Merge remote-tracking branch 'kvm/next' into kvm-next-5.20

KVM/s390, KVM/x86 and common infrastructure changes for 5.20

x86:

* Permit guests to ignore single-bit ECC errors

* Fix races in gfn->pfn cache refresh; do not pin pages tracked by the cache

* Intel IPI virtualization

* Allow getting/setting pending triple fault with KVM_GET/SET_VCPU_EVENTS

* PEBS virtualization

* Simplify PMU emulation by just using PERF_TYPE_RAW events

* More accurate event reinjection on SVM (avoid retrying instructions)

* Allow getting/setting the state of the speaker port data bit

* Refuse starting the kvm-intel module if VM-Entry/VM-Exit controls are inconsistent

* "Notify" VM exit (detect microarchitectural hangs) for Intel

* Cleanups for MCE MSR emulation

s390:

* add an interface to provide a hypervisor dump for secure guests

* improve selftests to use TAP interface

* enable interpretive execution of zPCI instructions (for PCI passthrough)

* First part of deferred teardown

* CPU Topology

* PV attestation

* Minor fixes

Generic:

* new selftests API using struct kvm_vcpu instead of a (vm, id) tuple

x86:

* Use try_cmpxchg64 instead of cmpxchg64

* Bugfixes

* Ignore benign host accesses to PMU MSRs when PMU is disabled

* Allow disabling KVM's "MONITOR/MWAIT are NOPs!" behavior

* x86/MMU: Allow NX huge pages to be disabled on a per-vm basis

* Port eager page splitting to shadow MMU as well

* Enable CMCI capability by default and handle injected UCNA errors

* Expose pid of vcpu threads in debugfs

* x2AVIC support for AMD

* cleanup PIO emulation

* Fixes for LLDT/LTR emulation

* Don't require refcounted "struct page" to create huge SPTEs

x86 cleanups:

* Use separate namespaces for guest PTEs and shadow PTEs bitmasks

* PIO emulation

* Reorganize rmap API, mostly around rmap destruction

* Do not workaround very old KVM bugs for L0 that runs with nesting enabled

* new selftests API for CPUID

2 files changed, 312 insertions, 138 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e3a6f7647474..32896c845ffe 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -168,7 +168,7 @@ __weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
 {
 }
 
-bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
+bool kvm_is_zone_device_page(struct page *page)
 {
 	/*
 	 * The metadata used by is_zone_device_page() to determine whether or
@@ -176,25 +176,42 @@ bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
 	 * the device has been pinned, e.g. by get_user_pages().  WARN if the
 	 * page_count() is zero to help detect bad usage of this helper.
 	 */
-	if (!pfn_valid(pfn) || WARN_ON_ONCE(!page_count(pfn_to_page(pfn))))
+	if (WARN_ON_ONCE(!page_count(page)))
 		return false;
 
-	return is_zone_device_page(pfn_to_page(pfn));
+	return is_zone_device_page(page);
 }
 
-bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
+/*
+ * Returns a 'struct page' if the pfn is "valid" and backed by a refcounted
+ * page, NULL otherwise.  Note, the list of refcounted PG_reserved page types
+ * is likely incomplete, it has been compiled purely through people wanting to
+ * back guest with a certain type of memory and encountering issues.
+ */
+struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn)
 {
+	struct page *page;
+
+	if (!pfn_valid(pfn))
+		return NULL;
+
+	page = pfn_to_page(pfn);
+	if (!PageReserved(page))
+		return page;
+
+	/* The ZERO_PAGE(s) is marked PG_reserved, but is refcounted. */
+	if (is_zero_pfn(pfn))
+		return page;
+
 	/*
 	 * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting
 	 * perspective they are "normal" pages, albeit with slightly different
 	 * usage rules.
 	 */
-	if (pfn_valid(pfn))
-		return PageReserved(pfn_to_page(pfn)) &&
-		       !is_zero_pfn(pfn) &&
-		       !kvm_is_zone_device_pfn(pfn);
+	if (kvm_is_zone_device_page(page))
+		return page;
 
-	return true;
+	return NULL;
 }
 
 /*
@@ -239,7 +256,7 @@ static bool kvm_request_needs_ipi(struct kvm_vcpu *vcpu, unsigned req)
 	return mode == IN_GUEST_MODE;
 }
 
-static void ack_flush(void *_completed)
+static void ack_kick(void *_completed)
 {
 }
 
