Merge tag 'kvmarm-6.2' of https://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for 6.2

- Enable the per-vcpu dirty-ring tracking mechanism, together with an
  option to keep the good old dirty log around for pages that are
  dirtied by something other than a vcpu.

- Switch to the relaxed parallel fault handling, using RCU to delay
  page table reclaim and giving better performance under load.

- Relax the MTE ABI, allowing a VMM to use the MAP_SHARED mapping
  option, which multi-process VMMs such as crosvm rely on.

- Merge the pKVM shadow vcpu state tracking that allows the hypervisor
  to have its own view of a vcpu, keeping that state private.

- Add support for the PMUv3p5 architecture revision, bringing support
  for 64bit counters on systems that support it, and fix the
  no-quite-compliant CHAIN-ed counter support for the machines that
  actually exist out there.

- Fix a handful of minor issues around 52bit VA/PA support (64kB pages
  only) as a prefix of the oncoming support for 4kB and 16kB pages.

- Add/Enable/Fix a bunch of selftests covering memslots, breakpoints,
  stage-2 faults and access tracking. You name it, we got it, we
  probably broke it.

- Pick a small set of documentation and spelling fixes, because no
  good merge window would be complete without those.

As a side effect, this tag also drags:

- The 'kvmarm-fixes-6.1-3' tag as a dependency to the dirty-ring
  series

- A shared branch with the arm64 tree that repaints all the system
  registers to match the ARM ARM's naming, and resulting in
  interesting conflicts

8 files changed, 307 insertions, 74 deletions

diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 0de4aabc0c76..316de70db91d 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -11,6 +11,7 @@
 #include "guest_modes.h"
 #include "kvm_util.h"
 #include "processor.h"
+#include <linux/bitfield.h>
 
 #define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN	0xac0000
 
@@ -76,13 +77,15 @@ static uint64_t __maybe_unused ptrs_per_pte(struct kvm_vm *vm)
 
 void virt_arch_pgd_alloc(struct kvm_vm *vm)
 {
-	if (!vm->pgd_created) {
-		vm_paddr_t paddr = vm_phy_pages_alloc(vm,
-			page_align(vm, ptrs_per_pgd(vm) * 8) / vm->page_size,
-			KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
-		vm->pgd = paddr;
-		vm->pgd_created = true;
-	}
+	size_t nr_pages = page_align(vm, ptrs_per_pgd(vm) * 8) / vm->page_size;
+
+	if (vm->pgd_created)
+		return;
+
+	vm->pgd = vm_phy_pages_alloc(vm, nr_pages,
+				     KVM_GUEST_PAGE_TABLE_MIN_PADDR,
+				     vm->memslots[MEM_REGION_PT]);
+	vm->pgd_created = true;
 }
 
 static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
@@ -133,12 +136,12 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 
 void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
 {
-	uint64_t attr_idx = 4; /* NORMAL (See DEFAULT_MAIR_EL1) */
+	uint64_t attr_idx = MT_NORMAL;
 
 	_virt_pg_map(vm, vaddr, paddr, attr_idx);
 }
 
-vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva)
 {
 	uint64_t *ptep;
 
@@ -169,11 +172,18 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 		TEST_FAIL("Page table levels must be 2, 3, or 4");
 	}
 
-	return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1));
+	return ptep;
 
 unmapped_gva:
 	TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva);
-	exit(1);
+	exit(EXIT_FAILURE);
+}
+
+vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	uint64_t *ptep = virt_get_pte_hva(vm, gva);
+
+	return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1));
 }
 
 static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t page, int level)
@@ -318,13 +328,16 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent)
 struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 				  struct kvm_vcpu_init *init, void *guest_code)
 {
-	size_t stack_size = vm->page_size == 4096 ?
-					DEFAULT_STACK_PGS * vm->page_size :
-					vm->page_size;
-	uint64_t stack_vaddr = vm_vaddr_alloc(vm, stack_size,
-					      DEFAULT_ARM64_GUEST_STACK_VADDR_MIN);
+	size_t stack_size;
+	uint64_t stack_vaddr;
 	struct kvm_vcpu *vcpu = __vm_vcpu_add(vm, vcpu_id);
 
