Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull x86 kvm updates from Paolo Bonzini:
 "x86:

   - KVM currently invalidates the entirety of the page tables, not just
     those for the memslot being touched, when a memslot is moved or
     deleted.

     This does not traditionally have particularly noticeable overhead,
     but Intel's TDX will require the guest to re-accept private pages
     if they are dropped from the secure EPT, which is a non starter.

     Actually, the only reason why this is not already being done is a
     bug which was never fully investigated and caused VM instability
     with assigned GeForce GPUs, so allow userspace to opt into the new
     behavior.

   - Advertise AVX10.1 to userspace (effectively prep work for the
     "real" AVX10 functionality that is on the horizon)

   - Rework common MSR handling code to suppress errors on userspace
     accesses to unsupported-but-advertised MSRs

     This will allow removing (almost?) all of KVM's exemptions for
     userspace access to MSRs that shouldn't exist based on the vCPU
     model (the actual cleanup is non-trivial future work)

   - Rework KVM's handling of x2APIC ICR, again, because AMD (x2AVIC)
     splits the 64-bit value into the legacy ICR and ICR2 storage,
     whereas Intel (APICv) stores the entire 64-bit value at the ICR
     offset

   - Fix a bug where KVM would fail to exit to userspace if one was
     triggered by a fastpath exit handler

   - Add fastpath handling of HLT VM-Exit to expedite re-entering the
     guest when there's already a pending wake event at the time of the
     exit

   - Fix a WARN caused by RSM entering a nested guest from SMM with
     invalid guest state, by forcing the vCPU out of guest mode prior to
     signalling SHUTDOWN (the SHUTDOWN hits the VM altogether, not the
     nested guest)

   - Overhaul the "unprotect and retry" logic to more precisely identify
     cases where retrying is actually helpful, and to harden all retry
     paths against putting the guest into an infinite retry loop

   - Add support for yielding, e.g. to honor NEED_RESCHED, when zapping
     rmaps in the shadow MMU

   - Refactor pieces of the shadow MMU related to aging SPTEs in
     prepartion for adding multi generation LRU support in KVM

   - Don't stuff the RSB after VM-Exit when RETPOLINE=y and AutoIBRS is
     enabled, i.e. when the CPU has already flushed the RSB

   - Trace the per-CPU host save area as a VMCB pointer to improve
     readability and cleanup the retrieval of the SEV-ES host save area

   - Remove unnecessary accounting of temporary nested VMCB related
     allocations

   - Set FINAL/PAGE in the page fault error code for EPT violations if
     and only if the GVA is valid. If the GVA is NOT valid, there is no
     guest-side page table walk and so stuffing paging related metadata
     is nonsensical

   - Fix a bug where KVM would incorrectly synthesize a nested VM-Exit
     instead of emulating posted interrupt delivery to L2

   - Add a lockdep assertion to detect unsafe accesses of vmcs12
     structures

   - Harden eVMCS loading against an impossible NULL pointer deref
     (really truly should be impossible)

   - Minor SGX fix and a cleanup

   - Misc cleanups

  Generic:

   - Register KVM's cpuhp and syscore callbacks when enabling
     virtualization in hardware, as the sole purpose of said callbacks
     is to disable and re-enable virtualization as needed

   - Enable virtualization when KVM is loaded, not right before the
     first VM is created

     Together with the previous change, this simplifies a lot the logic
     of the callbacks, because their very existence implies
     virtualization is enabled

   - Fix a bug that results in KVM prematurely exiting to userspace for
     coalesced MMIO/PIO in many cases, clean up the related code, and
     add a testcase

   - Fix a bug in kvm_clear_guest() where it would trigger a buffer
     overflow _if_ the gpa+len crosses a page boundary, which thankfully
     is guaranteed to not happen in the current code base. Add WARNs in
     more helpers that read/write guest memory to detect similar bugs

  Selftests:

   - Fix a goof that caused some Hyper-V tests to be skipped when run on
     bare metal, i.e. NOT in a VM

   - Add a regression test for KVM's handling of SHUTDOWN for an SEV-ES
     guest

   - Explicitly include one-off assets in .gitignore. Past Sean was
     completely wrong about not being able to detect missing .gitignore
     entries

   - Verify userspace single-stepping works when KVM happens to handle a
     VM-Exit in its fastpath

   - Misc cleanups"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (127 commits)
  Documentation: KVM: fix warning in "make htmldocs"
  s390: Enable KVM_S390_UCONTROL config in debug_defconfig
  selftests: kvm: s390: Add VM run test case
  KVM: SVM: let alternatives handle the cases when RSB filling is required
  KVM: VMX: Set PFERR_GUEST_{FINAL,PAGE}_MASK if and only if the GVA is valid
  KVM: x86/mmu: Use KVM_PAGES_PER_HPAGE() instead of an open coded equivalent
  KVM: x86/mmu: Add KVM_RMAP_MANY to replace open coded '1' and '1ul' literals
  KVM: x86/mmu: Fold mmu_spte_age() into kvm_rmap_age_gfn_range()
  KVM: x86/mmu: Morph kvm_handle_gfn_range() into an aging specific helper
  KVM: x86/mmu: Honor NEED_RESCHED when zapping rmaps and blocking is allowed
  KVM: x86/mmu: Add a helper to walk and zap rmaps for a memslot
  KVM: x86/mmu: Plumb a @can_yield parameter into __walk_slot_rmaps()
  KVM: x86/mmu: Move walk_slot_rmaps() up near for_each_slot_rmap_range()
  KVM: x86/mmu: WARN on MMIO cache hit when emulating write-protected gfn
  KVM: x86/mmu: Detect if unprotect will do anything based on invalid_list
  KVM: x86/mmu: Subsume kvm_mmu_unprotect_page() into the and_retry() version
  KVM: x86: Rename reexecute_instruction()=>kvm_unprotect_and_retry_on_failure()
  KVM: x86: Update retry protection fields when forcing retry on emulation failure
  KVM: x86: Apply retry protection to "unprotect on failure" path
  KVM: x86: Check EMULTYPE_WRITE_PF_TO_SP before unprotecting gfn
  ...

