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

Pull second set of KVM updates from Paolo Bonzini:
 "ARM:
   - Support for Group0 interrupts in guests
   - Cache management optimizations for ARMv8.4 systems
   - Userspace interface for RAS
   - Fault path optimization
   - Emulated physical timer fixes
   - Random cleanups

  x86:
   - fixes for L1TF
   - a new test case
   - non-support for SGX (inject the right exception in the guest)
   - fix lockdep false positive"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (49 commits)
  KVM: VMX: fixes for vmentry_l1d_flush module parameter
  kvm: selftest: add dirty logging test
  kvm: selftest: pass in extra memory when create vm
  kvm: selftest: include the tools headers
  kvm: selftest: unify the guest port macros
  tools: introduce test_and_clear_bit
  KVM: x86: SVM: Call x86_spec_ctrl_set_guest/host() with interrupts disabled
  KVM: vmx: Inject #UD for SGX ENCLS instruction in guest
  KVM: vmx: Add defines for SGX ENCLS exiting
  x86/kvm/vmx: Fix coding style in vmx_setup_l1d_flush()
  x86: kvm: avoid unused variable warning
  KVM: Documentation: rename the capability of KVM_CAP_ARM_SET_SERROR_ESR
  KVM: arm/arm64: Skip updating PTE entry if no change
  KVM: arm/arm64: Skip updating PMD entry if no change
  KVM: arm: Use true and false for boolean values
  KVM: arm/arm64: vgic: Do not use spin_lock_irqsave/restore with irq disabled
  KVM: arm/arm64: vgic: Move DEBUG_SPINLOCK_BUG_ON to vgic.h
  KVM: arm: vgic-v3: Add support for ICC_SGI0R and ICC_ASGI1R accesses
  KVM: arm64: vgic-v3: Add support for ICC_SGI0R_EL1 and ICC_ASGI1R_EL1 accesses
  KVM: arm/arm64: vgic-v3: Add core support for Group0 SGIs
  ...

12 files changed, 477 insertions, 106 deletions

diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 63440cc8d618..e63662db131b 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -97,6 +97,23 @@ static inline int test_and_set_bit(int nr, unsigned long *addr)
 }
 
 /**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ */
+static inline int test_and_clear_bit(int nr, unsigned long *addr)
+{
+        unsigned long mask = BIT_MASK(nr);
+        unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+        unsigned long old;
+
+        old = *p;
+        *p = old & ~mask;
+
+        return (old & mask) != 0;
+}
+
+/**
  * bitmap_alloc - Allocate bitmap
  * @nbits: Number of bits
  */
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index dd0e5163f01f..03b0f551bedf 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -11,13 +11,16 @@ TEST_GEN_PROGS_x86_64 += sync_regs_test
 TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += state_test
+TEST_GEN_PROGS_x86_64 += dirty_log_test
 
 TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
 LIBKVM += $(LIBKVM_$(UNAME_M))
 
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
-CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I..
+LINUX_TOOL_INCLUDE = $(top_srcdir)tools/include
+CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I..
+LDFLAGS += -lpthread
 
 # After inclusion, $(OUTPUT) is defined and
 # $(TEST_GEN_PROGS) starts with $(OUTPUT)/
diff --git a/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
index 8346b33c2073..11ec358bf969 100644
--- a/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
+++ b/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
@@ -23,20 +23,6 @@
 #define X86_FEATURE_OSXSAVE     (1<<27)
 #define VCPU_ID                 1
 
-enum {
-        GUEST_UPDATE_CR4 = 0x1000,
-        GUEST_FAILED,
-        GUEST_DONE,
-};
-
-static void exit_to_hv(uint16_t port)
-{
-        __asm__ __volatile__("in %[port], %%al"
-                             :
-                             : [port]"d"(port)
-                             : "rax");
-}
-
 static inline bool cr4_cpuid_is_sync(void)
 {
         int func, subfunc;
@@ -64,17 +50,15 @@ static void guest_code(void)
         set_cr4(cr4);
 