+	stack_size = vm->page_size == 4096 ? DEFAULT_STACK_PGS * vm->page_size :
+					     vm->page_size;
+	stack_vaddr = __vm_vaddr_alloc(vm, stack_size,
+				       DEFAULT_ARM64_GUEST_STACK_VADDR_MIN,
+				       MEM_REGION_DATA);
+
 	aarch64_vcpu_setup(vcpu, init);
 
 	vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size);
@@ -428,8 +441,8 @@ unexpected_exception:
 
 void vm_init_descriptor_tables(struct kvm_vm *vm)
 {
-	vm->handlers = vm_vaddr_alloc(vm, sizeof(struct handlers),
-			vm->page_size);
+	vm->handlers = __vm_vaddr_alloc(vm, sizeof(struct handlers),
+					vm->page_size, MEM_REGION_DATA);
 
 	*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
 }
@@ -486,9 +499,9 @@ void aarch64_get_supported_page_sizes(uint32_t ipa,
 	err = ioctl(vcpu_fd, KVM_GET_ONE_REG, &reg);
 	TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd));
 
-	*ps4k = ((val >> 28) & 0xf) != 0xf;
-	*ps64k = ((val >> 24) & 0xf) == 0;
-	*ps16k = ((val >> 20) & 0xf) != 0;
+	*ps4k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_TGRAN4), val) != 0xf;
+	*ps64k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_TGRAN64), val) == 0;
+	*ps16k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_TGRAN16), val) != 0;
 
 	close(vcpu_fd);
 	close(vm_fd);
diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c
index d71a9a5974de..820ac2d08c98 100644
--- a/tools/testing/selftests/kvm/lib/elf.c
+++ b/tools/testing/selftests/kvm/lib/elf.c
@@ -161,7 +161,8 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename)
 		seg_vend |= vm->page_size - 1;
 		size_t seg_size = seg_vend - seg_vstart + 1;
 
-		vm_vaddr_t vaddr = vm_vaddr_alloc(vm, seg_size, seg_vstart);
+		vm_vaddr_t vaddr = __vm_vaddr_alloc(vm, seg_size, seg_vstart,
+						    MEM_REGION_CODE);
 		TEST_ASSERT(vaddr == seg_vstart, "Unable to allocate "
 			"virtual memory for segment at requested min addr,\n"
 			"  segment idx: %u\n"
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 1d26a2160178..e9607eb089be 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -186,13 +186,10 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
 _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
 	       "Missing new mode params?");
 
-struct kvm_vm *____vm_create(enum vm_guest_mode mode, uint64_t nr_pages)
+struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 {
 	struct kvm_vm *vm;
 
-	pr_debug("%s: mode='%s' pages='%ld'\n", __func__,
-		 vm_guest_mode_string(mode), nr_pages);
-
 	vm = calloc(1, sizeof(*vm));
 	TEST_ASSERT(vm != NULL, "Insufficient Memory");
 
@@ -288,9 +285,6 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode, uint64_t nr_pages)
 
 	/* Allocate and setup memory for guest. */
 	vm->vpages_mapped = sparsebit_alloc();
-	if (nr_pages != 0)
-		vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-					    0, 0, nr_pages, 0);
 
 	return vm;
 }
@@ -337,8 +331,16 @@ struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
 						 nr_extra_pages);
 	struct userspace_mem_region *slot0;
 	struct kvm_vm *vm;
+	int i;
+
+	pr_debug("%s: mode='%s' pages='%ld'\n", __func__,
+		 vm_guest_mode_string(mode), nr_pages);
 