30 files changed, 1195 insertions, 203 deletions

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 6d9381d60172..7f57abf936e7 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -5,3 +5,7 @@
 !*.h
 !*.S
 !*.sh
+!.gitignore
+!config
+!settings
+!Makefile
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 0c4b254ab56b..960cf6a77198 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -130,6 +130,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test
 TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test
 TEST_GEN_PROGS_x86_64 += x86_64/recalc_apic_map_test
 TEST_GEN_PROGS_x86_64 += access_tracking_perf_test
+TEST_GEN_PROGS_x86_64 += coalesced_io_test
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
@@ -167,6 +168,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/vpmu_counter_access
 TEST_GEN_PROGS_aarch64 += aarch64/no-vgic-v3
 TEST_GEN_PROGS_aarch64 += access_tracking_perf_test
 TEST_GEN_PROGS_aarch64 += arch_timer
+TEST_GEN_PROGS_aarch64 += coalesced_io_test
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
 TEST_GEN_PROGS_aarch64 += dirty_log_perf_test
@@ -188,6 +190,7 @@ TEST_GEN_PROGS_s390x += s390x/tprot
 TEST_GEN_PROGS_s390x += s390x/cmma_test
 TEST_GEN_PROGS_s390x += s390x/debug_test
 TEST_GEN_PROGS_s390x += s390x/shared_zeropage_test
+TEST_GEN_PROGS_s390x += s390x/ucontrol_test
 TEST_GEN_PROGS_s390x += demand_paging_test
 TEST_GEN_PROGS_s390x += dirty_log_test
 TEST_GEN_PROGS_s390x += guest_print_test
@@ -200,6 +203,7 @@ TEST_GEN_PROGS_s390x += kvm_binary_stats_test
 TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test
 TEST_GEN_PROGS_riscv += riscv/ebreak_test
 TEST_GEN_PROGS_riscv += arch_timer
+TEST_GEN_PROGS_riscv += coalesced_io_test
 TEST_GEN_PROGS_riscv += demand_paging_test
 TEST_GEN_PROGS_riscv += dirty_log_test
 TEST_GEN_PROGS_riscv += get-reg-list
diff --git a/tools/testing/selftests/kvm/coalesced_io_test.c b/tools/testing/selftests/kvm/coalesced_io_test.c
new file mode 100644
index 000000000000..60cb25454899
--- /dev/null
+++ b/tools/testing/selftests/kvm/coalesced_io_test.c
@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include <linux/sizes.h>
+
+#include <kvm_util.h>
+#include <processor.h>
+
+#include "ucall_common.h"
+
+struct kvm_coalesced_io {
+	struct kvm_coalesced_mmio_ring *ring;
+	uint32_t ring_size;
+	uint64_t mmio_gpa;
+	uint64_t *mmio;
+
+	/*
+	 * x86-only, but define pio_port for all architectures to minimize the
+	 * amount of #ifdeffery and complexity, without having to sacrifice
+	 * verbose error messages.
+	 */
+	uint8_t pio_port;
+};
+
+static struct kvm_coalesced_io kvm_builtin_io_ring;
+
+#ifdef __x86_64__
+static const int has_pio = 1;
+#else
+static const int has_pio = 0;
+#endif
+
+static void guest_code(struct kvm_coalesced_io *io)
+{
+	int i, j;
+
+	for (;;) {
+		for (j = 0; j < 1 + has_pio; j++) {
+			/*
+			 * KVM always leaves one free entry, i.e. exits to
+			 * userspace before the last entry is filled.
+			 */
+			for (i = 0; i < io->ring_size - 1; i++) {
+#ifdef __x86_64__
+				if (i & 1)
+					outl(io->pio_port, io->pio_port + i);
+				else
+#endif
+					WRITE_ONCE(*io->mmio, io->mmio_gpa + i);
+			}
+#ifdef __x86_64__
+			if (j & 1)
+				outl(io->pio_port, io->pio_port + i);
+			else
+#endif
+				WRITE_ONCE(*io->mmio, io->mmio_gpa + i);
+		}
+		GUEST_SYNC(0);
+
+		WRITE_ONCE(*io->mmio, io->mmio_gpa + i);
+#ifdef __x86_64__
+		outl(io->pio_port, io->pio_port + i);
+#endif
+	}
+}
+
+static void vcpu_run_and_verify_io_exit(struct kvm_vcpu *vcpu,
+					struct kvm_coalesced_io *io,
+					uint32_t ring_start,
+					uint32_t expected_exit)
+{
+	const bool want_pio = expected_exit == KVM_EXIT_IO;
+	struct kvm_coalesced_mmio_ring *ring = io->ring;
+	struct kvm_run *run = vcpu->run;
+	uint32_t pio_value;
+
+	WRITE_ONCE(ring->first, ring_start);
+	WRITE_ONCE(ring->last, ring_start);
+
+	vcpu_run(vcpu);
+
+	/*
+	 * Annoyingly, reading PIO data is safe only for PIO exits, otherwise
+	 * data_offset is garbage, e.g. an MMIO gpa.
+	 */
+	if (run->exit_reason == KVM_EXIT_IO)
+		pio_value = *(uint32_t *)((void *)run + run->io.data_offset);
+	else
+		pio_value = 0;
+
+	TEST_ASSERT((!want_pio && (run->exit_reason == KVM_EXIT_MMIO && run->mmio.is_write &&
+				   run->mmio.phys_addr == io->mmio_gpa && run->mmio.len == 8 &&
+				   *(uint64_t *)run->mmio.data == io->mmio_gpa + io->ring_size - 1)) ||
+		    (want_pio  && (run->exit_reason == KVM_EXIT_IO && run->io.port == io->pio_port &&
+				   run->io.direction == KVM_EXIT_IO_OUT && run->io.count == 1 &&
+				   pio_value == io->pio_port + io->ring_size - 1)),
+		    "For start = %u, expected exit on %u-byte %s write 0x%llx = %lx, got exit_reason = %u (%s)\n  "
+		    "(MMIO addr = 0x%llx, write = %u, len = %u, data = %lx)\n  "
+		    "(PIO port = 0x%x, write = %u, len = %u, count = %u, data = %x",
+		    ring_start, want_pio ? 4 : 8, want_pio ? "PIO" : "MMIO",
+		    want_pio ? (unsigned long long)io->pio_port : io->mmio_gpa,
+		    (want_pio ? io->pio_port : io->mmio_gpa) + io->ring_size - 1, run->exit_reason,
+		    run->exit_reason == KVM_EXIT_MMIO ? "MMIO" : run->exit_reason == KVM_EXIT_IO ? "PIO" : "other",
+		    run->mmio.phys_addr, run->mmio.is_write, run->mmio.len, *(uint64_t *)run->mmio.data,
+		    run->io.port, run->io.direction, run->io.size, run->io.count, pio_value);
+}
+
+static void vcpu_run_and_verify_coalesced_io(struct kvm_vcpu *vcpu,
+					     struct kvm_coalesced_io *io,
+					     uint32_t ring_start,
+					     uint32_t expected_exit)
+{
+	struct kvm_coalesced_mmio_ring *ring = io->ring;
+	int i;
+
+	vcpu_run_and_verify_io_exit(vcpu, io, ring_start, expected_exit);
+
+	TEST_ASSERT((ring->last + 1) % io->ring_size == ring->first,
+		    "Expected ring to be full (minus 1), first = %u, last = %u, max = %u, start = %u",
+		    ring->first, ring->last, io->ring_size, ring_start);
+
+	for (i = 0; i < io->ring_size - 1; i++) {
+		uint32_t idx = (ring->first + i) % io->ring_size;
+		struct kvm_coalesced_mmio *entry = &ring->coalesced_mmio[idx];
+
+#ifdef __x86_64__
+		if (i & 1)
+			TEST_ASSERT(entry->phys_addr == io->pio_port &&
+				    entry->len == 4 && entry->pio &&
+				    *(uint32_t *)entry->data == io->pio_port + i,
+				    "Wanted 4-byte port I/O 0x%x = 0x%x in entry %u, got %u-byte %s 0x%llx = 0x%x",
+				    io->pio_port, io->pio_port + i, i,
+				    entry->len, entry->pio ? "PIO" : "MMIO",
+				    entry->phys_addr, *(uint32_t *)entry->data);
+		else
+#endif
+			TEST_ASSERT(entry->phys_addr == io->mmio_gpa &&
+				    entry->len == 8 && !entry->pio,
+				    "Wanted 8-byte MMIO to 0x%lx = %lx in entry %u, got %u-byte %s 0x%llx = 0x%lx",
+				    io->mmio_gpa, io->mmio_gpa + i, i,
+				    entry->len, entry->pio ? "PIO" : "MMIO",
+				    entry->phys_addr, *(uint64_t *)entry->data);
+	}
+}
+
+static void test_coalesced_io(struct kvm_vcpu *vcpu,
+			      struct kvm_coalesced_io *io, uint32_t ring_start)
+{
+	struct kvm_coalesced_mmio_ring *ring = io->ring;
+
+	kvm_vm_register_coalesced_io(vcpu->vm, io->mmio_gpa, 8, false /* pio */);
+#ifdef __x86_64__
+	kvm_vm_register_coalesced_io(vcpu->vm, io->pio_port, 8, true /* pio */);
+#endif
+
+	vcpu_run_and_verify_coalesced_io(vcpu, io, ring_start, KVM_EXIT_MMIO);
+#ifdef __x86_64__
+	vcpu_run_and_verify_coalesced_io(vcpu, io, ring_start, KVM_EXIT_IO);
+#endif
+
+	/*
+	 * Verify ucall, which may use non-coalesced MMIO or PIO, generates an
+	 * immediate exit.
+	 */
+	WRITE_ONCE(ring->first, ring_start);
+	WRITE_ONCE(ring->last, ring_start);
+	vcpu_run(vcpu);
+	TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC);
+	TEST_ASSERT_EQ(ring->first, ring_start);
+	TEST_ASSERT_EQ(ring->last, ring_start);
+
+	/* Verify that non-coalesced MMIO/PIO generates an exit to userspace. */
+	kvm_vm_unregister_coalesced_io(vcpu->vm, io->mmio_gpa, 8, false /* pio */);
+	vcpu_run_and_verify_io_exit(vcpu, io, ring_start, KVM_EXIT_MMIO);
+
+#ifdef __x86_64__
+	kvm_vm_unregister_coalesced_io(vcpu->vm, io->pio_port, 8, true /* pio */);
+	vcpu_run_and_verify_io_exit(vcpu, io, ring_start, KVM_EXIT_IO);
+#endif
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	int i;
+
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_COALESCED_MMIO));
+
+#ifdef __x86_64__
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_COALESCED_PIO));
+#endif
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
+	kvm_builtin_io_ring = (struct kvm_coalesced_io) {
+		/*
+		 * The I/O ring is a kernel-allocated page whose address is
+		 * relative to each vCPU's run page, with the page offset
+		 * provided by KVM in the return of KVM_CAP_COALESCED_MMIO.
+		 */
+		.ring = (void *)vcpu->run +
+			(kvm_check_cap(KVM_CAP_COALESCED_MMIO) * getpagesize()),
+
+		/*
+		 * The size of the I/O ring is fixed, but KVM defines the sized
+		 * based on the kernel's PAGE_SIZE.  Thus, userspace must query
+		 * the host's page size at runtime to compute the ring size.
+		 */
+		.ring_size = (getpagesize() - sizeof(struct kvm_coalesced_mmio_ring)) /
+			     sizeof(struct kvm_coalesced_mmio),
+
+		/*
+		 * Arbitrary address+port (MMIO mustn't overlap memslots), with
+		 * the MMIO GPA identity mapped in the guest.
+		 */
+		.mmio_gpa = 4ull * SZ_1G,
+		.mmio = (uint64_t *)(4ull * SZ_1G),
+		.pio_port = 0x80,
+	};
+
+	virt_map(vm, (uint64_t)kvm_builtin_io_ring.mmio, kvm_builtin_io_ring.mmio_gpa, 1);
+
+	sync_global_to_guest(vm, kvm_builtin_io_ring);
+	vcpu_args_set(vcpu, 1, &kvm_builtin_io_ring);
+
+	for (i = 0; i < kvm_builtin_io_ring.ring_size; i++)
+		test_coalesced_io(vcpu, &kvm_builtin_io_ring, i);
+
+	kvm_vm_free(vm);
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/guest_print_test.c b/tools/testing/selftests/kvm/guest_print_test.c
index 8092c2d0f5d6..bcf582852db9 100644
--- a/tools/testing/selftests/kvm/guest_print_test.c
+++ b/tools/testing/selftests/kvm/guest_print_test.c
@@ -107,6 +107,21 @@ static void ucall_abort(const char *assert_msg, const char *expected_assert_msg)
 		    expected_assert_msg, &assert_msg[offset]);
 }
 
+/*
+ * Open code vcpu_run(), sans the UCALL_ABORT handling, so that intentional
+ * guest asserts guest can be verified instead of being reported as failures.
+ */
+static void do_vcpu_run(struct kvm_vcpu *vcpu)
+{
+	int r;
+
+	do {
+		r = __vcpu_run(vcpu);
+	} while (r == -1 && errno == EINTR);
+
+	TEST_ASSERT(!r, KVM_IOCTL_ERROR(KVM_RUN, r));
+}
+
 static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf,
 		     const char *expected_assert)
 {
@@ -114,7 +129,7 @@ static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf,
 	struct ucall uc;
 
 	while (1) {
-		vcpu_run(vcpu);
+		do_vcpu_run(vcpu);
 
 		TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON,
 			    "Unexpected exit reason: %u (%s),",
@@ -159,7 +174,7 @@ static void test_limits(void)
 
 	vm = vm_create_with_one_vcpu(&vcpu, guest_code_limits);
 	run = vcpu->run;
-	vcpu_run(vcpu);
+	do_vcpu_run(vcpu);
 
 	TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON,
 		    "Unexpected exit reason: %u (%s),",
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 63c2aaae51f3..bc7c242480d6 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -428,8 +428,6 @@ const char *vm_guest_mode_string(uint32_t i);
 void kvm_vm_free(struct kvm_vm *vmp);
 void kvm_vm_restart(struct kvm_vm *vmp);
 void kvm_vm_release(struct kvm_vm *vmp);
-int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
-		       size_t len);
 void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename);
 int kvm_memfd_alloc(size_t size, bool hugepages);
 
@@ -460,6 +458,32 @@ static inline uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm)
 	return __vm_ioctl(vm, KVM_RESET_DIRTY_RINGS, NULL);
 }
 
