summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/kvm/s390
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing/selftests/kvm/s390')
-rw-r--r--tools/testing/selftests/kvm/s390/cmma_test.c695
-rw-r--r--tools/testing/selftests/kvm/s390/config2
-rw-r--r--tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c301
-rw-r--r--tools/testing/selftests/kvm/s390/debug_test.c160
-rw-r--r--tools/testing/selftests/kvm/s390/memop.c1187
-rw-r--r--tools/testing/selftests/kvm/s390/resets.c313
-rw-r--r--tools/testing/selftests/kvm/s390/shared_zeropage_test.c111
-rw-r--r--tools/testing/selftests/kvm/s390/sync_regs_test.c238
-rw-r--r--tools/testing/selftests/kvm/s390/tprot.c244
-rw-r--r--tools/testing/selftests/kvm/s390/ucontrol_test.c800
10 files changed, 4051 insertions, 0 deletions
diff --git a/tools/testing/selftests/kvm/s390/cmma_test.c b/tools/testing/selftests/kvm/s390/cmma_test.c
new file mode 100644
index 000000000000..85cc8c18d6e7
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390/cmma_test.c
@@ -0,0 +1,695 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Test for s390x CMMA migration
+ *
+ * Copyright IBM Corp. 2023
+ *
+ * Authors:
+ * Nico Boehr <nrb@linux.ibm.com>
+ */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#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 PAGE_SIZE
+
+#define TEST_DATA_TWO_PAGE_COUNT 256
+#define TEST_DATA_TWO_MEMSLOT 2
+#define TEST_DATA_TWO_START_GFN (2 * PAGE_SIZE)
+
+static char cmma_value_buf[MAIN_PAGE_COUNT + TEST_DATA_PAGE_COUNT];
+
+/**
+ * Dirty CMMA attributes of exactly one page in the TEST_DATA memslot,
+ * so use_cmma goes on and the CMMA related ioctls do something.
+ */
+static void guest_do_one_essa(void)
+{
+ asm volatile(
+ /* load TEST_DATA_START_GFN into r1 */
+ " llilf 1,%[start_gfn]\n"
+ /* calculate the address from the gfn */
+ " sllg 1,1,12(0)\n"
+ /* set the first page in TEST_DATA memslot to STABLE */
+ " .insn rrf,0xb9ab0000,2,1,1,0\n"
+ /* hypercall */
+ " diag 0,0,0x501\n"
+ "0: j 0b"
+ :
+ : [start_gfn] "L"(TEST_DATA_START_GFN)
+ : "r1", "r2", "memory", "cc"
+ );
+}
+
+/**
+ * Touch CMMA attributes of all pages in TEST_DATA memslot. Set them to stable
+ * state.
+ */
+static void guest_dirty_test_data(void)
+{
+ asm volatile(
+ /* r1 = TEST_DATA_START_GFN */
+ " xgr 1,1\n"
+ " llilf 1,%[start_gfn]\n"
+ /* r5 = TEST_DATA_PAGE_COUNT */
+ " lghi 5,%[page_count]\n"
+ /* r5 += r1 */
+ "2: agfr 5,1\n"
+ /* r2 = r1 << PAGE_SHIFT */
+ "1: sllg 2,1,12(0)\n"
+ /* essa(r4, r2, SET_STABLE) */
+ " .insn rrf,0xb9ab0000,4,2,1,0\n"
+ /* i++ */
+ " agfi 1,1\n"
+ /* if r1 < r5 goto 1 */
+ " cgrjl 1,5,1b\n"
+ /* hypercall */
+ " diag 0,0,0x501\n"
+ "0: j 0b"
+ :
+ : [start_gfn] "L"(TEST_DATA_START_GFN),
+ [page_count] "L"(TEST_DATA_PAGE_COUNT)
+ :
+ /* the counter in our loop over the pages */
+ "r1",
+ /* the calculated page physical address */
+ "r2",
+ /* ESSA output register */
+ "r4",
+ /* last page */
+ "r5",
+ "cc", "memory"
+ );
+}
+
+static void create_main_memslot(struct kvm_vm *vm)
+{
+ int i;
+
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, MAIN_PAGE_COUNT, 0);
+ /* set the array of memslots to zero like __vm_create does */
+ for (i = 0; i < NR_MEM_REGIONS; i++)
+ vm->memslots[i] = 0;
+}
+
+static void create_test_memslot(struct kvm_vm *vm)
+{
+ vm_userspace_mem_region_add(vm,
+ VM_MEM_SRC_ANONYMOUS,
+ TEST_DATA_START_GFN << vm->page_shift,
+ TEST_DATA_MEMSLOT,
+ TEST_DATA_PAGE_COUNT,
+ 0
+ );
+ vm->memslots[MEM_REGION_TEST_DATA] = TEST_DATA_MEMSLOT;
+}
+
+static void create_memslots(struct kvm_vm *vm)
+{
+ /*
+ * Our VM has the following memory layout:
+ * +------+---------------------------+
+ * | GFN | Memslot |
+ * +------+---------------------------+
+ * | 0 | |
+ * | ... | MAIN (Code, Stack, ...) |
+ * | 511 | |
+ * +------+---------------------------+
+ * | 4096 | |
+ * | ... | TEST_DATA |
+ * | 4607 | |
+ * +------+---------------------------+
+ */
+ create_main_memslot(vm);
+ create_test_memslot(vm);
+}
+
+static void finish_vm_setup(struct kvm_vm *vm)
+{
+ struct userspace_mem_region *slot0;
+
+ kvm_vm_elf_load(vm, program_invocation_name);
+
+ slot0 = memslot2region(vm, 0);
+ ucall_init(vm, slot0->region.guest_phys_addr + slot0->region.memory_size);
+
+ kvm_arch_vm_post_create(vm);
+}
+
+static struct kvm_vm *create_vm_two_memslots(void)
+{
+ struct kvm_vm *vm;
+
+ vm = vm_create_barebones();
+
+ create_memslots(vm);
+
+ finish_vm_setup(vm);
+
+ return vm;
+}
+
+static void enable_cmma(struct kvm_vm *vm)
+{
+ int r;
+
+ r = __kvm_device_attr_set(vm->fd, KVM_S390_VM_MEM_CTRL, KVM_S390_VM_MEM_ENABLE_CMMA, NULL);
+ TEST_ASSERT(!r, "enabling cmma failed r=%d errno=%d", r, errno);
+}
+
+static void enable_dirty_tracking(struct kvm_vm *vm)
+{
+ vm_mem_region_set_flags(vm, 0, KVM_MEM_LOG_DIRTY_PAGES);
+ vm_mem_region_set_flags(vm, TEST_DATA_MEMSLOT, KVM_MEM_LOG_DIRTY_PAGES);
+}
+
+static int __enable_migration_mode(struct kvm_vm *vm)
+{
+ return __kvm_device_attr_set(vm->fd,
+ KVM_S390_VM_MIGRATION,
+ KVM_S390_VM_MIGRATION_START,
+ NULL
+ );
+}
+
+static void enable_migration_mode(struct kvm_vm *vm)
+{
+ int r = __enable_migration_mode(vm);
+
+ TEST_ASSERT(!r, "enabling migration mode failed r=%d errno=%d", r, errno);
+}
+
+static bool is_migration_mode_on(struct kvm_vm *vm)
+{
+ u64 out;
+ int r;
+
+ r = __kvm_device_attr_get(vm->fd,
+ KVM_S390_VM_MIGRATION,
+ KVM_S390_VM_MIGRATION_STATUS,
+ &out
+ );
+ TEST_ASSERT(!r, "getting migration mode status failed r=%d errno=%d", r, errno);
+ return out;
+}
+
+static int vm_get_cmma_bits(struct kvm_vm *vm, u64 flags, int *errno_out)
+{
+ struct kvm_s390_cmma_log args;
+ int rc;
+
+ errno = 0;
+
+ args = (struct kvm_s390_cmma_log){
+ .start_gfn = 0,
+ .count = sizeof(cmma_value_buf),
+ .flags = flags,
+ .values = (__u64)&cmma_value_buf[0]
+ };
+ rc = __vm_ioctl(vm, KVM_S390_GET_CMMA_BITS, &args);
+
+ *errno_out = errno;
+ return rc;
+}
+
+static void test_get_cmma_basic(void)
+{
+ struct kvm_vm *vm = create_vm_two_memslots();
+ struct kvm_vcpu *vcpu;
+ int rc, errno_out;
+
+ /* GET_CMMA_BITS without CMMA enabled should fail */
+ rc = vm_get_cmma_bits(vm, 0, &errno_out);
+ TEST_ASSERT_EQ(rc, -1);
+ TEST_ASSERT_EQ(errno_out, ENXIO);
+
+ enable_cmma(vm);
+ vcpu = vm_vcpu_add(vm, 1, guest_do_one_essa);
+
+ vcpu_run(vcpu);
+
+ /* GET_CMMA_BITS without migration mode and without peeking should fail */
+ rc = vm_get_cmma_bits(vm, 0, &errno_out);
+ TEST_ASSERT_EQ(rc, -1);
+ TEST_ASSERT_EQ(errno_out, EINVAL);
+
+ /* GET_CMMA_BITS without migration mode and with peeking should work */
+ rc = vm_get_cmma_bits(vm, KVM_S390_CMMA_PEEK, &errno_out);
+ TEST_ASSERT_EQ(rc, 0);
+ TEST_ASSERT_EQ(errno_out, 0);
+
+ enable_dirty_tracking(vm);
+ enable_migration_mode(vm);
+
+ /* GET_CMMA_BITS with invalid flags */
+ rc = vm_get_cmma_bits(vm, 0xfeedc0fe, &errno_out);
+ TEST_ASSERT_EQ(rc, -1);
+ TEST_ASSERT_EQ(errno_out, EINVAL);
+
+ kvm_vm_free(vm);
+}
+
+static void assert_exit_was_hypercall(struct kvm_vcpu *vcpu)
+{
+ TEST_ASSERT_EQ(vcpu->run->exit_reason, 13);
+ TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, 4);
+ TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa, 0x8300);
+ TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipb, 0x5010000);
+}
+
+static void test_migration_mode(void)
+{
+ struct kvm_vm *vm = vm_create_barebones();
+ struct kvm_vcpu *vcpu;
+ u64 orig_psw;
+ int rc;
+
+ /* enabling migration mode on a VM without memory should fail */
+ rc = __enable_migration_mode(vm);
+ TEST_ASSERT_EQ(rc, -1);
+ TEST_ASSERT_EQ(errno, EINVAL);
+ TEST_ASSERT(!is_migration_mode_on(vm), "migration mode should still be off");
+ errno = 0;
+
+ create_memslots(vm);
+ finish_vm_setup(vm);
+
+ enable_cmma(vm);
+ vcpu = vm_vcpu_add(vm, 1, guest_do_one_essa);
+ orig_psw = vcpu->run->psw_addr;
+
+ /*
+ * Execute one essa instruction in the guest. Otherwise the guest will
+ * not have use_cmm enabled and GET_CMMA_BITS will return no pages.
+ */
+ vcpu_run(vcpu);
+ assert_exit_was_hypercall(vcpu);
+
+ /* migration mode when memslots have dirty tracking off should fail */
+ rc = __enable_migration_mode(vm);
+ TEST_ASSERT_EQ(rc, -1);
+ TEST_ASSERT_EQ(errno, EINVAL);
+ TEST_ASSERT(!is_migration_mode_on(vm), "migration mode should still be off");
+ errno = 0;
+
+ /* enable dirty tracking */
+ enable_dirty_tracking(vm);
+
+ /* enabling migration mode should work now */
+ rc = __enable_migration_mode(vm);
+ TEST_ASSERT_EQ(rc, 0);
+ TEST_ASSERT(is_migration_mode_on(vm), "migration mode should be on");
+ errno = 0;
+
+ /* execute another ESSA instruction to see this goes fine */
+ vcpu->run->psw_addr = orig_psw;
+ vcpu_run(vcpu);
+ assert_exit_was_hypercall(vcpu);
+
+ /*
+ * With migration mode on, create a new memslot with dirty tracking off.
+ * This should turn off migration mode.
+ */
+ TEST_ASSERT(is_migration_mode_on(vm), "migration mode should be on");
+ vm_userspace_mem_region_add(vm,
+ VM_MEM_SRC_ANONYMOUS,
+ TEST_DATA_TWO_START_GFN << vm->page_shift,
+ TEST_DATA_TWO_MEMSLOT,
+ TEST_DATA_TWO_PAGE_COUNT,
+ 0
+ );
+ TEST_ASSERT(!is_migration_mode_on(vm),
+ "creating memslot without dirty tracking turns off migration mode"
+ );
+
+ /* ESSA instructions should still execute fine */
+ vcpu->run->psw_addr = orig_psw;
+ vcpu_run(vcpu);
+ assert_exit_was_hypercall(vcpu);
+
+ /*
+ * Turn on dirty tracking on the new memslot.
+ * It should be possible to turn migration mode back on again.
+ */
+ vm_mem_region_set_flags(vm, TEST_DATA_TWO_MEMSLOT, KVM_MEM_LOG_DIRTY_PAGES);
+ rc = __enable_migration_mode(vm);
+ TEST_ASSERT_EQ(rc, 0);
+ TEST_ASSERT(is_migration_mode_on(vm), "migration mode should be on");
+ errno = 0;
+
+ /*
+ * Turn off dirty tracking again, this time with just a flag change.
+ * Again, migration mode should turn off.
+ */
+ TEST_ASSERT(is_migration_mode_on(vm), "migration mode should be on");
+ vm_mem_region_set_flags(vm, TEST_DATA_TWO_MEMSLOT, 0);
+ TEST_ASSERT(!is_migration_mode_on(vm),
+ "disabling dirty tracking should turn off migration mode"
+ );
+
+ /* ESSA instructions should still execute fine */
+ vcpu->run->psw_addr = orig_psw;
+ vcpu_run(vcpu);
+ assert_exit_was_hypercall(vcpu);
+
+ kvm_vm_free(vm);
+}
+
+/**
+ * Given a VM with the MAIN and TEST_DATA memslot, assert that both slots have
+ * CMMA attributes of all pages in both memslots and nothing more dirty.
+ * This has the useful side effect of ensuring nothing is CMMA dirty after this
+ * function.
+ */
+static void assert_all_slots_cmma_dirty(struct kvm_vm *vm)
+{
+ struct kvm_s390_cmma_log args;
+
+ /*
+ * First iteration - everything should be dirty.
+ * Start at the main memslot...
+ */
+ args = (struct kvm_s390_cmma_log){
+ .start_gfn = 0,
+ .count = sizeof(cmma_value_buf),
+ .flags = 0,
+ .values = (__u64)&cmma_value_buf[0]
+ };
+ memset(cmma_value_buf, 0xff, sizeof(cmma_value_buf));
+ vm_ioctl(vm, KVM_S390_GET_CMMA_BITS, &args);
+ TEST_ASSERT_EQ(args.count, MAIN_PAGE_COUNT);
+ TEST_ASSERT_EQ(args.remaining, TEST_DATA_PAGE_COUNT);
+ TEST_ASSERT_EQ(args.start_gfn, 0);
+
+ /* ...and then - after a hole - the TEST_DATA memslot should follow */
+ args = (struct kvm_s390_cmma_log){
+ .start_gfn = MAIN_PAGE_COUNT,
+ .count = sizeof(cmma_value_buf),
+ .flags = 0,
+ .values = (__u64)&cmma_value_buf[0]
+ };
+ memset(cmma_value_buf, 0xff, sizeof(cmma_value_buf));
+ vm_ioctl(vm, KVM_S390_GET_CMMA_BITS, &args);
+ TEST_ASSERT_EQ(args.count, TEST_DATA_PAGE_COUNT);
+ TEST_ASSERT_EQ(args.start_gfn, TEST_DATA_START_GFN);
+ TEST_ASSERT_EQ(args.remaining, 0);
+
+ /* ...and nothing else should be there */
+ args = (struct kvm_s390_cmma_log){
+ .start_gfn = TEST_DATA_START_GFN + TEST_DATA_PAGE_COUNT,
+ .count = sizeof(cmma_value_buf),
+ .flags = 0,
+ .values = (__u64)&cmma_value_buf[0]
+ };
+ memset(cmma_value_buf, 0xff, sizeof(cmma_value_buf));
+ vm_ioctl(vm, KVM_S390_GET_CMMA_BITS, &args);
+ TEST_ASSERT_EQ(args.count, 0);
+ TEST_ASSERT_EQ(args.start_gfn, 0);
+ TEST_ASSERT_EQ(args.remaining, 0);
+}
+
+/**
+ * Given a VM, assert no pages are CMMA dirty.
+ */
+static void assert_no_pages_cmma_dirty(struct kvm_vm *vm)
+{
+ struct kvm_s390_cmma_log args;
+
+ /* If we start from GFN 0 again, nothing should be dirty. */
+ args = (struct kvm_s390_cmma_log){
+ .start_gfn = 0,
+ .count = sizeof(cmma_value_buf),
+ .flags = 0,
+ .values = (__u64)&cmma_value_buf[0]
+ };
+ memset(cmma_value_buf, 0xff, sizeof(cmma_value_buf));
+ vm_ioctl(vm, KVM_S390_GET_CMMA_BITS, &args);
+ if (args.count || args.remaining || args.start_gfn)
+ TEST_FAIL("pages are still dirty start_gfn=0x%llx count=%u remaining=%llu",
+ args.start_gfn,
+ args.count,
+ args.remaining
+ );
+}
+
+static void test_get_initial_dirty(void)
+{
+ struct kvm_vm *vm = create_vm_two_memslots();
+ struct kvm_vcpu *vcpu;
+
+ enable_cmma(vm);
+ vcpu = vm_vcpu_add(vm, 1, guest_do_one_essa);
+
+ /*
+ * Execute one essa instruction in the guest. Otherwise the guest will
+ * not have use_cmm enabled and GET_CMMA_BITS will return no pages.