-	vm = ____vm_create(mode, nr_pages);
+	vm = ____vm_create(mode);
+
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, 0);
+	for (i = 0; i < NR_MEM_REGIONS; i++)
+		vm->memslots[i] = 0;
 
 	kvm_vm_elf_load(vm, program_invocation_name);
 
@@ -649,6 +651,12 @@ static void __vm_mem_region_delete(struct kvm_vm *vm,
 	sparsebit_free(&region->unused_phy_pages);
 	ret = munmap(region->mmap_start, region->mmap_size);
 	TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
+	if (region->fd >= 0) {
+		/* There's an extra map when using shared memory. */
+		ret = munmap(region->mmap_alias, region->mmap_size);
+		TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
+		close(region->fd);
+	}
 
 	free(region);
 }
@@ -986,6 +994,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 			    vm_mem_backing_src_alias(src_type)->name);
 	}
 
+	region->backing_src_type = src_type;
 	region->unused_phy_pages = sparsebit_alloc();
 	sparsebit_set_num(region->unused_phy_pages,
 		guest_paddr >> vm->page_shift, npages);
@@ -1280,32 +1289,15 @@ va_found:
 	return pgidx_start * vm->page_size;
 }
 
-/*
- * VM Virtual Address Allocate
- *
- * Input Args:
- *   vm - Virtual Machine
- *   sz - Size in bytes
- *   vaddr_min - Minimum starting virtual address
- *
- * Output Args: None
- *
- * Return:
- *   Starting guest virtual address
- *
- * Allocates at least sz bytes within the virtual address space of the vm
- * given by vm.  The allocated bytes are mapped to a virtual address >=
- * the address given by vaddr_min.  Note that each allocation uses a
- * a unique set of pages, with the minimum real allocation being at least
- * a page.
- */
-vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min)
+vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
+			    enum kvm_mem_region_type type)
 {
 	uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0);
 
 	virt_pgd_alloc(vm);
 	vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages,
-					      KVM_UTIL_MIN_PFN * vm->page_size, 0);
+					      KVM_UTIL_MIN_PFN * vm->page_size,
+					      vm->memslots[type]);
 
 	/*
 	 * Find an unused range of virtual page addresses of at least
@@ -1326,6 +1318,30 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min)
 }
 
 /*
+ * VM Virtual Address Allocate
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   sz - Size in bytes
+ *   vaddr_min - Minimum starting virtual address
+ *
+ * Output Args: None
+ *
+ * Return:
+ *   Starting guest virtual address
+ *
+ * Allocates at least sz bytes within the virtual address space of the vm
+ * given by vm.  The allocated bytes are mapped to a virtual address >=
+ * the address given by vaddr_min.  Note that each allocation uses a
+ * a unique set of pages, with the minimum real allocation being at least
+ * a page. The allocated physical space comes from the TEST_DATA memory region.
+ */
+vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min)
+{
+	return __vm_vaddr_alloc(vm, sz, vaddr_min, MEM_REGION_TEST_DATA);
+}
+
+/*
  * VM Virtual Address Allocate Pages
  *
  * Input Args:
@@ -1344,6 +1360,11 @@ vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages)
 	return vm_vaddr_alloc(vm, nr_pages * getpagesize(), KVM_UTIL_MIN_VADDR);
 }
 
+vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm, enum kvm_mem_region_type type)
+{
+	return __vm_vaddr_alloc(vm, getpagesize(), KVM_UTIL_MIN_VADDR, type);
+}
+
 /*
  * VM Virtual Address Allocate Page
  *
@@ -1570,7 +1591,7 @@ struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vcpu *vcpu)
 
 void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu)
 {
-	uint32_t page_size = vcpu->vm->page_size;
+	uint32_t page_size = getpagesize();
 	uint32_t size = vcpu->vm->dirty_ring_size;
 