@@ -248,7 +265,7 @@ static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait)
 	if (cpumask_empty(cpus))
 		return false;
 
-	smp_call_function_many(cpus, ack_flush, NULL, wait);
+	smp_call_function_many(cpus, ack_kick, NULL, wait);
 	return true;
 }
 
@@ -379,16 +396,31 @@ static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
 		return (void *)__get_free_page(gfp_flags);
 }
 
-int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
+int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min)
 {
+	gfp_t gfp = mc->gfp_custom ? mc->gfp_custom : GFP_KERNEL_ACCOUNT;
 	void *obj;
 
 	if (mc->nobjs >= min)
 		return 0;
-	while (mc->nobjs < ARRAY_SIZE(mc->objects)) {
-		obj = mmu_memory_cache_alloc_obj(mc, (mc->gfp_custom) ?
-						 mc->gfp_custom :
-						 GFP_KERNEL_ACCOUNT);
+
+	if (unlikely(!mc->objects)) {
+		if (WARN_ON_ONCE(!capacity))
+			return -EIO;
+
+		mc->objects = kvmalloc_array(sizeof(void *), capacity, gfp);
+		if (!mc->objects)
+			return -ENOMEM;
+
+		mc->capacity = capacity;
+	}
+
+	/* It is illegal to request a different capacity across topups. */
+	if (WARN_ON_ONCE(mc->capacity != capacity))
+		return -EIO;
+
+	while (mc->nobjs < mc->capacity) {
+		obj = mmu_memory_cache_alloc_obj(mc, gfp);
 		if (!obj)
 			return mc->nobjs >= min ? 0 : -ENOMEM;
 		mc->objects[mc->nobjs++] = obj;
@@ -396,6 +428,11 @@ int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
 	return 0;
 }
 
+int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
+{
+	return __kvm_mmu_topup_memory_cache(mc, KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, min);
+}
+
 int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc)
 {
 	return mc->nobjs;
@@ -409,6 +446,11 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc)
 		else
 			free_page((unsigned long)mc->objects[--mc->nobjs]);
 	}
+
+	kvfree(mc->objects);
+
+	mc->objects = NULL;
+	mc->capacity = 0;
 }
 
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
@@ -726,6 +768,15 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	kvm->mn_active_invalidate_count++;
 	spin_unlock(&kvm->mn_invalidate_lock);
 
+	/*
+	 * Invalidate pfn caches _before_ invalidating the secondary MMUs, i.e.
+	 * before acquiring mmu_lock, to avoid holding mmu_lock while acquiring
+	 * each cache's lock.  There are relatively few caches in existence at
+	 * any given time, and the caches themselves can check for hva overlap,
+	 * i.e. don't need to rely on memslot overlap checks for performance.
+	 * Because this runs without holding mmu_lock, the pfn caches must use
+	 * mn_active_invalidate_count (see above) instead of mmu_notifier_count.
+	 */
 	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
 					  hva_range.may_block);
 
@@ -2494,9 +2545,12 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault)
 
 static int kvm_try_get_pfn(kvm_pfn_t pfn)
 {
-	if (kvm_is_reserved_pfn(pfn))
+	struct page *page = kvm_pfn_to_refcounted_page(pfn);
+
+	if (!page)
 		return 1;
-	return get_page_unless_zero(pfn_to_page(pfn));
+
+	return get_page_unless_zero(page);
 }
 
 static int hva_to_pfn_remapped(struct vm_area_struct *vma,
@@ -2582,7 +2636,7 @@ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
 		     bool write_fault, bool *writable)
 {
 	struct vm_area_struct *vma;
-	kvm_pfn_t pfn = 0;
+	kvm_pfn_t pfn;
 	int npages, r;
 
 	/* we can do it either atomically or asynchronously, not both */
@@ -2713,34 +2767,32 @@ int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
 }
 EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
 
-static struct page *kvm_pfn_to_page(kvm_pfn_t pfn)
-{
-	if (is_error_noslot_pfn(pfn))
-		return KVM_ERR_PTR_BAD_PAGE;
-
-	if (kvm_is_reserved_pfn(pfn)) {
-		WARN_ON(1);
-		return KVM_ERR_PTR_BAD_PAGE;
-	}
-
-	return pfn_to_page(pfn);
-}
-
+/*
+ * Do not use this helper unless you are absolutely certain the gfn _must_ be
+ * backed by 'struct page'.  A valid example is if the backing memslot is
+ * controlled by KVM.  Note, if the returned page is valid, it's refcount has
+ * been elevated by gfn_to_pfn().
+ */
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 {
+	struct page *page;
 	kvm_pfn_t pfn;
 
 	pfn = gfn_to_pfn(kvm, gfn);
 
