Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

6 files changed, 230 insertions, 154 deletions

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 184dab4ee8..29b73eedfe 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -1,9 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # KVM common configuration items and defaults
 
-config HAVE_KVM
-       bool
-
 config KVM_COMMON
        bool
        select EVENTFD
@@ -55,6 +52,9 @@ config KVM_ASYNC_PF_SYNC
 config HAVE_KVM_MSI
        bool
 
+config HAVE_KVM_READONLY_MEM
+       bool
+
 config HAVE_KVM_CPU_RELAX_INTERCEPT
        bool
 
@@ -73,6 +73,7 @@ config KVM_COMPAT
 
 config HAVE_KVM_IRQ_BYPASS
        bool
+       select IRQ_BYPASS_MANAGER
 
 config HAVE_KVM_VCPU_ASYNC_IOCTL
        bool
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 28658b9e0d..99a63bad03 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -46,8 +46,8 @@ static void async_pf_execute(struct work_struct *work)
 {
 	struct kvm_async_pf *apf =
 		container_of(work, struct kvm_async_pf, work);
-	struct mm_struct *mm = apf->mm;
 	struct kvm_vcpu *vcpu = apf->vcpu;
+	struct mm_struct *mm = vcpu->kvm->mm;
 	unsigned long addr = apf->addr;
 	gpa_t cr2_or_gpa = apf->cr2_or_gpa;
 	int locked = 1;
@@ -56,15 +56,24 @@ static void async_pf_execute(struct work_struct *work)
 	might_sleep();
 
 	/*
-	 * This work is run asynchronously to the task which owns
-	 * mm and might be done in another context, so we must
-	 * access remotely.
+	 * Attempt to pin the VM's host address space, and simply skip gup() if
+	 * acquiring a pin fail, i.e. if the process is exiting.  Note, KVM
+	 * holds a reference to its associated mm_struct until the very end of
+	 * kvm_destroy_vm(), i.e. the struct itself won't be freed before this
+	 * work item is fully processed.
 	 */
-	mmap_read_lock(mm);
-	get_user_pages_remote(mm, addr, 1, FOLL_WRITE, NULL, &locked);
-	if (locked)
-		mmap_read_unlock(mm);
+	if (mmget_not_zero(mm)) {
+		mmap_read_lock(mm);
+		get_user_pages_remote(mm, addr, 1, FOLL_WRITE, NULL, &locked);
+		if (locked)
+			mmap_read_unlock(mm);
+		mmput(mm);
+	}
 
+	/*
+	 * Notify and kick the vCPU even if faulting in the page failed, e.g.
+	 * so that the vCPU can retry the fault synchronously.
+	 */
 	if (IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC))
 		kvm_arch_async_page_present(vcpu, apf);
 
@@ -74,19 +83,18 @@ static void async_pf_execute(struct work_struct *work)
 	apf->vcpu = NULL;
 	spin_unlock(&vcpu->async_pf.lock);
 
-	if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC) && first)
-		kvm_arch_async_page_present_queued(vcpu);
-
 	/*
-	 * apf may be freed by kvm_check_async_pf_completion() after
-	 * this point
+	 * The apf struct may be freed by kvm_check_async_pf_completion() as
+	 * soon as the lock is dropped.  Nullify it to prevent improper usage.
 	 */
+	apf = NULL;
+
+	if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC) && first)
+		kvm_arch_async_page_present_queued(vcpu);
 
 	trace_kvm_async_pf_completed(addr, cr2_or_gpa);
 
 	__kvm_vcpu_wake_up(vcpu);
-
-	mmput(mm);
 }
 
 static void kvm_flush_and_free_async_pf_work(struct kvm_async_pf *work)
@@ -132,10 +140,8 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 #ifdef CONFIG_KVM_ASYNC_PF_SYNC
 		flush_work(&work->work);
 #else
-		if (cancel_work_sync(&work->work)) {
-			mmput(work->mm);
+		if (cancel_work_sync(&work->work))
 			kmem_cache_free(async_pf_cache, work);
-		}
 #endif
 		spin_lock(&vcpu->async_pf.lock);
 	}
@@ -206,8 +212,6 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	work->cr2_or_gpa = cr2_or_gpa;
 	work->addr = hva;
 	work->arch = *arch;
-	work->mm = current->mm;
-	mmget(work->mm);
 