+ */
+ vcpu_run(vcpu);
+ assert_exit_was_hypercall(vcpu);
+
+ enable_dirty_tracking(vm);
+ enable_migration_mode(vm);
+
+ assert_all_slots_cmma_dirty(vm);
+
+ /* Start from the beginning again and make sure nothing else is dirty */
+ assert_no_pages_cmma_dirty(vm);
+
+ kvm_vm_free(vm);
+}
+
+static void query_cmma_range(struct kvm_vm *vm,
+ u64 start_gfn, u64 gfn_count,
+ struct kvm_s390_cmma_log *res_out)
+{
+ *res_out = (struct kvm_s390_cmma_log){
+ .start_gfn = start_gfn,
+ .count = gfn_count,
+ .flags = 0,
+ .values = (__u64)&cmma_value_buf[0]
+ };
+ memset(cmma_value_buf, 0xff, sizeof(cmma_value_buf));
+ vm_ioctl(vm, KVM_S390_GET_CMMA_BITS, res_out);
+}
+
+/**
+ * Assert the given cmma_log struct that was executed by query_cmma_range()
+ * indicates the first dirty gfn is at first_dirty_gfn and contains exactly
+ * dirty_gfn_count CMMA values.
+ */
+static void assert_cmma_dirty(u64 first_dirty_gfn,
+ u64 dirty_gfn_count,
+ const struct kvm_s390_cmma_log *res)
+{
+ TEST_ASSERT_EQ(res->start_gfn, first_dirty_gfn);
+ TEST_ASSERT_EQ(res->count, dirty_gfn_count);
+ for (size_t i = 0; i < dirty_gfn_count; i++)
+ TEST_ASSERT_EQ(cmma_value_buf[0], 0x0); /* stable state */
+ TEST_ASSERT_EQ(cmma_value_buf[dirty_gfn_count], 0xff); /* not touched */
+}
+
+static void test_get_skip_holes(void)
+{
+ size_t gfn_offset;
+ struct kvm_vm *vm = create_vm_two_memslots();
+ struct kvm_s390_cmma_log log;
+ struct kvm_vcpu *vcpu;
+ u64 orig_psw;
+
+ enable_cmma(vm);
+ vcpu = vm_vcpu_add(vm, 1, guest_dirty_test_data);
+
+ orig_psw = vcpu->run->psw_addr;
+
+ /*
+ * Execute some essa instructions in the guest. Otherwise the guest will
+ * not have use_cmm enabled and GET_CMMA_BITS will return no pages.
+ */
+ vcpu_run(vcpu);
+ assert_exit_was_hypercall(vcpu);
+
+ enable_dirty_tracking(vm);
+ enable_migration_mode(vm);
+
+ /* un-dirty all pages */
+ assert_all_slots_cmma_dirty(vm);
+
+ /* Then, dirty just the TEST_DATA memslot */
+ vcpu->run->psw_addr = orig_psw;
+ vcpu_run(vcpu);
+
+ gfn_offset = TEST_DATA_START_GFN;
+ /**
+ * Query CMMA attributes of one page, starting at page 0. Since the
+ * main memslot was not touched by the VM, this should yield the first
+ * page of the TEST_DATA memslot.
+ * The dirty bitmap should now look like this:
+ * 0: not dirty
+ * [0x1, 0x200): dirty
+ */
+ query_cmma_range(vm, 0, 1, &log);
+ assert_cmma_dirty(gfn_offset, 1, &log);
+ gfn_offset++;
+
+ /**
+ * Query CMMA attributes of 32 (0x20) pages past the end of the TEST_DATA
+ * memslot. This should wrap back to the beginning of the TEST_DATA
+ * memslot, page 1.
+ * The dirty bitmap should now look like this:
+ * [0, 0x21): not dirty
+ * [0x21, 0x200): dirty
+ */
+ query_cmma_range(vm, TEST_DATA_START_GFN + TEST_DATA_PAGE_COUNT, 0x20, &log);
+ assert_cmma_dirty(gfn_offset, 0x20, &log);
+ gfn_offset += 0x20;
+
+ /* Skip 32 pages */
+ gfn_offset += 0x20;
+
+ /**
+ * After skipping 32 pages, query the next 32 (0x20) pages.
+ * The dirty bitmap should now look like this:
+ * [0, 0x21): not dirty
+ * [0x21, 0x41): dirty
+ * [0x41, 0x61): not dirty
+ * [0x61, 0x200): dirty
+ */
+ query_cmma_range(vm, gfn_offset, 0x20, &log);
+ assert_cmma_dirty(gfn_offset, 0x20, &log);
+ gfn_offset += 0x20;
+
+ /**
+ * Query 1 page from the beginning of the TEST_DATA memslot. This should
+ * yield page 0x21.
+ * The dirty bitmap should now look like this:
+ * [0, 0x22): not dirty
+ * [0x22, 0x41): dirty
+ * [0x41, 0x61): not dirty
+ * [0x61, 0x200): dirty
+ */
+ query_cmma_range(vm, TEST_DATA_START_GFN, 1, &log);
+ assert_cmma_dirty(TEST_DATA_START_GFN + 0x21, 1, &log);
+ gfn_offset++;
+
+ /**
+ * Query 15 (0xF) pages from page 0x23 in TEST_DATA memslot.
+ * This should yield pages [0x23, 0x33).
+ * The dirty bitmap should now look like this:
+ * [0, 0x22): not dirty
+ * 0x22: dirty
+ * [0x23, 0x33): not dirty
+ * [0x33, 0x41): dirty
+ * [0x41, 0x61): not dirty
+ * [0x61, 0x200): dirty
+ */
+ gfn_offset = TEST_DATA_START_GFN + 0x23;
+ query_cmma_range(vm, gfn_offset, 15, &log);
+ assert_cmma_dirty(gfn_offset, 15, &log);
+
+ /**
+ * Query 17 (0x11) pages from page 0x22 in TEST_DATA memslot.
+ * This should yield page [0x22, 0x33)
+ * The dirty bitmap should now look like this:
+ * [0, 0x33): not dirty
+ * [0x33, 0x41): dirty
+ * [0x41, 0x61): not dirty
+ * [0x61, 0x200): dirty
+ */
+ gfn_offset = TEST_DATA_START_GFN + 0x22;
+ query_cmma_range(vm, gfn_offset, 17, &log);
+ assert_cmma_dirty(gfn_offset, 17, &log);
+
+ /**
+ * Query 25 (0x19) pages from page 0x40 in TEST_DATA memslot.
+ * This should yield page 0x40 and nothing more, since there are more
+ * than 16 non-dirty pages after page 0x40.
+ * The dirty bitmap should now look like this:
+ * [0, 0x33): not dirty
+ * [0x33, 0x40): dirty
+ * [0x40, 0x61): not dirty
+ * [0x61, 0x200): dirty
+ */
+ gfn_offset = TEST_DATA_START_GFN + 0x40;
+ query_cmma_range(vm, gfn_offset, 25, &log);
+ assert_cmma_dirty(gfn_offset, 1, &log);
+
+ /**
+ * Query pages [0x33, 0x40).
+ * The dirty bitmap should now look like this:
+ * [0, 0x61): not dirty
+ * [0x61, 0x200): dirty
+ */
+ gfn_offset = TEST_DATA_START_GFN + 0x33;
+ query_cmma_range(vm, gfn_offset, 0x40 - 0x33, &log);
+ assert_cmma_dirty(gfn_offset, 0x40 - 0x33, &log);
+
+ /**
+ * Query the remaining pages [0x61, 0x200).
+ */
+ gfn_offset = TEST_DATA_START_GFN;
+ query_cmma_range(vm, gfn_offset, TEST_DATA_PAGE_COUNT - 0x61, &log);
+ assert_cmma_dirty(TEST_DATA_START_GFN + 0x61, TEST_DATA_PAGE_COUNT - 0x61, &log);
+
+ assert_no_pages_cmma_dirty(vm);
+}
+
+struct testdef {
+ const char *name;
+ void (*test)(void);
+} testlist[] = {
+ { "migration mode and dirty tracking", test_migration_mode },
+ { "GET_CMMA_BITS: basic calls", test_get_cmma_basic },
+ { "GET_CMMA_BITS: all pages are dirty initially", test_get_initial_dirty },
+ { "GET_CMMA_BITS: holes are skipped", test_get_skip_holes },
+};
+
+/**
+ * The kernel may support CMMA, but the machine may not (i.e. if running as
+ * guest-3).
+ *
+ * In this case, the CMMA capabilities are all there, but the CMMA-related
+ * ioctls fail. To find out whether the machine supports CMMA, create a
+ * temporary VM and then query the CMMA feature of the VM.
+ */
+static int machine_has_cmma(void)
+{
+ struct kvm_vm *vm = vm_create_barebones();
+ int r;
+
+ r = !__kvm_has_device_attr(vm->fd, KVM_S390_VM_MEM_CTRL, KVM_S390_VM_MEM_ENABLE_CMMA);
+ kvm_vm_free(vm);
+
+ return r;
+}
+
+int main(int argc, char *argv[])
+{
+ int idx;
+
+ TEST_REQUIRE(kvm_has_cap(KVM_CAP_SYNC_REGS));
+ TEST_REQUIRE(kvm_has_cap(KVM_CAP_S390_CMMA_MIGRATION));
+ TEST_REQUIRE(machine_has_cmma());
+
+ ksft_print_header();
+
+ ksft_set_plan(ARRAY_SIZE(testlist));
+
+ for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) {
+ testlist[idx].test();
+ ksft_test_result_pass("%s\n", testlist[idx].name);
+ }
+
+ ksft_finished(); /* Print results and exit() accordingly */
+}
diff --git a/tools/testing/selftests/kvm/s390/config b/tools/testing/selftests/kvm/s390/config
new file mode 100644
index 000000000000..23270f2d679f
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390/config
@@ -0,0 +1,2 @@
+CONFIG_KVM=y
+CONFIG_KVM_S390_UCONTROL=y
diff --git a/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c b/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c
new file mode 100644
index 000000000000..27255880dabd
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c
@@ -0,0 +1,301 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright IBM Corp. 2024
+ *
+ * Authors:
+ * Hariharan Mari <hari55@linux.ibm.com>
+ *
+ * The tests compare the result of the KVM ioctl for obtaining CPU subfunction data with those
+ * from an ASM block performing the same CPU subfunction. Currently KVM doesn't mask instruction
+ * query data reported via the CPU Model, allowing us to directly compare it with the data
+ * acquired through executing the queries in the test.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include "facility.h"
+
+#include "kvm_util.h"
+
+#define PLO_FUNCTION_MAX 256
+
+/* Query available CPU subfunctions */
+struct kvm_s390_vm_cpu_subfunc cpu_subfunc;
+
+static void get_cpu_machine_subfuntions(struct kvm_vm *vm,
+ struct kvm_s390_vm_cpu_subfunc *cpu_subfunc)
+{
+ int r;
+
+ r = __kvm_device_attr_get(vm->fd, KVM_S390_VM_CPU_MODEL,
+ KVM_S390_VM_CPU_MACHINE_SUBFUNC, cpu_subfunc);
+
+ TEST_ASSERT(!r, "Get cpu subfunctions failed r=%d errno=%d", r, errno);
+}
+
+static inline int plo_test_bit(unsigned char nr)
+{
+ unsigned long function = nr | 0x100;
+ int cc;
+
+ asm volatile(" lgr 0,%[function]\n"
+ /* Parameter registers are ignored for "test bit" */
+ " plo 0,0,0,0(0)\n"
+ " ipm %0\n"
+ " srl %0,28\n"
+ : "=d" (cc)
+ : [function] "d" (function)
+ : "cc", "0");
+ return cc == 0;
+}
+
+/* Testing Perform Locked Operation (PLO) CPU subfunction's ASM block */
+static void test_plo_asm_block(u8 (*query)[32])
+{
+ for (int i = 0; i < PLO_FUNCTION_MAX; ++i) {
+ if (plo_test_bit(i))
+ (*query)[i >> 3] |= 0x80 >> (i & 7);
+ }
+}
+
+/* Testing Crypto Compute Message Authentication Code (KMAC) CPU subfunction's ASM block */
+static void test_kmac_asm_block(u8 (*query)[16])
+{
+ asm volatile(" la %%r1,%[query]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rre,0xb91e0000,0,2\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "r0", "r1");
+}
+
+/* Testing Crypto Cipher Message with Chaining (KMC) CPU subfunction's ASM block */
+static void test_kmc_asm_block(u8 (*query)[16])
+{
+ asm volatile(" la %%r1,%[query]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rre,0xb92f0000,2,4\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "r0", "r1");
+}
+
+/* Testing Crypto Cipher Message (KM) CPU subfunction's ASM block */
+static void test_km_asm_block(u8 (*query)[16])
+{
+ asm volatile(" la %%r1,%[query]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rre,0xb92e0000,2,4\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "r0", "r1");
+}
+
+/* Testing Crypto Compute Intermediate Message Digest (KIMD) CPU subfunction's ASM block */
+static void test_kimd_asm_block(u8 (*query)[16])
+{
+ asm volatile(" la %%r1,%[query]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rre,0xb93e0000,0,2\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "r0", "r1");
+}
+
+/* Testing Crypto Compute Last Message Digest (KLMD) CPU subfunction's ASM block */
+static void test_klmd_asm_block(u8 (*query)[16])
+{
+ asm volatile(" la %%r1,%[query]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rre,0xb93f0000,0,2\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "r0", "r1");
+}
+
+/* Testing Crypto Cipher Message with Counter (KMCTR) CPU subfunction's ASM block */
+static void test_kmctr_asm_block(u8 (*query)[16])
+{
+ asm volatile(" la %%r1,%[query]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rrf,0xb92d0000,2,4,6,0\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "r0", "r1");
+}
+
+/* Testing Crypto Cipher Message with Cipher Feedback (KMF) CPU subfunction's ASM block */
+static void test_kmf_asm_block(u8 (*query)[16])
+{
+ asm volatile(" la %%r1,%[query]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rre,0xb92a0000,2,4\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "r0", "r1");
+}
+
+/* Testing Crypto Cipher Message with Output Feedback (KMO) CPU subfunction's ASM block */
+static void test_kmo_asm_block(u8 (*query)[16])
+{
+ asm volatile(" la %%r1,%[query]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rre,0xb92b0000,2,4\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "r0", "r1");
+}
+
+/* Testing Crypto Perform Cryptographic Computation (PCC) CPU subfunction's ASM block */
+static void test_pcc_asm_block(u8 (*query)[16])
+{
+ asm volatile(" la %%r1,%[query]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rre,0xb92c0000,0,0\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "r0", "r1");
+}
+
+/* Testing Crypto Perform Random Number Operation (PRNO) CPU subfunction's ASM block */
+static void test_prno_asm_block(u8 (*query)[16])
+{
+ asm volatile(" la %%r1,%[query]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rre,0xb93c0000,2,4\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "r0", "r1");
+}
+
+/* Testing Crypto Cipher Message with Authentication (KMA) CPU subfunction's ASM block */
+static void test_kma_asm_block(u8 (*query)[16])
+{
+ asm volatile(" la %%r1,%[query]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rrf,0xb9290000,2,4,6,0\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "r0", "r1");
+}
+
+/* Testing Crypto Compute Digital Signature Authentication (KDSA) CPU subfunction's ASM block */
+static void test_kdsa_asm_block(u8 (*query)[16])
+{
+ asm volatile(" la %%r1,%[query]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rre,0xb93a0000,0,2\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "r0", "r1");
+}
+
+/* Testing Sort Lists (SORTL) CPU subfunction's ASM block */
+static void test_sortl_asm_block(u8 (*query)[32])
+{
+ asm volatile(" lghi 0,0\n"
+ " la 1,%[query]\n"
+ " .insn rre,0xb9380000,2,4\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "0", "1");
+}
+
+/* Testing Deflate Conversion Call (DFLTCC) CPU subfunction's ASM block */
+static void test_dfltcc_asm_block(u8 (*query)[32])
+{
+ asm volatile(" lghi 0,0\n"
+ " la 1,%[query]\n"
+ " .insn rrf,0xb9390000,2,4,6,0\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "0", "1");
+}
+
+/*
+ * Testing Perform Function with Concurrent Results (PFCR)
+ * CPU subfunctions's ASM block
+ */
+static void test_pfcr_asm_block(u8 (*query)[16])
+{
+ asm volatile(" lghi 0,0\n"
+ " .insn rsy,0xeb0000000016,0,0,%[query]\n"
+ : [query] "=QS" (*query)
+ :
+ : "cc", "0");
+}
+
+typedef void (*testfunc_t)(u8 (*array)[]);
+
+struct testdef {
+ const char *subfunc_name;
+ u8 *subfunc_array;
+ size_t array_size;
+ testfunc_t test;
+ int facility_bit;
+} testlist[] = {
+ /*
+ * PLO was introduced in the very first 64-bit machine generation.
+ * Hence it is assumed PLO is always installed in Z Arch.