-	return kvm_pfn_to_page(pfn);
+	if (is_error_noslot_pfn(pfn))
+		return KVM_ERR_PTR_BAD_PAGE;
+
+	page = kvm_pfn_to_refcounted_page(pfn);
+	if (!page)
+		return KVM_ERR_PTR_BAD_PAGE;
+
+	return page;
 }
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
 void kvm_release_pfn(kvm_pfn_t pfn, bool dirty)
 {
-	if (pfn == 0)
-		return;
-
 	if (dirty)
 		kvm_release_pfn_dirty(pfn);
 	else
@@ -2806,28 +2858,48 @@ void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
 
-struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)
+static bool kvm_is_ad_tracked_page(struct page *page)
 {
-	kvm_pfn_t pfn;
+	/*
+	 * Per page-flags.h, pages tagged PG_reserved "should in general not be
+	 * touched (e.g. set dirty) except by its owner".
+	 */
+	return !PageReserved(page);
+}
 
-	pfn = kvm_vcpu_gfn_to_pfn(vcpu, gfn);
+static void kvm_set_page_dirty(struct page *page)
+{
+	if (kvm_is_ad_tracked_page(page))
+		SetPageDirty(page);
+}
 
-	return kvm_pfn_to_page(pfn);
+static void kvm_set_page_accessed(struct page *page)
+{
+	if (kvm_is_ad_tracked_page(page))
+		mark_page_accessed(page);
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_page);
 
 void kvm_release_page_clean(struct page *page)
 {
 	WARN_ON(is_error_page(page));
 
-	kvm_release_pfn_clean(page_to_pfn(page));
+	kvm_set_page_accessed(page);
+	put_page(page);
 }
 EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
 void kvm_release_pfn_clean(kvm_pfn_t pfn)
 {
-	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn))
-		put_page(pfn_to_page(pfn));
+	struct page *page;
+
+	if (is_error_noslot_pfn(pfn))
+		return;
+
+	page = kvm_pfn_to_refcounted_page(pfn);
+	if (!page)
+		return;
+
+	kvm_release_page_clean(page);
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
 
@@ -2835,28 +2907,48 @@ void kvm_release_page_dirty(struct page *page)
 {
 	WARN_ON(is_error_page(page));
 
-	kvm_release_pfn_dirty(page_to_pfn(page));
+	kvm_set_page_dirty(page);
+	kvm_release_page_clean(page);
 }
 EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
 
 void kvm_release_pfn_dirty(kvm_pfn_t pfn)
 {
-	kvm_set_pfn_dirty(pfn);
-	kvm_release_pfn_clean(pfn);
+	struct page *page;
+
+	if (is_error_noslot_pfn(pfn))
+		return;
+
+	page = kvm_pfn_to_refcounted_page(pfn);
+	if (!page)
+		return;
+
+	kvm_release_page_dirty(page);
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
 
+/*
+ * Note, checking for an error/noslot pfn is the caller's responsibility when
+ * directly marking a page dirty/accessed.  Unlike the "release" helpers, the
+ * "set" helpers are not to be used when the pfn might point at garbage.
+ */
 void kvm_set_pfn_dirty(kvm_pfn_t pfn)
 {
-	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn))
-		SetPageDirty(pfn_to_page(pfn));
+	if (WARN_ON(is_error_noslot_pfn(pfn)))
+		return;
+
+	if (pfn_valid(pfn))
+		kvm_set_page_dirty(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
 
 void kvm_set_pfn_accessed(kvm_pfn_t pfn)
 {
-	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn))
-		mark_page_accessed(pfn_to_page(pfn));
+	if (WARN_ON(is_error_noslot_pfn(pfn)))
+		return;
+
+	if (pfn_valid(pfn))
+		kvm_set_page_accessed(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
 
@@ -3730,9 +3822,18 @@ static int create_vcpu_fd(struct kvm_vcpu *vcpu)
 	return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC);
 }
 
+#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
+static int vcpu_get_pid(void *data, u64 *val)
+{
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
+	*val = pid_nr(rcu_access_pointer(vcpu->pid));
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vcpu_get_pid_fops, vcpu_get_pid, NULL, "%llu\n");
+
 static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
 {
-#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
 	struct dentry *debugfs_dentry;
 	char dir_name[ITOA_MAX_LEN * 2];
 