 	INIT_WORK(&work->work, async_pf_execute);
 
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 0f4e0cf4f1..747fe251e4 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -510,8 +510,10 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 	}
 
 	if (folio_test_hwpoison(folio)) {
+		folio_unlock(folio);
+		folio_put(folio);
 		r = -EHWPOISON;
-		goto out_unlock;
+		goto out_fput;
 	}
 
 	page = folio_file_page(folio, index);
@@ -522,7 +524,6 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 
 	r = 0;
 
-out_unlock:
 	folio_unlock(folio);
 out_fput:
 	fput(file);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 0f50960b0e..d9ce063c76 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -421,7 +421,7 @@ int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity,
 		if (WARN_ON_ONCE(!capacity))
 			return -EIO;
 
-		mc->objects = kvmalloc_array(sizeof(void *), capacity, gfp);
+		mc->objects = kvmalloc_array(capacity, sizeof(void *), gfp);
 		if (!mc->objects)
 			return -ENOMEM;
 
@@ -832,8 +832,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 * mn_active_invalidate_count (see above) instead of
 	 * mmu_invalidate_in_progress.
 	 */
-	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
-					  hva_range.may_block);
+	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end);
 
 	/*
 	 * If one or more memslots were found and thus zapped, notify arch code
@@ -890,7 +889,9 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 
 	/* Pairs with the increment in range_start(). */
 	spin_lock(&kvm->mn_invalidate_lock);
-	wake = (--kvm->mn_active_invalidate_count == 0);
+	if (!WARN_ON_ONCE(!kvm->mn_active_invalidate_count))
+		--kvm->mn_active_invalidate_count;
+	wake = !kvm->mn_active_invalidate_count;
 	spin_unlock(&kvm->mn_invalidate_lock);
 
 	/*
@@ -1150,10 +1151,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname)
 				    &stat_fops_per_vm);
 	}
 
-	ret = kvm_arch_create_vm_debugfs(kvm);
-	if (ret)
-		goto out_err;
-
+	kvm_arch_create_vm_debugfs(kvm);
 	return 0;
 out_err:
 	kvm_destroy_vm_debugfs(kvm);
@@ -1183,9 +1181,8 @@ void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm)
  * Cleanup should be automatic done in kvm_destroy_vm_debugfs() recursively, so
  * a per-arch destroy interface is not needed.
  */
-int __weak kvm_arch_create_vm_debugfs(struct kvm *kvm)
+void __weak kvm_arch_create_vm_debugfs(struct kvm *kvm)
 {
-	return 0;
 }
 
 static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
@@ -1614,7 +1611,7 @@ static int check_memory_region_flags(struct kvm *kvm,
 	if (mem->flags & KVM_MEM_GUEST_MEMFD)
 		valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
 
-#ifdef __KVM_HAVE_READONLY_MEM
+#ifdef CONFIG_HAVE_KVM_READONLY_MEM
 	/*
 	 * GUEST_MEMFD is incompatible with read-only memslots, as writes to
 	 * read-only memslots have emulated MMIO, not page fault, semantics,
@@ -4048,6 +4045,18 @@ static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)
 	return false;
 }
 
+/*
+ * By default, simply query the target vCPU's current mode when checking if a
+ * vCPU was preempted in kernel mode.  All architectures except x86 (or more
+ * specifical, except VMX) allow querying whether or not a vCPU is in kernel
+ * mode even if the vCPU is NOT loaded, i.e. using kvm_arch_vcpu_in_kernel()
+ * directly for cross-vCPU checks is functionally correct and accurate.
+ */
+bool __weak kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu)
+{
+	return kvm_arch_vcpu_in_kernel(vcpu);
+}
+
 bool __weak kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu)
 {
 	return false;
@@ -4057,12 +4066,13 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 {
 	struct kvm *kvm = me->kvm;
 	struct kvm_vcpu *vcpu;
-	int last_boosted_vcpu = me->kvm->last_boosted_vcpu;
+	int last_boosted_vcpu;
 	unsigned long i;
 	int yielded = 0;
 	int try = 3;
 	int pass;
 