+ */
+ { "PLO", cpu_subfunc.plo, sizeof(cpu_subfunc.plo), test_plo_asm_block, 1 },
+ /* MSA - Facility bit 17 */
+ { "KMAC", cpu_subfunc.kmac, sizeof(cpu_subfunc.kmac), test_kmac_asm_block, 17 },
+ { "KMC", cpu_subfunc.kmc, sizeof(cpu_subfunc.kmc), test_kmc_asm_block, 17 },
+ { "KM", cpu_subfunc.km, sizeof(cpu_subfunc.km), test_km_asm_block, 17 },
+ { "KIMD", cpu_subfunc.kimd, sizeof(cpu_subfunc.kimd), test_kimd_asm_block, 17 },
+ { "KLMD", cpu_subfunc.klmd, sizeof(cpu_subfunc.klmd), test_klmd_asm_block, 17 },
+ /* MSA - Facility bit 77 */
+ { "KMCTR", cpu_subfunc.kmctr, sizeof(cpu_subfunc.kmctr), test_kmctr_asm_block, 77 },
+ { "KMF", cpu_subfunc.kmf, sizeof(cpu_subfunc.kmf), test_kmf_asm_block, 77 },
+ { "KMO", cpu_subfunc.kmo, sizeof(cpu_subfunc.kmo), test_kmo_asm_block, 77 },
+ { "PCC", cpu_subfunc.pcc, sizeof(cpu_subfunc.pcc), test_pcc_asm_block, 77 },
+ /* MSA5 - Facility bit 57 */
+ { "PPNO", cpu_subfunc.ppno, sizeof(cpu_subfunc.ppno), test_prno_asm_block, 57 },
+ /* MSA8 - Facility bit 146 */
+ { "KMA", cpu_subfunc.kma, sizeof(cpu_subfunc.kma), test_kma_asm_block, 146 },
+ /* MSA9 - Facility bit 155 */
+ { "KDSA", cpu_subfunc.kdsa, sizeof(cpu_subfunc.kdsa), test_kdsa_asm_block, 155 },
+ /* SORTL - Facility bit 150 */
+ { "SORTL", cpu_subfunc.sortl, sizeof(cpu_subfunc.sortl), test_sortl_asm_block, 150 },
+ /* DFLTCC - Facility bit 151 */
+ { "DFLTCC", cpu_subfunc.dfltcc, sizeof(cpu_subfunc.dfltcc), test_dfltcc_asm_block, 151 },
+ /* Concurrent-function facility - Facility bit 201 */
+ { "PFCR", cpu_subfunc.pfcr, sizeof(cpu_subfunc.pfcr), test_pfcr_asm_block, 201 },
+};
+
+int main(int argc, char *argv[])
+{
+ struct kvm_vm *vm;
+ int idx;
+
+ ksft_print_header();
+
+ vm = vm_create(1);
+
+ memset(&cpu_subfunc, 0, sizeof(cpu_subfunc));
+ get_cpu_machine_subfuntions(vm, &cpu_subfunc);
+
+ ksft_set_plan(ARRAY_SIZE(testlist));
+ for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) {
+ if (test_facility(testlist[idx].facility_bit)) {
+ u8 *array = malloc(testlist[idx].array_size);
+
+ testlist[idx].test((u8 (*)[testlist[idx].array_size])array);
+
+ TEST_ASSERT_EQ(memcmp(testlist[idx].subfunc_array,
+ array, testlist[idx].array_size), 0);
+
+ ksft_test_result_pass("%s\n", testlist[idx].subfunc_name);
+ free(array);
+ } else {
+ ksft_test_result_skip("%s feature is not avaialable\n",
+ testlist[idx].subfunc_name);
+ }
+ }
+
+ kvm_vm_free(vm);
+ ksft_finished();
+}
diff --git a/tools/testing/selftests/kvm/s390/debug_test.c b/tools/testing/selftests/kvm/s390/debug_test.c
new file mode 100644
index 000000000000..ad8095968601
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390/debug_test.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* 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 IPA0_DIAG 0x8300
+#define PGM_SPECIFICATION 0x06
+
+/* Common code for testing single-stepping interruptions. */
+extern char int_handler[];
+asm("int_handler:\n"
+ "j .\n");
+
+static struct kvm_vm *test_step_int_1(struct kvm_vcpu **vcpu, void *guest_code,
+ size_t new_psw_off, uint64_t *new_psw)
+{
+ struct kvm_guest_debug debug = {};
+ struct kvm_regs regs;
+ struct kvm_vm *vm;
+ char *lowcore;
+
+ vm = vm_create_with_one_vcpu(vcpu, guest_code);
+ lowcore = addr_gpa2hva(vm, 0);
+ new_psw[0] = (*vcpu)->run->psw_mask;
+ new_psw[1] = (uint64_t)int_handler;
+ memcpy(lowcore + new_psw_off, new_psw, 16);
+ vcpu_regs_get(*vcpu, &regs);
+ regs.gprs[2] = -1;
+ vcpu_regs_set(*vcpu, &regs);
+ debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP;
+ vcpu_guest_debug_set(*vcpu, &debug);
+ vcpu_run(*vcpu);
+
+ return vm;
+}
+
+static void test_step_int(void *guest_code, size_t new_psw_off)
+{
+ struct kvm_vcpu *vcpu;
+ uint64_t new_psw[2];
+ struct kvm_vm *vm;
+
+ vm = test_step_int_1(&vcpu, guest_code, new_psw_off, new_psw);
+ TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_DEBUG);
+ TEST_ASSERT_EQ(vcpu->run->psw_mask, new_psw[0]);
+ TEST_ASSERT_EQ(vcpu->run->psw_addr, new_psw[1]);
+ kvm_vm_free(vm);
+}
+
+/* Test single-stepping "boring" program interruptions. */
+extern char test_step_pgm_guest_code[];
+asm("test_step_pgm_guest_code:\n"
+ ".insn rr,0x1d00,%r1,%r0 /* dr %r1,%r0 */\n"
+ "j .\n");
+
+static void test_step_pgm(void)
+{
+ test_step_int(test_step_pgm_guest_code, __LC_PGM_NEW_PSW);
+}
+
+/*
+ * Test single-stepping program interruptions caused by DIAG.
+ * Userspace emulation must not interfere with single-stepping.
+ */
+extern char test_step_pgm_diag_guest_code[];
+asm("test_step_pgm_diag_guest_code:\n"
+ "diag %r0,%r0,0\n"
+ "j .\n");
+
+static void test_step_pgm_diag(void)
+{
+ struct kvm_s390_irq irq = {
+ .type = KVM_S390_PROGRAM_INT,
+ .u.pgm.code = PGM_SPECIFICATION,
+ };
+ struct kvm_vcpu *vcpu;
+ uint64_t new_psw[2];
+ struct kvm_vm *vm;
+
+ 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_INST);
+ TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa & 0xff00, IPA0_DIAG);
+ vcpu_ioctl(vcpu, KVM_S390_IRQ, &irq);
+ vcpu_run(vcpu);
+ TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_DEBUG);
+ TEST_ASSERT_EQ(vcpu->run->psw_mask, new_psw[0]);
+ TEST_ASSERT_EQ(vcpu->run->psw_addr, new_psw[1]);
+ kvm_vm_free(vm);
+}
+
+/*
+ * Test single-stepping program interruptions caused by ISKE.
+ * CPUSTAT_KSS handling must not interfere with single-stepping.
+ */
+extern char test_step_pgm_iske_guest_code[];
+asm("test_step_pgm_iske_guest_code:\n"
+ "iske %r2,%r2\n"
+ "j .\n");
+
+static void test_step_pgm_iske(void)
+{
+ test_step_int(test_step_pgm_iske_guest_code, __LC_PGM_NEW_PSW);
+}
+
+/*
+ * Test single-stepping program interruptions caused by LCTL.
+ * KVM emulation must not interfere with single-stepping.
+ */
+extern char test_step_pgm_lctl_guest_code[];
+asm("test_step_pgm_lctl_guest_code:\n"
+ "lctl %c0,%c0,1\n"
+ "j .\n");
+
+static void test_step_pgm_lctl(void)
+{
+ test_step_int(test_step_pgm_lctl_guest_code, __LC_PGM_NEW_PSW);
+}
+
+/* Test single-stepping supervisor-call interruptions. */
+extern char test_step_svc_guest_code[];
+asm("test_step_svc_guest_code:\n"
+ "svc 0\n"
+ "j .\n");
+
+static void test_step_svc(void)
+{
+ test_step_int(test_step_svc_guest_code, __LC_SVC_NEW_PSW);
+}
+
+/* Run all tests above. */
+static struct testdef {
+ const char *name;
+ void (*test)(void);
+} testlist[] = {
+ { "single-step pgm", test_step_pgm },
+ { "single-step pgm caused by diag", test_step_pgm_diag },
+ { "single-step pgm caused by iske", test_step_pgm_iske },
+ { "single-step pgm caused by lctl", test_step_pgm_lctl },
+ { "single-step svc", test_step_svc },
+};
+
+int main(int argc, char *argv[])
+{
+ int idx;
+
+ ksft_print_header();
+ ksft_set_plan(ARRAY_SIZE(testlist));
+ for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) {
+ testlist[idx].test();
+ ksft_test_result_pass("%s\n", testlist[idx].name);
+ }
+ ksft_finished();
+}
diff --git a/tools/testing/selftests/kvm/s390/memop.c b/tools/testing/selftests/kvm/s390/memop.c
new file mode 100644
index 000000000000..4374b4cd2a80
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390/memop.c
@@ -0,0 +1,1187 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Test for s390x KVM_S390_MEM_OP
+ *
+ * Copyright (C) 2019, Red Hat, Inc.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <pthread.h>
+
+#include <linux/bits.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "kselftest.h"
+#include "ucall_common.h"
+#include "processor.h"
+
+enum mop_target {
+ LOGICAL,
+ SIDA,
+ ABSOLUTE,
+ INVALID,
+};
+
+enum mop_access_mode {
+ READ,
+ WRITE,
+ CMPXCHG,
+};
+
+struct mop_desc {
+ uintptr_t gaddr;
+ uintptr_t gaddr_v;
+ uint64_t set_flags;
+ unsigned int f_check : 1;
+ unsigned int f_inject : 1;
+ unsigned int f_key : 1;
+ unsigned int _gaddr_v : 1;
+ unsigned int _set_flags : 1;
+ unsigned int _sida_offset : 1;
+ unsigned int _ar : 1;
+ uint32_t size;
+ enum mop_target target;
+ enum mop_access_mode mode;
+ void *buf;
+ uint32_t sida_offset;
+ void *old;
+ uint8_t old_value[16];
+ bool *cmpxchg_success;
+ uint8_t ar;
+ uint8_t key;
+};
+
+const uint8_t NO_KEY = 0xff;
+
+static struct kvm_s390_mem_op ksmo_from_desc(struct mop_desc *desc)
+{
+ struct kvm_s390_mem_op ksmo = {
+ .gaddr = (uintptr_t)desc->gaddr,
+ .size = desc->size,
+ .buf = ((uintptr_t)desc->buf),
+ .reserved = "ignored_ignored_ignored_ignored"
+ };
+
+ switch (desc->target) {
+ case LOGICAL:
+ if (desc->mode == READ)
+ ksmo.op = KVM_S390_MEMOP_LOGICAL_READ;
+ if (desc->mode == WRITE)
+ ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE;
+ break;
+ case SIDA:
+ if (desc->mode == READ)
+ ksmo.op = KVM_S390_MEMOP_SIDA_READ;
+ if (desc->mode == WRITE)
+ ksmo.op = KVM_S390_MEMOP_SIDA_WRITE;
+ break;
+ case ABSOLUTE:
+ if (desc->mode == READ)
+ ksmo.op = KVM_S390_MEMOP_ABSOLUTE_READ;
+ if (desc->mode == WRITE)
+ ksmo.op = KVM_S390_MEMOP_ABSOLUTE_WRITE;
+ if (desc->mode == CMPXCHG) {
+ ksmo.op = KVM_S390_MEMOP_ABSOLUTE_CMPXCHG;
+ ksmo.old_addr = (uint64_t)desc->old;
+ memcpy(desc->old_value, desc->old, desc->size);
+ }
+ break;
+ case INVALID:
+ ksmo.op = -1;
+ }
+ if (desc->f_check)
+ ksmo.flags |= KVM_S390_MEMOP_F_CHECK_ONLY;
+ if (desc->f_inject)
+ ksmo.flags |= KVM_S390_MEMOP_F_INJECT_EXCEPTION;
+ if (desc->_set_flags)
+ ksmo.flags = desc->set_flags;
+ if (desc->f_key && desc->key != NO_KEY) {
+ ksmo.flags |= KVM_S390_MEMOP_F_SKEY_PROTECTION;
+ ksmo.key = desc->key;
+ }
+ if (desc->_ar)
+ ksmo.ar = desc->ar;
+ else
+ ksmo.ar = 0;
+ if (desc->_sida_offset)
+ ksmo.sida_offset = desc->sida_offset;
+
+ return ksmo;
+}
+
+struct test_info {
+ struct kvm_vm *vm;
+ struct kvm_vcpu *vcpu;
+};
+
+#define PRINT_MEMOP false
+static void print_memop(struct kvm_vcpu *vcpu, const struct kvm_s390_mem_op *ksmo)
+{
+ if (!PRINT_MEMOP)
+ return;
+
+ if (!vcpu)
+ printf("vm memop(");
+ else
+ printf("vcpu memop(");
+ switch (ksmo->op) {
+ case KVM_S390_MEMOP_LOGICAL_READ:
+ printf("LOGICAL, READ, ");
+ break;
+ case KVM_S390_MEMOP_LOGICAL_WRITE:
+ printf("LOGICAL, WRITE, ");
+ break;
+ case KVM_S390_MEMOP_SIDA_READ:
+ printf("SIDA, READ, ");
+ break;
+ case KVM_S390_MEMOP_SIDA_WRITE:
+ printf("SIDA, WRITE, ");
+ break;
+ case KVM_S390_MEMOP_ABSOLUTE_READ:
+ printf("ABSOLUTE, READ, ");
+ break;
+ case KVM_S390_MEMOP_ABSOLUTE_WRITE:
+ printf("ABSOLUTE, WRITE, ");
+ break;
+ case KVM_S390_MEMOP_ABSOLUTE_CMPXCHG:
+ printf("ABSOLUTE, CMPXCHG, ");
+ break;
+ }
+ printf("gaddr=%llu, size=%u, buf=%llu, ar=%u, key=%u, old_addr=%llx",
+ ksmo->gaddr, ksmo->size, ksmo->buf, ksmo->ar, ksmo->key,
+ ksmo->old_addr);
+ if (ksmo->flags & KVM_S390_MEMOP_F_CHECK_ONLY)
+ printf(", CHECK_ONLY");
+ if (ksmo->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION)
+ printf(", INJECT_EXCEPTION");
+ if (ksmo->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION)
+ printf(", SKEY_PROTECTION");
+ puts(")");
+}
+
+static int err_memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo,
+ struct mop_desc *desc)
+{
+ struct kvm_vcpu *vcpu = info.vcpu;
+
+ if (!vcpu)
+ return __vm_ioctl(info.vm, KVM_S390_MEM_OP, ksmo);
+ else
+ return __vcpu_ioctl(vcpu, KVM_S390_MEM_OP, ksmo);
+}
+
+static void memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo,
+ struct mop_desc *desc)
+{
+ int r;
+
+ r = err_memop_ioctl(info, ksmo, desc);
+ if (ksmo->op == KVM_S390_MEMOP_ABSOLUTE_CMPXCHG) {
+ if (desc->cmpxchg_success) {
+ int diff = memcmp(desc->old_value, desc->old, desc->size);
+ *desc->cmpxchg_success = !diff;
+ }
+ }
+ TEST_ASSERT(!r, __KVM_IOCTL_ERROR("KVM_S390_MEM_OP", r));
+}
+
+#define MEMOP(err, info_p, mop_target_p, access_mode_p, buf_p, size_p, ...) \
+({ \
+ struct test_info __info = (info_p); \
+ struct mop_desc __desc = { \
+ .target = (mop_target_p), \
+ .mode = (access_mode_p), \
+ .buf = (buf_p), \
+ .size = (size_p), \
+ __VA_ARGS__ \
+ }; \
+ struct kvm_s390_mem_op __ksmo; \
+ \
+ if (__desc._gaddr_v) { \
+ if (__desc.target == ABSOLUTE) \
+ __desc.gaddr = addr_gva2gpa(__info.vm, __desc.gaddr_v); \
+ else \
+ __desc.gaddr = __desc.gaddr_v; \
+ } \
+ __ksmo = ksmo_from_desc(&__desc); \
+ print_memop(__info.vcpu, &__ksmo); \
+ err##memop_ioctl(__info, &__ksmo, &__desc); \
+})
+
+#define MOP(...) MEMOP(, __VA_ARGS__)
+#define ERR_MOP(...) MEMOP(err_, __VA_ARGS__)
+
+#define GADDR(a) .gaddr = ((uintptr_t)a)
+#define GADDR_V(v) ._gaddr_v = 1, .gaddr_v = ((uintptr_t)v)
+#define CHECK_ONLY .f_check = 1
+#define SET_FLAGS(f) ._set_flags = 1, .set_flags = (f)
+#define SIDA_OFFSET(o) ._sida_offset = 1, .sida_offset = (o)
+#define AR(a) ._ar = 1, .ar = (a)
+#define KEY(a) .f_key = 1, .key = (a)
+#define INJECT .f_inject = 1
+#define CMPXCHG_OLD(o) .old = (o)
+#define CMPXCHG_SUCCESS(s) .cmpxchg_success = (s)
+
+#define CHECK_N_DO(f, ...) ({ f(__VA_ARGS__, CHECK_ONLY); f(__VA_ARGS__); })
+
+#define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38))
+#define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39))
+
+static uint8_t __aligned(PAGE_SIZE) mem1[65536];
+static uint8_t __aligned(PAGE_SIZE) mem2[65536];
+
+struct test_default {
+ struct kvm_vm *kvm_vm;
+ struct test_info vm;
+ struct test_info vcpu;
+ struct kvm_run *run;
+ int size;
+};
+
+static struct test_default test_default_init(void *guest_code)
+{
+ struct kvm_vcpu *vcpu;
+ struct test_default t;
+
+ t.size = min((size_t)kvm_check_cap(KVM_CAP_S390_MEM_OP), sizeof(mem1));
+ t.kvm_vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+ t.vm = (struct test_info) { t.kvm_vm, NULL };
+ t.vcpu = (struct test_info) { t.kvm_vm, vcpu };
+ t.run = vcpu->run;
+ return t;
+}
+
+enum stage {
+ /* Synced state set by host, e.g. DAT */
+ STAGE_INITED,
+ /* Guest did nothing */
+ STAGE_IDLED,
+ /* Guest set storage keys (specifics up to test case) */
+ STAGE_SKEYS_SET,
+ /* Guest copied memory (locations up to test case) */
+ STAGE_COPIED,
+ /* End of guest code reached */
+ STAGE_DONE,
+};
+
+#define HOST_SYNC(info_p, stage) \
+({ \
+ struct test_info __info = (info_p); \
+ struct kvm_vcpu *__vcpu = __info.vcpu; \
+ struct ucall uc; \
+ int __stage = (stage); \
+ \
+ vcpu_run(__vcpu); \
+ get_ucall(__vcpu, &uc); \
+ if (uc.cmd == UCALL_ABORT) { \
+ REPORT_GUEST_ASSERT(uc); \
+ } \
+ TEST_ASSERT_EQ(uc.cmd, UCALL_SYNC); \
+ TEST_ASSERT_EQ(uc.args[1], __stage); \
+}) \
+
+static void prepare_mem12(void)
+{
+ int i;
+
+ for (i = 0; i < sizeof(mem1); i++)
+ mem1[i] = rand();
+ memset(mem2, 0xaa, sizeof(mem2));
+}
+
+#define ASSERT_MEM_EQ(p1, p2, size) \
+ TEST_ASSERT(!memcmp(p1, p2, size), "Memory contents do not match!")