@@ -3742,10 +3843,12 @@ static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
 	snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id);
 	debugfs_dentry = debugfs_create_dir(dir_name,
 					    vcpu->kvm->debugfs_dentry);
+	debugfs_create_file("pid", 0444, debugfs_dentry, vcpu,
+			    &vcpu_get_pid_fops);
 
 	kvm_arch_create_vcpu_debugfs(vcpu, debugfs_dentry);
-#endif
 }
+#endif
 
 /*
  * Creates some virtual cpus.  Good luck creating more than one.
@@ -3765,13 +3868,15 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 		return -EINVAL;
 	}
 
+	r = kvm_arch_vcpu_precreate(kvm, id);
+	if (r) {
+		mutex_unlock(&kvm->lock);
+		return r;
+	}
+
 	kvm->created_vcpus++;
 	mutex_unlock(&kvm->lock);
 
-	r = kvm_arch_vcpu_precreate(kvm, id);
-	if (r)
-		goto vcpu_decrement;
-
 	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
 	if (!vcpu) {
 		r = -ENOMEM;
diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c
index dd84676615f1..ab519f72f2cd 100644
--- a/virt/kvm/pfncache.c
+++ b/virt/kvm/pfncache.c
@@ -95,48 +95,143 @@ bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 }
 EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_check);
 
-static void __release_gpc(struct kvm *kvm, kvm_pfn_t pfn, void *khva, gpa_t gpa)
+static void gpc_unmap_khva(struct kvm *kvm, kvm_pfn_t pfn, void *khva)
 {
-	/* Unmap the old page if it was mapped before, and release it */
-	if (!is_error_noslot_pfn(pfn)) {
-		if (khva) {
-			if (pfn_valid(pfn))
-				kunmap(pfn_to_page(pfn));
+	/* Unmap the old pfn/page if it was mapped before. */
+	if (!is_error_noslot_pfn(pfn) && khva) {
+		if (pfn_valid(pfn))
+			kunmap(pfn_to_page(pfn));
 #ifdef CONFIG_HAS_IOMEM
-			else
-				memunmap(khva);
+		else
+			memunmap(khva);
 #endif
-		}
-
-		kvm_release_pfn(pfn, false);
 	}
 }
 
-static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, unsigned long uhva)
+static inline bool mmu_notifier_retry_cache(struct kvm *kvm, unsigned long mmu_seq)
 {
+	/*
+	 * mn_active_invalidate_count acts for all intents and purposes
+	 * like mmu_notifier_count here; but the latter cannot be used
+	 * here because the invalidation of caches in the mmu_notifier
+	 * event occurs _before_ mmu_notifier_count is elevated.
+	 *
+	 * Note, it does not matter that mn_active_invalidate_count
+	 * is not protected by gpc->lock.  It is guaranteed to
+	 * be elevated before the mmu_notifier acquires gpc->lock, and
+	 * isn't dropped until after mmu_notifier_seq is updated.
+	 */
+	if (kvm->mn_active_invalidate_count)
+		return true;
+
+	/*
+	 * Ensure mn_active_invalidate_count is read before
+	 * mmu_notifier_seq.  This pairs with the smp_wmb() in
+	 * mmu_notifier_invalidate_range_end() to guarantee either the
+	 * old (non-zero) value of mn_active_invalidate_count or the
+	 * new (incremented) value of mmu_notifier_seq is observed.
+	 */
+	smp_rmb();
+	return kvm->mmu_notifier_seq != mmu_seq;
+}
+
+static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
+{
+	/* Note, the new page offset may be different than the old! */
+	void *old_khva = gpc->khva - offset_in_page(gpc->khva);
+	kvm_pfn_t new_pfn = KVM_PFN_ERR_FAULT;
+	void *new_khva = NULL;
 	unsigned long mmu_seq;
-	kvm_pfn_t new_pfn;
-	int retry;
+
+	lockdep_assert_held(&gpc->refresh_lock);
+
+	lockdep_assert_held_write(&gpc->lock);
+
+	/*
+	 * Invalidate the cache prior to dropping gpc->lock, the gpa=>uhva
+	 * assets have already been updated and so a concurrent check() from a
+	 * different task may not fail the gpa/uhva/generation checks.
+	 */
+	gpc->valid = false;
 
 	do {
 		mmu_seq = kvm->mmu_notifier_seq;
 		smp_rmb();
 