+	last_boosted_vcpu = READ_ONCE(kvm->last_boosted_vcpu);
 	kvm_vcpu_set_in_spin_loop(me, true);
 	/*
 	 * We boost the priority of a VCPU that is runnable but not
@@ -4084,16 +4094,23 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 				continue;
 			if (kvm_vcpu_is_blocking(vcpu) && !vcpu_dy_runnable(vcpu))
 				continue;
+
+			/*
+			 * Treat the target vCPU as being in-kernel if it has a
+			 * pending interrupt, as the vCPU trying to yield may
+			 * be spinning waiting on IPI delivery, i.e. the target
+			 * vCPU is in-kernel for the purposes of directed yield.
+			 */
 			if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode &&
 			    !kvm_arch_dy_has_pending_interrupt(vcpu) &&
-			    !kvm_arch_vcpu_in_kernel(vcpu))
+			    !kvm_arch_vcpu_preempted_in_kernel(vcpu))
 				continue;
 			if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
 				continue;
 
 			yielded = kvm_vcpu_yield_to(vcpu);
 			if (yielded > 0) {
-				kvm->last_boosted_vcpu = i;
+				WRITE_ONCE(kvm->last_boosted_vcpu, i);
 				break;
 			} else if (yielded < 0) {
 				try--;
diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index ecefc7ec51..715f19669d 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -26,13 +26,11 @@ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible,
 #ifdef CONFIG_HAVE_KVM_PFNCACHE
 void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
 				       unsigned long start,
-				       unsigned long end,
-				       bool may_block);
+				       unsigned long end);
 #else
 static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
 						     unsigned long start,
-						     unsigned long end,
-						     bool may_block)
+						     unsigned long end)
 {
 }
 #endif /* HAVE_KVM_PFNCACHE */
diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c
index 2d6aba6778..e3453e869e 100644
--- a/virt/kvm/pfncache.c
+++ b/virt/kvm/pfncache.c
@@ -23,57 +23,51 @@
  * MMU notifier 'invalidate_range_start' hook.
  */
 void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start,
-				       unsigned long end, bool may_block)
+				       unsigned long end)
 {
-	DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
 	struct gfn_to_pfn_cache *gpc;
-	bool evict_vcpus = false;
 
 	spin_lock(&kvm->gpc_lock);
 	list_for_each_entry(gpc, &kvm->gpc_list, list) {
-		write_lock_irq(&gpc->lock);
+		read_lock_irq(&gpc->lock);
 
 		/* Only a single page so no need to care about length */
 		if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) &&
 		    gpc->uhva >= start && gpc->uhva < end) {
-			gpc->valid = false;
+			read_unlock_irq(&gpc->lock);
 
 			/*
-			 * If a guest vCPU could be using the physical address,
-			 * it needs to be forced out of guest mode.
+			 * There is a small window here where the cache could
+			 * be modified, and invalidation would no longer be
+			 * necessary. Hence check again whether invalidation
+			 * is still necessary once the write lock has been
+			 * acquired.
 			 */
-			if (gpc->usage & KVM_GUEST_USES_PFN) {
-				if (!evict_vcpus) {
-					evict_vcpus = true;
-					bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS);
-				}
-				__set_bit(gpc->vcpu->vcpu_idx, vcpu_bitmap);
-			}
+
+			write_lock_irq(&gpc->lock);
+			if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) &&
+			    gpc->uhva >= start && gpc->uhva < end)
+				gpc->valid = false;
+			write_unlock_irq(&gpc->lock);
+			continue;
 		}
-		write_unlock_irq(&gpc->lock);
+
+		read_unlock_irq(&gpc->lock);
 	}
 	spin_unlock(&kvm->gpc_lock);
+}
 