+
+static void default_write_read(struct test_info copy_cpu, struct test_info mop_cpu,
+ enum mop_target mop_target, uint32_t size, uint8_t key)
+{
+ prepare_mem12();
+ CHECK_N_DO(MOP, mop_cpu, mop_target, WRITE, mem1, size,
+ GADDR_V(mem1), KEY(key));
+ HOST_SYNC(copy_cpu, STAGE_COPIED);
+ CHECK_N_DO(MOP, mop_cpu, mop_target, READ, mem2, size,
+ GADDR_V(mem2), KEY(key));
+ ASSERT_MEM_EQ(mem1, mem2, size);
+}
+
+static void default_read(struct test_info copy_cpu, struct test_info mop_cpu,
+ enum mop_target mop_target, uint32_t size, uint8_t key)
+{
+ prepare_mem12();
+ CHECK_N_DO(MOP, mop_cpu, mop_target, WRITE, mem1, size, GADDR_V(mem1));
+ HOST_SYNC(copy_cpu, STAGE_COPIED);
+ CHECK_N_DO(MOP, mop_cpu, mop_target, READ, mem2, size,
+ GADDR_V(mem2), KEY(key));
+ ASSERT_MEM_EQ(mem1, mem2, size);
+}
+
+static void default_cmpxchg(struct test_default *test, uint8_t key)
+{
+ for (int size = 1; size <= 16; size *= 2) {
+ for (int offset = 0; offset < 16; offset += size) {
+ uint8_t __aligned(16) new[16] = {};
+ uint8_t __aligned(16) old[16];
+ bool succ;
+
+ prepare_mem12();
+ default_write_read(test->vcpu, test->vcpu, LOGICAL, 16, NO_KEY);
+
+ memcpy(&old, mem1, 16);
+ MOP(test->vm, ABSOLUTE, CMPXCHG, new + offset,
+ size, GADDR_V(mem1 + offset),
+ CMPXCHG_OLD(old + offset),
+ CMPXCHG_SUCCESS(&succ), KEY(key));
+ HOST_SYNC(test->vcpu, STAGE_COPIED);
+ MOP(test->vm, ABSOLUTE, READ, mem2, 16, GADDR_V(mem2));
+ TEST_ASSERT(succ, "exchange of values should succeed");
+ memcpy(mem1 + offset, new + offset, size);
+ ASSERT_MEM_EQ(mem1, mem2, 16);
+
+ memcpy(&old, mem1, 16);
+ new[offset]++;
+ old[offset]++;
+ MOP(test->vm, ABSOLUTE, CMPXCHG, new + offset,
+ size, GADDR_V(mem1 + offset),
+ CMPXCHG_OLD(old + offset),
+ CMPXCHG_SUCCESS(&succ), KEY(key));
+ HOST_SYNC(test->vcpu, STAGE_COPIED);
+ MOP(test->vm, ABSOLUTE, READ, mem2, 16, GADDR_V(mem2));
+ TEST_ASSERT(!succ, "exchange of values should not succeed");
+ ASSERT_MEM_EQ(mem1, mem2, 16);
+ ASSERT_MEM_EQ(&old, mem1, 16);
+ }
+ }
+}
+
+static void guest_copy(void)
+{
+ GUEST_SYNC(STAGE_INITED);
+ memcpy(&mem2, &mem1, sizeof(mem2));
+ GUEST_SYNC(STAGE_COPIED);
+}
+
+static void test_copy(void)
+{
+ struct test_default t = test_default_init(guest_copy);
+
+ HOST_SYNC(t.vcpu, STAGE_INITED);
+
+ default_write_read(t.vcpu, t.vcpu, LOGICAL, t.size, NO_KEY);
+
+ kvm_vm_free(t.kvm_vm);
+}
+
+static void test_copy_access_register(void)
+{
+ struct test_default t = test_default_init(guest_copy);
+
+ HOST_SYNC(t.vcpu, STAGE_INITED);
+
+ prepare_mem12();
+ t.run->psw_mask &= ~(3UL << (63 - 17));
+ t.run->psw_mask |= 1UL << (63 - 17); /* Enable AR mode */
+
+ /*
+ * Primary address space gets used if an access register
+ * contains zero. The host makes use of AR[1] so is a good
+ * candidate to ensure the guest AR (of zero) is used.
+ */
+ CHECK_N_DO(MOP, t.vcpu, LOGICAL, WRITE, mem1, t.size,
+ GADDR_V(mem1), AR(1));
+ HOST_SYNC(t.vcpu, STAGE_COPIED);
+
+ CHECK_N_DO(MOP, t.vcpu, LOGICAL, READ, mem2, t.size,
+ GADDR_V(mem2), AR(1));
+ ASSERT_MEM_EQ(mem1, mem2, t.size);
+
+ kvm_vm_free(t.kvm_vm);
+}
+
+static void set_storage_key_range(void *addr, size_t len, uint8_t key)
+{
+ uintptr_t _addr, abs, i;
+ int not_mapped = 0;
+
+ _addr = (uintptr_t)addr;
+ for (i = _addr & PAGE_MASK; i < _addr + len; i += PAGE_SIZE) {
+ abs = i;
+ asm volatile (
+ "lra %[abs], 0(0,%[abs])\n"
+ " jz 0f\n"
+ " llill %[not_mapped],1\n"
+ " j 1f\n"
+ "0: sske %[key], %[abs]\n"
+ "1:"
+ : [abs] "+&a" (abs), [not_mapped] "+r" (not_mapped)
+ : [key] "r" (key)
+ : "cc"
+ );
+ GUEST_ASSERT_EQ(not_mapped, 0);
+ }
+}
+
+static void guest_copy_key(void)
+{
+ set_storage_key_range(mem1, sizeof(mem1), 0x90);
+ set_storage_key_range(mem2, sizeof(mem2), 0x90);
+ GUEST_SYNC(STAGE_SKEYS_SET);
+
+ for (;;) {
+ memcpy(&mem2, &mem1, sizeof(mem2));
+ GUEST_SYNC(STAGE_COPIED);
+ }
+}
+
+static void test_copy_key(void)
+{
+ struct test_default t = test_default_init(guest_copy_key);
+
+ HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+ /* vm, no key */
+ default_write_read(t.vcpu, t.vm, ABSOLUTE, t.size, NO_KEY);
+
+ /* vm/vcpu, machting key or key 0 */
+ default_write_read(t.vcpu, t.vcpu, LOGICAL, t.size, 0);
+ default_write_read(t.vcpu, t.vcpu, LOGICAL, t.size, 9);
+ default_write_read(t.vcpu, t.vm, ABSOLUTE, t.size, 0);
+ default_write_read(t.vcpu, t.vm, ABSOLUTE, t.size, 9);
+ /*
+ * There used to be different code paths for key handling depending on
+ * if the region crossed a page boundary.
+ * There currently are not, but the more tests the merrier.
+ */
+ default_write_read(t.vcpu, t.vcpu, LOGICAL, 1, 0);
+ default_write_read(t.vcpu, t.vcpu, LOGICAL, 1, 9);
+ default_write_read(t.vcpu, t.vm, ABSOLUTE, 1, 0);
+ default_write_read(t.vcpu, t.vm, ABSOLUTE, 1, 9);
+
+ /* vm/vcpu, mismatching keys on read, but no fetch protection */
+ default_read(t.vcpu, t.vcpu, LOGICAL, t.size, 2);
+ default_read(t.vcpu, t.vm, ABSOLUTE, t.size, 2);
+
+ kvm_vm_free(t.kvm_vm);
+}
+
+static void test_cmpxchg_key(void)
+{
+ struct test_default t = test_default_init(guest_copy_key);
+
+ HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+ default_cmpxchg(&t, NO_KEY);
+ default_cmpxchg(&t, 0);
+ default_cmpxchg(&t, 9);
+
+ kvm_vm_free(t.kvm_vm);
+}
+
+static __uint128_t cut_to_size(int size, __uint128_t val)
+{
+ switch (size) {
+ case 1:
+ return (uint8_t)val;
+ case 2:
+ return (uint16_t)val;
+ case 4:
+ return (uint32_t)val;
+ case 8:
+ return (uint64_t)val;
+ case 16:
+ return val;
+ }
+ GUEST_FAIL("Invalid size = %u", size);
+ return 0;
+}
+
+static bool popcount_eq(__uint128_t a, __uint128_t b)
+{
+ unsigned int count_a, count_b;
+
+ count_a = __builtin_popcountl((uint64_t)(a >> 64)) +
+ __builtin_popcountl((uint64_t)a);
+ count_b = __builtin_popcountl((uint64_t)(b >> 64)) +
+ __builtin_popcountl((uint64_t)b);
+ return count_a == count_b;
+}
+
+static __uint128_t rotate(int size, __uint128_t val, int amount)
+{
+ unsigned int bits = size * 8;
+
+ amount = (amount + bits) % bits;
+ val = cut_to_size(size, val);
+ if (!amount)
+ return val;
+ return (val << (bits - amount)) | (val >> amount);
+}
+
+const unsigned int max_block = 16;
+
+static void choose_block(bool guest, int i, int *size, int *offset)
+{
+ unsigned int rand;
+
+ rand = i;
+ if (guest) {
+ rand = rand * 19 + 11;
+ *size = 1 << ((rand % 3) + 2);
+ rand = rand * 19 + 11;
+ *offset = (rand % max_block) & ~(*size - 1);
+ } else {
+ rand = rand * 17 + 5;
+ *size = 1 << (rand % 5);
+ rand = rand * 17 + 5;
+ *offset = (rand % max_block) & ~(*size - 1);
+ }
+}
+
+static __uint128_t permutate_bits(bool guest, int i, int size, __uint128_t old)
+{
+ unsigned int rand;
+ int amount;
+ bool swap;
+
+ rand = i;
+ rand = rand * 3 + 1;
+ if (guest)
+ rand = rand * 3 + 1;
+ swap = rand % 2 == 0;
+ if (swap) {
+ int i, j;
+ __uint128_t new;
+ uint8_t byte0, byte1;
+
+ rand = rand * 3 + 1;
+ i = rand % size;
+ rand = rand * 3 + 1;
+ j = rand % size;
+ if (i == j)
+ return old;
+ new = rotate(16, old, i * 8);
+ byte0 = new & 0xff;
+ new &= ~0xff;
+ new = rotate(16, new, -i * 8);
+ new = rotate(16, new, j * 8);
+ byte1 = new & 0xff;
+ new = (new & ~0xff) | byte0;
+ new = rotate(16, new, -j * 8);
+ new = rotate(16, new, i * 8);
+ new = new | byte1;
+ new = rotate(16, new, -i * 8);
+ return new;
+ }
+ rand = rand * 3 + 1;
+ amount = rand % (size * 8);
+ return rotate(size, old, amount);
+}
+
+static bool _cmpxchg(int size, void *target, __uint128_t *old_addr, __uint128_t new)
+{
+ bool ret;
+
+ switch (size) {
+ case 4: {
+ uint32_t old = *old_addr;
+
+ asm volatile ("cs %[old],%[new],%[address]"
+ : [old] "+d" (old),
+ [address] "+Q" (*(uint32_t *)(target))
+ : [new] "d" ((uint32_t)new)
+ : "cc"
+ );
+ ret = old == (uint32_t)*old_addr;
+ *old_addr = old;
+ return ret;
+ }
+ case 8: {
+ uint64_t old = *old_addr;
+
+ asm volatile ("csg %[old],%[new],%[address]"
+ : [old] "+d" (old),
+ [address] "+Q" (*(uint64_t *)(target))
+ : [new] "d" ((uint64_t)new)
+ : "cc"
+ );
+ ret = old == (uint64_t)*old_addr;
+ *old_addr = old;
+ return ret;
+ }
+ case 16: {
+ __uint128_t old = *old_addr;
+
+ asm volatile ("cdsg %[old],%[new],%[address]"
+ : [old] "+d" (old),
+ [address] "+Q" (*(__uint128_t *)(target))
+ : [new] "d" (new)
+ : "cc"
+ );
+ ret = old == *old_addr;
+ *old_addr = old;
+ return ret;
+ }
+ }
+ GUEST_FAIL("Invalid size = %u", size);
+ return 0;
+}
+
+const unsigned int cmpxchg_iter_outer = 100, cmpxchg_iter_inner = 10000;
+
+static void guest_cmpxchg_key(void)
+{
+ int size, offset;
+ __uint128_t old, new;
+
+ set_storage_key_range(mem1, max_block, 0x10);
+ set_storage_key_range(mem2, max_block, 0x10);
+ GUEST_SYNC(STAGE_SKEYS_SET);
+
+ for (int i = 0; i < cmpxchg_iter_outer; i++) {
+ do {
+ old = 1;
+ } while (!_cmpxchg(16, mem1, &old, 0));
+ for (int j = 0; j < cmpxchg_iter_inner; j++) {
+ choose_block(true, i + j, &size, &offset);
+ do {
+ new = permutate_bits(true, i + j, size, old);
+ } while (!_cmpxchg(size, mem2 + offset, &old, new));
+ }
+ }
+
+ GUEST_SYNC(STAGE_DONE);
+}
+
+static void *run_guest(void *data)
+{
+ struct test_info *info = data;
+
+ HOST_SYNC(*info, STAGE_DONE);
+ return NULL;
+}
+
+static char *quad_to_char(__uint128_t *quad, int size)
+{
+ return ((char *)quad) + (sizeof(*quad) - size);
+}
+
+static void test_cmpxchg_key_concurrent(void)
+{
+ struct test_default t = test_default_init(guest_cmpxchg_key);
+ int size, offset;
+ __uint128_t old, new;
+ bool success;
+ pthread_t thread;
+
+ HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+ prepare_mem12();
+ MOP(t.vcpu, LOGICAL, WRITE, mem1, max_block, GADDR_V(mem2));
+ pthread_create(&thread, NULL, run_guest, &t.vcpu);
+
+ for (int i = 0; i < cmpxchg_iter_outer; i++) {
+ do {
+ old = 0;
+ new = 1;
+ MOP(t.vm, ABSOLUTE, CMPXCHG, &new,
+ sizeof(new), GADDR_V(mem1),
+ CMPXCHG_OLD(&old),
+ CMPXCHG_SUCCESS(&success), KEY(1));
+ } while (!success);
+ for (int j = 0; j < cmpxchg_iter_inner; j++) {
+ choose_block(false, i + j, &size, &offset);
+ do {
+ new = permutate_bits(false, i + j, size, old);
+ MOP(t.vm, ABSOLUTE, CMPXCHG, quad_to_char(&new, size),
+ size, GADDR_V(mem2 + offset),
+ CMPXCHG_OLD(quad_to_char(&old, size)),
+ CMPXCHG_SUCCESS(&success), KEY(1));
+ } while (!success);
+ }
+ }
+
+ pthread_join(thread, NULL);
+
+ MOP(t.vcpu, LOGICAL, READ, mem2, max_block, GADDR_V(mem2));
+ TEST_ASSERT(popcount_eq(*(__uint128_t *)mem1, *(__uint128_t *)mem2),
+ "Must retain number of set bits");
+
+ kvm_vm_free(t.kvm_vm);
+}
+
+static void guest_copy_key_fetch_prot(void)
+{
+ /*
+ * For some reason combining the first sync with override enablement
+ * results in an exception when calling HOST_SYNC.
+ */
+ GUEST_SYNC(STAGE_INITED);
+ /* Storage protection override applies to both store and fetch. */
+ set_storage_key_range(mem1, sizeof(mem1), 0x98);
+ set_storage_key_range(mem2, sizeof(mem2), 0x98);
+ GUEST_SYNC(STAGE_SKEYS_SET);
+
+ for (;;) {
+ memcpy(&mem2, &mem1, sizeof(mem2));
+ GUEST_SYNC(STAGE_COPIED);
+ }
+}
+
+static void test_copy_key_storage_prot_override(void)
+{
+ struct test_default t = test_default_init(guest_copy_key_fetch_prot);
+
+ HOST_SYNC(t.vcpu, STAGE_INITED);
+ t.run->s.regs.crs[0] |= CR0_STORAGE_PROTECTION_OVERRIDE;
+ t.run->kvm_dirty_regs = KVM_SYNC_CRS;
+ HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+ /* vcpu, mismatching keys, storage protection override in effect */
+ default_write_read(t.vcpu, t.vcpu, LOGICAL, t.size, 2);
+
+ kvm_vm_free(t.kvm_vm);
+}
+
+static void test_copy_key_fetch_prot(void)
+{
+ struct test_default t = test_default_init(guest_copy_key_fetch_prot);
+
+ HOST_SYNC(t.vcpu, STAGE_INITED);
+ HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+ /* vm/vcpu, matching key, fetch protection in effect */
+ default_read(t.vcpu, t.vcpu, LOGICAL, t.size, 9);
+ default_read(t.vcpu, t.vm, ABSOLUTE, t.size, 9);
+
+ kvm_vm_free(t.kvm_vm);
+}
+
+#define ERR_PROT_MOP(...) \
+({ \
+ int rv; \
+ \
+ rv = ERR_MOP(__VA_ARGS__); \
+ TEST_ASSERT(rv == 4, "Should result in protection exception"); \
+})
+
+static void guest_error_key(void)
+{
+ GUEST_SYNC(STAGE_INITED);
+ set_storage_key_range(mem1, PAGE_SIZE, 0x18);
+ set_storage_key_range(mem1 + PAGE_SIZE, sizeof(mem1) - PAGE_SIZE, 0x98);
+ GUEST_SYNC(STAGE_SKEYS_SET);
+ GUEST_SYNC(STAGE_IDLED);
+}
+
+static void test_errors_key(void)
+{
+ struct test_default t = test_default_init(guest_error_key);
+
+ HOST_SYNC(t.vcpu, STAGE_INITED);
+ HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+ /* vm/vcpu, mismatching keys, fetch protection in effect */
+ CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2));
+ CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, t.size, GADDR_V(mem1), KEY(2));
+ CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2));
+ CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, t.size, GADDR_V(mem1), KEY(2));
+
+ kvm_vm_free(t.kvm_vm);
+}
+
+static void test_errors_cmpxchg_key(void)
+{
+ struct test_default t = test_default_init(guest_copy_key_fetch_prot);
+ int i;
+
+ HOST_SYNC(t.vcpu, STAGE_INITED);
+ HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+ for (i = 1; i <= 16; i *= 2) {
+ __uint128_t old = 0;
+
+ ERR_PROT_MOP(t.vm, ABSOLUTE, CMPXCHG, mem2, i, GADDR_V(mem2),
+ CMPXCHG_OLD(&old), KEY(2));
+ }
+
+ kvm_vm_free(t.kvm_vm);
+}
+
+static void test_termination(void)
+{
+ struct test_default t = test_default_init(guest_error_key);
+ uint64_t prefix;
+ uint64_t teid;
+ uint64_t teid_mask = BIT(63 - 56) | BIT(63 - 60) | BIT(63 - 61);
+ uint64_t psw[2];
+
+ HOST_SYNC(t.vcpu, STAGE_INITED);
+ HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+ /* vcpu, mismatching keys after first page */
+ ERR_PROT_MOP(t.vcpu, LOGICAL, WRITE, mem1, t.size, GADDR_V(mem1), KEY(1), INJECT);
+ /*
+ * The memop injected a program exception and the test needs to check the
+ * Translation-Exception Identification (TEID). It is necessary to run
+ * the guest in order to be able to read the TEID from guest memory.