+static inline void kvm_vm_register_coalesced_io(struct kvm_vm *vm,
+						uint64_t address,
+						uint64_t size, bool pio)
+{
+	struct kvm_coalesced_mmio_zone zone = {
+		.addr = address,
+		.size = size,
+		.pio  = pio,
+	};
+
+	vm_ioctl(vm, KVM_REGISTER_COALESCED_MMIO, &zone);
+}
+
+static inline void kvm_vm_unregister_coalesced_io(struct kvm_vm *vm,
+						  uint64_t address,
+						  uint64_t size, bool pio)
+{
+	struct kvm_coalesced_mmio_zone zone = {
+		.addr = address,
+		.size = size,
+		.pio  = pio,
+	};
+
+	vm_ioctl(vm, KVM_UNREGISTER_COALESCED_MMIO, &zone);
+}
+
 static inline int vm_get_stats_fd(struct kvm_vm *vm)
 {
 	int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL);
diff --git a/tools/testing/selftests/kvm/include/s390x/debug_print.h b/tools/testing/selftests/kvm/include/s390x/debug_print.h
new file mode 100644
index 000000000000..1bf275631cc6
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/s390x/debug_print.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Definition for kernel virtual machines on s390x
+ *
+ * Copyright IBM Corp. 2024
+ *
+ * Authors:
+ *  Christoph Schlameuss <schlameuss@linux.ibm.com>
+ */
+
+#ifndef SELFTEST_KVM_DEBUG_PRINT_H
+#define SELFTEST_KVM_DEBUG_PRINT_H
+
+#include "asm/ptrace.h"
+#include "kvm_util.h"
+#include "sie.h"
+
+static inline void print_hex_bytes(const char *name, u64 addr, size_t len)
+{
+	u64 pos;
+
+	pr_debug("%s (%p)\n", name, (void *)addr);
+	pr_debug("            0/0x00---------|");
+	if (len > 8)
+		pr_debug(" 8/0x08---------|");
+	if (len > 16)
+		pr_debug(" 16/0x10--------|");
+	if (len > 24)
+		pr_debug(" 24/0x18--------|");
+	for (pos = 0; pos < len; pos += 8) {
+		if ((pos % 32) == 0)
+			pr_debug("\n %3lu 0x%.3lx ", pos, pos);
+		pr_debug(" %16lx", *((u64 *)(addr + pos)));
+	}
+	pr_debug("\n");
+}
+
+static inline void print_hex(const char *name, u64 addr)
+{
+	print_hex_bytes(name, addr, 512);
+}
+
+static inline void print_psw(struct kvm_run *run, struct kvm_s390_sie_block *sie_block)
+{
+	pr_debug("flags:0x%x psw:0x%.16llx:0x%.16llx exit:%u %s\n",
+		 run->flags,
+		 run->psw_mask, run->psw_addr,
+		 run->exit_reason, exit_reason_str(run->exit_reason));
+	pr_debug("sie_block psw:0x%.16llx:0x%.16llx\n",
+		 sie_block->psw_mask, sie_block->psw_addr);
+}
+
+static inline void print_run(struct kvm_run *run, struct kvm_s390_sie_block *sie_block)
+{
+	print_hex_bytes("run", (u64)run, 0x150);
+	print_hex("sie_block", (u64)sie_block);
+	print_psw(run, sie_block);
+}
+
+static inline void print_regs(struct kvm_run *run)
+{
+	struct kvm_sync_regs *sync_regs = &run->s.regs;
+
+	print_hex_bytes("GPRS", (u64)sync_regs->gprs, 8 * NUM_GPRS);
+	print_hex_bytes("ACRS", (u64)sync_regs->acrs, 4 * NUM_ACRS);
+	print_hex_bytes("CRS", (u64)sync_regs->crs, 8 * NUM_CRS);
+}
+
+#endif /* SELFTEST_KVM_DEBUG_PRINT_H */
diff --git a/tools/testing/selftests/kvm/include/s390x/processor.h b/tools/testing/selftests/kvm/include/s390x/processor.h
index 255c9b990f4c..481bd2fd6a32 100644
--- a/tools/testing/selftests/kvm/include/s390x/processor.h
+++ b/tools/testing/selftests/kvm/include/s390x/processor.h
@@ -21,6 +21,11 @@
 #define PAGE_PROTECT	0x200		/* HW read-only bit  */
 #define PAGE_NOEXEC	0x100		/* HW no-execute bit */
 
+/* Page size definitions */
+#define PAGE_SHIFT 12
+#define PAGE_SIZE BIT_ULL(PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE - 1))
+
 /* Is there a portable way to do this? */
 static inline void cpu_relax(void)
 {
diff --git a/tools/testing/selftests/kvm/include/s390x/sie.h b/tools/testing/selftests/kvm/include/s390x/sie.h
new file mode 100644
index 000000000000..160acd4a1db9
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/s390x/sie.h
@@ -0,0 +1,240 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Definition for kernel virtual machines on s390.
+ *
+ * Adapted copy of struct definition kvm_s390_sie_block from
+ * arch/s390/include/asm/kvm_host.h for use in userspace selftest programs.
+ *
+ * Copyright IBM Corp. 2008, 2024
+ *
+ * Authors:
+ *  Christoph Schlameuss <schlameuss@linux.ibm.com>
+ *  Carsten Otte <cotte@de.ibm.com>
+ */
+
+#ifndef SELFTEST_KVM_SIE_H
+#define SELFTEST_KVM_SIE_H
+
+#include <linux/types.h>
+
+struct kvm_s390_sie_block {
+#define CPUSTAT_STOPPED    0x80000000
+#define CPUSTAT_WAIT       0x10000000
+#define CPUSTAT_ECALL_PEND 0x08000000
+#define CPUSTAT_STOP_INT   0x04000000
+#define CPUSTAT_IO_INT     0x02000000
+#define CPUSTAT_EXT_INT    0x01000000
+#define CPUSTAT_RUNNING    0x00800000
+#define CPUSTAT_RETAINED   0x00400000
+#define CPUSTAT_TIMING_SUB 0x00020000
+#define CPUSTAT_SIE_SUB    0x00010000
+#define CPUSTAT_RRF        0x00008000
+#define CPUSTAT_SLSV       0x00004000
+#define CPUSTAT_SLSR       0x00002000
+#define CPUSTAT_ZARCH      0x00000800
+#define CPUSTAT_MCDS       0x00000100
+#define CPUSTAT_KSS        0x00000200
+#define CPUSTAT_SM         0x00000080
+#define CPUSTAT_IBS        0x00000040
+#define CPUSTAT_GED2       0x00000010
+#define CPUSTAT_G          0x00000008
+#define CPUSTAT_GED        0x00000004
+#define CPUSTAT_J          0x00000002
+#define CPUSTAT_P          0x00000001
+	__u32 cpuflags;			/* 0x0000 */
+	__u32: 1;			/* 0x0004 */
+	__u32 prefix : 18;
+	__u32: 1;
+	__u32 ibc : 12;
+	__u8	reserved08[4];		/* 0x0008 */
+#define PROG_IN_SIE BIT(0)
+	__u32	prog0c;			/* 0x000c */
+	union {
+		__u8	reserved10[16];	/* 0x0010 */
+		struct {
+			__u64	pv_handle_cpu;
+			__u64	pv_handle_config;
+		};
+	};
+#define PROG_BLOCK_SIE	BIT(0)
+#define PROG_REQUEST	BIT(1)
+	__u32	prog20;			/* 0x0020 */
+	__u8	reserved24[4];		/* 0x0024 */
+	__u64	cputm;			/* 0x0028 */
+	__u64	ckc;			/* 0x0030 */
+	__u64	epoch;			/* 0x0038 */
+	__u32	svcc;			/* 0x0040 */
+#define LCTL_CR0	0x8000
+#define LCTL_CR6	0x0200
+#define LCTL_CR9	0x0040
+#define LCTL_CR10	0x0020
+#define LCTL_CR11	0x0010
+#define LCTL_CR14	0x0002
+	__u16   lctl;			/* 0x0044 */
+	__s16	icpua;			/* 0x0046 */
+#define ICTL_OPEREXC	0x80000000
+#define ICTL_PINT	0x20000000
+#define ICTL_LPSW	0x00400000
+#define ICTL_STCTL	0x00040000
+#define ICTL_ISKE	0x00004000
+#define ICTL_SSKE	0x00002000
+#define ICTL_RRBE	0x00001000
+#define ICTL_TPROT	0x00000200
+	__u32	ictl;			/* 0x0048 */
+#define ECA_CEI		0x80000000
+#define ECA_IB		0x40000000
+#define ECA_SIGPI	0x10000000
+#define ECA_MVPGI	0x01000000
+#define ECA_AIV		0x00200000
+#define ECA_VX		0x00020000
+#define ECA_PROTEXCI	0x00002000
+#define ECA_APIE	0x00000008
+#define ECA_SII		0x00000001
+	__u32	eca;			/* 0x004c */
+#define ICPT_INST	0x04
+#define ICPT_PROGI	0x08
+#define ICPT_INSTPROGI	0x0C
+#define ICPT_EXTREQ	0x10
+#define ICPT_EXTINT	0x14
+#define ICPT_IOREQ	0x18
+#define ICPT_WAIT	0x1c
+#define ICPT_VALIDITY	0x20
+#define ICPT_STOP	0x28
+#define ICPT_OPEREXC	0x2C
+#define ICPT_PARTEXEC	0x38
+#define ICPT_IOINST	0x40
+#define ICPT_KSS	0x5c
+#define ICPT_MCHKREQ	0x60
+#define ICPT_INT_ENABLE	0x64
+#define ICPT_PV_INSTR	0x68
+#define ICPT_PV_NOTIFY	0x6c
+#define ICPT_PV_PREF	0x70
+	__u8	icptcode;		/* 0x0050 */
+	__u8	icptstatus;		/* 0x0051 */
+	__u16	ihcpu;			/* 0x0052 */
+	__u8	reserved54;		/* 0x0054 */
+#define IICTL_CODE_NONE		 0x00
+#define IICTL_CODE_MCHK		 0x01
+#define IICTL_CODE_EXT		 0x02
+#define IICTL_CODE_IO		 0x03
+#define IICTL_CODE_RESTART	 0x04
+#define IICTL_CODE_SPECIFICATION 0x10
+#define IICTL_CODE_OPERAND	 0x11
+	__u8	iictl;			/* 0x0055 */
+	__u16	ipa;			/* 0x0056 */
+	__u32	ipb;			/* 0x0058 */
+	__u32	scaoh;			/* 0x005c */
+#define FPF_BPBC	0x20
+	__u8	fpf;			/* 0x0060 */
+#define ECB_GS		0x40
+#define ECB_TE		0x10
+#define ECB_SPECI	0x08
+#define ECB_SRSI	0x04
+#define ECB_HOSTPROTINT	0x02
+#define ECB_PTF		0x01
+	__u8	ecb;			/* 0x0061 */
+#define ECB2_CMMA	0x80
+#define ECB2_IEP	0x20
+#define ECB2_PFMFI	0x08
+#define ECB2_ESCA	0x04
+#define ECB2_ZPCI_LSI	0x02
+	__u8	ecb2;			/* 0x0062 */
+#define ECB3_AISI	0x20
+#define ECB3_AISII	0x10
+#define ECB3_DEA	0x08
+#define ECB3_AES	0x04
+#define ECB3_RI		0x01
+	__u8	ecb3;			/* 0x0063 */
+#define ESCA_SCAOL_MASK ~0x3fU
+	__u32	scaol;			/* 0x0064 */
+	__u8	sdf;			/* 0x0068 */
+	__u8	epdx;			/* 0x0069 */
+	__u8	cpnc;			/* 0x006a */
+	__u8	reserved6b;		/* 0x006b */
+	__u32	todpr;			/* 0x006c */
+#define GISA_FORMAT1 0x00000001
+	__u32	gd;			/* 0x0070 */
+	__u8	reserved74[12];		/* 0x0074 */
+	__u64	mso;			/* 0x0080 */
+	__u64	msl;			/* 0x0088 */
+	__u64	psw_mask;		/* 0x0090 */
+	__u64	psw_addr;		/* 0x0098 */
+	__u64	gg14;			/* 0x00a0 */
+	__u64	gg15;			/* 0x00a8 */
+	__u8	reservedb0[8];		/* 0x00b0 */
+#define HPID_KVM	0x4
+#define HPID_VSIE	0x5
+	__u8	hpid;			/* 0x00b8 */
+	__u8	reservedb9[7];		/* 0x00b9 */
+	union {
+		struct {
+			__u32	eiparams;	/* 0x00c0 */
+			__u16	extcpuaddr;	/* 0x00c4 */
+			__u16	eic;		/* 0x00c6 */
+		};
+		__u64	mcic;			/* 0x00c0 */
+	} __packed;
+	__u32	reservedc8;		/* 0x00c8 */
+	union {
+		struct {
+			__u16	pgmilc;		/* 0x00cc */
+			__u16	iprcc;		/* 0x00ce */
+		};
+		__u32	edc;			/* 0x00cc */
+	} __packed;
+	union {
+		struct {
+			__u32	dxc;		/* 0x00d0 */
+			__u16	mcn;		/* 0x00d4 */
+			__u8	perc;		/* 0x00d6 */
+			__u8	peratmid;	/* 0x00d7 */
+		};
+		__u64	faddr;			/* 0x00d0 */
+	} __packed;
+	__u64	peraddr;		/* 0x00d8 */
+	__u8	eai;			/* 0x00e0 */
+	__u8	peraid;			/* 0x00e1 */
+	__u8	oai;			/* 0x00e2 */
+	__u8	armid;			/* 0x00e3 */
+	__u8	reservede4[4];		/* 0x00e4 */
+	union {
+		__u64	tecmc;		/* 0x00e8 */
+		struct {
+			__u16	subchannel_id;	/* 0x00e8 */
+			__u16	subchannel_nr;	/* 0x00ea */
+			__u32	io_int_parm;	/* 0x00ec */
+			__u32	io_int_word;	/* 0x00f0 */
+		};
+	} __packed;
+	__u8	reservedf4[8];		/* 0x00f4 */
+#define CRYCB_FORMAT_MASK	0x00000003
+#define CRYCB_FORMAT0		0x00000000
+#define CRYCB_FORMAT1		0x00000001
+#define CRYCB_FORMAT2		0x00000003
+	__u32	crycbd;			/* 0x00fc */
+	__u64	gcr[16];		/* 0x0100 */
+	union {
+		__u64	gbea;		/* 0x0180 */
+		__u64	sidad;
+	};
+	__u8    reserved188[8];		/* 0x0188 */
+	__u64   sdnxo;			/* 0x0190 */
+	__u8    reserved198[8];		/* 0x0198 */
+	__u32	fac;			/* 0x01a0 */
+	__u8	reserved1a4[20];	/* 0x01a4 */
+	__u64	cbrlo;			/* 0x01b8 */
+	__u8	reserved1c0[8];		/* 0x01c0 */
+#define ECD_HOSTREGMGMT	0x20000000
+#define ECD_MEF		0x08000000
+#define ECD_ETOKENF	0x02000000
+#define ECD_ECC		0x00200000
+	__u32	ecd;			/* 0x01c8 */
+	__u8	reserved1cc[18];	/* 0x01cc */
+	__u64	pp;			/* 0x01de */
+	__u8	reserved1e6[2];		/* 0x01e6 */
+	__u64	itdba;			/* 0x01e8 */
+	__u64   riccbd;			/* 0x01f0 */
+	__u64	gvrd;			/* 0x01f8 */
+} __packed __aligned(512);
+
+#endif /* SELFTEST_KVM_SIE_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86_64/apic.h
index 0f268b55fa06..51990094effd 100644
--- a/tools/testing/selftests/kvm/include/x86_64/apic.h
+++ b/tools/testing/selftests/kvm/include/x86_64/apic.h
@@ -11,6 +11,7 @@
 #include <stdint.h>
 