-	if (evict_vcpus) {
-		/*
-		 * KVM needs to ensure the vCPU is fully out of guest context
-		 * before allowing the invalidation to continue.
-		 */
-		unsigned int req = KVM_REQ_OUTSIDE_GUEST_MODE;
-		bool called;
-
-		/*
-		 * If the OOM reaper is active, then all vCPUs should have
-		 * been stopped already, so perform the request without
-		 * KVM_REQUEST_WAIT and be sad if any needed to be IPI'd.
-		 */
-		if (!may_block)
-			req &= ~KVM_REQUEST_WAIT;
-
-		called = kvm_make_vcpus_request_mask(kvm, req, vcpu_bitmap);
+static bool kvm_gpc_is_valid_len(gpa_t gpa, unsigned long uhva,
+				 unsigned long len)
+{
+	unsigned long offset = kvm_is_error_gpa(gpa) ? offset_in_page(uhva) :
+						       offset_in_page(gpa);
 
-		WARN_ON_ONCE(called && !may_block);
-	}
+	/*
+	 * The cached access must fit within a single page. The 'len' argument
+	 * to activate() and refresh() exists only to enforce that.
+	 */
+	return offset + len <= PAGE_SIZE;
 }
 
 bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len)
@@ -83,10 +77,17 @@ bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len)
 	if (!gpc->active)
 		return false;
 
-	if ((gpc->gpa & ~PAGE_MASK) + len > PAGE_SIZE)
+	/*
+	 * If the page was cached from a memslot, make sure the memslots have
+	 * not been re-configured.
+	 */
+	if (!kvm_is_error_gpa(gpc->gpa) && gpc->generation != slots->generation)
 		return false;
 
-	if (gpc->generation != slots->generation || kvm_is_error_hva(gpc->uhva))
+	if (kvm_is_error_hva(gpc->uhva))
+		return false;
+
+	if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len))
 		return false;
 
 	if (!gpc->valid)
@@ -94,19 +95,33 @@ bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len)
 
 	return true;
 }
-EXPORT_SYMBOL_GPL(kvm_gpc_check);
 
-static void gpc_unmap_khva(kvm_pfn_t pfn, void *khva)
+static void *gpc_map(kvm_pfn_t 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));
+	if (pfn_valid(pfn))
+		return kmap(pfn_to_page(pfn));
+
 #ifdef CONFIG_HAS_IOMEM
-		else
-			memunmap(khva);
+	return memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
+#else
+	return NULL;
 #endif
+}
+
+static void gpc_unmap(kvm_pfn_t pfn, void *khva)
+{
+	/* Unmap the old pfn/page if it was mapped before. */
+	if (is_error_noslot_pfn(pfn) || !khva)
+		return;
+
+	if (pfn_valid(pfn)) {
+		kunmap(pfn_to_page(pfn));
+		return;
 	}
+
+#ifdef CONFIG_HAS_IOMEM
+	memunmap(khva);
+#endif
 }
 
 static inline bool mmu_notifier_retry_cache(struct kvm *kvm, unsigned long mmu_seq)
@@ -140,7 +155,7 @@ static inline bool mmu_notifier_retry_cache(struct kvm *kvm, unsigned long mmu_s
 static kvm_pfn_t hva_to_pfn_retry(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);
+	void *old_khva = (void *)PAGE_ALIGN_DOWN((uintptr_t)gpc->khva);
 	kvm_pfn_t new_pfn = KVM_PFN_ERR_FAULT;
 	void *new_khva = NULL;
 	unsigned long mmu_seq;
@@ -175,7 +190,7 @@ static kvm_pfn_t hva_to_pfn_retry(struct gfn_to_pfn_cache *gpc)
 			 * the existing mapping and didn't create a new one.
 			 */
 			if (new_khva != old_khva)
-				gpc_unmap_khva(new_pfn, new_khva);
+				gpc_unmap(new_pfn, new_khva);
 
 			kvm_release_pfn_clean(new_pfn);
 
@@ -192,20 +207,14 @@ static kvm_pfn_t hva_to_pfn_retry(struct gfn_to_pfn_cache *gpc)
 		 * 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;
-			}
+		if (new_pfn == gpc->pfn)
+			new_khva = old_khva;
+		else
+			new_khva = gpc_map(new_pfn);
+
+		if (!new_khva) {
+			kvm_release_pfn_clean(new_pfn);
+			goto out_error;
 		}
 
 		write_lock_irq(&gpc->lock);
@@ -219,7 +228,7 @@ static kvm_pfn_t hva_to_pfn_retry(struct gfn_to_pfn_cache *gpc)
 
 	gpc->valid = true;
 	gpc->pfn = new_pfn;
-	gpc->khva = new_khva + (gpc->gpa & ~PAGE_MASK);
+	gpc->khva = new_khva + offset_in_page(gpc->uhva);
 