+ * Set the guest program new PSW, so the guest state is not clobbered.
+ */
+ prefix = t.run->s.regs.prefix;
+ psw[0] = t.run->psw_mask;
+ psw[1] = t.run->psw_addr;
+ MOP(t.vm, ABSOLUTE, WRITE, psw, sizeof(psw), GADDR(prefix + 464));
+ HOST_SYNC(t.vcpu, STAGE_IDLED);
+ MOP(t.vm, ABSOLUTE, READ, &teid, sizeof(teid), GADDR(prefix + 168));
+ /* Bits 56, 60, 61 form a code, 0 being the only one allowing for termination */
+ TEST_ASSERT_EQ(teid & teid_mask, 0);
+
+ kvm_vm_free(t.kvm_vm);
+}
+
+static void test_errors_key_storage_prot_override(void)
+{
+ struct test_default t = test_default_init(guest_copy_key_fetch_prot);
+
+ HOST_SYNC(t.vcpu, STAGE_INITED);
+ t.run->s.regs.crs[0] |= CR0_STORAGE_PROTECTION_OVERRIDE;
+ t.run->kvm_dirty_regs = KVM_SYNC_CRS;
+ HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+ /* vm, mismatching keys, storage protection override not applicable to vm */
+ CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2));
+ CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, t.size, GADDR_V(mem2), KEY(2));
+
+ kvm_vm_free(t.kvm_vm);
+}
+
+const uint64_t last_page_addr = -PAGE_SIZE;
+
+static void guest_copy_key_fetch_prot_override(void)
+{
+ int i;
+ char *page_0 = 0;
+
+ GUEST_SYNC(STAGE_INITED);
+ set_storage_key_range(0, PAGE_SIZE, 0x18);
+ set_storage_key_range((void *)last_page_addr, PAGE_SIZE, 0x0);
+ asm volatile ("sske %[key],%[addr]\n" :: [addr] "r"(0L), [key] "r"(0x18) : "cc");
+ GUEST_SYNC(STAGE_SKEYS_SET);
+
+ for (;;) {
+ for (i = 0; i < PAGE_SIZE; i++)
+ page_0[i] = mem1[i];
+ GUEST_SYNC(STAGE_COPIED);
+ }
+}
+
+static void test_copy_key_fetch_prot_override(void)
+{
+ struct test_default t = test_default_init(guest_copy_key_fetch_prot_override);
+ vm_vaddr_t guest_0_page, guest_last_page;
+
+ guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0);
+ guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr);
+ if (guest_0_page != 0 || guest_last_page != last_page_addr) {
+ print_skip("did not allocate guest pages at required positions");
+ goto out;
+ }
+
+ HOST_SYNC(t.vcpu, STAGE_INITED);
+ t.run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE;
+ t.run->kvm_dirty_regs = KVM_SYNC_CRS;
+ HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+ /* vcpu, mismatching keys on fetch, fetch protection override applies */
+ prepare_mem12();
+ MOP(t.vcpu, LOGICAL, WRITE, mem1, PAGE_SIZE, GADDR_V(mem1));
+ HOST_SYNC(t.vcpu, STAGE_COPIED);
+ CHECK_N_DO(MOP, t.vcpu, LOGICAL, READ, mem2, 2048, GADDR_V(guest_0_page), KEY(2));
+ ASSERT_MEM_EQ(mem1, mem2, 2048);
+
+ /*
+ * vcpu, mismatching keys on fetch, fetch protection override applies,
+ * wraparound
+ */
+ prepare_mem12();
+ MOP(t.vcpu, LOGICAL, WRITE, mem1, 2 * PAGE_SIZE, GADDR_V(guest_last_page));
+ HOST_SYNC(t.vcpu, STAGE_COPIED);
+ CHECK_N_DO(MOP, t.vcpu, LOGICAL, READ, mem2, PAGE_SIZE + 2048,
+ GADDR_V(guest_last_page), KEY(2));
+ ASSERT_MEM_EQ(mem1, mem2, 2048);
+
+out:
+ kvm_vm_free(t.kvm_vm);
+}
+
+static void test_errors_key_fetch_prot_override_not_enabled(void)
+{
+ struct test_default t = test_default_init(guest_copy_key_fetch_prot_override);
+ vm_vaddr_t guest_0_page, guest_last_page;
+
+ guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0);
+ guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr);
+ if (guest_0_page != 0 || guest_last_page != last_page_addr) {
+ print_skip("did not allocate guest pages at required positions");
+ goto out;
+ }
+ HOST_SYNC(t.vcpu, STAGE_INITED);
+ HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+ /* vcpu, mismatching keys on fetch, fetch protection override not enabled */
+ CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, 2048, GADDR_V(0), KEY(2));
+
+out:
+ kvm_vm_free(t.kvm_vm);
+}
+
+static void test_errors_key_fetch_prot_override_enabled(void)
+{
+ struct test_default t = test_default_init(guest_copy_key_fetch_prot_override);
+ vm_vaddr_t guest_0_page, guest_last_page;
+
+ guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0);
+ guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr);
+ if (guest_0_page != 0 || guest_last_page != last_page_addr) {
+ print_skip("did not allocate guest pages at required positions");
+ goto out;
+ }
+ HOST_SYNC(t.vcpu, STAGE_INITED);
+ t.run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE;
+ t.run->kvm_dirty_regs = KVM_SYNC_CRS;
+ HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+ /*
+ * vcpu, mismatching keys on fetch,
+ * fetch protection override does not apply because memory range exceeded
+ */
+ CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, 2048 + 1, GADDR_V(0), KEY(2));
+ CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, PAGE_SIZE + 2048 + 1,
+ GADDR_V(guest_last_page), KEY(2));
+ /* vm, fetch protected override does not apply */
+ CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, 2048, GADDR(0), KEY(2));
+ CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, 2048, GADDR_V(guest_0_page), KEY(2));
+
+out:
+ kvm_vm_free(t.kvm_vm);
+}
+
+static void guest_idle(void)
+{
+ GUEST_SYNC(STAGE_INITED); /* for consistency's sake */
+ for (;;)
+ GUEST_SYNC(STAGE_IDLED);
+}
+
+static void _test_errors_common(struct test_info info, enum mop_target target, int size)
+{
+ int rv;
+
+ /* Bad size: */
+ rv = ERR_MOP(info, target, WRITE, mem1, -1, GADDR_V(mem1));
+ TEST_ASSERT(rv == -1 && errno == E2BIG, "ioctl allows insane sizes");
+
+ /* Zero size: */
+ rv = ERR_MOP(info, target, WRITE, mem1, 0, GADDR_V(mem1));
+ TEST_ASSERT(rv == -1 && (errno == EINVAL || errno == ENOMEM),
+ "ioctl allows 0 as size");
+
+ /* Bad flags: */
+ rv = ERR_MOP(info, target, WRITE, mem1, size, GADDR_V(mem1), SET_FLAGS(-1));
+ TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows all flags");
+
+ /* Bad guest address: */
+ rv = ERR_MOP(info, target, WRITE, mem1, size, GADDR((void *)~0xfffUL), CHECK_ONLY);
+ TEST_ASSERT(rv > 0, "ioctl does not report bad guest memory address with CHECK_ONLY");
+ rv = ERR_MOP(info, target, WRITE, mem1, size, GADDR((void *)~0xfffUL));
+ TEST_ASSERT(rv > 0, "ioctl does not report bad guest memory address on write");
+
+ /* Bad host address: */
+ rv = ERR_MOP(info, target, WRITE, 0, size, GADDR_V(mem1));
+ TEST_ASSERT(rv == -1 && errno == EFAULT,
+ "ioctl does not report bad host memory address");
+
+ /* Bad key: */
+ rv = ERR_MOP(info, target, WRITE, mem1, size, GADDR_V(mem1), KEY(17));
+ TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows invalid key");
+}
+
+static void test_errors(void)
+{
+ struct test_default t = test_default_init(guest_idle);
+ int rv;
+
+ HOST_SYNC(t.vcpu, STAGE_INITED);
+
+ _test_errors_common(t.vcpu, LOGICAL, t.size);
+ _test_errors_common(t.vm, ABSOLUTE, t.size);
+
+ /* Bad operation: */
+ rv = ERR_MOP(t.vcpu, INVALID, WRITE, mem1, t.size, GADDR_V(mem1));
+ TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows bad operations");
+ /* virtual addresses are not translated when passing INVALID */
+ rv = ERR_MOP(t.vm, INVALID, WRITE, mem1, PAGE_SIZE, GADDR(0));
+ TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows bad operations");
+
+ /* Bad access register: */
+ t.run->psw_mask &= ~(3UL << (63 - 17));
+ t.run->psw_mask |= 1UL << (63 - 17); /* Enable AR mode */
+ HOST_SYNC(t.vcpu, STAGE_IDLED); /* To sync new state to SIE block */
+ rv = ERR_MOP(t.vcpu, LOGICAL, WRITE, mem1, t.size, GADDR_V(mem1), AR(17));
+ TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows ARs > 15");
+ t.run->psw_mask &= ~(3UL << (63 - 17)); /* Disable AR mode */
+ HOST_SYNC(t.vcpu, STAGE_IDLED); /* Run to sync new state */
+
+ /* Check that the SIDA calls are rejected for non-protected guests */
+ rv = ERR_MOP(t.vcpu, SIDA, READ, mem1, 8, GADDR(0), SIDA_OFFSET(0x1c0));
+ TEST_ASSERT(rv == -1 && errno == EINVAL,
+ "ioctl does not reject SIDA_READ in non-protected mode");
+ rv = ERR_MOP(t.vcpu, SIDA, WRITE, mem1, 8, GADDR(0), SIDA_OFFSET(0x1c0));
+ TEST_ASSERT(rv == -1 && errno == EINVAL,
+ "ioctl does not reject SIDA_WRITE in non-protected mode");
+
+ kvm_vm_free(t.kvm_vm);
+}
+
+static void test_errors_cmpxchg(void)
+{
+ struct test_default t = test_default_init(guest_idle);
+ __uint128_t old;
+ int rv, i, power = 1;
+
+ HOST_SYNC(t.vcpu, STAGE_INITED);
+
+ for (i = 0; i < 32; i++) {
+ if (i == power) {
+ power *= 2;
+ continue;
+ }
+ rv = ERR_MOP(t.vm, ABSOLUTE, CMPXCHG, mem1, i, GADDR_V(mem1),
+ CMPXCHG_OLD(&old));
+ TEST_ASSERT(rv == -1 && errno == EINVAL,
+ "ioctl allows bad size for cmpxchg");
+ }
+ for (i = 1; i <= 16; i *= 2) {
+ rv = ERR_MOP(t.vm, ABSOLUTE, CMPXCHG, mem1, i, GADDR((void *)~0xfffUL),
+ CMPXCHG_OLD(&old));
+ TEST_ASSERT(rv > 0, "ioctl allows bad guest address for cmpxchg");
+ }
+ for (i = 2; i <= 16; i *= 2) {
+ rv = ERR_MOP(t.vm, ABSOLUTE, CMPXCHG, mem1, i, GADDR_V(mem1 + 1),
+ CMPXCHG_OLD(&old));
+ TEST_ASSERT(rv == -1 && errno == EINVAL,
+ "ioctl allows bad alignment for cmpxchg");
+ }
+
+ kvm_vm_free(t.kvm_vm);
+}
+
+int main(int argc, char *argv[])
+{
+ int extension_cap, idx;
+
+ TEST_REQUIRE(kvm_has_cap(KVM_CAP_S390_MEM_OP));
+ extension_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP_EXTENSION);
+
+ struct testdef {
+ const char *name;
+ void (*test)(void);
+ bool requirements_met;
+ } testlist[] = {
+ {
+ .name = "simple copy",
+ .test = test_copy,
+ .requirements_met = true,
+ },
+ {
+ .name = "generic error checks",
+ .test = test_errors,
+ .requirements_met = true,
+ },
+ {
+ .name = "copy with storage keys",
+ .test = test_copy_key,
+ .requirements_met = extension_cap > 0,
+ },
+ {
+ .name = "cmpxchg with storage keys",
+ .test = test_cmpxchg_key,
+ .requirements_met = extension_cap & 0x2,
+ },
+ {
+ .name = "concurrently cmpxchg with storage keys",
+ .test = test_cmpxchg_key_concurrent,
+ .requirements_met = extension_cap & 0x2,
+ },
+ {
+ .name = "copy with key storage protection override",
+ .test = test_copy_key_storage_prot_override,
+ .requirements_met = extension_cap > 0,
+ },
+ {
+ .name = "copy with key fetch protection",
+ .test = test_copy_key_fetch_prot,
+ .requirements_met = extension_cap > 0,
+ },
+ {
+ .name = "copy with key fetch protection override",
+ .test = test_copy_key_fetch_prot_override,
+ .requirements_met = extension_cap > 0,
+ },
+ {
+ .name = "copy with access register mode",
+ .test = test_copy_access_register,
+ .requirements_met = true,
+ },
+ {
+ .name = "error checks with key",
+ .test = test_errors_key,
+ .requirements_met = extension_cap > 0,
+ },
+ {
+ .name = "error checks for cmpxchg with key",
+ .test = test_errors_cmpxchg_key,
+ .requirements_met = extension_cap & 0x2,
+ },
+ {
+ .name = "error checks for cmpxchg",
+ .test = test_errors_cmpxchg,
+ .requirements_met = extension_cap & 0x2,
+ },
+ {
+ .name = "termination",
+ .test = test_termination,
+ .requirements_met = extension_cap > 0,
+ },
+ {
+ .name = "error checks with key storage protection override",
+ .test = test_errors_key_storage_prot_override,
+ .requirements_met = extension_cap > 0,
+ },
+ {
+ .name = "error checks without key fetch prot override",
+ .test = test_errors_key_fetch_prot_override_not_enabled,
+ .requirements_met = extension_cap > 0,
+ },
+ {
+ .name = "error checks with key fetch prot override",
+ .test = test_errors_key_fetch_prot_override_enabled,
+ .requirements_met = extension_cap > 0,
+ },
+ };
+
+ ksft_print_header();
+ ksft_set_plan(ARRAY_SIZE(testlist));
+
+ for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) {
+ if (testlist[idx].requirements_met) {
+ testlist[idx].test();
+ ksft_test_result_pass("%s\n", testlist[idx].name);
+ } else {
+ ksft_test_result_skip("%s - requirements not met (kernel has extension cap %#x)\n",
+ testlist[idx].name, extension_cap);
+ }
+ }
+
+ ksft_finished(); /* Print results and exit() accordingly */
+}
diff --git a/tools/testing/selftests/kvm/s390/resets.c b/tools/testing/selftests/kvm/s390/resets.c
new file mode 100644
index 000000000000..b58f75b381e5
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390/resets.c
@@ -0,0 +1,313 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Test for s390x CPU resets
+ *
+ * Copyright (C) 2020, IBM
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "kselftest.h"
+
+#define LOCAL_IRQS 32
+
+#define ARBITRARY_NON_ZERO_VCPU_ID 3
+
+struct kvm_s390_irq buf[ARBITRARY_NON_ZERO_VCPU_ID + LOCAL_IRQS];
+
+static uint8_t regs_null[512];
+
+static void guest_code_initial(void)
+{
+ /* set several CRs to "safe" value */
+ unsigned long cr2_59 = 0x10; /* enable guarded storage */
+ unsigned long cr8_63 = 0x1; /* monitor mask = 1 */
+ unsigned long cr10 = 1; /* PER START */
+ unsigned long cr11 = -1; /* PER END */
+
+
+ /* Dirty registers */
+ asm volatile (
+ " lghi 2,0x11\n" /* Round toward 0 */
+ " sfpc 2\n" /* set fpc to !=0 */
+ " lctlg 2,2,%0\n"
+ " lctlg 8,8,%1\n"
+ " lctlg 10,10,%2\n"
+ " lctlg 11,11,%3\n"
+ /* now clobber some general purpose regs */
+ " llihh 0,0xffff\n"
+ " llihl 1,0x5555\n"
+ " llilh 2,0xaaaa\n"
+ " llill 3,0x0000\n"
+ /* now clobber a floating point reg */
+ " lghi 4,0x1\n"
+ " cdgbr 0,4\n"
+ /* now clobber an access reg */
+ " sar 9,4\n"
+ /* We embed diag 501 here to control register content */
+ " diag 0,0,0x501\n"
+ :
+ : "m" (cr2_59), "m" (cr8_63), "m" (cr10), "m" (cr11)
+ /* no clobber list as this should not return */
+ );
+}
+
+static void test_one_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t value)
+{
+ uint64_t eval_reg;
+
+ eval_reg = vcpu_get_reg(vcpu, id);
+ TEST_ASSERT(eval_reg == value, "value == 0x%lx", value);
+}
+
+static void assert_noirq(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_irq_state irq_state;
+ int irqs;
+
+ irq_state.len = sizeof(buf);
+ irq_state.buf = (unsigned long)buf;
+ irqs = __vcpu_ioctl(vcpu, KVM_S390_GET_IRQ_STATE, &irq_state);
+ /*
+ * irqs contains the number of retrieved interrupts. Any interrupt
+ * (notably, the emergency call interrupt we have injected) should
+ * be cleared by the resets, so this should be 0.