         /* verify CR4.OSXSAVE == CPUID.OSXSAVE */
-        if (!cr4_cpuid_is_sync())
-                exit_to_hv(GUEST_FAILED);
+        GUEST_ASSERT(cr4_cpuid_is_sync());
 
         /* notify hypervisor to change CR4 */
-        exit_to_hv(GUEST_UPDATE_CR4);
+        GUEST_SYNC(0);
 
         /* check again */
-        if (!cr4_cpuid_is_sync())
-                exit_to_hv(GUEST_FAILED);
+        GUEST_ASSERT(cr4_cpuid_is_sync());
 
-        exit_to_hv(GUEST_DONE);
+        GUEST_DONE();
 }
 
 int main(int argc, char *argv[])
@@ -95,7 +79,7 @@ int main(int argc, char *argv[])
         setbuf(stdout, NULL);
 
         /* Create VM */
-        vm = vm_create_default(VCPU_ID, guest_code);
+        vm = vm_create_default(VCPU_ID, 0, guest_code);
         vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
         run = vcpu_state(vm, VCPU_ID);
 
@@ -104,16 +88,16 @@ int main(int argc, char *argv[])
 
                 if (run->exit_reason == KVM_EXIT_IO) {
                         switch (run->io.port) {
-                        case GUEST_UPDATE_CR4:
+                        case GUEST_PORT_SYNC:
                                 /* emulate hypervisor clearing CR4.OSXSAVE */
                                 vcpu_sregs_get(vm, VCPU_ID, &sregs);
                                 sregs.cr4 &= ~X86_CR4_OSXSAVE;
                                 vcpu_sregs_set(vm, VCPU_ID, &sregs);
                                 break;
-                        case GUEST_FAILED:
+                        case GUEST_PORT_ABORT:
                                 TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
                                 break;
-                        case GUEST_DONE:
+                        case GUEST_PORT_DONE:
                                 goto done;
                         default:
                                 TEST_ASSERT(false, "Unknown port 0x%x.",
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
new file mode 100644
index 000000000000..0c2cdc105f96
--- /dev/null
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -0,0 +1,308 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM dirty page logging test
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+
+#define  DEBUG                 printf
+
+#define  VCPU_ID                        1
+/* The memory slot index to track dirty pages */
+#define  TEST_MEM_SLOT_INDEX            1
+/*
+ * GPA offset of the testing memory slot. Must be bigger than the
+ * default vm mem slot, which is DEFAULT_GUEST_PHY_PAGES.
+ */
+#define  TEST_MEM_OFFSET                (1ULL << 30) /* 1G */
+/* Size of the testing memory slot */
+#define  TEST_MEM_PAGES                 (1ULL << 18) /* 1G for 4K pages */
+/* How many pages to dirty for each guest loop */
+#define  TEST_PAGES_PER_LOOP            1024
+/* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */
+#define  TEST_HOST_LOOP_N               32
+/* Interval for each host loop (ms) */
+#define  TEST_HOST_LOOP_INTERVAL        10
+
+/*
+ * Guest variables.  We use these variables to share data between host
+ * and guest.  There are two copies of the variables, one in host memory
+ * (which is unused) and one in guest memory.  When the host wants to
+ * access these variables, it needs to call addr_gva2hva() to access the
+ * guest copy.
+ */
+uint64_t guest_random_array[TEST_PAGES_PER_LOOP];
+uint64_t guest_iteration;
+uint64_t guest_page_size;
+
+/*
+ * Writes to the first byte of a random page within the testing memory
+ * region continuously.
+ */
+void guest_code(void)
+{
+        int i = 0;
+        uint64_t volatile *array = guest_random_array;
+        uint64_t volatile *guest_addr;
+
+        while (true) {
+                for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
+                        /*
+                         * Write to the first 8 bytes of a random page
+                         * on the testing memory region.
+                         */
+                        guest_addr = (uint64_t *)
+                            (TEST_MEM_OFFSET +
+                             (array[i] % TEST_MEM_PAGES) * guest_page_size);
+                        *guest_addr = guest_iteration;
+                }
+                /* Tell the host that we need more random numbers */
+                GUEST_SYNC(1);
+        }
+}
+
+/*
+ * Host variables.  These variables should only be used by the host
+ * rather than the guest.
+ */
+bool host_quit;
+
+/* Points to the test VM memory region on which we track dirty logs */
+void *host_test_mem;
+
+/* For statistics only */
+uint64_t host_dirty_count;