+		write_unlock_irq(&gpc->lock);
+
+		/*
+		 * If the previous iteration "failed" due to an mmu_notifier
+		 * event, release the pfn and unmap the kernel virtual address
+		 * from the previous attempt.  Unmapping might sleep, so this
+		 * needs to be done after dropping the lock.  Opportunistically
+		 * check for resched while the lock isn't held.
+		 */
+		if (new_pfn != KVM_PFN_ERR_FAULT) {
+			/*
+			 * Keep the mapping if the previous iteration reused
+			 * the existing mapping and didn't create a new one.
+			 */
+			if (new_khva != old_khva)
+				gpc_unmap_khva(kvm, new_pfn, new_khva);
+
+			kvm_release_pfn_clean(new_pfn);
+
+			cond_resched();
+		}
+
 		/* We always request a writeable mapping */
-		new_pfn = hva_to_pfn(uhva, false, NULL, true, NULL);
+		new_pfn = hva_to_pfn(gpc->uhva, false, NULL, true, NULL);
 		if (is_error_noslot_pfn(new_pfn))
-			break;
+			goto out_error;
+
+		/*
+		 * Obtain a new kernel mapping if KVM itself will access the
+		 * pfn.  Note, kmap() and memremap() can both sleep, so this
+		 * too must be done outside of gpc->lock!
+		 */
+		if (gpc->usage & KVM_HOST_USES_PFN) {
+			if (new_pfn == gpc->pfn) {
+				new_khva = old_khva;
+			} else if (pfn_valid(new_pfn)) {
+				new_khva = kmap(pfn_to_page(new_pfn));
+#ifdef CONFIG_HAS_IOMEM
+			} else {
+				new_khva = memremap(pfn_to_hpa(new_pfn), PAGE_SIZE, MEMREMAP_WB);
+#endif
+			}
+			if (!new_khva) {
+				kvm_release_pfn_clean(new_pfn);
+				goto out_error;
+			}
+		}
+
+		write_lock_irq(&gpc->lock);
+
+		/*
+		 * Other tasks must wait for _this_ refresh to complete before
+		 * attempting to refresh.
+		 */
+		WARN_ON_ONCE(gpc->valid);
+	} while (mmu_notifier_retry_cache(kvm, mmu_seq));
+
+	gpc->valid = true;
+	gpc->pfn = new_pfn;
+	gpc->khva = new_khva + (gpc->gpa & ~PAGE_MASK);
 
-		KVM_MMU_READ_LOCK(kvm);
-		retry = mmu_notifier_retry_hva(kvm, mmu_seq, uhva);
-		KVM_MMU_READ_UNLOCK(kvm);
-		if (!retry)
-			break;
+	/*
+	 * Put the reference to the _new_ pfn.  The pfn is now tracked by the
+	 * cache and can be safely migrated, swapped, etc... as the cache will
+	 * invalidate any mappings in response to relevant mmu_notifier events.
+	 */
+	kvm_release_pfn_clean(new_pfn);
 
-		cond_resched();
-	} while (1);
+	return 0;
 
-	return new_pfn;
+out_error:
+	write_lock_irq(&gpc->lock);
+
+	return -EFAULT;
 }
 
 int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
@@ -146,9 +241,7 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 	unsigned long page_offset = gpa & ~PAGE_MASK;
 	kvm_pfn_t old_pfn, new_pfn;
 	unsigned long old_uhva;
-	gpa_t old_gpa;
 	void *old_khva;
-	bool old_valid;
 	int ret = 0;
 
 	/*
@@ -158,13 +251,18 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 	if (page_offset + len > PAGE_SIZE)
 		return -EINVAL;
 
+	/*
+	 * If another task is refreshing the cache, wait for it to complete.
+	 * There is no guarantee that concurrent refreshes will see the same
+	 * gpa, memslots generation, etc..., so they must be fully serialized.
+	 */
+	mutex_lock(&gpc->refresh_lock);
+
 	write_lock_irq(&gpc->lock);
 
-	old_gpa = gpc->gpa;
 	old_pfn = gpc->pfn;
 	old_khva = gpc->khva - offset_in_page(gpc->khva);
 	old_uhva = gpc->uhva;
-	old_valid = gpc->valid;
 
 	/* If the userspace HVA is invalid, refresh that first */
 	if (gpc->gpa != gpa || gpc->generation != slots->generation ||
@@ -177,64 +275,17 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 		gpc->uhva = gfn_to_hva_memslot(gpc->memslot, gfn);
 
 		if (kvm_is_error_hva(gpc->uhva)) {
-			gpc->pfn = KVM_PFN_ERR_FAULT;
 			ret = -EFAULT;
 			goto out;
 		}
-
-		gpc->uhva += page_offset;
 	}
 