+ */
+ TEST_ASSERT(irqs >= 0, "Could not fetch IRQs: errno %d", errno);
+ TEST_ASSERT(!irqs, "IRQ pending");
+}
+
+static void assert_clear(struct kvm_vcpu *vcpu)
+{
+ struct kvm_sync_regs *sync_regs = &vcpu->run->s.regs;
+ struct kvm_sregs sregs;
+ struct kvm_regs regs;
+ struct kvm_fpu fpu;
+
+ vcpu_regs_get(vcpu, &regs);
+ TEST_ASSERT(!memcmp(&regs.gprs, regs_null, sizeof(regs.gprs)), "grs == 0");
+
+ vcpu_sregs_get(vcpu, &sregs);
+ TEST_ASSERT(!memcmp(&sregs.acrs, regs_null, sizeof(sregs.acrs)), "acrs == 0");
+
+ vcpu_fpu_get(vcpu, &fpu);
+ TEST_ASSERT(!memcmp(&fpu.fprs, regs_null, sizeof(fpu.fprs)), "fprs == 0");
+
+ /* sync regs */
+ TEST_ASSERT(!memcmp(sync_regs->gprs, regs_null, sizeof(sync_regs->gprs)),
+ "gprs0-15 == 0 (sync_regs)");
+
+ TEST_ASSERT(!memcmp(sync_regs->acrs, regs_null, sizeof(sync_regs->acrs)),
+ "acrs0-15 == 0 (sync_regs)");
+
+ TEST_ASSERT(!memcmp(sync_regs->vrs, regs_null, sizeof(sync_regs->vrs)),
+ "vrs0-15 == 0 (sync_regs)");
+}
+
+static void assert_initial_noclear(struct kvm_vcpu *vcpu)
+{
+ struct kvm_sync_regs *sync_regs = &vcpu->run->s.regs;
+
+ TEST_ASSERT(sync_regs->gprs[0] == 0xffff000000000000UL,
+ "gpr0 == 0xffff000000000000 (sync_regs)");
+ TEST_ASSERT(sync_regs->gprs[1] == 0x0000555500000000UL,
+ "gpr1 == 0x0000555500000000 (sync_regs)");
+ TEST_ASSERT(sync_regs->gprs[2] == 0x00000000aaaa0000UL,
+ "gpr2 == 0x00000000aaaa0000 (sync_regs)");
+ TEST_ASSERT(sync_regs->gprs[3] == 0x0000000000000000UL,
+ "gpr3 == 0x0000000000000000 (sync_regs)");
+ TEST_ASSERT(sync_regs->fprs[0] == 0x3ff0000000000000UL,
+ "fpr0 == 0f1 (sync_regs)");
+ TEST_ASSERT(sync_regs->acrs[9] == 1, "ar9 == 1 (sync_regs)");
+}
+
+static void assert_initial(struct kvm_vcpu *vcpu)
+{
+ struct kvm_sync_regs *sync_regs = &vcpu->run->s.regs;
+ struct kvm_sregs sregs;
+ struct kvm_fpu fpu;
+
+ /* KVM_GET_SREGS */
+ vcpu_sregs_get(vcpu, &sregs);
+ TEST_ASSERT(sregs.crs[0] == 0xE0UL, "cr0 == 0xE0 (KVM_GET_SREGS)");
+ TEST_ASSERT(sregs.crs[14] == 0xC2000000UL,
+ "cr14 == 0xC2000000 (KVM_GET_SREGS)");
+ TEST_ASSERT(!memcmp(&sregs.crs[1], regs_null, sizeof(sregs.crs[1]) * 12),
+ "cr1-13 == 0 (KVM_GET_SREGS)");
+ TEST_ASSERT(sregs.crs[15] == 0, "cr15 == 0 (KVM_GET_SREGS)");
+
+ /* sync regs */
+ TEST_ASSERT(sync_regs->crs[0] == 0xE0UL, "cr0 == 0xE0 (sync_regs)");
+ TEST_ASSERT(sync_regs->crs[14] == 0xC2000000UL,
+ "cr14 == 0xC2000000 (sync_regs)");
+ TEST_ASSERT(!memcmp(&sync_regs->crs[1], regs_null, 8 * 12),
+ "cr1-13 == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->crs[15] == 0, "cr15 == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->fpc == 0, "fpc == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->todpr == 0, "todpr == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->cputm == 0, "cputm == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->ckc == 0, "ckc == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->pp == 0, "pp == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->gbea == 1, "gbea == 1 (sync_regs)");
+
+ /* kvm_run */
+ TEST_ASSERT(vcpu->run->psw_addr == 0, "psw_addr == 0 (kvm_run)");
+ TEST_ASSERT(vcpu->run->psw_mask == 0, "psw_mask == 0 (kvm_run)");
+
+ vcpu_fpu_get(vcpu, &fpu);
+ TEST_ASSERT(!fpu.fpc, "fpc == 0");
+
+ test_one_reg(vcpu, KVM_REG_S390_GBEA, 1);
+ test_one_reg(vcpu, KVM_REG_S390_PP, 0);
+ test_one_reg(vcpu, KVM_REG_S390_TODPR, 0);
+ test_one_reg(vcpu, KVM_REG_S390_CPU_TIMER, 0);
+ test_one_reg(vcpu, KVM_REG_S390_CLOCK_COMP, 0);
+}
+
+static void assert_normal_noclear(struct kvm_vcpu *vcpu)
+{
+ struct kvm_sync_regs *sync_regs = &vcpu->run->s.regs;
+
+ TEST_ASSERT(sync_regs->crs[2] == 0x10, "cr2 == 10 (sync_regs)");
+ TEST_ASSERT(sync_regs->crs[8] == 1, "cr10 == 1 (sync_regs)");
+ TEST_ASSERT(sync_regs->crs[10] == 1, "cr10 == 1 (sync_regs)");
+ TEST_ASSERT(sync_regs->crs[11] == -1, "cr11 == -1 (sync_regs)");
+}
+
+static void assert_normal(struct kvm_vcpu *vcpu)
+{
+ test_one_reg(vcpu, KVM_REG_S390_PFTOKEN, KVM_S390_PFAULT_TOKEN_INVALID);
+ TEST_ASSERT(vcpu->run->s.regs.pft == KVM_S390_PFAULT_TOKEN_INVALID,
+ "pft == 0xff..... (sync_regs)");
+ assert_noirq(vcpu);
+}
+
+static void inject_irq(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_irq_state irq_state;
+ struct kvm_s390_irq *irq = &buf[0];
+ int irqs;
+
+ /* Inject IRQ */
+ irq_state.len = sizeof(struct kvm_s390_irq);
+ irq_state.buf = (unsigned long)buf;
+ irq->type = KVM_S390_INT_EMERGENCY;
+ irq->u.emerg.code = vcpu->id;
+ irqs = __vcpu_ioctl(vcpu, KVM_S390_SET_IRQ_STATE, &irq_state);
+ TEST_ASSERT(irqs >= 0, "Error injecting EMERGENCY IRQ errno %d", errno);
+}
+
+static struct kvm_vm *create_vm(struct kvm_vcpu **vcpu)
+{
+ struct kvm_vm *vm;
+
+ vm = vm_create(1);
+
+ *vcpu = vm_vcpu_add(vm, ARBITRARY_NON_ZERO_VCPU_ID, guest_code_initial);
+
+ return vm;
+}
+
+static void test_normal(void)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+
+ ksft_print_msg("Testing normal reset\n");
+ vm = create_vm(&vcpu);
+
+ vcpu_run(vcpu);
+
+ inject_irq(vcpu);
+
+ vcpu_ioctl(vcpu, KVM_S390_NORMAL_RESET, NULL);
+
+ /* must clears */
+ assert_normal(vcpu);
+ /* must not clears */
+ assert_normal_noclear(vcpu);
+ assert_initial_noclear(vcpu);
+
+ kvm_vm_free(vm);
+}
+
+static void test_initial(void)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+
+ ksft_print_msg("Testing initial reset\n");
+ vm = create_vm(&vcpu);
+
+ vcpu_run(vcpu);
+
+ inject_irq(vcpu);
+
+ vcpu_ioctl(vcpu, KVM_S390_INITIAL_RESET, NULL);
+
+ /* must clears */
+ assert_normal(vcpu);
+ assert_initial(vcpu);
+ /* must not clears */
+ assert_initial_noclear(vcpu);
+
+ kvm_vm_free(vm);
+}
+
+static void test_clear(void)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+
+ ksft_print_msg("Testing clear reset\n");
+ vm = create_vm(&vcpu);
+
+ vcpu_run(vcpu);
+
+ inject_irq(vcpu);
+
+ vcpu_ioctl(vcpu, KVM_S390_CLEAR_RESET, NULL);
+
+ /* must clears */
+ assert_normal(vcpu);
+ assert_initial(vcpu);
+ assert_clear(vcpu);
+
+ kvm_vm_free(vm);
+}
+
+struct testdef {
+ const char *name;
+ void (*test)(void);
+ bool needs_cap;
+} testlist[] = {
+ { "initial", test_initial, false },
+ { "normal", test_normal, true },
+ { "clear", test_clear, true },
+};
+
+int main(int argc, char *argv[])
+{
+ bool has_s390_vcpu_resets = kvm_check_cap(KVM_CAP_S390_VCPU_RESETS);
+ int idx;
+
+ ksft_print_header();
+ ksft_set_plan(ARRAY_SIZE(testlist));
+
+ for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) {
+ if (!testlist[idx].needs_cap || has_s390_vcpu_resets) {
+ testlist[idx].test();
+ ksft_test_result_pass("%s\n", testlist[idx].name);
+ } else {
+ ksft_test_result_skip("%s - no VCPU_RESETS capability\n",
+ testlist[idx].name);
+ }
+ }
+
+ ksft_finished(); /* Print results and exit() accordingly */
+}
diff --git a/tools/testing/selftests/kvm/s390/shared_zeropage_test.c b/tools/testing/selftests/kvm/s390/shared_zeropage_test.c
new file mode 100644
index 000000000000..bba0d9a6dcc8
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390/shared_zeropage_test.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Test shared zeropage handling (with/without storage keys)
+ *
+ * Copyright (C) 2024, Red Hat, Inc.
+ */
+#include <sys/mman.h>
+
+#include <linux/fs.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "kselftest.h"
+#include "ucall_common.h"
+
+static void set_storage_key(void *addr, uint8_t skey)
+{
+ asm volatile("sske %0,%1" : : "d" (skey), "a" (addr));
+}
+
+static void guest_code(void)
+{
+ /* Issue some storage key instruction. */
+ set_storage_key((void *)0, 0x98);
+ GUEST_DONE();
+}
+
+/*
+ * Returns 1 if the shared zeropage is mapped, 0 if something else is mapped.
+ * Returns < 0 on error or if nothing is mapped.
+ */
+static int maps_shared_zeropage(int pagemap_fd, void *addr)
+{
+ struct page_region region;
+ struct pm_scan_arg arg = {
+ .start = (uintptr_t)addr,
+ .end = (uintptr_t)addr + 4096,
+ .vec = (uintptr_t)&region,
+ .vec_len = 1,
+ .size = sizeof(struct pm_scan_arg),
+ .category_mask = PAGE_IS_PFNZERO,
+ .category_anyof_mask = PAGE_IS_PRESENT,
+ .return_mask = PAGE_IS_PFNZERO,
+ };
+ return ioctl(pagemap_fd, PAGEMAP_SCAN, &arg);
+}
+
+int main(int argc, char *argv[])
+{
+ char *mem, *page0, *page1, *page2, tmp;
+ const size_t pagesize = getpagesize();
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+ struct ucall uc;
+ int pagemap_fd;
+
+ ksft_print_header();
+ ksft_set_plan(3);
+
+ /*
+ * We'll use memory that is not mapped into the VM for simplicity.
+ * Shared zeropages are enabled/disabled per-process.
+ */
+ mem = mmap(0, 3 * pagesize, PROT_READ, MAP_PRIVATE | MAP_ANON, -1, 0);
+ TEST_ASSERT(mem != MAP_FAILED, "mmap() failed");
+
+ /* Disable THP. Ignore errors on older kernels. */
+ madvise(mem, 3 * pagesize, MADV_NOHUGEPAGE);
+
+ page0 = mem;
+ page1 = page0 + pagesize;
+ page2 = page1 + pagesize;
+
+ /* Can we even detect shared zeropages? */
+ pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+ TEST_REQUIRE(pagemap_fd >= 0);
+
+ tmp = *page0;
+ asm volatile("" : "+r" (tmp));
+ TEST_REQUIRE(maps_shared_zeropage(pagemap_fd, page0) == 1);
+
+ vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
+ /* Verify that we get the shared zeropage after VM creation. */
+ tmp = *page1;
+ asm volatile("" : "+r" (tmp));
+ ksft_test_result(maps_shared_zeropage(pagemap_fd, page1) == 1,
+ "Shared zeropages should be enabled\n");
+
+ /*
+ * Let our VM execute a storage key instruction that should
+ * unshare all shared zeropages.
+ */
+ vcpu_run(vcpu);
+ get_ucall(vcpu, &uc);
+ TEST_ASSERT_EQ(uc.cmd, UCALL_DONE);
+
+ /* Verify that we don't have a shared zeropage anymore. */
+ ksft_test_result(!maps_shared_zeropage(pagemap_fd, page1),
+ "Shared zeropage should be gone\n");
+
+ /* Verify that we don't get any new shared zeropages. */
+ tmp = *page2;
+ asm volatile("" : "+r" (tmp));
+ ksft_test_result(!maps_shared_zeropage(pagemap_fd, page2),
+ "Shared zeropages should be disabled\n");
+
+ kvm_vm_free(vm);
+
+ ksft_finished();
+}
diff --git a/tools/testing/selftests/kvm/s390/sync_regs_test.c b/tools/testing/selftests/kvm/s390/sync_regs_test.c
new file mode 100644
index 000000000000..53def355ccba
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390/sync_regs_test.c
@@ -0,0 +1,238 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Test for s390x KVM_CAP_SYNC_REGS
+ *
+ * Based on the same test for x86:
+ * Copyright (C) 2018, Google LLC.
+ *
+ * Adaptions for s390x:
+ * Copyright (C) 2019, Red Hat, Inc.
+ *
+ * Test expected behavior of the KVM_CAP_SYNC_REGS functionality.
+ */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "diag318_test_handler.h"
+#include "kselftest.h"
+
+static void guest_code(void)
+{
+ /*
+ * We embed diag 501 here instead of doing a ucall to avoid that
+ * the compiler has messed with r11 at the time of the ucall.