+uint64_t host_clear_count;
+uint64_t host_track_next_count;
+
+/*
+ * We use this bitmap to track some pages that should have its dirty
+ * bit set in the _next_ iteration.  For example, if we detected the
+ * page value changed to current iteration but at the same time the
+ * page bit is cleared in the latest bitmap, then the system must
+ * report that write in the next get dirty log call.
+ */
+unsigned long *host_bmap_track;
+
+void generate_random_array(uint64_t *guest_array, uint64_t size)
+{
+        uint64_t i;
+
+        for (i = 0; i < size; i++) {
+                guest_array[i] = random();
+        }
+}
+
+void *vcpu_worker(void *data)
+{
+        int ret;
+        uint64_t loops, *guest_array, pages_count = 0;
+        struct kvm_vm *vm = data;
+        struct kvm_run *run;
+        struct guest_args args;
+
+        run = vcpu_state(vm, VCPU_ID);
+
+        /* Retrieve the guest random array pointer and cache it */
+        guest_array = addr_gva2hva(vm, (vm_vaddr_t)guest_random_array);
+
+        DEBUG("VCPU starts\n");
+
+        generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
+
+        while (!READ_ONCE(host_quit)) {
+                /* Let the guest to dirty these random pages */
+                ret = _vcpu_run(vm, VCPU_ID);
+                guest_args_read(vm, VCPU_ID, &args);
+                if (run->exit_reason == KVM_EXIT_IO &&
+                    args.port == GUEST_PORT_SYNC) {
+                        pages_count += TEST_PAGES_PER_LOOP;
+                        generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
+                } else {
+                        TEST_ASSERT(false,
+                                    "Invalid guest sync status: "
+                                    "exit_reason=%s\n",
+                                    exit_reason_str(run->exit_reason));
+                }
+        }
+
+        DEBUG("VCPU exits, dirtied %"PRIu64" pages\n", pages_count);
+
+        return NULL;
+}
+
+void vm_dirty_log_verify(unsigned long *bmap, uint64_t iteration)
+{
+        uint64_t page;
+        uint64_t volatile *value_ptr;
+
+        for (page = 0; page < TEST_MEM_PAGES; page++) {
+                value_ptr = host_test_mem + page * getpagesize();
+
+                /* If this is a special page that we were tracking... */
+                if (test_and_clear_bit(page, host_bmap_track)) {
+                        host_track_next_count++;
+                        TEST_ASSERT(test_bit(page, bmap),
+                                    "Page %"PRIu64" should have its dirty bit "
+                                    "set in this iteration but it is missing",
+                                    page);
+                }
+
+                if (test_bit(page, bmap)) {
+                        host_dirty_count++;
+                        /*
+                         * If the bit is set, the value written onto
+                         * the corresponding page should be either the
+                         * previous iteration number or the current one.
+                         */
+                        TEST_ASSERT(*value_ptr == iteration ||
+                                    *value_ptr == iteration - 1,
+                                    "Set page %"PRIu64" value %"PRIu64
+                                    " incorrect (iteration=%"PRIu64")",
+                                    page, *value_ptr, iteration);
+                } else {
+                        host_clear_count++;
+                        /*
+                         * If cleared, the value written can be any
+                         * value smaller or equals to the iteration
+                         * number.  Note that the value can be exactly
+                         * (iteration-1) if that write can happen
+                         * like this:
+                         *
+                         * (1) increase loop count to "iteration-1"
+                         * (2) write to page P happens (with value
+                         *     "iteration-1")
+                         * (3) get dirty log for "iteration-1"; we'll
+                         *     see that page P bit is set (dirtied),
+                         *     and not set the bit in host_bmap_track
+                         * (4) increase loop count to "iteration"
+                         *     (which is current iteration)
+                         * (5) get dirty log for current iteration,
+                         *     we'll see that page P is cleared, with
+                         *     value "iteration-1".
+                         */