 	TEST_ASSERT(size > 0, "Should enable dirty ring first");
@@ -1911,7 +1932,8 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
 
 vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm)
 {
-	return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
+	return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR,
+				 vm->memslots[MEM_REGION_PT]);
 }
 
 /*
diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c
index 2de8a5d527b3..5f1d3173c238 100644
--- a/tools/testing/selftests/kvm/lib/memstress.c
+++ b/tools/testing/selftests/kvm/lib/memstress.c
@@ -292,6 +292,7 @@ void memstress_start_vcpu_threads(int nr_vcpus,
 
 	vcpu_thread_fn = vcpu_fn;
 	WRITE_ONCE(all_vcpu_threads_running, false);
+	WRITE_ONCE(memstress_args.stop_vcpus, false);
 
 	for (i = 0; i < nr_vcpus; i++) {
 		struct vcpu_thread *vcpu = &vcpu_threads[i];
@@ -314,6 +315,8 @@ void memstress_join_vcpu_threads(int nr_vcpus)
 {
 	int i;
 
+	WRITE_ONCE(memstress_args.stop_vcpus, true);
+
 	for (i = 0; i < nr_vcpus; i++)
 		pthread_join(vcpu_threads[i].thread, NULL);
 }
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index 604478151212..d146ca71e0c0 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -55,13 +55,15 @@ static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva, int level)
 
 void virt_arch_pgd_alloc(struct kvm_vm *vm)
 {
-	if (!vm->pgd_created) {
-		vm_paddr_t paddr = vm_phy_pages_alloc(vm,
-			page_align(vm, ptrs_per_pte(vm) * 8) / vm->page_size,
-			KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
-		vm->pgd = paddr;
-		vm->pgd_created = true;
-	}
+	size_t nr_pages = page_align(vm, ptrs_per_pte(vm) * 8) / vm->page_size;
+
+	if (vm->pgd_created)
+		return;
+
+	vm->pgd = vm_phy_pages_alloc(vm, nr_pages,
+				     KVM_GUEST_PAGE_TABLE_MIN_PADDR,
+				     vm->memslots[MEM_REGION_PT]);
+	vm->pgd_created = true;
 }
 
 void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
@@ -279,15 +281,18 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 				  void *guest_code)
 {
 	int r;
-	size_t stack_size = vm->page_size == 4096 ?
-					DEFAULT_STACK_PGS * vm->page_size :
-					vm->page_size;
-	unsigned long stack_vaddr = vm_vaddr_alloc(vm, stack_size,
-					DEFAULT_RISCV_GUEST_STACK_VADDR_MIN);
+	size_t stack_size;
+	unsigned long stack_vaddr;
 	unsigned long current_gp = 0;
 	struct kvm_mp_state mps;
 	struct kvm_vcpu *vcpu;
 
+	stack_size = vm->page_size == 4096 ? DEFAULT_STACK_PGS * vm->page_size :
+					     vm->page_size;
+	stack_vaddr = __vm_vaddr_alloc(vm, stack_size,
+				       DEFAULT_RISCV_GUEST_STACK_VADDR_MIN,
+				       MEM_REGION_DATA);
+
 	vcpu = __vm_vcpu_add(vm, vcpu_id);
 	riscv_vcpu_mmu_setup(vcpu);
 
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index 89d7340d9cbd..15945121daf1 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -21,7 +21,8 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm)
 		return;
 
 	paddr = vm_phy_pages_alloc(vm, PAGES_PER_REGION,
-				   KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
+				   KVM_GUEST_PAGE_TABLE_MIN_PADDR,
+				   vm->memslots[MEM_REGION_PT]);
 	memset(addr_gpa2hva(vm, paddr), 0xff, PAGES_PER_REGION * vm->page_size);
 
 	vm->pgd = paddr;
@@ -167,8 +168,9 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 	TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x",
 		    vm->page_size);
 