+ */
+ asm volatile (
+ "0: diag 0,0,0x501\n"
+ " ahi 11,1\n"
+ " j 0b\n"
+ );
+}
+
+#define REG_COMPARE(reg) \
+ TEST_ASSERT(left->reg == right->reg, \
+ "Register " #reg \
+ " values did not match: 0x%llx, 0x%llx", \
+ left->reg, right->reg)
+
+#define REG_COMPARE32(reg) \
+ TEST_ASSERT(left->reg == right->reg, \
+ "Register " #reg \
+ " values did not match: 0x%x, 0x%x", \
+ left->reg, right->reg)
+
+
+static void compare_regs(struct kvm_regs *left, struct kvm_sync_regs *right)
+{
+ int i;
+
+ for (i = 0; i < 16; i++)
+ REG_COMPARE(gprs[i]);
+}
+
+static void compare_sregs(struct kvm_sregs *left, struct kvm_sync_regs *right)
+{
+ int i;
+
+ for (i = 0; i < 16; i++)
+ REG_COMPARE32(acrs[i]);
+
+ for (i = 0; i < 16; i++)
+ REG_COMPARE(crs[i]);
+}
+
+#undef REG_COMPARE
+
+#define TEST_SYNC_FIELDS (KVM_SYNC_GPRS|KVM_SYNC_ACRS|KVM_SYNC_CRS|KVM_SYNC_DIAG318)
+#define INVALID_SYNC_FIELD 0x80000000
+
+void test_read_invalid(struct kvm_vcpu *vcpu)
+{
+ struct kvm_run *run = vcpu->run;
+ int rv;
+
+ /* Request reading invalid register set from VCPU. */
+ run->kvm_valid_regs = INVALID_SYNC_FIELD;
+ rv = _vcpu_run(vcpu);
+ TEST_ASSERT(rv < 0 && errno == EINVAL,
+ "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
+ rv);
+ run->kvm_valid_regs = 0;
+
+ run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
+ rv = _vcpu_run(vcpu);
+ TEST_ASSERT(rv < 0 && errno == EINVAL,
+ "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
+ rv);
+ run->kvm_valid_regs = 0;
+}
+
+void test_set_invalid(struct kvm_vcpu *vcpu)
+{
+ struct kvm_run *run = vcpu->run;
+ int rv;
+
+ /* Request setting invalid register set into VCPU. */
+ run->kvm_dirty_regs = INVALID_SYNC_FIELD;
+ rv = _vcpu_run(vcpu);
+ TEST_ASSERT(rv < 0 && errno == EINVAL,
+ "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
+ rv);
+ run->kvm_dirty_regs = 0;
+
+ run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
+ rv = _vcpu_run(vcpu);
+ TEST_ASSERT(rv < 0 && errno == EINVAL,
+ "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
+ rv);
+ run->kvm_dirty_regs = 0;
+}
+
+void test_req_and_verify_all_valid_regs(struct kvm_vcpu *vcpu)
+{
+ struct kvm_run *run = vcpu->run;
+ struct kvm_sregs sregs;
+ struct kvm_regs regs;
+ int rv;
+
+ /* Request and verify all valid register sets. */
+ run->kvm_valid_regs = TEST_SYNC_FIELDS;
+ rv = _vcpu_run(vcpu);
+ TEST_ASSERT(rv == 0, "vcpu_run failed: %d", rv);
+ TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
+ TEST_ASSERT(run->s390_sieic.icptcode == 4 &&
+ (run->s390_sieic.ipa >> 8) == 0x83 &&
+ (run->s390_sieic.ipb >> 16) == 0x501,
+ "Unexpected interception code: ic=%u, ipa=0x%x, ipb=0x%x",
+ run->s390_sieic.icptcode, run->s390_sieic.ipa,
+ run->s390_sieic.ipb);
+
+ vcpu_regs_get(vcpu, &regs);
+ compare_regs(&regs, &run->s.regs);
+
+ vcpu_sregs_get(vcpu, &sregs);
+ compare_sregs(&sregs, &run->s.regs);
+}
+
+void test_set_and_verify_various_reg_values(struct kvm_vcpu *vcpu)
+{
+ struct kvm_run *run = vcpu->run;
+ struct kvm_sregs sregs;
+ struct kvm_regs regs;
+ int rv;
+
+ /* Set and verify various register values */
+ run->s.regs.gprs[11] = 0xBAD1DEA;
+ run->s.regs.acrs[0] = 1 << 11;
+
+ run->kvm_valid_regs = TEST_SYNC_FIELDS;
+ run->kvm_dirty_regs = KVM_SYNC_GPRS | KVM_SYNC_ACRS;
+
+ if (get_diag318_info() > 0) {
+ run->s.regs.diag318 = get_diag318_info();
+ run->kvm_dirty_regs |= KVM_SYNC_DIAG318;
+ }
+
+ rv = _vcpu_run(vcpu);
+ TEST_ASSERT(rv == 0, "vcpu_run failed: %d", rv);
+ TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
+ TEST_ASSERT(run->s.regs.gprs[11] == 0xBAD1DEA + 1,
+ "r11 sync regs value incorrect 0x%llx.",
+ run->s.regs.gprs[11]);
+ TEST_ASSERT(run->s.regs.acrs[0] == 1 << 11,
+ "acr0 sync regs value incorrect 0x%x.",
+ run->s.regs.acrs[0]);
+ TEST_ASSERT(run->s.regs.diag318 == get_diag318_info(),
+ "diag318 sync regs value incorrect 0x%llx.",
+ run->s.regs.diag318);
+
+ vcpu_regs_get(vcpu, &regs);
+ compare_regs(&regs, &run->s.regs);
+
+ vcpu_sregs_get(vcpu, &sregs);
+ compare_sregs(&sregs, &run->s.regs);
+}
+
+void test_clear_kvm_dirty_regs_bits(struct kvm_vcpu *vcpu)
+{
+ struct kvm_run *run = vcpu->run;
+ int rv;
+
+ /* Clear kvm_dirty_regs bits, verify new s.regs values are
+ * overwritten with existing guest values.
+ */
+ run->kvm_valid_regs = TEST_SYNC_FIELDS;
+ run->kvm_dirty_regs = 0;
+ run->s.regs.gprs[11] = 0xDEADBEEF;
+ run->s.regs.diag318 = 0x4B1D;
+ rv = _vcpu_run(vcpu);
+ TEST_ASSERT(rv == 0, "vcpu_run failed: %d", rv);
+ TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
+ TEST_ASSERT(run->s.regs.gprs[11] != 0xDEADBEEF,
+ "r11 sync regs value incorrect 0x%llx.",
+ run->s.regs.gprs[11]);
+ TEST_ASSERT(run->s.regs.diag318 != 0x4B1D,
+ "diag318 sync regs value incorrect 0x%llx.",
+ run->s.regs.diag318);
+}
+
+struct testdef {
+ const char *name;
+ void (*test)(struct kvm_vcpu *vcpu);
+} testlist[] = {
+ { "read invalid", test_read_invalid },
+ { "set invalid", test_set_invalid },
+ { "request+verify all valid regs", test_req_and_verify_all_valid_regs },
+ { "set+verify various regs", test_set_and_verify_various_reg_values },
+ { "clear kvm_dirty_regs bits", test_clear_kvm_dirty_regs_bits },
+};
+
+int main(int argc, char *argv[])
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+ int idx;
+
+ TEST_REQUIRE(kvm_has_cap(KVM_CAP_SYNC_REGS));
+
+ ksft_print_header();
+
+ ksft_set_plan(ARRAY_SIZE(testlist));
+
+ /* Create VM */
+ vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
+ for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) {
+ testlist[idx].test(vcpu);
+ ksft_test_result_pass("%s\n", testlist[idx].name);
+ }
+
+ kvm_vm_free(vm);
+
+ ksft_finished(); /* Print results and exit() accordingly */
+}
diff --git a/tools/testing/selftests/kvm/s390/tprot.c b/tools/testing/selftests/kvm/s390/tprot.c
new file mode 100644
index 000000000000..12d5e1cb62e3
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390/tprot.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Test TEST PROTECTION emulation.
+ *
+ * Copyright IBM Corp. 2021
+ */
+#include <sys/mman.h>
+#include "test_util.h"
+#include "kvm_util.h"
+#include "kselftest.h"
+#include "ucall_common.h"
+#include "processor.h"
+
+#define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38))
+#define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39))
+
+static __aligned(PAGE_SIZE) uint8_t pages[2][PAGE_SIZE];
+static uint8_t *const page_store_prot = pages[0];
+static uint8_t *const page_fetch_prot = pages[1];
+
+/* Nonzero return value indicates that address not mapped */
+static int set_storage_key(void *addr, uint8_t key)
+{
+ int not_mapped = 0;
+
+ asm volatile (
+ "lra %[addr], 0(0,%[addr])\n"
+ " jz 0f\n"
+ " llill %[not_mapped],1\n"
+ " j 1f\n"
+ "0: sske %[key], %[addr]\n"
+ "1:"
+ : [addr] "+&a" (addr), [not_mapped] "+r" (not_mapped)
+ : [key] "r" (key)
+ : "cc"
+ );
+ return -not_mapped;
+}
+
+enum permission {
+ READ_WRITE = 0,
+ READ = 1,
+ RW_PROTECTED = 2,
+ TRANSL_UNAVAIL = 3,
+};
+
+static enum permission test_protection(void *addr, uint8_t key)
+{
+ uint64_t mask;
+
+ asm volatile (
+ "tprot %[addr], 0(%[key])\n"
+ " ipm %[mask]\n"
+ : [mask] "=r" (mask)
+ : [addr] "Q" (*(char *)addr),
+ [key] "a" (key)
+ : "cc"
+ );
+
+ return (enum permission)(mask >> 28);
+}
+
+enum stage {
+ STAGE_INIT_SIMPLE,
+ TEST_SIMPLE,
+ STAGE_INIT_FETCH_PROT_OVERRIDE,
+ TEST_FETCH_PROT_OVERRIDE,
+ TEST_STORAGE_PROT_OVERRIDE,
+ STAGE_END /* must be the last entry (it's the amount of tests) */
+};
+
+struct test {
+ enum stage stage;
+ void *addr;
+ uint8_t key;
+ enum permission expected;
+} tests[] = {
+ /*
+ * We perform each test in the array by executing TEST PROTECTION on
+ * the specified addr with the specified key and checking if the returned
+ * permissions match the expected value.
+ * Both guest and host cooperate to set up the required test conditions.
+ * A central condition is that the page targeted by addr has to be DAT
+ * protected in the host mappings, in order for KVM to emulate the
+ * TEST PROTECTION instruction.
+ * Since the page tables are shared, the host uses mprotect to achieve
+ * this.
+ *
+ * Test resulting in RW_PROTECTED/TRANSL_UNAVAIL will be interpreted
+ * by SIE, not KVM, but there is no harm in testing them also.
+ * See Enhanced Suppression-on-Protection Facilities in the
+ * Interpretive-Execution Mode
+ */
+ /*
+ * guest: set storage key of page_store_prot to 1
+ * storage key of page_fetch_prot to 9 and enable
+ * protection for it
+ * STAGE_INIT_SIMPLE
+ * host: write protect both via mprotect
+ */
+ /* access key 0 matches any storage key -> RW */
+ { TEST_SIMPLE, page_store_prot, 0x00, READ_WRITE },
+ /* access key matches storage key -> RW */
+ { TEST_SIMPLE, page_store_prot, 0x10, READ_WRITE },
+ /* mismatched keys, but no fetch protection -> RO */
+ { TEST_SIMPLE, page_store_prot, 0x20, READ },
+ /* access key 0 matches any storage key -> RW */
+ { TEST_SIMPLE, page_fetch_prot, 0x00, READ_WRITE },
+ /* access key matches storage key -> RW */
+ { TEST_SIMPLE, page_fetch_prot, 0x90, READ_WRITE },
+ /* mismatched keys, fetch protection -> inaccessible */
+ { TEST_SIMPLE, page_fetch_prot, 0x10, RW_PROTECTED },
+ /* page 0 not mapped yet -> translation not available */
+ { TEST_SIMPLE, (void *)0x00, 0x10, TRANSL_UNAVAIL },
+ /*
+ * host: try to map page 0
+ * guest: set storage key of page 0 to 9 and enable fetch protection
+ * STAGE_INIT_FETCH_PROT_OVERRIDE
+ * host: write protect page 0
+ * enable fetch protection override
+ */
+ /* mismatched keys, fetch protection, but override applies -> RO */
+ { TEST_FETCH_PROT_OVERRIDE, (void *)0x00, 0x10, READ },
+ /* mismatched keys, fetch protection, override applies to 0-2048 only -> inaccessible */
+ { TEST_FETCH_PROT_OVERRIDE, (void *)2049, 0x10, RW_PROTECTED },
+ /*
+ * host: enable storage protection override
+ */
+ /* mismatched keys, but override applies (storage key 9) -> RW */
+ { TEST_STORAGE_PROT_OVERRIDE, page_fetch_prot, 0x10, READ_WRITE },
+ /* mismatched keys, no fetch protection, override doesn't apply -> RO */
+ { TEST_STORAGE_PROT_OVERRIDE, page_store_prot, 0x20, READ },
+ /* mismatched keys, but override applies (storage key 9) -> RW */
+ { TEST_STORAGE_PROT_OVERRIDE, (void *)2049, 0x10, READ_WRITE },
+ /* end marker */
+ { STAGE_END, 0, 0, 0 },
+};
+
+static enum stage perform_next_stage(int *i, bool mapped_0)
+{
+ enum stage stage = tests[*i].stage;
+ enum permission result;
+ bool skip;
+
+ for (; tests[*i].stage == stage; (*i)++) {
+ /*
+ * Some fetch protection override tests require that page 0
+ * be mapped, however, when the hosts tries to map that page via
+ * vm_vaddr_alloc, it may happen that some other page gets mapped
+ * instead.
+ * In order to skip these tests we detect this inside the guest
+ */
+ skip = tests[*i].addr < (void *)PAGE_SIZE &&
+ tests[*i].expected != TRANSL_UNAVAIL &&
+ !mapped_0;
+ if (!skip) {
+ result = test_protection(tests[*i].addr, tests[*i].key);
+ __GUEST_ASSERT(result == tests[*i].expected,
+ "Wanted %u, got %u, for i = %u",
+ tests[*i].expected, result, *i);
+ }
+ }
+ return stage;
+}
+
+static void guest_code(void)
+{
+ bool mapped_0;
+ int i = 0;
+
+ GUEST_ASSERT_EQ(set_storage_key(page_store_prot, 0x10), 0);
+ GUEST_ASSERT_EQ(set_storage_key(page_fetch_prot, 0x98), 0);
+ GUEST_SYNC(STAGE_INIT_SIMPLE);
+ GUEST_SYNC(perform_next_stage(&i, false));
+
+ /* Fetch-protection override */
+ mapped_0 = !set_storage_key((void *)0, 0x98);
+ GUEST_SYNC(STAGE_INIT_FETCH_PROT_OVERRIDE);
+ GUEST_SYNC(perform_next_stage(&i, mapped_0));
+
+ /* Storage-protection override */
+ GUEST_SYNC(perform_next_stage(&i, mapped_0));
+}
+
+#define HOST_SYNC_NO_TAP(vcpup, stage) \
+({ \
+ struct kvm_vcpu *__vcpu = (vcpup); \
+ struct ucall uc; \
+ int __stage = (stage); \
+ \
+ vcpu_run(__vcpu); \
+ get_ucall(__vcpu, &uc); \
+ if (uc.cmd == UCALL_ABORT) \
+ REPORT_GUEST_ASSERT(uc); \
+ TEST_ASSERT_EQ(uc.cmd, UCALL_SYNC); \
+ TEST_ASSERT_EQ(uc.args[1], __stage); \
+})
+
+#define HOST_SYNC(vcpu, stage) \
+({ \
+ HOST_SYNC_NO_TAP(vcpu, stage); \
+ ksft_test_result_pass("" #stage "\n"); \
+})
+
+int main(int argc, char *argv[])
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+ struct kvm_run *run;
+ vm_vaddr_t guest_0_page;
+
+ ksft_print_header();
+ ksft_set_plan(STAGE_END);
+
+ vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+ run = vcpu->run;
+
+ HOST_SYNC(vcpu, STAGE_INIT_SIMPLE);
+ mprotect(addr_gva2hva(vm, (vm_vaddr_t)pages), PAGE_SIZE * 2, PROT_READ);
+ HOST_SYNC(vcpu, TEST_SIMPLE);
+
+ guest_0_page = vm_vaddr_alloc(vm, PAGE_SIZE, 0);
+ if (guest_0_page != 0) {
+ /* Use NO_TAP so we don't get a PASS print */
+ HOST_SYNC_NO_TAP(vcpu, STAGE_INIT_FETCH_PROT_OVERRIDE);
+ ksft_test_result_skip("STAGE_INIT_FETCH_PROT_OVERRIDE - "
+ "Did not allocate page at 0\n");
+ } else {
+ HOST_SYNC(vcpu, STAGE_INIT_FETCH_PROT_OVERRIDE);
+ }
+ if (guest_0_page == 0)
+ mprotect(addr_gva2hva(vm, (vm_vaddr_t)0), PAGE_SIZE, PROT_READ);
+ run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE;
+ run->kvm_dirty_regs = KVM_SYNC_CRS;
+ HOST_SYNC(vcpu, TEST_FETCH_PROT_OVERRIDE);
+
+ run->s.regs.crs[0] |= CR0_STORAGE_PROTECTION_OVERRIDE;
+ run->kvm_dirty_regs = KVM_SYNC_CRS;
+ HOST_SYNC(vcpu, TEST_STORAGE_PROT_OVERRIDE);
+
+ kvm_vm_free(vm);
+
+ ksft_finished(); /* Print results and exit() accordingly */
+}
diff --git a/tools/testing/selftests/kvm/s390/ucontrol_test.c b/tools/testing/selftests/kvm/s390/ucontrol_test.c
new file mode 100644
index 000000000000..d265b34c54be
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390/ucontrol_test.c
@@ -0,0 +1,800 @@
+// 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 PGM_SEGMENT_TRANSLATION 0x10
+
+#define VM_MEM_SIZE (4 * SZ_1M)
+#define VM_MEM_EXT_SIZE (2 * SZ_1M)
+#define VM_MEM_MAX_M ((VM_MEM_SIZE + VM_MEM_EXT_SIZE) / 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"
+);
+
+/* Test program manipulating memory */
+extern char test_mem_asm[];
+asm("test_mem_asm:\n"
+ "xgr %r0, %r0\n"
+
+ "0:\n"
+ " ahi %r0,1\n"
+ " st %r1,0(%r5,%r6)\n"
+
+ " xgr %r1,%r1\n"