+                        TEST_ASSERT(*value_ptr <= iteration,
+                                    "Clear page %"PRIu64" value %"PRIu64
+                                    " incorrect (iteration=%"PRIu64")",
+                                    page, *value_ptr, iteration);
+                        if (*value_ptr == iteration) {
+                                /*
+                                 * This page is _just_ modified; it
+                                 * should report its dirtyness in the
+                                 * next run
+                                 */
+                                set_bit(page, host_bmap_track);
+                        }
+                }
+        }
+}
+
+void help(char *name)
+{
+        puts("");
+        printf("usage: %s [-i iterations] [-I interval] [-h]\n", name);
+        puts("");
+        printf(" -i: specify iteration counts (default: %"PRIu64")\n",
+               TEST_HOST_LOOP_N);
+        printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
+               TEST_HOST_LOOP_INTERVAL);
+        puts("");
+        exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+        pthread_t vcpu_thread;
+        struct kvm_vm *vm;
+        uint64_t volatile *psize, *iteration;
+        unsigned long *bmap, iterations = TEST_HOST_LOOP_N,
+            interval = TEST_HOST_LOOP_INTERVAL;
+        int opt;
+
+        while ((opt = getopt(argc, argv, "hi:I:")) != -1) {
+                switch (opt) {
+                case 'i':
+                        iterations = strtol(optarg, NULL, 10);
+                        break;
+                case 'I':
+                        interval = strtol(optarg, NULL, 10);
+                        break;
+                case 'h':
+                default:
+                        help(argv[0]);
+                        break;
+                }
+        }
+
+        TEST_ASSERT(iterations > 2, "Iteration must be bigger than zero\n");
+        TEST_ASSERT(interval > 0, "Interval must be bigger than zero");
+
+        DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
+              iterations, interval);
+
+        srandom(time(0));
+
+        bmap = bitmap_alloc(TEST_MEM_PAGES);
+        host_bmap_track = bitmap_alloc(TEST_MEM_PAGES);
+
+        vm = vm_create_default(VCPU_ID, TEST_MEM_PAGES, guest_code);
+
+        /* Add an extra memory slot for testing dirty logging */
+        vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+                                    TEST_MEM_OFFSET,
+                                    TEST_MEM_SLOT_INDEX,
+                                    TEST_MEM_PAGES,
+                                    KVM_MEM_LOG_DIRTY_PAGES);
+        /* Cache the HVA pointer of the region */
+        host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
+
+        /* Do 1:1 mapping for the dirty track memory slot */
+        virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
+                 TEST_MEM_PAGES * getpagesize(), 0);
+
+        vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+        /* Tell the guest about the page size on the system */
+        psize = addr_gva2hva(vm, (vm_vaddr_t)&guest_page_size);
+        *psize = getpagesize();
+
+        /* Start the iterations */
+        iteration = addr_gva2hva(vm, (vm_vaddr_t)&guest_iteration);
+        *iteration = 1;
+
+        /* Start dirtying pages */
+        pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
+
+        while (*iteration < iterations) {
+                /* Give the vcpu thread some time to dirty some pages */
+                usleep(interval * 1000);
+                kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+                vm_dirty_log_verify(bmap, *iteration);
+                (*iteration)++;
+        }
+
+        /* Tell the vcpu thread to quit */
+        host_quit = true;
+        pthread_join(vcpu_thread, NULL);
+
+        DEBUG("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
+              "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count,
+              host_track_next_count);
+
+        free(bmap);
+        free(host_bmap_track);
+        kvm_vm_free(vm);
+
+        return 0;
+}
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index d32632f71ab8..bb5a25fb82c6 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -55,6 +55,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
 void kvm_vm_free(struct kvm_vm *vmp);
 void kvm_vm_restart(struct kvm_vm *vmp, int perm);
 void kvm_vm_release(struct kvm_vm *vmp);
+void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log);
 