-	stack_vaddr = vm_vaddr_alloc(vm, stack_size,
-				     DEFAULT_GUEST_STACK_VADDR_MIN);
+	stack_vaddr = __vm_vaddr_alloc(vm, stack_size,
+				       DEFAULT_GUEST_STACK_VADDR_MIN,
+				       MEM_REGION_DATA);
 
 	vcpu = __vm_vcpu_add(vm, vcpu_id);
 
diff --git a/tools/testing/selftests/kvm/lib/userfaultfd_util.c b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
new file mode 100644
index 000000000000..92cef20902f1
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM userfaultfd util
+ * Adapted from demand_paging_test.c
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ * Copyright (C) 2019-2022 Google LLC
+ */
+
+#define _GNU_SOURCE /* for pipe2 */
+
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#include <poll.h>
+#include <pthread.h>
+#include <linux/userfaultfd.h>
+#include <sys/syscall.h>
+
+#include "kvm_util.h"
+#include "test_util.h"
+#include "memstress.h"
+#include "userfaultfd_util.h"
+
+#ifdef __NR_userfaultfd
+
+static void *uffd_handler_thread_fn(void *arg)
+{
+	struct uffd_desc *uffd_desc = (struct uffd_desc *)arg;
+	int uffd = uffd_desc->uffd;
+	int pipefd = uffd_desc->pipefds[0];
+	useconds_t delay = uffd_desc->delay;
+	int64_t pages = 0;
+	struct timespec start;
+	struct timespec ts_diff;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	while (1) {
+		struct uffd_msg msg;
+		struct pollfd pollfd[2];
+		char tmp_chr;
+		int r;
+
+		pollfd[0].fd = uffd;
+		pollfd[0].events = POLLIN;
+		pollfd[1].fd = pipefd;
+		pollfd[1].events = POLLIN;
+
+		r = poll(pollfd, 2, -1);
+		switch (r) {
+		case -1:
+			pr_info("poll err");
+			continue;
+		case 0:
+			continue;
+		case 1:
+			break;
+		default:
+			pr_info("Polling uffd returned %d", r);
+			return NULL;
+		}
+
+		if (pollfd[0].revents & POLLERR) {
+			pr_info("uffd revents has POLLERR");
+			return NULL;
+		}
+
+		if (pollfd[1].revents & POLLIN) {
+			r = read(pollfd[1].fd, &tmp_chr, 1);
+			TEST_ASSERT(r == 1,
+				    "Error reading pipefd in UFFD thread\n");
+			return NULL;
+		}
+
+		if (!(pollfd[0].revents & POLLIN))
+			continue;
+
+		r = read(uffd, &msg, sizeof(msg));
+		if (r == -1) {
+			if (errno == EAGAIN)
+				continue;
+			pr_info("Read of uffd got errno %d\n", errno);
+			return NULL;
+		}
+
+		if (r != sizeof(msg)) {
+			pr_info("Read on uffd returned unexpected size: %d bytes", r);
+			return NULL;
+		}
+
+		if (!(msg.event & UFFD_EVENT_PAGEFAULT))
+			continue;
+
+		if (delay)
+			usleep(delay);
+		r = uffd_desc->handler(uffd_desc->uffd_mode, uffd, &msg);
+		if (r < 0)
+			return NULL;
+		pages++;
+	}
+
+	ts_diff = timespec_elapsed(start);
+	PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n",
+		       pages, ts_diff.tv_sec, ts_diff.tv_nsec,
+		       pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
+
+	return NULL;
+}
+
+struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
+					   void *hva, uint64_t len,
+					   uffd_handler_t handler)
+{
+	struct uffd_desc *uffd_desc;
+	bool is_minor = (uffd_mode == UFFDIO_REGISTER_MODE_MINOR);
+	int uffd;
+	struct uffdio_api uffdio_api;
+	struct uffdio_register uffdio_register;
+	uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY;
+	int ret;
+
+	PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n",
+		       is_minor ? "MINOR" : "MISSING",
+		       is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY");
+
+	uffd_desc = malloc(sizeof(struct uffd_desc));
+	TEST_ASSERT(uffd_desc, "malloc failed");
+
+	/* In order to get minor faults, prefault via the alias. */
+	if (is_minor)
+		expected_ioctls = ((uint64_t) 1) << _UFFDIO_CONTINUE;
+
+	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+	TEST_ASSERT(uffd >= 0, "uffd creation failed, errno: %d", errno);
+
+	uffdio_api.api = UFFD_API;
+	uffdio_api.features = 0;
+	TEST_ASSERT(ioctl(uffd, UFFDIO_API, &uffdio_api) != -1,
+		    "ioctl UFFDIO_API failed: %" PRIu64,
+		    (uint64_t)uffdio_api.api);
+
+	uffdio_register.range.start = (uint64_t)hva;
+	uffdio_register.range.len = len;
+	uffdio_register.mode = uffd_mode;
+	TEST_ASSERT(ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) != -1,
+		    "ioctl UFFDIO_REGISTER failed");
+	TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) ==
+		    expected_ioctls, "missing userfaultfd ioctls");
+
+	ret = pipe2(uffd_desc->pipefds, O_CLOEXEC | O_NONBLOCK);
+	TEST_ASSERT(!ret, "Failed to set up pipefd");
+
+	uffd_desc->uffd_mode = uffd_mode;
+	uffd_desc->uffd = uffd;
+	uffd_desc->delay = delay;
+	uffd_desc->handler = handler;
+	pthread_create(&uffd_desc->thread, NULL, uffd_handler_thread_fn,
+		       uffd_desc);
+
+	PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n",
+		       hva, hva + len);
+
+	return uffd_desc;
+}
+
+void uffd_stop_demand_paging(struct uffd_desc *uffd)
+{
+	char c = 0;
+	int ret;
+
+	ret = write(uffd->pipefds[1], &c, 1);
+	TEST_ASSERT(ret == 1, "Unable to write to pipefd");
+
+	ret = pthread_join(uffd->thread, NULL);
+	TEST_ASSERT(ret == 0, "Pthread_join failed.");
+
+	close(uffd->uffd);
+
+	close(uffd->pipefds[1]);
+	close(uffd->pipefds[0]);
+
+	free(uffd);
+}
+
+#endif /* __NR_userfaultfd */
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index d532c20c74fd..c5c46f5b767c 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -499,7 +499,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt)
 {
 	if (!vm->gdt)
-		vm->gdt = vm_vaddr_alloc_page(vm);
+		vm->gdt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA);
 