 #include "processor.h"
+#include "ucall_common.h"
 
 #define APIC_DEFAULT_GPA		0xfee00000ULL
 
@@ -93,9 +94,27 @@ static inline uint64_t x2apic_read_reg(unsigned int reg)
 	return rdmsr(APIC_BASE_MSR + (reg >> 4));
 }
 
+static inline uint8_t x2apic_write_reg_safe(unsigned int reg, uint64_t value)
+{
+	return wrmsr_safe(APIC_BASE_MSR + (reg >> 4), value);
+}
+
 static inline void x2apic_write_reg(unsigned int reg, uint64_t value)
 {
-	wrmsr(APIC_BASE_MSR + (reg >> 4), value);
+	uint8_t fault = x2apic_write_reg_safe(reg, value);
+
+	__GUEST_ASSERT(!fault, "Unexpected fault 0x%x on WRMSR(%x) = %lx\n",
+		       fault, APIC_BASE_MSR + (reg >> 4), value);
 }
 
+static inline void x2apic_write_reg_fault(unsigned int reg, uint64_t value)
+{
+	uint8_t fault = x2apic_write_reg_safe(reg, value);
+
+	__GUEST_ASSERT(fault == GP_VECTOR,
+		       "Wanted #GP on WRMSR(%x) = %lx, got 0x%x\n",
+		       APIC_BASE_MSR + (reg >> 4), value, fault);
+}
+
+
 #endif /* SELFTEST_KVM_APIC_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h
index fa65b908b13e..6849e2552f1b 100644
--- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h
+++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h
@@ -186,6 +186,18 @@
 #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED		\
 	KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 14)
 
+/* HYPERV_CPUID_NESTED_FEATURES.EAX */
+#define HV_X64_NESTED_DIRECT_FLUSH			\
+	KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EAX, 17)
+#define HV_X64_NESTED_GUEST_MAPPING_FLUSH		\
+	KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EAX, 18)
+#define HV_X64_NESTED_MSR_BITMAP			\
+	KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EAX, 19)
+
+/* HYPERV_CPUID_NESTED_FEATURES.EBX */
+#define HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL		\
+	KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EBX, 0)
+
 /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */
 #define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING	\
 	KVM_X86_CPU_FEATURE(HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, 0, EAX, 1)
@@ -343,4 +355,10 @@ struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm,
 /* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */
 #define HV_INVARIANT_TSC_EXPOSED               BIT_ULL(0)
 
+const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void);
+const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu);
+void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu);
+
+bool kvm_hv_cpu_has(struct kvm_x86_cpu_feature feature);
+
 #endif /* !SELFTEST_KVM_HYPERV_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index a0c1440017bb..e247f99e0473 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -25,6 +25,10 @@ extern bool host_cpu_is_intel;
 extern bool host_cpu_is_amd;
 extern uint64_t guest_tsc_khz;
 
+#ifndef MAX_NR_CPUID_ENTRIES
+#define MAX_NR_CPUID_ENTRIES 100
+#endif
+
 /* Forced emulation prefix, used to invoke the emulator unconditionally. */
 #define KVM_FEP "ud2; .byte 'k', 'v', 'm';"
 
@@ -908,8 +912,6 @@ static inline void vcpu_xcrs_set(struct kvm_vcpu *vcpu, struct kvm_xcrs *xcrs)
 const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid,
 					       uint32_t function, uint32_t index);
 const struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
-const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void);
-const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu);
 
 static inline uint32_t kvm_cpu_fms(void)
 {
@@ -1009,7 +1011,6 @@ static inline struct kvm_cpuid2 *allocate_kvm_cpuid2(int nr_entries)
 }
 
 void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid);
-void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu);
 
 static inline struct kvm_cpuid_entry2 *__vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu,
 							      uint32_t function,
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 56b170b725b3..a2b7df5f1d39 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -712,16 +712,13 @@ void kvm_vm_release(struct kvm_vm *vmp)
 }
 
 static void __vm_mem_region_delete(struct kvm_vm *vm,
-				   struct userspace_mem_region *region,
-				   bool unlink)
+				   struct userspace_mem_region *region)
 {
 	int ret;
 
-	if (unlink) {
-		rb_erase(&region->gpa_node, &vm->regions.gpa_tree);
-		rb_erase(&region->hva_node, &vm->regions.hva_tree);
-		hash_del(&region->slot_node);
-	}
+	rb_erase(&region->gpa_node, &vm->regions.gpa_tree);
+	rb_erase(&region->hva_node, &vm->regions.hva_tree);
+	hash_del(&region->slot_node);
 
 	region->region.memory_size = 0;
 	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
@@ -762,7 +759,7 @@ void kvm_vm_free(struct kvm_vm *vmp)
 
 	/* Free userspace_mem_regions. */
 	hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node)
-		__vm_mem_region_delete(vmp, region, false);
+		__vm_mem_region_delete(vmp, region);
 
 	/* Free sparsebit arrays. */
 	sparsebit_free(&vmp->vpages_valid);
@@ -794,76 +791,6 @@ int kvm_memfd_alloc(size_t size, bool hugepages)
 	return fd;
 }
 
-/*
- * Memory Compare, host virtual to guest virtual
- *
- * Input Args:
- *   hva - Starting host virtual address
- *   vm - Virtual Machine
- *   gva - Starting guest virtual address
- *   len - number of bytes to compare
- *
- * Output Args: None
- *
- * Input/Output Args: None
- *
- * Return:
- *   Returns 0 if the bytes starting at hva for a length of len
- *   are equal the guest virtual bytes starting at gva.  Returns
- *   a value < 0, if bytes at hva are less than those at gva.
- *   Otherwise a value > 0 is returned.
- *
- * Compares the bytes starting at the host virtual address hva, for
- * a length of len, to the guest bytes starting at the guest virtual
- * address given by gva.
- */
-int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len)
-{
-	size_t amt;
-
-	/*
-	 * Compare a batch of bytes until either a match is found
-	 * or all the bytes have been compared.
-	 */
-	for (uintptr_t offset = 0; offset < len; offset += amt) {
-		uintptr_t ptr1 = (uintptr_t)hva + offset;
-
-		/*
-		 * Determine host address for guest virtual address
-		 * at offset.
-		 */
-		uintptr_t ptr2 = (uintptr_t)addr_gva2hva(vm, gva + offset);
-
-		/*
-		 * Determine amount to compare on this pass.
-		 * Don't allow the comparsion to cross a page boundary.
-		 */
-		amt = len - offset;
-		if ((ptr1 >> vm->page_shift) != ((ptr1 + amt) >> vm->page_shift))
-			amt = vm->page_size - (ptr1 % vm->page_size);
-		if ((ptr2 >> vm->page_shift) != ((ptr2 + amt) >> vm->page_shift))
-			amt = vm->page_size - (ptr2 % vm->page_size);
-
-		assert((ptr1 >> vm->page_shift) == ((ptr1 + amt - 1) >> vm->page_shift));
-		assert((ptr2 >> vm->page_shift) == ((ptr2 + amt - 1) >> vm->page_shift));
-
-		/*
-		 * Perform the comparison.  If there is a difference
-		 * return that result to the caller, otherwise need
-		 * to continue on looking for a mismatch.
-		 */
-		int ret = memcmp((void *)ptr1, (void *)ptr2, amt);
-		if (ret != 0)
-			return ret;
-	}
-
-	/*
-	 * No mismatch found.  Let the caller know the two memory
-	 * areas are equal.
-	 */
-	return 0;
-}
-
 static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree,
 					       struct userspace_mem_region *region)
 {
@@ -1270,7 +1197,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa)
  */
 void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot)
 {
-	__vm_mem_region_delete(vm, memslot2region(vm, slot), true);
+	__vm_mem_region_delete(vm, memslot2region(vm, slot));
 }
 
 void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size,
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index 4ad4492eea1d..20cfe970e3e3 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -14,7 +14,7 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm)
 {
 	vm_paddr_t paddr;
 