 int kvm_memcmp_hva_gva(void *hva,
         struct kvm_vm *vm, const vm_vaddr_t gva, size_t len);
@@ -80,6 +81,8 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
 void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, int gdt_memslot);
 vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
         uint32_t data_memslot, uint32_t pgd_memslot);
+void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+              size_t size, uint32_t pgd_memslot);
 void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
 void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
 vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
@@ -127,7 +130,8 @@ kvm_get_supported_cpuid_entry(uint32_t function)
         return kvm_get_supported_cpuid_index(function, 0);
 }
 
-struct kvm_vm *vm_create_default(uint32_t vcpuid, void *guest_code);
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_size,
+                                 void *guest_code);
 void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
 
 typedef void (*vmx_guest_code_t)(vm_vaddr_t vmxon_vaddr,
@@ -144,4 +148,43 @@ allocate_kvm_dirty_log(struct kvm_userspace_memory_region *region);
 
 int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd);
 
+#define GUEST_PORT_SYNC         0x1000
+#define GUEST_PORT_ABORT        0x1001
+#define GUEST_PORT_DONE         0x1002
+
+static inline void __exit_to_l0(uint16_t port, uint64_t arg0, uint64_t arg1)
+{
+        __asm__ __volatile__("in %[port], %%al"
+                             :
+                             : [port]"d"(port), "D"(arg0), "S"(arg1)
+                             : "rax");
+}
+
+/*
+ * Allows to pass three arguments to the host: port is 16bit wide,
+ * arg0 & arg1 are 64bit wide
+ */
+#define GUEST_SYNC_ARGS(_port, _arg0, _arg1) \
+        __exit_to_l0(_port, (uint64_t) (_arg0), (uint64_t) (_arg1))
+
+#define GUEST_ASSERT(_condition) do {                           \
+                if (!(_condition))                              \
+                        GUEST_SYNC_ARGS(GUEST_PORT_ABORT,       \
+                                        "Failed guest assert: " \
+                                        #_condition, __LINE__); \
+        } while (0)
+
+#define GUEST_SYNC(stage)  GUEST_SYNC_ARGS(GUEST_PORT_SYNC, "hello", stage)
+
+#define GUEST_DONE()  GUEST_SYNC_ARGS(GUEST_PORT_DONE, 0, 0)
+
+struct guest_args {
+        uint64_t arg0;
+        uint64_t arg1;
+        uint16_t port;
+} __attribute__ ((packed));
+
+void guest_args_read(struct kvm_vm *vm, uint32_t vcpu_id,
+                     struct guest_args *args);
+
 #endif /* SELFTEST_KVM_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index ac53730b30aa..73c3933436ec 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -28,8 +28,6 @@ int test_seq_read(const char *path, char **bufp, size_t *sizep);
 void test_assert(bool exp, const char *exp_str,
                  const char *file, unsigned int line, const char *fmt, ...);
 
-#define ARRAY_SIZE(array) (sizeof(array) / sizeof((array)[0]))
-
 #define TEST_ASSERT(e, fmt, ...) \
         test_assert((e), #e, __FILE__, __LINE__, fmt, ##__VA_ARGS__)
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 643309d6de74..e9ba389c48db 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -14,6 +14,7 @@
 #include <sys/mman.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <linux/kernel.h>
 
 #define KVM_DEV_PATH "/dev/kvm"
 
@@ -168,6 +169,16 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm)
         }
 }
 