 	/*
 	 * If the userspace HVA changed or the PFN was already invalid,
 	 * drop the lock and do the HVA to PFN lookup again.
 	 */
-	if (!old_valid || old_uhva != gpc->uhva) {
-		unsigned long uhva = gpc->uhva;
-		void *new_khva = NULL;
-
-		/* Placeholders for "hva is valid but not yet mapped" */
-		gpc->pfn = KVM_PFN_ERR_FAULT;
-		gpc->khva = NULL;
-		gpc->valid = true;
-
-		write_unlock_irq(&gpc->lock);
-
-		new_pfn = hva_to_pfn_retry(kvm, uhva);
-		if (is_error_noslot_pfn(new_pfn)) {
-			ret = -EFAULT;
-			goto map_done;
-		}
-
-		if (gpc->usage & KVM_HOST_USES_PFN) {
-			if (new_pfn == old_pfn) {
-				new_khva = old_khva;
-				old_pfn = KVM_PFN_ERR_FAULT;
-				old_khva = NULL;
-			} else if (pfn_valid(new_pfn)) {
-				new_khva = kmap(pfn_to_page(new_pfn));
-#ifdef CONFIG_HAS_IOMEM
-			} else {
-				new_khva = memremap(pfn_to_hpa(new_pfn), PAGE_SIZE, MEMREMAP_WB);
-#endif
-			}
-			if (new_khva)
-				new_khva += page_offset;
-			else
-				ret = -EFAULT;
-		}
-
-	map_done:
-		write_lock_irq(&gpc->lock);
-		if (ret) {
-			gpc->valid = false;
-			gpc->pfn = KVM_PFN_ERR_FAULT;
-			gpc->khva = NULL;
-		} else {
-			/* At this point, gpc->valid may already have been cleared */
-			gpc->pfn = new_pfn;
-			gpc->khva = new_khva;
-		}
+	if (!gpc->valid || old_uhva != gpc->uhva) {
+		ret = hva_to_pfn_retry(kvm, gpc);
 	} else {
 		/* If the HVA→PFN mapping was already valid, don't unmap it. */
 		old_pfn = KVM_PFN_ERR_FAULT;
@@ -242,9 +293,26 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 	}
 
  out:
+	/*
+	 * Invalidate the cache and purge the pfn/khva if the refresh failed.
+	 * Some/all of the uhva, gpa, and memslot generation info may still be
+	 * valid, leave it as is.
+	 */
+	if (ret) {
+		gpc->valid = false;
+		gpc->pfn = KVM_PFN_ERR_FAULT;
+		gpc->khva = NULL;
+	}
+
+	/* Snapshot the new pfn before dropping the lock! */
+	new_pfn = gpc->pfn;
+
 	write_unlock_irq(&gpc->lock);
 
-	__release_gpc(kvm, old_pfn, old_khva, old_gpa);
+	mutex_unlock(&gpc->refresh_lock);
+
+	if (old_pfn != new_pfn)
+		gpc_unmap_khva(kvm, old_pfn, old_khva);
 
 	return ret;
 }
@@ -254,14 +322,13 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
 {
 	void *old_khva;
 	kvm_pfn_t old_pfn;
-	gpa_t old_gpa;
 
+	mutex_lock(&gpc->refresh_lock);
 	write_lock_irq(&gpc->lock);
 
 	gpc->valid = false;
 
 	old_khva = gpc->khva - offset_in_page(gpc->khva);
-	old_gpa = gpc->gpa;
 	old_pfn = gpc->pfn;
 
 	/*
@@ -272,8 +339,9 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
 	gpc->pfn = KVM_PFN_ERR_FAULT;
 
 	write_unlock_irq(&gpc->lock);
+	mutex_unlock(&gpc->refresh_lock);
 
-	__release_gpc(kvm, old_pfn, old_khva, old_gpa);
+	gpc_unmap_khva(kvm, old_pfn, old_khva);
 }
 EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_unmap);
 
@@ -286,6 +354,7 @@ int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 
 	if (!gpc->active) {
 		rwlock_init(&gpc->lock);
+		mutex_init(&gpc->refresh_lock);
 
 		gpc->khva = NULL;
 		gpc->pfn = KVM_PFN_ERR_FAULT;