 	dt->base = vm->gdt;
 	dt->limit = getpagesize();
@@ -509,7 +509,7 @@ static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp,
 				int selector)
 {
 	if (!vm->tss)
-		vm->tss = vm_vaddr_alloc_page(vm);
+		vm->tss = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA);
 
 	memset(segp, 0, sizeof(*segp));
 	segp->base = vm->tss;
@@ -599,8 +599,9 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 	vm_vaddr_t stack_vaddr;
 	struct kvm_vcpu *vcpu;
 
-	stack_vaddr = vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(),
-				     DEFAULT_GUEST_STACK_VADDR_MIN);
+	stack_vaddr = __vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(),
+				       DEFAULT_GUEST_STACK_VADDR_MIN,
+				       MEM_REGION_DATA);
 
 	vcpu = __vm_vcpu_add(vm, vcpu_id);
 	vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid());
@@ -1093,8 +1094,8 @@ void vm_init_descriptor_tables(struct kvm_vm *vm)
 	extern void *idt_handlers;
 	int i;
 
-	vm->idt = vm_vaddr_alloc_page(vm);
-	vm->handlers = vm_vaddr_alloc_page(vm);
+	vm->idt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA);
+	vm->handlers = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA);
 	/* Handlers have the same address in both address spaces.*/
 	for (i = 0; i < NUM_INTERRUPTS; i++)
 		set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0,