+void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
+{
+        struct kvm_dirty_log args = { .dirty_bitmap = log, .slot = slot };
+        int ret;
+
+        ret = ioctl(vm->fd, KVM_GET_DIRTY_LOG, &args);
+        TEST_ASSERT(ret == 0, "%s: KVM_GET_DIRTY_LOG failed: %s",
+                    strerror(-ret));
+}
+
 /* Userspace Memory Region Find
  *
  * Input Args:
@@ -923,6 +934,39 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
         return vaddr_start;
 }
 
+/*
+ * Map a range of VM virtual address to the VM's physical address
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vaddr - Virtuall address to map
+ *   paddr - VM Physical Address
+ *   size - The size of the range to map
+ *   pgd_memslot - Memory region slot for new virtual translation tables
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Within the VM given by vm, creates a virtual translation for the
+ * page range starting at vaddr to the page range starting at paddr.
+ */
+void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+              size_t size, uint32_t pgd_memslot)
+{
+        size_t page_size = vm->page_size;
+        size_t npages = size / page_size;
+
+        TEST_ASSERT(vaddr + size > vaddr, "Vaddr overflow");
+        TEST_ASSERT(paddr + size > paddr, "Paddr overflow");
+
+        while (npages--) {
+                virt_pg_map(vm, vaddr, paddr, pgd_memslot);
+                vaddr += page_size;
+                paddr += page_size;
+        }
+}
+
 /* Address VM Physical to Host Virtual
  *
  * Input Args:
@@ -1536,3 +1580,17 @@ void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva)
 {
         return addr_gpa2hva(vm, addr_gva2gpa(vm, gva));
 }
+
+void guest_args_read(struct kvm_vm *vm, uint32_t vcpu_id,
+                     struct guest_args *args)
+{
+        struct kvm_run *run = vcpu_state(vm, vcpu_id);
+        struct kvm_regs regs;
+
+        memset(&regs, 0, sizeof(regs));
+        vcpu_regs_get(vm, vcpu_id, &regs);
+
+        args->port = run->io.port;
+        args->arg0 = regs.rdi;
+        args->arg1 = regs.rsi;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86.c b/tools/testing/selftests/kvm/lib/x86.c
index e38345252df5..a3122f1949a8 100644
--- a/tools/testing/selftests/kvm/lib/x86.c
+++ b/tools/testing/selftests/kvm/lib/x86.c
@@ -702,6 +702,9 @@ void vcpu_set_cpuid(struct kvm_vm *vm,
  *
  * Input Args:
  *   vcpuid - The id of the single VCPU to add to the VM.
+ *   extra_mem_pages - The size of extra memories to add (this will
+ *                     decide how much extra space we will need to
+ *                     setup the page tables using mem slot 0)
  *   guest_code - The vCPU's entry point
  *
  * Output Args: None
@@ -709,12 +712,23 @@ void vcpu_set_cpuid(struct kvm_vm *vm,
  * Return:
  *   Pointer to opaque structure that describes the created VM.
  */
-struct kvm_vm *vm_create_default(uint32_t vcpuid, void *guest_code)
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
+                                 void *guest_code)
 {
         struct kvm_vm *vm;
+        /*
+         * For x86 the maximum page table size for a memory region
+         * will be when only 4K pages are used.  In that case the
+         * total extra size for page tables (for extra N pages) will
+         * be: N/512+N/512^2+N/512^3+... which is definitely smaller
+         * than N/512*2.
+         */
+        uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
 
         /* Create VM */
-        vm = vm_create(VM_MODE_FLAT48PG, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+        vm = vm_create(VM_MODE_FLAT48PG,
+                       DEFAULT_GUEST_PHY_PAGES + extra_pg_pages,
+                       O_RDWR);
 
         /* Setup guest code */
         kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
diff --git a/tools/testing/selftests/kvm/set_sregs_test.c b/tools/testing/selftests/kvm/set_sregs_test.c
index 090fd3f19352..881419d5746e 100644
--- a/tools/testing/selftests/kvm/set_sregs_test.c
+++ b/tools/testing/selftests/kvm/set_sregs_test.c
@@ -36,7 +36,7 @@ int main(int argc, char *argv[])
         setbuf(stdout, NULL);
 