-	TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x",
+	TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x",
 		    vm->page_size);
 
 	if (vm->pgd_created)
@@ -79,7 +79,7 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa)
 	}
 
 	/* Fill in page table entry */
-	idx = (gva >> 12) & 0x0ffu;		/* page index */
+	idx = (gva >> PAGE_SHIFT) & 0x0ffu;		/* page index */
 	if (!(entry[idx] & PAGE_INVALID))
 		fprintf(stderr,
 			"WARNING: PTE for gpa=0x%"PRIx64" already set!\n", gpa);
@@ -91,7 +91,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 	int ri, idx;
 	uint64_t *entry;
 
-	TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x",
+	TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x",
 		    vm->page_size);
 
 	entry = addr_gpa2hva(vm, vm->pgd);
@@ -103,7 +103,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 		entry = addr_gpa2hva(vm, entry[idx] & REGION_ENTRY_ORIGIN);
 	}
 
-	idx = (gva >> 12) & 0x0ffu;		/* page index */
+	idx = (gva >> PAGE_SHIFT) & 0x0ffu;		/* page index */
 
 	TEST_ASSERT(!(entry[idx] & PAGE_INVALID),
 		    "No page mapping for vm virtual address 0x%lx", gva);
@@ -168,7 +168,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 	struct kvm_sregs sregs;
 	struct kvm_vcpu *vcpu;
 
-	TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x",
+	TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x",
 		    vm->page_size);
 
 	stack_vaddr = __vm_vaddr_alloc(vm, stack_size,
diff --git a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c
index efb7e7a1354d..15bc8cd583aa 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c
@@ -8,6 +8,73 @@
 #include "processor.h"
 #include "hyperv.h"
 
+const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void)
+{
+	static struct kvm_cpuid2 *cpuid;
+	int kvm_fd;
+
+	if (cpuid)
+		return cpuid;
+
+	cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES);
+	kvm_fd = open_kvm_dev_path_or_exit();
+
+	kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
+
+	close(kvm_fd);
+	return cpuid;
+}
+
+void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu)
+{
+	static struct kvm_cpuid2 *cpuid_full;
+	const struct kvm_cpuid2 *cpuid_sys, *cpuid_hv;
+	int i, nent = 0;
+
+	if (!cpuid_full) {
+		cpuid_sys = kvm_get_supported_cpuid();
+		cpuid_hv = kvm_get_supported_hv_cpuid();
+
+		cpuid_full = allocate_kvm_cpuid2(cpuid_sys->nent + cpuid_hv->nent);
+		if (!cpuid_full) {
+			perror("malloc");
+			abort();
+		}
+
+		/* Need to skip KVM CPUID leaves 0x400000xx */
+		for (i = 0; i < cpuid_sys->nent; i++) {
+			if (cpuid_sys->entries[i].function >= 0x40000000 &&
+			    cpuid_sys->entries[i].function < 0x40000100)
+				continue;
+			cpuid_full->entries[nent] = cpuid_sys->entries[i];
+			nent++;
+		}
+
+		memcpy(&cpuid_full->entries[nent], cpuid_hv->entries,
+		       cpuid_hv->nent * sizeof(struct kvm_cpuid_entry2));
+		cpuid_full->nent = nent + cpuid_hv->nent;
+	}
+
+	vcpu_init_cpuid(vcpu, cpuid_full);
+}
+
+const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid2 *cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES);
+
+	vcpu_ioctl(vcpu, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
+
+	return cpuid;
+}
+
+bool kvm_hv_cpu_has(struct kvm_x86_cpu_feature feature)
+{
+	if (!kvm_has_cap(KVM_CAP_SYS_HYPERV_CPUID))
+		return false;
+
+	return kvm_cpuid_has(kvm_get_supported_hv_cpuid(), feature);
+}
+
 struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm,
 						       vm_vaddr_t *p_hv_pages_gva)
 {
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 153739f2e201..974bcd2df6d7 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -19,8 +19,6 @@
 #define KERNEL_DS	0x10
 #define KERNEL_TSS	0x18
 
-#define MAX_NR_CPUID_ENTRIES 100
-
 vm_vaddr_t exception_handlers;
 bool host_cpu_is_amd;
 bool host_cpu_is_intel;
@@ -566,10 +564,8 @@ void route_exception(struct ex_regs *regs)
 	if (kvm_fixup_exception(regs))
 		return;
 
-	ucall_assert(UCALL_UNHANDLED,
-		     "Unhandled exception in guest", __FILE__, __LINE__,
-		     "Unhandled exception '0x%lx' at guest RIP '0x%lx'",
-		     regs->vector, regs->rip);
+	GUEST_FAIL("Unhandled exception '0x%lx' at guest RIP '0x%lx'",
+		   regs->vector, regs->rip);
 }
 
 static void vm_init_descriptor_tables(struct kvm_vm *vm)
@@ -611,7 +607,7 @@ void assert_on_unhandled_exception(struct kvm_vcpu *vcpu)
 {
 	struct ucall uc;
 
-	if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED)
+	if (get_ucall(vcpu, &uc) == UCALL_ABORT)
 		REPORT_GUEST_ASSERT(uc);
 }
 
@@ -1195,65 +1191,6 @@ void xen_hypercall(uint64_t nr, uint64_t a0, void *a1)
 	GUEST_ASSERT(!__xen_hypercall(nr, a0, a1));
 }
 
-const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void)
-{
-	static struct kvm_cpuid2 *cpuid;
-	int kvm_fd;
-
-	if (cpuid)
-		return cpuid;
-
-	cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES);
-	kvm_fd = open_kvm_dev_path_or_exit();
-
-	kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
-
-	close(kvm_fd);
-	return cpuid;
-}
-
-void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu)
-{
-	static struct kvm_cpuid2 *cpuid_full;
-	const struct kvm_cpuid2 *cpuid_sys, *cpuid_hv;
-	int i, nent = 0;
-
-	if (!cpuid_full) {
-		cpuid_sys = kvm_get_supported_cpuid();
-		cpuid_hv = kvm_get_supported_hv_cpuid();
-
-		cpuid_full = allocate_kvm_cpuid2(cpuid_sys->nent + cpuid_hv->nent);
-		if (!cpuid_full) {
-			perror("malloc");
-			abort();
-		}
-
-		/* Need to skip KVM CPUID leaves 0x400000xx */
-		for (i = 0; i < cpuid_sys->nent; i++) {
-			if (cpuid_sys->entries[i].function >= 0x40000000 &&
-			    cpuid_sys->entries[i].function < 0x40000100)
-				continue;
-			cpuid_full->entries[nent] = cpuid_sys->entries[i];
-			nent++;
-		}
-
-		memcpy(&cpuid_full->entries[nent], cpuid_hv->entries,
-		       cpuid_hv->nent * sizeof(struct kvm_cpuid_entry2));
-		cpuid_full->nent = nent + cpuid_hv->nent;
-	}
-
-	vcpu_init_cpuid(vcpu, cpuid_full);
-}
-
-const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpuid2 *cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES);
-
-	vcpu_ioctl(vcpu, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
-
-	return cpuid;
-}
-
 unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
 {
 	const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 49f162573126..e3343f0df9e1 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -79,6 +79,7 @@ struct test_params {
 	useconds_t delay;
 	uint64_t nr_iterations;
 	bool partition_vcpu_memory_access;
+	bool disable_slot_zap_quirk;
 };
 
 static void run_test(enum vm_guest_mode mode, void *arg)
@@ -89,6 +90,13 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
 				 VM_MEM_SRC_ANONYMOUS,
 				 p->partition_vcpu_memory_access);
+#ifdef __x86_64__
+	if (p->disable_slot_zap_quirk)
+		vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL);
+
+	pr_info("Memslot zap quirk %s\n", p->disable_slot_zap_quirk ?
+		"disabled" : "enabled");
+#endif
 
 	pr_info("Finished creating vCPUs\n");
 
@@ -107,11 +115,12 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 static void help(char *name)
 {
 	puts("");
-	printf("usage: %s [-h] [-m mode] [-d delay_usec]\n"
+	printf("usage: %s [-h] [-m mode] [-d delay_usec] [-q]\n"
 	       "          [-b memory] [-v vcpus] [-o] [-i iterations]\n", name);
 	guest_modes_help();
 	printf(" -d: add a delay between each iteration of adding and\n"
 	       "     deleting a memslot in usec.\n");
+	printf(" -q: Disable memslot zap quirk.\n");
 	printf(" -b: specify the size of the memory region which should be\n"
 	       "     accessed by each vCPU. e.g. 10M or 3G.\n"
 	       "     Default: 1G\n");
@@ -137,7 +146,7 @@ int main(int argc, char *argv[])
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hm:d:b:v:oi:")) != -1) {
+	while ((opt = getopt(argc, argv, "hm:d:qb:v:oi:")) != -1) {
 		switch (opt) {
 		case 'm':
 			guest_modes_cmdline(optarg);
@@ -160,6 +169,12 @@ int main(int argc, char *argv[])
 		case 'i':
 			p.nr_iterations = atoi_positive("Number of iterations", optarg);
 			break;
+		case 'q':
+			p.disable_slot_zap_quirk = true;
+
+			TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) &
+				     KVM_X86_QUIRK_SLOT_ZAP_ALL);
+			break;
 		case 'h':
 		default:
 			help(argv[0]);
diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
index 579a64f97333..893366982f77 100644
--- a/tools/testing/selftests/kvm/memslot_perf_test.c
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -113,6 +113,7 @@ static_assert(ATOMIC_BOOL_LOCK_FREE == 2, "atomic bool is not lockless");
 static sem_t vcpu_ready;
 
 static bool map_unmap_verify;
+static bool disable_slot_zap_quirk;
 
 static bool verbose;
 #define pr_info_v(...)				\
@@ -578,6 +579,9 @@ static bool test_memslot_move_prepare(struct vm_data *data,
 	uint32_t guest_page_size = data->vm->page_size;
 	uint64_t movesrcgpa, movetestgpa;
 
