu_zap_oldest_mmu_pages(kvm, sc->nr_to_scan); - -unlock: - write_unlock(&kvm->mmu_lock); - srcu_read_unlock(&kvm->srcu, idx); - - /* - * unfair on small ones - * per-vm shrinkers cry out - * sadness comes quickly - */ - list_move_tail(&kvm->vm_list, &vm_list); - break; - } - - mutex_unlock(&kvm_lock); - return freed; + kmem_cache_destroy(pte_list_desc_cache); + kmem_cache_destroy(mmu_page_header_cache); } -static unsigned long mmu_shrink_count(struct shrinker *shrink, - struct shrink_control *sc) +static void kvm_wake_nx_recovery_thread(struct kvm *kvm) { - return percpu_counter_read_positive(&kvm_total_used_mmu_pages); -} - -static struct shrinker *mmu_shrinker; + /* + * The NX recovery thread is spawned on-demand at the first KVM_RUN and + * may not be valid even though the VM is globally visible. Do nothing, + * as such a VM can't have any possible NX huge pages. + */ + struct vhost_task *nx_thread = READ_ONCE(kvm->arch.nx_huge_page_recovery_thread); -static void mmu_destroy_caches(void) -{ - kmem_cache_destroy(pte_list_desc_cache); - kmem_cache_destroy(mmu_page_header_cache); + if (nx_thread) + vhost_task_wake(nx_thread); } static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp) @@ -7002,7 +7366,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) kvm_mmu_zap_all_fast(kvm); mutex_unlock(&kvm->slots_lock); - wake_up_process(kvm->arch.nx_huge_page_recovery_thread); + kvm_wake_nx_recovery_thread(kvm); } mutex_unlock(&kvm_lock); } @@ -7062,23 +7426,8 @@ int kvm_mmu_vendor_module_init(void) if (!mmu_page_header_cache) goto out; - if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL)) - goto out; - - 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: - percpu_counter_destroy(&kvm_total_used_mmu_pages); out: mmu_destroy_caches(); return ret; @@ -7087,6 +7436,12 @@ out: void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); + if (tdp_mmu_enabled) { + read_lock(&vcpu->kvm->mmu_lock); + mmu_free_root_page(vcpu->kvm, &vcpu->arch.mmu->mirror_root_hpa, + NULL); + read_unlock(&vcpu->kvm->mmu_lock); + } free_mmu_pages(&vcpu->arch.root_mmu); free_mmu_pages(&vcpu->arch.guest_mmu); mmu_free_memory_caches(vcpu); @@ -7095,8 +7450,6 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu) void kvm_mmu_vendor_module_exit(void) { mmu_destroy_caches(); - percpu_counter_destroy(&kvm_total_used_mmu_pages); - shrinker_free(mmu_shrinker); } /* @@ -7148,7 +7501,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) - wake_up_process(kvm->arch.nx_huge_page_recovery_thread); + kvm_wake_nx_recovery_thread(kvm); mutex_unlock(&kvm_lock); } @@ -7251,62 +7604,68 @@ static void kvm_recover_nx_huge_pages(struct kvm *kvm) srcu_read_unlock(&kvm->srcu, rcu_idx); } -static long get_nx_huge_page_recovery_timeout(u64 start_time) +static void kvm_nx_huge_page_recovery_worker_kill(void *data) +{ +} + +static bool kvm_nx_huge_page_recovery_worker(void *data) { + struct kvm *kvm = data; bool enabled; uint period; + long remaining_time; enabled = calc_nx_huge_pages_recovery_period(&period); + if (!enabled) + return false; + + remaining_time = kvm->arch.nx_huge_page_last + msecs_to_jiffies(period) + - get_jiffies_64(); + if (remaining_time > 0) { + schedule_timeout(remaining_time); + /* check for signals and come back */ + return true; + } - return enabled ? start_time + msecs_to_jiffies(period) - get_jiffies_64() - : MAX_SCHEDULE_TIMEOUT; + __set_current_state(TASK_RUNNING); + kvm_recover_nx_huge_pages(kvm); + kvm->arch.nx_huge_page_last = get_jiffies_64(); + return true; } -static int kvm_nx_huge_page_recovery_worker(struct kvm *kvm, uintptr_t data) +static int kvm_mmu_start_lpage_recovery(struct once *once) { - u64 start_time; - long remaining_time; + struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once); + struct kvm *kvm = container_of(ka, struct kvm, arch); + struct vhost_task *nx_thread; - while (true) { - start_time = get_jiffies_64(); - remaining_time = get_nx_huge_page_recovery_timeout(start_time); + kvm->arch.nx_huge_page_last = get_jiffies_64(); + nx_thread = vhost_task_create(kvm_nx_huge_page_recovery_worker, + kvm_nx_huge_page_recovery_worker_kill, + kvm, "kvm-nx-lpage-recovery"); - set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop() && remaining_time > 0) { - schedule_timeout(remaining_time); - remaining_time = get_nx_huge_page_recovery_timeout(start_time); - set_current_state(TASK_INTERRUPTIBLE); - } - - set_current_state(TASK_RUNNING); + if (IS_ERR(nx_thread)) + return PTR_ERR(nx_thread); - if (kthread_should_stop()) - return 0; + vhost_task_start(nx_thread); - kvm_recover_nx_huge_pages(kvm); - } + /* Make the task visible only once it is fully started. */ + WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread); + return 0; } int kvm_mmu_post_init_vm(struct kvm *kvm) { - int err; - if (nx_hugepage_mitigation_hard_disabled) return 0; - err = kvm_vm_create_worker_thread(kvm, kvm_nx_huge_page_recovery_worker, 0, - "kvm-nx-lpage-recovery", - &kvm->arch.nx_huge_page_recovery_thread); - if (!err) - kthread_unpark(kvm->arch.nx_huge_page_recovery_thread); - - return err; + return call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery); } 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); + vhost_task_stop(kvm->arch.nx_huge_page_recovery_thread); } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES @@ -7327,6 +7686,12 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) return false; + /* Unmap the old attribute page. */ + if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE) + range->attr_filter = KVM_FILTER_SHARED; + else + range->attr_filter = KVM_FILTER_PRIVATE; + return kvm_unmap_gfn_range(kvm, range); } @@ -7355,7 +7720,7 @@ static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot, 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); + return kvm_range_has_memory_attributes(kvm, start, end, ~0, attrs); for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) { if (hugepage_test_mixed(slot, gfn, level - 1) || |