1 files changed, 232 insertions, 20 deletions

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 74776ee228f2..d787cb802b4a 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2018, Google LLC.
  */
 
+#define _GNU_SOURCE /* for program_invocation_name */
 #include "test_util.h"
 #include "kvm_util.h"
 #include "kvm_util_internal.h"
@@ -14,6 +15,7 @@
 #include <sys/mman.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <unistd.h>
 #include <linux/kernel.h>
 
 #define KVM_UTIL_PGS_PER_HUGEPG 512
@@ -85,6 +87,44 @@ int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap)
 	return ret;
 }
 
+/* VCPU Enable Capability
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpu_id - VCPU
+ *   cap - Capability
+ *
+ * Output Args: None
+ *
+ * Return: On success, 0. On failure a TEST_ASSERT failure is produced.
+ *
+ * Enables a capability (KVM_CAP_*) on the VCPU.
+ */
+int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
+		    struct kvm_enable_cap *cap)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpu_id);
+	int r;
+
+	TEST_ASSERT(vcpu, "cannot find vcpu %d", vcpu_id);
+
+	r = ioctl(vcpu->fd, KVM_ENABLE_CAP, cap);
+	TEST_ASSERT(!r, "KVM_ENABLE_CAP vCPU ioctl failed,\n"
+			"  rc: %i, errno: %i", r, errno);
+
+	return r;
+}
+
+void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size)
+{
+	struct kvm_enable_cap cap = { 0 };
+
+	cap.cap = KVM_CAP_DIRTY_LOG_RING;
+	cap.args[0] = ring_size;
+	vm_enable_cap(vm, &cap);
+	vm->dirty_ring_size = ring_size;
+}
+
 static void vm_open(struct kvm_vm *vm, int perm)
 {
 	vm->kvm_fd = open(KVM_DEV_PATH, perm);
@@ -113,14 +153,7 @@ const char * const vm_guest_mode_string[] = {
 _Static_assert(sizeof(vm_guest_mode_string)/sizeof(char *) == NUM_VM_MODES,
 	       "Missing new mode strings?");
 
-struct vm_guest_mode_params {
-	unsigned int pa_bits;
-	unsigned int va_bits;
-	unsigned int page_size;
-	unsigned int page_shift;
-};
-
-static const struct vm_guest_mode_params vm_guest_mode_params[] = {
+const struct vm_guest_mode_params vm_guest_mode_params[] = {
 	{ 52, 48,  0x1000, 12 },
 	{ 52, 48, 0x10000, 16 },
 	{ 48, 48,  0x1000, 12 },
@@ -151,7 +184,7 @@ _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params)
  * descriptor to control the created VM is created with the permissions
  * given by perm (e.g. O_RDWR).
  */
-struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
+struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 {
 	struct kvm_vm *vm;
 
@@ -242,9 +275,61 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	return vm;
 }
 
-struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
+struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
+				    uint64_t extra_mem_pages, uint32_t num_percpu_pages,
+				    void *guest_code, uint32_t vcpuids[])
 {
-	return _vm_create(mode, phy_pages, perm);
+	/* The maximum page table size for a memory region will be when the
+	 * smallest pages are used. Considering each page contains x page
+	 * table descriptors, the total extra size for page tables (for extra
+	 * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller
+	 * than N/x*2.
+	 */
+	uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus;
+	uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2;
+	uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages;
+	struct kvm_vm *vm;
+	int i;
+
+	TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS),
+		    "nr_vcpus = %d too large for host, max-vcpus = %d",
+		    nr_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS));
+
+	pages = vm_adjust_num_guest_pages(mode, pages);
+	vm = vm_create(mode, pages, O_RDWR);
+
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+
+#ifdef __x86_64__
+	vm_create_irqchip(vm);
+#endif
+
+	for (i = 0; i < nr_vcpus; ++i) {
+		uint32_t vcpuid = vcpuids ? vcpuids[i] : i;
+
+		vm_vcpu_add_default(vm, vcpuid, guest_code);
+
+#ifdef __x86_64__
+		vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid());
+#endif
+	}
+
+	return vm;
+}
+
+struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages,
+					    uint32_t num_percpu_pages, void *guest_code,
+					    uint32_t vcpuids[])
+{
+	return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, extra_mem_pages,
+				    num_percpu_pages, guest_code, vcpuids);
+}
+
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
+				 void *guest_code)
+{
+	return vm_create_default_with_vcpus(1, extra_mem_pages, 0, guest_code,
+					    (uint32_t []){ vcpuid });
 }
 