         /* Create VM */
-        vm = vm_create_default(VCPU_ID, NULL);
+        vm = vm_create_default(VCPU_ID, 0, NULL);
 
         vcpu_sregs_get(vm, VCPU_ID, &sregs);
         sregs.apic_base = 1 << 10;
diff --git a/tools/testing/selftests/kvm/state_test.c b/tools/testing/selftests/kvm/state_test.c
index ecabf25b7077..900e3e9dfb9f 100644
--- a/tools/testing/selftests/kvm/state_test.c
+++ b/tools/testing/selftests/kvm/state_test.c
@@ -21,28 +21,6 @@
 #include "vmx.h"
 
 #define VCPU_ID         5
-#define PORT_SYNC       0x1000
-#define PORT_ABORT      0x1001
-#define PORT_DONE       0x1002
-
-static inline void __exit_to_l0(uint16_t port, uint64_t arg0, uint64_t arg1)
-{
-        __asm__ __volatile__("in %[port], %%al"
-                             :
-                             : [port]"d"(port), "D"(arg0), "S"(arg1)
-                             : "rax");
-}
-
-#define exit_to_l0(_port, _arg0, _arg1) \
-        __exit_to_l0(_port, (uint64_t) (_arg0), (uint64_t) (_arg1))
-
-#define GUEST_ASSERT(_condition) do { \
-        if (!(_condition)) \
-                exit_to_l0(PORT_ABORT, "Failed guest assert: " #_condition, __LINE__);\
-} while (0)
-
-#define GUEST_SYNC(stage) \
-        exit_to_l0(PORT_SYNC, "hello", stage);
 
 static bool have_nested_state;
 
@@ -137,7 +115,7 @@ void guest_code(struct vmx_pages *vmx_pages)
         if (vmx_pages)
                 l1_guest_code(vmx_pages);
 
-        exit_to_l0(PORT_DONE, 0, 0);
+        GUEST_DONE();
 }
 
 int main(int argc, char *argv[])
@@ -154,7 +132,7 @@ int main(int argc, char *argv[])
         struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
         /* Create VM */
-        vm = vm_create_default(VCPU_ID, guest_code);
+        vm = vm_create_default(VCPU_ID, 0, guest_code);
         vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
         run = vcpu_state(vm, VCPU_ID);
 
@@ -178,13 +156,13 @@ int main(int argc, char *argv[])
                 memset(&regs1, 0, sizeof(regs1));
                 vcpu_regs_get(vm, VCPU_ID, &regs1);
                 switch (run->io.port) {
-                case PORT_ABORT:
+                case GUEST_PORT_ABORT:
                         TEST_ASSERT(false, "%s at %s:%d", (const char *) regs1.rdi,
                                     __FILE__, regs1.rsi);
                         /* NOT REACHED */
-                case PORT_SYNC:
+                case GUEST_PORT_SYNC:
                         break;
-                case PORT_DONE:
+                case GUEST_PORT_DONE:
                         goto done;
                 default:
                         TEST_ASSERT(false, "Unknown port 0x%x.", run->io.port);
diff --git a/tools/testing/selftests/kvm/sync_regs_test.c b/tools/testing/selftests/kvm/sync_regs_test.c
index eae1ece3c31b..213343e5dff9 100644
--- a/tools/testing/selftests/kvm/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/sync_regs_test.c
@@ -22,28 +22,11 @@
 #include "x86.h"
 