+ " l %r1,0(%r5,%r6)\n"
+ " ahi %r0,1\n"
+ " diag 0,0,0x44\n"
+
+ " j 0b\n"
+);
+
+/* Test program manipulating storage keys */
+extern char test_skey_asm[];
+asm("test_skey_asm:\n"
+ "xgr %r0, %r0\n"
+
+ "0:\n"
+ " ahi %r0,1\n"
+ " st %r1,0(%r5,%r6)\n"
+
+ " sske %r1,%r6\n"
+ " xgr %r1,%r1\n"
+ " iske %r1,%r6\n"
+ " ahi %r0,1\n"
+ " diag 0,0,0x44\n"
+
+ " rrbe %r1,%r6\n"
+ " iske %r1,%r6\n"
+ " ahi %r0,1\n"
+ " diag 0,0,0x44\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;
+ vm_paddr_t pgd;
+ 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_MAX_M * SZ_1M);
+ 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 = (u64)&limit,
+ };
+ int rc;
+
+ rc = ioctl(self->vm_fd, KVM_HAS_DEVICE_ATTR, &attr);
+ EXPECT_EQ(0, 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);
+}
+
+/* calculate host virtual addr from guest physical addr */
+static void *gpa2hva(FIXTURE_DATA(uc_kvm) *self, u64 gpa)
+{
+ return (void *)(self->base_hva - self->base_gpa + gpa);
+}
+
+/* map / make additional memory available */
+static int uc_map_ext(FIXTURE_DATA(uc_kvm) *self, u64 vcpu_addr, u64 length)
+{
+ struct kvm_s390_ucas_mapping map = {
+ .user_addr = (u64)gpa2hva(self, vcpu_addr),
+ .vcpu_addr = vcpu_addr,
+ .length = length,
+ };
+ pr_info("ucas map %p %p 0x%llx",
+ (void *)map.user_addr, (void *)map.vcpu_addr, map.length);
+ return ioctl(self->vcpu_fd, KVM_S390_UCAS_MAP, &map);
+}
+
+/* unmap previously mapped memory */
+static int uc_unmap_ext(FIXTURE_DATA(uc_kvm) *self, u64 vcpu_addr, u64 length)
+{
+ struct kvm_s390_ucas_mapping map = {
+ .user_addr = (u64)gpa2hva(self, vcpu_addr),
+ .vcpu_addr = vcpu_addr,
+ .length = length,
+ };
+ pr_info("ucas unmap %p %p 0x%llx",
+ (void *)map.user_addr, (void *)map.vcpu_addr, map.length);
+ return ioctl(self->vcpu_fd, KVM_S390_UCAS_UNMAP, &map);
+}
+
+/* handle ucontrol exit by mapping the accessed segment */
+static void uc_handle_exit_ucontrol(FIXTURE_DATA(uc_kvm) *self)
+{
+ struct kvm_run *run = self->run;
+ u64 seg_addr;
+ int rc;
+
+ TEST_ASSERT_EQ(KVM_EXIT_S390_UCONTROL, run->exit_reason);
+ switch (run->s390_ucontrol.pgm_code) {
+ case PGM_SEGMENT_TRANSLATION:
+ seg_addr = run->s390_ucontrol.trans_exc_code & ~(SZ_1M - 1);
+ pr_info("ucontrol pic segment translation 0x%llx, mapping segment 0x%lx\n",
+ run->s390_ucontrol.trans_exc_code, seg_addr);
+ /* map / make additional memory available */
+ rc = uc_map_ext(self, seg_addr, SZ_1M);
+ TEST_ASSERT_EQ(0, rc);
+ break;
+ default:
+ TEST_FAIL("UNEXPECTED PGM CODE %d", run->s390_ucontrol.pgm_code);
+ }
+}
+
+/*
+ * Handle the SIEIC exit
+ * * fail on codes not expected in the test cases
+ * Returns if interception is handled / execution can be continued
+ */
+static void uc_skey_enable(FIXTURE_DATA(uc_kvm) *self)
+{
+ struct kvm_s390_sie_block *sie_block = self->sie_block;
+
+ /* disable KSS */
+ sie_block->cpuflags &= ~CPUSTAT_KSS;
+ /* disable skey inst interception */
+ sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE);
+}
+
+/*
+ * Handle the instruction intercept
+ * Returns if interception is handled / execution can be continued
+ */
+static bool uc_handle_insn_ic(FIXTURE_DATA(uc_kvm) *self)
+{
+ struct kvm_s390_sie_block *sie_block = self->sie_block;
+ int ilen = insn_length(sie_block->ipa >> 8);
+ struct kvm_run *run = self->run;
+
+ switch (run->s390_sieic.ipa) {
+ case 0xB229: /* ISKE */
+ case 0xB22b: /* SSKE */
+ case 0xB22a: /* RRBE */
+ uc_skey_enable(self);
+
+ /* rewind to reexecute intercepted instruction */
+ run->psw_addr = run->psw_addr - ilen;
+ pr_info("rewind guest addr to 0x%.16llx\n", run->psw_addr);
+ return true;
+ default:
+ return false;
+ }
+}
+
+/*
+ * Handle the SIEIC exit
+ * * fail on codes not expected in the test cases
+ * Returns if interception is handled / execution can be continued
+ */
+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%.8x\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 uc_handle_insn_ic(self);
+ case ICPT_KSS:
+ uc_skey_enable(self);
+ return true;
+ 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_UCONTROL:
+ /** check program interruption code
+ * handle page fault --> ucas map
+ */
+ uc_handle_exit_ucontrol(self);
+ break;
+ 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_no_user_region)
+{
+ struct kvm_userspace_memory_region region = {
+ .slot = 1,
+ .guest_phys_addr = self->code_gpa,
+ .memory_size = VM_MEM_EXT_SIZE,
+ .userspace_addr = (uintptr_t)self->code_hva,
+ };
+ struct kvm_userspace_memory_region2 region2 = {
+ .slot = 1,
+ .guest_phys_addr = self->code_gpa,
+ .memory_size = VM_MEM_EXT_SIZE,
+ .userspace_addr = (uintptr_t)self->code_hva,
+ };
+
+ ASSERT_EQ(-1, ioctl(self->vm_fd, KVM_SET_USER_MEMORY_REGION, &region));
+ ASSERT_TRUE(errno == EEXIST || errno == EINVAL)
+ TH_LOG("errno %s (%i) not expected for ioctl KVM_SET_USER_MEMORY_REGION",
+ strerror(errno), errno);
+
+ ASSERT_EQ(-1, ioctl(self->vm_fd, KVM_SET_USER_MEMORY_REGION2, &region2));
+ ASSERT_TRUE(errno == EEXIST || errno == EINVAL)
+ TH_LOG("errno %s (%i) not expected for ioctl KVM_SET_USER_MEMORY_REGION2",
+ strerror(errno), errno);
+}
+
+TEST_F(uc_kvm, uc_map_unmap)
+{
+ struct kvm_sync_regs *sync_regs = &self->run->s.regs;
+ struct kvm_run *run = self->run;
+ const u64 disp = 1;
+ int rc;
+
+ /* copy test_mem_asm to code_hva / code_gpa */
+ TH_LOG("copy code %p to vm mapped memory %p / %p",
+ &test_mem_asm, (void *)self->code_hva, (void *)self->code_gpa);
+ memcpy((void *)self->code_hva, &test_mem_asm, PAGE_SIZE);
+
+ /* DAT disabled + 64 bit mode */
+ run->psw_mask = 0x0000000180000000ULL;
+ run->psw_addr = self->code_gpa;
+
+ /* set register content for test_mem_asm to access not mapped memory*/
+ sync_regs->gprs[1] = 0x55;
+ sync_regs->gprs[5] = self->base_gpa;
+ sync_regs->gprs[6] = VM_MEM_SIZE + disp;
+ run->kvm_dirty_regs |= KVM_SYNC_GPRS;
+
+ /* run and expect to fail with ucontrol pic segment translation */
+ ASSERT_EQ(0, uc_run_once(self));
+ ASSERT_EQ(1, sync_regs->gprs[0]);
+ ASSERT_EQ(KVM_EXIT_S390_UCONTROL, run->exit_reason);
+
+ ASSERT_EQ(PGM_SEGMENT_TRANSLATION, run->s390_ucontrol.pgm_code);
+ ASSERT_EQ(self->base_gpa + VM_MEM_SIZE, run->s390_ucontrol.trans_exc_code);
+
+ /* fail to map memory with not segment aligned address */
+ rc = uc_map_ext(self, self->base_gpa + VM_MEM_SIZE + disp, VM_MEM_EXT_SIZE);
+ ASSERT_GT(0, rc)
+ TH_LOG("ucas map for non segment address should fail but didn't; "
+ "result %d not expected, %s", rc, strerror(errno));
+
+ /* map / make additional memory available */
+ rc = uc_map_ext(self, self->base_gpa + VM_MEM_SIZE, VM_MEM_EXT_SIZE);
+ ASSERT_EQ(0, rc)
+ TH_LOG("ucas map result %d not expected, %s", rc, strerror(errno));
+ ASSERT_EQ(0, uc_run_once(self));
+ ASSERT_EQ(false, uc_handle_exit(self));
+ uc_assert_diag44(self);
+
+ /* assert registers and memory are in expected state */
+ ASSERT_EQ(2, sync_regs->gprs[0]);
+ ASSERT_EQ(0x55, sync_regs->gprs[1]);
+ ASSERT_EQ(0x55, *(u32 *)gpa2hva(self, self->base_gpa + VM_MEM_SIZE + disp));
+
+ /* unmap and run loop again */
+ rc = uc_unmap_ext(self, self->base_gpa + VM_MEM_SIZE, VM_MEM_EXT_SIZE);
+ ASSERT_EQ(0, rc)
+ TH_LOG("ucas unmap result %d not expected, %s", rc, strerror(errno));
+ ASSERT_EQ(0, uc_run_once(self));
+ ASSERT_EQ(3, sync_regs->gprs[0]);
+ ASSERT_EQ(KVM_EXIT_S390_UCONTROL, run->exit_reason);
+ ASSERT_EQ(PGM_SEGMENT_TRANSLATION, run->s390_ucontrol.pgm_code);
+ /* handle ucontrol exit and remap memory after previous map and unmap */
+ ASSERT_EQ(true, uc_handle_exit(self));
+}
+
+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_F(uc_kvm, uc_skey)
+{
+ struct kvm_s390_sie_block *sie_block = self->sie_block;
+ struct kvm_sync_regs *sync_regs = &self->run->s.regs;
+ u64 test_vaddr = VM_MEM_SIZE - (SZ_1M / 2);
+ struct kvm_run *run = self->run;
+ const u8 skeyvalue = 0x34;
+
+ /* copy test_skey_asm to code_hva / code_gpa */
+ TH_LOG("copy code %p to vm mapped memory %p / %p",
+ &test_skey_asm, (void *)self->code_hva, (void *)self->code_gpa);
+ memcpy((void *)self->code_hva, &test_skey_asm, PAGE_SIZE);
+
+ /* set register content for test_skey_asm to access not mapped memory */
+ sync_regs->gprs[1] = skeyvalue;
+ sync_regs->gprs[5] = self->base_gpa;
+ sync_regs->gprs[6] = test_vaddr;
+ run->kvm_dirty_regs |= KVM_SYNC_GPRS;
+
+ /* DAT disabled + 64 bit mode */
+ run->psw_mask = 0x0000000180000000ULL;
+ run->psw_addr = self->code_gpa;
+
+ ASSERT_EQ(0, uc_run_once(self));
+ ASSERT_EQ(true, uc_handle_exit(self));
+ ASSERT_EQ(1, sync_regs->gprs[0]);
+
+ /* SSKE + ISKE */
+ sync_regs->gprs[1] = skeyvalue;
+ run->kvm_dirty_regs |= KVM_SYNC_GPRS;
+ ASSERT_EQ(0, uc_run_once(self));
+
+ /*
+ * Bail out and skip the test after uc_skey_enable was executed but iske
+ * is still intercepted. Instructions are not handled by the kernel.
+ * Thus there is no need to test this here.
+ */
+ TEST_ASSERT_EQ(0, sie_block->cpuflags & CPUSTAT_KSS);
+ TEST_ASSERT_EQ(0, sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE));
+ TEST_ASSERT_EQ(KVM_EXIT_S390_SIEIC, self->run->exit_reason);
+ TEST_ASSERT_EQ(ICPT_INST, sie_block->icptcode);
+ TEST_REQUIRE(sie_block->ipa != 0xb22b);
+
+ /* SSKE + ISKE contd. */
+ ASSERT_EQ(false, uc_handle_exit(self));
+ ASSERT_EQ(2, sync_regs->gprs[0]);
+ ASSERT_EQ(skeyvalue, sync_regs->gprs[1]);
+ uc_assert_diag44(self);
+
+ /* RRBE + ISKE */
+ sync_regs->gprs[1] = skeyvalue;
+ run->kvm_dirty_regs |= KVM_SYNC_GPRS;
+ ASSERT_EQ(0, uc_run_once(self));
+ ASSERT_EQ(false, uc_handle_exit(self));
+ ASSERT_EQ(3, sync_regs->gprs[0]);
+ /* assert R reset but rest of skey unchanged */
+ ASSERT_EQ(skeyvalue & 0xfa, sync_regs->gprs[1]);
+ ASSERT_EQ(0, sync_regs->gprs[1] & 0x04);
+ uc_assert_diag44(self);
+}
+
+static char uc_flic_b[PAGE_SIZE];
+static struct kvm_s390_io_adapter uc_flic_ioa = { .id = 0 };
+static struct kvm_s390_io_adapter_req uc_flic_ioam = { .id = 0 };
+static struct kvm_s390_ais_req uc_flic_asim = { .isc = 0 };
+static struct kvm_s390_ais_all uc_flic_asima = { .simm = 0 };
+static struct uc_flic_attr_test {
+ char *name;
+ struct kvm_device_attr a;
+ int hasrc;
+ int geterrno;
+ int seterrno;
+} uc_flic_attr_tests[] = {
+ {
+ .name = "KVM_DEV_FLIC_GET_ALL_IRQS",
+ .seterrno = EINVAL,
+ .a = {
+ .group = KVM_DEV_FLIC_GET_ALL_IRQS,
+ .addr = (u64)&uc_flic_b,
+ .attr = PAGE_SIZE,
+ },
+ },
+ {
+ .name = "KVM_DEV_FLIC_ENQUEUE",
+ .geterrno = EINVAL,
+ .a = { .group = KVM_DEV_FLIC_ENQUEUE, },
+ },
+ {
+ .name = "KVM_DEV_FLIC_CLEAR_IRQS",
+ .geterrno = EINVAL,
+ .a = { .group = KVM_DEV_FLIC_CLEAR_IRQS, },
+ },
+ {
+ .name = "KVM_DEV_FLIC_ADAPTER_REGISTER",
+ .geterrno = EINVAL,
+ .a = {
+ .group = KVM_DEV_FLIC_ADAPTER_REGISTER,
+ .addr = (u64)&uc_flic_ioa,
+ },
+ },
+ {
+ .name = "KVM_DEV_FLIC_ADAPTER_MODIFY",
+ .geterrno = EINVAL,
+ .seterrno = EINVAL,
+ .a = {
+ .group = KVM_DEV_FLIC_ADAPTER_MODIFY,
+ .addr = (u64)&uc_flic_ioam,
+ .attr = sizeof(uc_flic_ioam),
+ },
+ },
+ {
+ .name = "KVM_DEV_FLIC_CLEAR_IO_IRQ",
+ .geterrno = EINVAL,
+ .seterrno = EINVAL,
+ .a = {
+ .group = KVM_DEV_FLIC_CLEAR_IO_IRQ,
+ .attr = 32,
+ },
+ },
+ {
+ .name = "KVM_DEV_FLIC_AISM",
+ .geterrno = EINVAL,
+ .seterrno = ENOTSUP,
+ .a = {
+ .group = KVM_DEV_FLIC_AISM,
+ .addr = (u64)&uc_flic_asim,
+ },
+ },
+ {
+ .name = "KVM_DEV_FLIC_AIRQ_INJECT",
+ .geterrno = EINVAL,
+ .a = { .group = KVM_DEV_FLIC_AIRQ_INJECT, },
+ },
+ {
+ .name = "KVM_DEV_FLIC_AISM_ALL",
+ .geterrno = ENOTSUP,
+ .seterrno = ENOTSUP,
+ .a = {
+ .group = KVM_DEV_FLIC_AISM_ALL,
+ .addr = (u64)&uc_flic_asima,
+ .attr = sizeof(uc_flic_asima),
+ },
+ },
+ {
+ .name = "KVM_DEV_FLIC_APF_ENABLE",
+ .geterrno = EINVAL,
+ .seterrno = EINVAL,
+ .a = { .group = KVM_DEV_FLIC_APF_ENABLE, },
+ },
+ {
+ .name = "KVM_DEV_FLIC_APF_DISABLE_WAIT",
+ .geterrno = EINVAL,
+ .seterrno = EINVAL,
+ .a = { .group = KVM_DEV_FLIC_APF_DISABLE_WAIT, },
+ },
+};
+
+TEST_F(uc_kvm, uc_flic_attrs)
+{
+ struct kvm_create_device cd = { .type = KVM_DEV_TYPE_FLIC };
+ struct kvm_device_attr attr;
+ u64 value;
+ int rc, i;
+
+ rc = ioctl(self->vm_fd, KVM_CREATE_DEVICE, &cd);
+ ASSERT_EQ(0, rc) TH_LOG("create device failed with err %s (%i)",
+ strerror(errno), errno);
+
+ for (i = 0; i < ARRAY_SIZE(uc_flic_attr_tests); i++) {
+ TH_LOG("test %s", uc_flic_attr_tests[i].name);
+ attr = (struct kvm_device_attr) {
+ .group = uc_flic_attr_tests[i].a.group,
+ .attr = uc_flic_attr_tests[i].a.attr,
+ .addr = uc_flic_attr_tests[i].a.addr,
+ };
+ if (attr.addr == 0)
+ attr.addr = (u64)&value;
+
+ rc = ioctl(cd.fd, KVM_HAS_DEVICE_ATTR, &attr);
+ EXPECT_EQ(uc_flic_attr_tests[i].hasrc, !!rc)
+ TH_LOG("expected dev attr missing %s",
+ uc_flic_attr_tests[i].name);
+
+ rc = ioctl(cd.fd, KVM_GET_DEVICE_ATTR, &attr);
+ EXPECT_EQ(!!uc_flic_attr_tests[i].geterrno, !!rc)
+ TH_LOG("get dev attr rc not expected on %s %s (%i)",
+ uc_flic_attr_tests[i].name,
+ strerror(errno), errno);
+ if (uc_flic_attr_tests[i].geterrno)
+ EXPECT_EQ(uc_flic_attr_tests[i].geterrno, errno)
+ TH_LOG("get dev attr errno not expected on %s %s (%i)",
+ uc_flic_attr_tests[i].name,
+ strerror(errno), errno);
+
+ rc = ioctl(cd.fd, KVM_SET_DEVICE_ATTR, &attr);
+ EXPECT_EQ(!!uc_flic_attr_tests[i].seterrno, !!rc)
+ TH_LOG("set sev attr rc not expected on %s %s (%i)",
+ uc_flic_attr_tests[i].name,
+ strerror(errno), errno);
+ if (uc_flic_attr_tests[i].seterrno)
+ EXPECT_EQ(uc_flic_attr_tests[i].seterrno, errno)
+ TH_LOG("set dev attr errno not expected on %s %s (%i)",
+ uc_flic_attr_tests[i].name,
+ strerror(errno), errno);
+ }
+
+ close(cd.fd);
+}
+
+TEST_F(uc_kvm, uc_set_gsi_routing)
+{
+ struct kvm_irq_routing *routing = kvm_gsi_routing_create();
+ struct kvm_irq_routing_entry ue = {
+ .type = KVM_IRQ_ROUTING_S390_ADAPTER,
+ .gsi = 1,
+ .u.adapter = (struct kvm_irq_routing_s390_adapter) {
+ .ind_addr = 0,
+ },
+ };
+ int rc;
+
+ routing->entries[0] = ue;
+ routing->nr = 1;
+ rc = ioctl(self->vm_fd, KVM_SET_GSI_ROUTING, routing);
+ ASSERT_EQ(-1, rc) TH_LOG("err %s (%i)", strerror(errno), errno);
+ ASSERT_EQ(EINVAL, errno) TH_LOG("err %s (%i)", strerror(errno), errno);
+}
+
+TEST_HARNESS_MAIN