 	/*
 	 * Put the reference to the _new_ pfn.  The pfn is now tracked by the
@@ -236,30 +245,21 @@ out_error:
 	return -EFAULT;
 }
 
-static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa,
-			     unsigned long len)
+static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva)
 {
-	struct kvm_memslots *slots = kvm_memslots(gpc->kvm);
-	unsigned long page_offset = gpa & ~PAGE_MASK;
+	unsigned long page_offset;
 	bool unmap_old = false;
 	unsigned long old_uhva;
 	kvm_pfn_t old_pfn;
+	bool hva_change = false;
 	void *old_khva;
 	int ret;
 
-	/*
-	 * If must fit within a single page. The 'len' argument is
-	 * only to enforce that.
-	 */
-	if (page_offset + len > PAGE_SIZE)
+	/* Either gpa or uhva must be valid, but not both */
+	if (WARN_ON_ONCE(kvm_is_error_gpa(gpa) == kvm_is_error_hva(uhva)))
 		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);
+	lockdep_assert_held(&gpc->refresh_lock);
 
 	write_lock_irq(&gpc->lock);
 
@@ -269,30 +269,56 @@ static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa,
 	}
 
 	old_pfn = gpc->pfn;
-	old_khva = gpc->khva - offset_in_page(gpc->khva);
-	old_uhva = gpc->uhva;
-
-	/* If the userspace HVA is invalid, refresh that first */
-	if (gpc->gpa != gpa || gpc->generation != slots->generation ||
-	    kvm_is_error_hva(gpc->uhva)) {
-		gfn_t gfn = gpa_to_gfn(gpa);
-
-		gpc->gpa = gpa;
-		gpc->generation = slots->generation;
-		gpc->memslot = __gfn_to_memslot(slots, gfn);
-		gpc->uhva = gfn_to_hva_memslot(gpc->memslot, gfn);
-
-		if (kvm_is_error_hva(gpc->uhva)) {
-			ret = -EFAULT;
-			goto out;
+	old_khva = (void *)PAGE_ALIGN_DOWN((uintptr_t)gpc->khva);
+	old_uhva = PAGE_ALIGN_DOWN(gpc->uhva);
+
+	if (kvm_is_error_gpa(gpa)) {
+		page_offset = offset_in_page(uhva);
+
+		gpc->gpa = INVALID_GPA;
+		gpc->memslot = NULL;
+		gpc->uhva = PAGE_ALIGN_DOWN(uhva);
+
+		if (gpc->uhva != old_uhva)
+			hva_change = true;
+	} else {
+		struct kvm_memslots *slots = kvm_memslots(gpc->kvm);
+
+		page_offset = offset_in_page(gpa);
+
+		if (gpc->gpa != gpa || gpc->generation != slots->generation ||
+		    kvm_is_error_hva(gpc->uhva)) {
+			gfn_t gfn = gpa_to_gfn(gpa);
+
+			gpc->gpa = gpa;
+			gpc->generation = slots->generation;
+			gpc->memslot = __gfn_to_memslot(slots, gfn);
+			gpc->uhva = gfn_to_hva_memslot(gpc->memslot, gfn);
+
+			if (kvm_is_error_hva(gpc->uhva)) {
+				ret = -EFAULT;
+				goto out;
+			}
+
+			/*
+			 * Even if the GPA and/or the memslot generation changed, the
+			 * HVA may still be the same.
+			 */
+			if (gpc->uhva != old_uhva)
+				hva_change = true;
+		} else {
+			gpc->uhva = old_uhva;
 		}
 	}
 
+	/* Note: the offset must be correct before calling hva_to_pfn_retry() */
+	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 (!gpc->valid || old_uhva != gpc->uhva) {
+	if (!gpc->valid || hva_change) {
 		ret = hva_to_pfn_retry(gpc);
 	} else {
 		/*
@@ -323,41 +349,53 @@ static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa,
 out_unlock:
 	write_unlock_irq(&gpc->lock);
 