 #define VCPU_ID 5
-#define PORT_HOST_SYNC 0x1000
-
-static void __exit_to_l0(uint16_t port, uint64_t arg0, uint64_t arg1)
-{
-                __asm__ __volatile__("in %[port], %%al"
-                                     :
-                                     : [port]"d"(port), "D"(arg0), "S"(arg1)
-                                     : "rax");
-}
-
-#define exit_to_l0(_port, _arg0, _arg1) \
-        __exit_to_l0(_port, (uint64_t) (_arg0), (uint64_t) (_arg1))
-
-#define GUEST_ASSERT(_condition) do { \
-        if (!(_condition)) \
-                exit_to_l0(PORT_ABORT, "Failed guest assert: " #_condition, 0);\
-} while (0)
 
 void guest_code(void)
 {
         for (;;) {
-                exit_to_l0(PORT_HOST_SYNC, "hello", 0);
+                GUEST_SYNC(0);
                 asm volatile ("inc %r11");
         }
 }
@@ -111,7 +94,7 @@ int main(int argc, char *argv[])
         }
 
         /* Create VM */
-        vm = vm_create_default(VCPU_ID, guest_code);
+        vm = vm_create_default(VCPU_ID, 0, guest_code);
 
         run = vcpu_state(vm, VCPU_ID);
 
diff --git a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
index fc414c284368..49bcc68b0235 100644
--- a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
@@ -62,27 +62,12 @@ struct kvm_single_msr {
 /* The virtual machine object. */
 static struct kvm_vm *vm;
 
-#define exit_to_l0(_port, _arg) do_exit_to_l0(_port, (unsigned long) (_arg))
-static void do_exit_to_l0(uint16_t port, unsigned long arg)
-{
-        __asm__ __volatile__("in %[port], %%al"
-                :
-                : [port]"d"(port), "D"(arg)
-                : "rax");
-}
-
-
-#define GUEST_ASSERT(_condition) do {                                        \
-        if (!(_condition))                                                   \
-                exit_to_l0(PORT_ABORT, "Failed guest assert: " #_condition); \
-} while (0)
-
 static void check_ia32_tsc_adjust(int64_t max)
 {
         int64_t adjust;
 
         adjust = rdmsr(MSR_IA32_TSC_ADJUST);
-        exit_to_l0(PORT_REPORT, adjust);
+        GUEST_SYNC(adjust);
         GUEST_ASSERT(adjust <= max);
 }
 
@@ -132,7 +117,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 
         check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
 
-        exit_to_l0(PORT_DONE, 0);
+        GUEST_DONE();
 }
 
 void report(int64_t val)
@@ -152,7 +137,7 @@ int main(int argc, char *argv[])
                 exit(KSFT_SKIP);
         }
 
-        vm = vm_create_default(VCPU_ID, (void *) l1_guest_code);
+        vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
         vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 
         /* Allocate VMX pages and shared descriptors (vmx_pages). */
@@ -161,26 +146,26 @@ int main(int argc, char *argv[])
 
         for (;;) {
                 volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
-                struct kvm_regs regs;
+                struct guest_args args;
 
                 vcpu_run(vm, VCPU_ID);
-                vcpu_regs_get(vm, VCPU_ID, &regs);
+                guest_args_read(vm, VCPU_ID, &args);
                 TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-                            "Got exit_reason other than KVM_EXIT_IO: %u (%s), rip=%lx\n",
+                            "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
                             run->exit_reason,
-                            exit_reason_str(run->exit_reason), regs.rip);
+                            exit_reason_str(run->exit_reason));
 
-                switch (run->io.port) {
-                case PORT_ABORT:
-                        TEST_ASSERT(false, "%s", (const char *) regs.rdi);
+                switch (args.port) {
+                case GUEST_PORT_ABORT:
+                        TEST_ASSERT(false, "%s", (const char *) args.arg0);
                         /* NOT REACHED */
-                case PORT_REPORT:
-                        report(regs.rdi);
+                case GUEST_PORT_SYNC:
+                        report(args.arg1);
                         break;
-                case PORT_DONE:
+                case GUEST_PORT_DONE:
                         goto done;
                 default:
-                        TEST_ASSERT(false, "Unknown port 0x%x.", run->io.port);
+                        TEST_ASSERT(false, "Unknown port 0x%x.", args.port);
                 }
         }