+	if (disable_slot_zap_quirk)
+		vm_enable_cap(data->vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL);
+
 	movesrcgpa = vm_slot2gpa(data, data->nslots - 1);
 
 	if (isactive) {
@@ -896,6 +900,7 @@ static void help(char *name, struct test_args *targs)
 	pr_info(" -h: print this help screen.\n");
 	pr_info(" -v: enable verbose mode (not for benchmarking).\n");
 	pr_info(" -d: enable extra debug checks.\n");
+	pr_info(" -q: Disable memslot zap quirk during memslot move.\n");
 	pr_info(" -s: specify memslot count cap (-1 means no cap; currently: %i)\n",
 		targs->nslots);
 	pr_info(" -f: specify the first test to run (currently: %i; max %zu)\n",
@@ -954,7 +959,7 @@ static bool parse_args(int argc, char *argv[],
 	uint32_t max_mem_slots;
 	int opt;
 
-	while ((opt = getopt(argc, argv, "hvds:f:e:l:r:")) != -1) {
+	while ((opt = getopt(argc, argv, "hvdqs:f:e:l:r:")) != -1) {
 		switch (opt) {
 		case 'h':
 		default:
@@ -966,6 +971,11 @@ static bool parse_args(int argc, char *argv[],
 		case 'd':
 			map_unmap_verify = true;
 			break;
+		case 'q':
+			disable_slot_zap_quirk = true;
+			TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) &
+				     KVM_X86_QUIRK_SLOT_ZAP_ALL);
+			break;
 		case 's':
 			targs->nslots = atoi_paranoid(optarg);
 			if (targs->nslots <= 1 && targs->nslots != -1) {
diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390x/cmma_test.c
index b39033844756..e32dd59703a0 100644
--- a/tools/testing/selftests/kvm/s390x/cmma_test.c
+++ b/tools/testing/selftests/kvm/s390x/cmma_test.c
@@ -17,16 +17,17 @@
 #include "kvm_util.h"
 #include "kselftest.h"
 #include "ucall_common.h"
+#include "processor.h"
 
 #define MAIN_PAGE_COUNT 512
 
 #define TEST_DATA_PAGE_COUNT 512
 #define TEST_DATA_MEMSLOT 1
-#define TEST_DATA_START_GFN 4096
+#define TEST_DATA_START_GFN PAGE_SIZE
 
 #define TEST_DATA_TWO_PAGE_COUNT 256
 #define TEST_DATA_TWO_MEMSLOT 2
-#define TEST_DATA_TWO_START_GFN 8192
+#define TEST_DATA_TWO_START_GFN (2 * PAGE_SIZE)
 
 static char cmma_value_buf[MAIN_PAGE_COUNT + TEST_DATA_PAGE_COUNT];
 
@@ -66,7 +67,7 @@ static void guest_dirty_test_data(void)
 		"	lghi 5,%[page_count]\n"
 		/* r5 += r1 */
 		"2:	agfr 5,1\n"
-		/* r2 = r1 << 12 */
+		/* r2 = r1 << PAGE_SHIFT */
 		"1:	sllg 2,1,12(0)\n"
 		/* essa(r4, r2, SET_STABLE) */
 		"	.insn rrf,0xb9ab0000,4,2,1,0\n"
diff --git a/tools/testing/selftests/kvm/s390x/config b/tools/testing/selftests/kvm/s390x/config
new file mode 100644
index 000000000000..23270f2d679f
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390x/config
@@ -0,0 +1,2 @@
+CONFIG_KVM=y
+CONFIG_KVM_S390_UCONTROL=y
diff --git a/tools/testing/selftests/kvm/s390x/debug_test.c b/tools/testing/selftests/kvm/s390x/debug_test.c
index 84313fb27529..ad8095968601 100644
--- a/tools/testing/selftests/kvm/s390x/debug_test.c
+++ b/tools/testing/selftests/kvm/s390x/debug_test.c
@@ -2,12 +2,12 @@
 /* Test KVM debugging features. */
 #include "kvm_util.h"
 #include "test_util.h"
+#include "sie.h"
 
 #include <linux/kvm.h>
 
 #define __LC_SVC_NEW_PSW 0x1c0
 #define __LC_PGM_NEW_PSW 0x1d0
-#define ICPT_INSTRUCTION 0x04
 #define IPA0_DIAG 0x8300
 #define PGM_SPECIFICATION 0x06
 
@@ -85,7 +85,7 @@ static void test_step_pgm_diag(void)
 	vm = test_step_int_1(&vcpu, test_step_pgm_diag_guest_code,
 			     __LC_PGM_NEW_PSW, new_psw);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
-	TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_INSTRUCTION);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_INST);
 	TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa & 0xff00, IPA0_DIAG);
 	vcpu_ioctl(vcpu, KVM_S390_IRQ, &irq);
 	vcpu_run(vcpu);
diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c
index f2df7416be84..4374b4cd2a80 100644
--- a/tools/testing/selftests/kvm/s390x/memop.c
+++ b/tools/testing/selftests/kvm/s390x/memop.c
@@ -16,6 +16,7 @@
 #include "kvm_util.h"
 #include "kselftest.h"
 #include "ucall_common.h"
+#include "processor.h"
 
 enum mop_target {
 	LOGICAL,
@@ -226,9 +227,6 @@ static void memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo,
 
 #define CHECK_N_DO(f, ...) ({ f(__VA_ARGS__, CHECK_ONLY); f(__VA_ARGS__); })
 
-#define PAGE_SHIFT 12
-#define PAGE_SIZE (1ULL << PAGE_SHIFT)
-#define PAGE_MASK (~(PAGE_SIZE - 1))
 #define CR0_FETCH_PROTECTION_OVERRIDE	(1UL << (63 - 38))
 #define CR0_STORAGE_PROTECTION_OVERRIDE	(1UL << (63 - 39))
 
diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c
index 7a742a673b7c..12d5e1cb62e3 100644
--- a/tools/testing/selftests/kvm/s390x/tprot.c
+++ b/tools/testing/selftests/kvm/s390x/tprot.c
@@ -9,9 +9,8 @@
 #include "kvm_util.h"
 #include "kselftest.h"
 #include "ucall_common.h"
+#include "processor.h"
 
-#define PAGE_SHIFT 12
-#define PAGE_SIZE (1 << PAGE_SHIFT)
 #define CR0_FETCH_PROTECTION_OVERRIDE	(1UL << (63 - 38))
 #define CR0_STORAGE_PROTECTION_OVERRIDE	(1UL << (63 - 39))
 