 /*
@@ -304,6 +389,11 @@ void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
 		    __func__, strerror(-ret));
 }
 
+uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm)
+{
+	return ioctl(vm->fd, KVM_RESET_DIRTY_RINGS);
+}
+
 /*
  * Userspace Memory Region Find
  *
@@ -408,10 +498,17 @@ struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid)
  *
  * Removes a vCPU from a VM and frees its resources.
  */
-static void vm_vcpu_rm(struct vcpu *vcpu)
+static void vm_vcpu_rm(struct kvm_vm *vm, struct vcpu *vcpu)
 {
 	int ret;
 
+	if (vcpu->dirty_gfns) {
+		ret = munmap(vcpu->dirty_gfns, vm->dirty_ring_size);
+		TEST_ASSERT(ret == 0, "munmap of VCPU dirty ring failed, "
+			    "rc: %i errno: %i", ret, errno);
+		vcpu->dirty_gfns = NULL;
+	}
+
 	ret = munmap(vcpu->state, sizeof(*vcpu->state));
 	TEST_ASSERT(ret == 0, "munmap of VCPU fd failed, rc: %i "
 		"errno: %i", ret, errno);
@@ -429,7 +526,7 @@ void kvm_vm_release(struct kvm_vm *vmp)
 	int ret;
 
 	list_for_each_entry_safe(vcpu, tmp, &vmp->vcpus, list)
-		vm_vcpu_rm(vcpu);
+		vm_vcpu_rm(vmp, vcpu);
 
 	ret = close(vmp->fd);
 	TEST_ASSERT(ret == 0, "Close of vm fd failed,\n"
@@ -664,13 +761,21 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 
 	/* As needed perform madvise */
 	if (src_type == VM_MEM_SRC_ANONYMOUS || src_type == VM_MEM_SRC_ANONYMOUS_THP) {
-		ret = madvise(region->host_mem, npages * vm->page_size,
-			     src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
-		TEST_ASSERT(ret == 0, "madvise failed,\n"
-			    "  addr: %p\n"
-			    "  length: 0x%lx\n"
-			    "  src_type: %x",
-			    region->host_mem, npages * vm->page_size, src_type);
+		struct stat statbuf;
+
+		ret = stat("/sys/kernel/mm/transparent_hugepage", &statbuf);
+		TEST_ASSERT(ret == 0 || (ret == -1 && errno == ENOENT),
+			    "stat /sys/kernel/mm/transparent_hugepage");
+
+		TEST_ASSERT(ret == 0 || src_type != VM_MEM_SRC_ANONYMOUS_THP,
+			    "VM_MEM_SRC_ANONYMOUS_THP requires THP to be configured in the host kernel");
+
+		if (ret == 0) {
+			ret = madvise(region->host_mem, npages * vm->page_size,
+				      src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
+			TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %x",
+				    region->host_mem, npages * vm->page_size, src_type);
+		}
 	}
 
 	region->unused_phy_pages = sparsebit_alloc();
@@ -1195,9 +1300,21 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
 	do {
 		rc = ioctl(vcpu->fd, KVM_RUN, NULL);
 	} while (rc == -1 && errno == EINTR);
+
+	assert_on_unhandled_exception(vm, vcpuid);
+
 	return rc;
 }
 