-	mutex_unlock(&gpc->refresh_lock);
-
 	if (unmap_old)
-		gpc_unmap_khva(old_pfn, old_khva);
+		gpc_unmap(old_pfn, old_khva);
 
 	return ret;
 }
 
 int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len)
 {
-	return __kvm_gpc_refresh(gpc, gpc->gpa, len);
+	unsigned long uhva;
+
+	guard(mutex)(&gpc->refresh_lock);
+
+	if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len))
+		return -EINVAL;
+
+	/*
+	 * If the GPA is valid then ignore the HVA, as a cache can be GPA-based
+	 * or HVA-based, not both.  For GPA-based caches, the HVA will be
+	 * recomputed during refresh if necessary.
+	 */
+	uhva = kvm_is_error_gpa(gpc->gpa) ? gpc->uhva : KVM_HVA_ERR_BAD;
+
+	return __kvm_gpc_refresh(gpc, gpc->gpa, uhva);
 }
-EXPORT_SYMBOL_GPL(kvm_gpc_refresh);
 
-void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm,
-		  struct kvm_vcpu *vcpu, enum pfn_cache_usage usage)
+void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm)
 {
-	WARN_ON_ONCE(!usage || (usage & KVM_GUEST_AND_HOST_USE_PFN) != usage);
-	WARN_ON_ONCE((usage & KVM_GUEST_USES_PFN) && !vcpu);
-
 	rwlock_init(&gpc->lock);
 	mutex_init(&gpc->refresh_lock);
 
 	gpc->kvm = kvm;
-	gpc->vcpu = vcpu;
-	gpc->usage = usage;
 	gpc->pfn = KVM_PFN_ERR_FAULT;
+	gpc->gpa = INVALID_GPA;
 	gpc->uhva = KVM_HVA_ERR_BAD;
+	gpc->active = gpc->valid = false;
 }
-EXPORT_SYMBOL_GPL(kvm_gpc_init);
 
-int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len)
+static int __kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva,
+			      unsigned long len)
 {
 	struct kvm *kvm = gpc->kvm;
 
+	if (!kvm_gpc_is_valid_len(gpa, uhva, len))
+		return -EINVAL;
+
+	guard(mutex)(&gpc->refresh_lock);
+
 	if (!gpc->active) {
 		if (KVM_BUG_ON(gpc->valid, kvm))
 			return -EIO;
@@ -375,9 +413,25 @@ int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len)
 		gpc->active = true;
 		write_unlock_irq(&gpc->lock);
 	}
-	return __kvm_gpc_refresh(gpc, gpa, len);
+	return __kvm_gpc_refresh(gpc, gpa, uhva);
+}
+
+int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len)
+{
+	/*
+	 * Explicitly disallow INVALID_GPA so that the magic value can be used
+	 * by KVM to differentiate between GPA-based and HVA-based caches.
+	 */
+	if (WARN_ON_ONCE(kvm_is_error_gpa(gpa)))
+		return -EINVAL;
+
+	return __kvm_gpc_activate(gpc, gpa, KVM_HVA_ERR_BAD, len);
+}
+
+int kvm_gpc_activate_hva(struct gfn_to_pfn_cache *gpc, unsigned long uhva, unsigned long len)
+{
+	return __kvm_gpc_activate(gpc, INVALID_GPA, uhva, len);
 }
-EXPORT_SYMBOL_GPL(kvm_gpc_activate);
 
 void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc)
 {
@@ -385,6 +439,8 @@ void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc)
 	kvm_pfn_t old_pfn;
 	void *old_khva;
 
+	guard(mutex)(&gpc->refresh_lock);
+
 	if (gpc->active) {
 		/*
 		 * Deactivate the cache before removing it from the list, KVM
@@ -412,7 +468,6 @@ void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc)
 		list_del(&gpc->list);
 		spin_unlock(&kvm->gpc_lock);
 
-		gpc_unmap_khva(old_pfn, old_khva);
+		gpc_unmap(old_pfn, old_khva);
 	}
 }
-EXPORT_SYMBOL_GPL(kvm_gpc_deactivate);