@@ -151,7 +150,7 @@ static enum stage perform_next_stage(int *i, bool mapped_0)
 		 * instead.
 		 * In order to skip these tests we detect this inside the guest
 		 */
-		skip = tests[*i].addr < (void *)4096 &&
+		skip = tests[*i].addr < (void *)PAGE_SIZE &&
 		       tests[*i].expected != TRANSL_UNAVAIL &&
 		       !mapped_0;
 		if (!skip) {
diff --git a/tools/testing/selftests/kvm/s390x/ucontrol_test.c b/tools/testing/selftests/kvm/s390x/ucontrol_test.c
new file mode 100644
index 000000000000..f257beec1430
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390x/ucontrol_test.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Test code for the s390x kvm ucontrol interface
+ *
+ * Copyright IBM Corp. 2024
+ *
+ * Authors:
+ *  Christoph Schlameuss <schlameuss@linux.ibm.com>
+ */
+#include "debug_print.h"
+#include "kselftest_harness.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "sie.h"
+
+#include <linux/capability.h>
+#include <linux/sizes.h>
+
+#define VM_MEM_SIZE (4 * SZ_1M)
+
+/* so directly declare capget to check caps without libcap */
+int capget(cap_user_header_t header, cap_user_data_t data);
+
+/**
+ * In order to create user controlled virtual machines on S390,
+ * check KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL
+ * as privileged user (SYS_ADMIN).
+ */
+void require_ucontrol_admin(void)
+{
+	struct __user_cap_data_struct data[_LINUX_CAPABILITY_U32S_3];
+	struct __user_cap_header_struct hdr = {
+		.version = _LINUX_CAPABILITY_VERSION_3,
+	};
+	int rc;
+
+	rc = capget(&hdr, data);
+	TEST_ASSERT_EQ(0, rc);
+	TEST_REQUIRE((data->effective & CAP_TO_MASK(CAP_SYS_ADMIN)) > 0);
+
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_S390_UCONTROL));
+}
+
+/* Test program setting some registers and looping */
+extern char test_gprs_asm[];
+asm("test_gprs_asm:\n"
+	"xgr	%r0, %r0\n"
+	"lgfi	%r1,1\n"
+	"lgfi	%r2,2\n"
+	"lgfi	%r3,3\n"
+	"lgfi	%r4,4\n"
+	"lgfi	%r5,5\n"
+	"lgfi	%r6,6\n"
+	"lgfi	%r7,7\n"
+	"0:\n"
+	"	diag	0,0,0x44\n"
+	"	ahi	%r0,1\n"
+	"	j	0b\n"
+);
+
+FIXTURE(uc_kvm)
+{
+	struct kvm_s390_sie_block *sie_block;
+	struct kvm_run *run;
+	uintptr_t base_gpa;
+	uintptr_t code_gpa;
+	uintptr_t base_hva;
+	uintptr_t code_hva;
+	int kvm_run_size;
+	void *vm_mem;
+	int vcpu_fd;
+	int kvm_fd;
+	int vm_fd;
+};
+
+/**
+ * create VM with single vcpu, map kvm_run and SIE control block for easy access
+ */
+FIXTURE_SETUP(uc_kvm)
+{
+	struct kvm_s390_vm_cpu_processor info;
+	int rc;
+
+	require_ucontrol_admin();
+
+	self->kvm_fd = open_kvm_dev_path_or_exit();
+	self->vm_fd = ioctl(self->kvm_fd, KVM_CREATE_VM, KVM_VM_S390_UCONTROL);
+	ASSERT_GE(self->vm_fd, 0);
+
+	kvm_device_attr_get(self->vm_fd, KVM_S390_VM_CPU_MODEL,
+			    KVM_S390_VM_CPU_PROCESSOR, &info);
+	TH_LOG("create VM 0x%llx", info.cpuid);
+
+	self->vcpu_fd = ioctl(self->vm_fd, KVM_CREATE_VCPU, 0);
+	ASSERT_GE(self->vcpu_fd, 0);
+
+	self->kvm_run_size = ioctl(self->kvm_fd, KVM_GET_VCPU_MMAP_SIZE, NULL);
+	ASSERT_GE(self->kvm_run_size, sizeof(struct kvm_run))
+		  TH_LOG(KVM_IOCTL_ERROR(KVM_GET_VCPU_MMAP_SIZE, self->kvm_run_size));
+	self->run = (struct kvm_run *)mmap(NULL, self->kvm_run_size,
+		    PROT_READ | PROT_WRITE, MAP_SHARED, self->vcpu_fd, 0);
+	ASSERT_NE(self->run, MAP_FAILED);
+	/**
+	 * For virtual cpus that have been created with S390 user controlled
+	 * virtual machines, the resulting vcpu fd can be memory mapped at page
+	 * offset KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of
+	 * the virtual cpu's hardware control block.
+	 */
+	self->sie_block = (struct kvm_s390_sie_block *)mmap(NULL, PAGE_SIZE,
+			  PROT_READ | PROT_WRITE, MAP_SHARED,
+			  self->vcpu_fd, KVM_S390_SIE_PAGE_OFFSET << PAGE_SHIFT);
+	ASSERT_NE(self->sie_block, MAP_FAILED);
+
+	TH_LOG("VM created %p %p", self->run, self->sie_block);
+
+	self->base_gpa = 0;
+	self->code_gpa = self->base_gpa + (3 * SZ_1M);
+
+	self->vm_mem = aligned_alloc(SZ_1M, VM_MEM_SIZE);
+	ASSERT_NE(NULL, self->vm_mem) TH_LOG("malloc failed %u", errno);
+	self->base_hva = (uintptr_t)self->vm_mem;
+	self->code_hva = self->base_hva - self->base_gpa + self->code_gpa;
+	struct kvm_s390_ucas_mapping map = {
+		.user_addr = self->base_hva,
+		.vcpu_addr = self->base_gpa,
+		.length = VM_MEM_SIZE,
+	};
+	TH_LOG("ucas map %p %p 0x%llx",
+	       (void *)map.user_addr, (void *)map.vcpu_addr, map.length);
+	rc = ioctl(self->vcpu_fd, KVM_S390_UCAS_MAP, &map);
+	ASSERT_EQ(0, rc) TH_LOG("ucas map result %d not expected, %s",
+				rc, strerror(errno));
+
+	TH_LOG("page in %p", (void *)self->base_gpa);
+	rc = ioctl(self->vcpu_fd, KVM_S390_VCPU_FAULT, self->base_gpa);
+	ASSERT_EQ(0, rc) TH_LOG("vcpu fault (%p) result %d not expected, %s",
+				(void *)self->base_hva, rc, strerror(errno));
+
+	self->sie_block->cpuflags &= ~CPUSTAT_STOPPED;
+}
+
+FIXTURE_TEARDOWN(uc_kvm)
+{
+	munmap(self->sie_block, PAGE_SIZE);
+	munmap(self->run, self->kvm_run_size);
+	close(self->vcpu_fd);
+	close(self->vm_fd);
+	close(self->kvm_fd);
+	free(self->vm_mem);
+}
+
+TEST_F(uc_kvm, uc_sie_assertions)
+{
+	/* assert interception of Code 08 (Program Interruption) is set */
+	EXPECT_EQ(0, self->sie_block->ecb & ECB_SPECI);
+}
+
+TEST_F(uc_kvm, uc_attr_mem_limit)
+{
+	u64 limit;
+	struct kvm_device_attr attr = {
+		.group = KVM_S390_VM_MEM_CTRL,
+		.attr = KVM_S390_VM_MEM_LIMIT_SIZE,
+		.addr = (unsigned long)&limit,
+	};
+	int rc;
+
+	rc = ioctl(self->vm_fd, KVM_GET_DEVICE_ATTR, &attr);
+	EXPECT_EQ(0, rc);
+	EXPECT_EQ(~0UL, limit);
+
+	/* assert set not supported */
+	rc = ioctl(self->vm_fd, KVM_SET_DEVICE_ATTR, &attr);
+	EXPECT_EQ(-1, rc);
+	EXPECT_EQ(EINVAL, errno);
+}
+
+TEST_F(uc_kvm, uc_no_dirty_log)
+{
+	struct kvm_dirty_log dlog;
+	int rc;
+
+	rc = ioctl(self->vm_fd, KVM_GET_DIRTY_LOG, &dlog);
+	EXPECT_EQ(-1, rc);
+	EXPECT_EQ(EINVAL, errno);
+}
+
+/**
+ * Assert HPAGE CAP cannot be enabled on UCONTROL VM
+ */
+TEST(uc_cap_hpage)
+{
+	int rc, kvm_fd, vm_fd, vcpu_fd;
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_S390_HPAGE_1M,
+	};
+
+	require_ucontrol_admin();
+
+	kvm_fd = open_kvm_dev_path_or_exit();
+	vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, KVM_VM_S390_UCONTROL);
+	ASSERT_GE(vm_fd, 0);
+
+	/* assert hpages are not supported on ucontrol vm */
+	rc = ioctl(vm_fd, KVM_CHECK_EXTENSION, KVM_CAP_S390_HPAGE_1M);
+	EXPECT_EQ(0, rc);
+
+	/* Test that KVM_CAP_S390_HPAGE_1M can't be enabled for a ucontrol vm */
+	rc = ioctl(vm_fd, KVM_ENABLE_CAP, cap);
+	EXPECT_EQ(-1, rc);
+	EXPECT_EQ(EINVAL, errno);
+
+	/* assert HPAGE CAP is rejected after vCPU creation */
+	vcpu_fd = ioctl(vm_fd, KVM_CREATE_VCPU, 0);
+	ASSERT_GE(vcpu_fd, 0);
+	rc = ioctl(vm_fd, KVM_ENABLE_CAP, cap);
+	EXPECT_EQ(-1, rc);
+	EXPECT_EQ(EBUSY, errno);
+
+	close(vcpu_fd);
+	close(vm_fd);
+	close(kvm_fd);
+}
+
+/* verify SIEIC exit
+ * * fail on codes not expected in the test cases
+ */
+static bool uc_handle_sieic(FIXTURE_DATA(uc_kvm) * self)
+{
+	struct kvm_s390_sie_block *sie_block = self->sie_block;
+	struct kvm_run *run = self->run;
+
+	/* check SIE interception code */
+	pr_info("sieic: 0x%.2x 0x%.4x 0x%.4x\n",
+		run->s390_sieic.icptcode,
+		run->s390_sieic.ipa,
+		run->s390_sieic.ipb);
+	switch (run->s390_sieic.icptcode) {
+	case ICPT_INST:
+		/* end execution in caller on intercepted instruction */
+		pr_info("sie instruction interception\n");
+		return false;
+	case ICPT_OPEREXC:
+		/* operation exception */
+		TEST_FAIL("sie exception on %.4x%.8x", sie_block->ipa, sie_block->ipb);
+	default:
+		TEST_FAIL("UNEXPECTED SIEIC CODE %d", run->s390_sieic.icptcode);
+	}
+	return true;
+}
+
+/* verify VM state on exit */
+static bool uc_handle_exit(FIXTURE_DATA(uc_kvm) * self)
+{
+	struct kvm_run *run = self->run;
+
+	switch (run->exit_reason) {
+	case KVM_EXIT_S390_SIEIC:
+		return uc_handle_sieic(self);
+	default:
+		pr_info("exit_reason %2d not handled\n", run->exit_reason);
+	}
+	return true;
+}
+
+/* run the VM until interrupted */
+static int uc_run_once(FIXTURE_DATA(uc_kvm) * self)
+{
+	int rc;
+
+	rc = ioctl(self->vcpu_fd, KVM_RUN, NULL);
+	print_run(self->run, self->sie_block);
+	print_regs(self->run);
+	pr_debug("run %d / %d %s\n", rc, errno, strerror(errno));
+	return rc;
+}
+
+static void uc_assert_diag44(FIXTURE_DATA(uc_kvm) * self)
+{
+	struct kvm_s390_sie_block *sie_block = self->sie_block;
+
+	/* assert vm was interrupted by diag 0x0044 */
+	TEST_ASSERT_EQ(KVM_EXIT_S390_SIEIC, self->run->exit_reason);
+	TEST_ASSERT_EQ(ICPT_INST, sie_block->icptcode);
+	TEST_ASSERT_EQ(0x8300, sie_block->ipa);
+	TEST_ASSERT_EQ(0x440000, sie_block->ipb);
+}
+
+TEST_F(uc_kvm, uc_gprs)
+{
+	struct kvm_sync_regs *sync_regs = &self->run->s.regs;
+	struct kvm_run *run = self->run;
+	struct kvm_regs regs = {};
+
+	/* Set registers to values that are different from the ones that we expect below */
+	for (int i = 0; i < 8; i++)
+		sync_regs->gprs[i] = 8;
+	run->kvm_dirty_regs |= KVM_SYNC_GPRS;
+
+	/* copy test_gprs_asm to code_hva / code_gpa */
+	TH_LOG("copy code %p to vm mapped memory %p / %p",
+	       &test_gprs_asm, (void *)self->code_hva, (void *)self->code_gpa);
+	memcpy((void *)self->code_hva, &test_gprs_asm, PAGE_SIZE);
+
+	/* DAT disabled + 64 bit mode */
+	run->psw_mask = 0x0000000180000000ULL;
+	run->psw_addr = self->code_gpa;
+
+	/* run and expect interception of diag 44 */
+	ASSERT_EQ(0, uc_run_once(self));
+	ASSERT_EQ(false, uc_handle_exit(self));
+	uc_assert_diag44(self);
+
+	/* Retrieve and check guest register values */
+	ASSERT_EQ(0, ioctl(self->vcpu_fd, KVM_GET_REGS, &regs));
+	for (int i = 0; i < 8; i++) {
+		ASSERT_EQ(i, regs.gprs[i]);
+		ASSERT_EQ(i, sync_regs->gprs[i]);
+	}
+
+	/* run and expect interception of diag 44 again */
+	ASSERT_EQ(0, uc_run_once(self));
+	ASSERT_EQ(false, uc_handle_exit(self));
+	uc_assert_diag44(self);
+
+	/* check continued increment of register 0 value */
+	ASSERT_EQ(0, ioctl(self->vcpu_fd, KVM_GET_REGS, &regs));
+	ASSERT_EQ(1, regs.gprs[0]);
+	ASSERT_EQ(1, sync_regs->gprs[0]);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index bb8002084f52..a8267628e9ed 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -175,7 +175,7 @@ static void guest_code_move_memory_region(void)
 	GUEST_DONE();
 }
 