+int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+	return vcpu->fd;
+}
+
 void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
@@ -1252,6 +1369,35 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 }
 
 /*
+ * VM VCPU Get Reg List
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *
+ * Output Args:
+ *   None
+ *
+ * Return:
+ *   A pointer to an allocated struct kvm_reg_list
+ *
+ * Get the list of guest registers which are supported for
+ * KVM_GET_ONE_REG/KVM_SET_ONE_REG calls
+ */
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list;
+	int ret;
+
+	ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, &reg_list_n);
+	TEST_ASSERT(ret == -1 && errno == E2BIG, "KVM_GET_REG_LIST n=0");
+	reg_list = calloc(1, sizeof(*reg_list) + reg_list_n.n * sizeof(__u64));
+	reg_list->n = reg_list_n.n;
+	vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, reg_list);
+	return reg_list;
+}
+
+/*
  * VM VCPU Regs Get
  *
  * Input Args:
@@ -1497,6 +1643,42 @@ int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid,
 	return ret;
 }
 
+void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct vcpu *vcpu;
+	uint32_t size = vm->dirty_ring_size;
+
+	TEST_ASSERT(size > 0, "Should enable dirty ring first");
+
+	vcpu = vcpu_find(vm, vcpuid);
+
+	TEST_ASSERT(vcpu, "Cannot find vcpu %u", vcpuid);
+
+	if (!vcpu->dirty_gfns) {
+		void *addr;
+
+		addr = mmap(NULL, size, PROT_READ,
+			    MAP_PRIVATE, vcpu->fd,
+			    vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET);
+		TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped private");
+
+		addr = mmap(NULL, size, PROT_READ | PROT_EXEC,
+			    MAP_PRIVATE, vcpu->fd,
+			    vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET);
+		TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped exec");
+
+		addr = mmap(NULL, size, PROT_READ | PROT_WRITE,
+			    MAP_SHARED, vcpu->fd,
+			    vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET);
+		TEST_ASSERT(addr != MAP_FAILED, "Dirty ring map failed");
+
+		vcpu->dirty_gfns = addr;
+		vcpu->dirty_gfns_count = size / sizeof(struct kvm_dirty_gfn);
+	}
+
+	return vcpu->dirty_gfns;
+}
+
 /*
  * VM Ioctl
  *
@@ -1519,6 +1701,32 @@ void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
 }
 
 /*
+ * KVM system ioctl
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   cmd - Ioctl number
+ *   arg - Argument to pass to the ioctl
+ *
+ * Return: None
+ *
+ * Issues an arbitrary ioctl on a KVM fd.
+ */
+void kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
+{
+	int ret;
+
+	ret = ioctl(vm->kvm_fd, cmd, arg);
+	TEST_ASSERT(ret == 0, "KVM ioctl %lu failed, rc: %i errno: %i (%s)",
+		cmd, ret, errno, strerror(errno));
+}
+
+int _kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
+{
+	return ioctl(vm->kvm_fd, cmd, arg);
+}
+
+/*
  * VM Dump
  *
  * Input Args:
@@ -1590,6 +1798,10 @@ static struct exit_reason {
 	{KVM_EXIT_INTERNAL_ERROR, "INTERNAL_ERROR"},
 	{KVM_EXIT_OSI, "OSI"},
 	{KVM_EXIT_PAPR_HCALL, "PAPR_HCALL"},
+	{KVM_EXIT_DIRTY_RING_FULL, "DIRTY_RING_FULL"},
+	{KVM_EXIT_X86_RDMSR, "RDMSR"},
+	{KVM_EXIT_X86_WRMSR, "WRMSR"},
+	{KVM_EXIT_XEN, "XEN"},
 #ifdef KVM_EXIT_MEMORY_NOT_PRESENT
 	{KVM_EXIT_MEMORY_NOT_PRESENT, "MEMORY_NOT_PRESENT"},
 #endif