-static void test_move_memory_region(void)
+static void test_move_memory_region(bool disable_slot_zap_quirk)
 {
 	pthread_t vcpu_thread;
 	struct kvm_vcpu *vcpu;
@@ -184,6 +184,9 @@ static void test_move_memory_region(void)
 
 	vm = spawn_vm(&vcpu, &vcpu_thread, guest_code_move_memory_region);
 
+	if (disable_slot_zap_quirk)
+		vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL);
+
 	hva = addr_gpa2hva(vm, MEM_REGION_GPA);
 
 	/*
@@ -266,7 +269,7 @@ static void guest_code_delete_memory_region(void)
 	GUEST_ASSERT(0);
 }
 
-static void test_delete_memory_region(void)
+static void test_delete_memory_region(bool disable_slot_zap_quirk)
 {
 	pthread_t vcpu_thread;
 	struct kvm_vcpu *vcpu;
@@ -276,6 +279,9 @@ static void test_delete_memory_region(void)
 
 	vm = spawn_vm(&vcpu, &vcpu_thread, guest_code_delete_memory_region);
 
+	if (disable_slot_zap_quirk)
+		vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL);
+
 	/* Delete the memory region, the guest should not die. */
 	vm_mem_region_delete(vm, MEM_REGION_SLOT);
 	wait_for_vcpu();
@@ -553,7 +559,10 @@ int main(int argc, char *argv[])
 {
 #ifdef __x86_64__
 	int i, loops;
+	int j, disable_slot_zap_quirk = 0;
 
+	if (kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_SLOT_ZAP_ALL)
+		disable_slot_zap_quirk = 1;
 	/*
 	 * FIXME: the zero-memslot test fails on aarch64 and s390x because
 	 * KVM_RUN fails with ENOEXEC or EFAULT.
@@ -579,13 +588,17 @@ int main(int argc, char *argv[])
 	else
 		loops = 10;
 
-	pr_info("Testing MOVE of in-use region, %d loops\n", loops);
-	for (i = 0; i < loops; i++)
-		test_move_memory_region();
+	for (j = 0; j <= disable_slot_zap_quirk; j++) {
+		pr_info("Testing MOVE of in-use region, %d loops, slot zap quirk %s\n",
+			loops, j ? "disabled" : "enabled");
+		for (i = 0; i < loops; i++)
+			test_move_memory_region(!!j);
 
-	pr_info("Testing DELETE of in-use region, %d loops\n", loops);
-	for (i = 0; i < loops; i++)
-		test_delete_memory_region();
+		pr_info("Testing DELETE of in-use region, %d loops, slot zap quirk %s\n",
+			loops, j ? "disabled" : "enabled");
+		for (i = 0; i < loops; i++)
+			test_delete_memory_region(!!j);
+	}
 #endif
 
 	return 0;
diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c
index f6b295e0b2d2..76cc2df9238a 100644
--- a/tools/testing/selftests/kvm/x86_64/debug_regs.c
+++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c
@@ -47,15 +47,18 @@ static void guest_code(void)
 	/*
 	 * Single step test, covers 2 basic instructions and 2 emulated
 	 *
-	 * Enable interrupts during the single stepping to see that
-	 * pending interrupt we raised is not handled due to KVM_GUESTDBG_BLOCKIRQ
+	 * Enable interrupts during the single stepping to see that pending
+	 * interrupt we raised is not handled due to KVM_GUESTDBG_BLOCKIRQ.
+	 *
+	 * Write MSR_IA32_TSC_DEADLINE to verify that KVM's fastpath handler
+	 * exits to userspace due to single-step being enabled.
 	 */
 	asm volatile("ss_start: "
 		     "sti\n\t"
 		     "xor %%eax,%%eax\n\t"
 		     "cpuid\n\t"
-		     "movl $0x1a0,%%ecx\n\t"
-		     "rdmsr\n\t"
+		     "movl $" __stringify(MSR_IA32_TSC_DEADLINE) ", %%ecx\n\t"
+		     "wrmsr\n\t"
 		     "cli\n\t"
 		     : : : "eax", "ebx", "ecx", "edx");
 
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
index e192720bfe14..74cf19661309 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
@@ -242,7 +242,7 @@ int main(int argc, char *argv[])
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE));
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS));
-	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH));
+	TEST_REQUIRE(kvm_hv_cpu_has(HV_X64_NESTED_DIRECT_FLUSH));
 
 	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
index b987a3d79715..0ddb63229bcb 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
@@ -157,7 +157,7 @@ int main(int argc, char *argv[])
 	int stage;
 
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM));
-	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH));
+	TEST_REQUIRE(kvm_hv_cpu_has(HV_X64_NESTED_DIRECT_FLUSH));
 
 	/* Create VM */
 	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
diff --git a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c
index 7c70c0da4fb7..2e9197eb1652 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c
@@ -160,6 +160,36 @@ static void test_sev(void *guest_code, uint64_t policy)
 	kvm_vm_free(vm);
 }
 
+static void guest_shutdown_code(void)
+{
+	struct desc_ptr idt;
+
+	/* Clobber the IDT so that #UD is guaranteed to trigger SHUTDOWN. */
+	memset(&idt, 0, sizeof(idt));
+	__asm__ __volatile__("lidt %0" :: "m"(idt));
+
+	__asm__ __volatile__("ud2");
+}
+
+static void test_sev_es_shutdown(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+
+	uint32_t type = KVM_X86_SEV_ES_VM;
+
+	vm = vm_sev_create_with_one_vcpu(type, guest_shutdown_code, &vcpu);
+
+	vm_sev_launch(vm, SEV_POLICY_ES, NULL);
+
+	vcpu_run(vcpu);
+	TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SHUTDOWN,
+		    "Wanted SHUTDOWN, got %s",
+		    exit_reason_str(vcpu->run->exit_reason));
+
+	kvm_vm_free(vm);
+}
+
 int main(int argc, char *argv[])
 {
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV));
@@ -171,6 +201,8 @@ int main(int argc, char *argv[])
 		test_sev(guest_sev_es_code, SEV_POLICY_ES | SEV_POLICY_NO_DBG);
 		test_sev(guest_sev_es_code, SEV_POLICY_ES);
 
+		test_sev_es_shutdown();
+
 		if (kvm_has_cap(KVM_CAP_XCRS) &&
 		    (xgetbv(0) & XFEATURE_MASK_X87_AVX) == XFEATURE_MASK_X87_AVX) {
 			test_sync_vmsa(0);
diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
index 618cd2442390..88bcca188799 100644
--- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
@@ -13,6 +13,7 @@
 struct xapic_vcpu {
 	struct kvm_vcpu *vcpu;
 	bool is_x2apic;
+	bool has_xavic_errata;
 };
 
 static void xapic_guest_code(void)
@@ -31,6 +32,10 @@ static void xapic_guest_code(void)
 	}
 }
 
+#define X2APIC_RSVD_BITS_MASK  (GENMASK_ULL(31, 20) | \
+				GENMASK_ULL(17, 16) | \
+				GENMASK_ULL(13, 13))
+
 static void x2apic_guest_code(void)
 {
 	asm volatile("cli");
@@ -41,7 +46,12 @@ static void x2apic_guest_code(void)
 		uint64_t val = x2apic_read_reg(APIC_IRR) |
 			       x2apic_read_reg(APIC_IRR + 0x10) << 32;
 
-		x2apic_write_reg(APIC_ICR, val);
+		if (val & X2APIC_RSVD_BITS_MASK) {
+			x2apic_write_reg_fault(APIC_ICR, val);
+		} else {
+			x2apic_write_reg(APIC_ICR, val);
+			GUEST_ASSERT_EQ(x2apic_read_reg(APIC_ICR), val);
+		}
 		GUEST_SYNC(val);
 	} while (1);
 }
@@ -71,27 +81,28 @@ static void ____test_icr(struct xapic_vcpu *x, uint64_t val)
 	icr = (u64)(*((u32 *)&xapic.regs[APIC_ICR])) |
 	      (u64)(*((u32 *)&xapic.regs[APIC_ICR2])) << 32;
 	if (!x->is_x2apic) {
-		val &= (-1u | (0xffull << (32 + 24)));
-		TEST_ASSERT_EQ(icr, val & ~APIC_ICR_BUSY);
-	} else {
-		TEST_ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY);
+		if (!x->has_xavic_errata)
+			val &= (-1u | (0xffull << (32 + 24)));
+	} else if (val & X2APIC_RSVD_BITS_MASK) {
+		return;
 	}
-}
 
-#define X2APIC_RSVED_BITS_MASK  (GENMASK_ULL(31,20) | \
-				 GENMASK_ULL(17,16) | \
-				 GENMASK_ULL(13,13))
+	if (x->has_xavic_errata)
+		TEST_ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY);
+	else
+		TEST_ASSERT_EQ(icr, val & ~APIC_ICR_BUSY);
+}
 
 static void __test_icr(struct xapic_vcpu *x, uint64_t val)
 {
-	if (x->is_x2apic) {
-		/* Hardware writing vICR register requires reserved bits 31:20,
-		 * 17:16 and 13 kept as zero to avoid #GP exception. Data value
-		 * written to vICR should mask out those bits above.
-		 */
-		val &= ~X2APIC_RSVED_BITS_MASK;
-	}
-	____test_icr(x, val | APIC_ICR_BUSY);
+	/*
+	 * The BUSY bit is reserved on both AMD and Intel, but only AMD treats
+	 * it is as _must_ be zero.  Intel simply ignores the bit.  Don't test
+	 * the BUSY bit for x2APIC, as there is no single correct behavior.
+	 */
+	if (!x->is_x2apic)
+		____test_icr(x, val | APIC_ICR_BUSY);
+
 	____test_icr(x, val & ~(u64)APIC_ICR_BUSY);
 }
 
@@ -231,6 +242,15 @@ int main(int argc, char *argv[])
 	vm = vm_create_with_one_vcpu(&x.vcpu, xapic_guest_code);
 	x.is_x2apic = false;
 
+	/*
+	 * AMD's AVIC implementation is buggy (fails to clear the ICR BUSY bit),
+	 * and also diverges from KVM with respect to ICR2[23:0] (KVM and Intel
+	 * drops writes, AMD does not).  Account for the errata when checking
+	 * that KVM reads back what was written.
+	 */
+	x.has_xavic_errata = host_cpu_is_amd &&
+			     get_kvm_amd_param_bool("avic");
+
 	vcpu_clear_cpuid_feature(x.vcpu, X86_FEATURE_X2APIC);
 
 	virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA);
diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
index e149d0574961..2585087cdf5c 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
@@ -10,6 +10,7 @@
 #include "test_util.h"
 #include "kvm_util.h"
 #include "processor.h"
+#include "hyperv.h"
 
 #define HCALL_REGION_GPA	0xc0000000ULL
 #define HCALL_REGION_SLOT	10