1 files changed, 121 insertions, 123 deletions

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index b2262b5fad9e..5649cf2f40e8 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -4,15 +4,15 @@
  *
  * Copyright (C) 2018, Google LLC.
  */
-
-#define _GNU_SOURCE /* for program_invocation_name */
 #include "test_util.h"
 #include "kvm_util.h"
 #include "processor.h"
+#include "ucall_common.h"
 
 #include <assert.h>
 #include <sched.h>
 #include <sys/mman.h>
+#include <sys/resource.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
@@ -20,6 +20,10 @@
 
 #define KVM_UTIL_MIN_PFN	2
 
+uint32_t guest_random_seed;
+struct guest_random_state guest_rng;
+static uint32_t last_guest_seed;
+
 static int vcpu_mmap_sz(void);
 
 int open_path_or_exit(const char *path, int flags)
@@ -193,6 +197,11 @@ static void vm_open(struct kvm_vm *vm)
 
 	vm->fd = __kvm_ioctl(vm->kvm_fd, KVM_CREATE_VM, (void *)vm->type);
 	TEST_ASSERT(vm->fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VM, vm->fd));
+
+	if (kvm_has_cap(KVM_CAP_BINARY_STATS_FD))
+		vm->stats.fd = vm_get_stats_fd(vm);
+	else
+		vm->stats.fd = -1;
 }
 
 const char *vm_guest_mode_string(uint32_t i)
@@ -213,6 +222,7 @@ const char *vm_guest_mode_string(uint32_t i)
 		[VM_MODE_P36V48_4K]	= "PA-bits:36,  VA-bits:48,  4K pages",
 		[VM_MODE_P36V48_16K]	= "PA-bits:36,  VA-bits:48, 16K pages",
 		[VM_MODE_P36V48_64K]	= "PA-bits:36,  VA-bits:48, 64K pages",
+		[VM_MODE_P47V47_16K]	= "PA-bits:47,  VA-bits:47, 16K pages",
 		[VM_MODE_P36V47_16K]	= "PA-bits:36,  VA-bits:47, 16K pages",
 	};
 	_Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES,
@@ -239,6 +249,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
 	[VM_MODE_P36V48_4K]	= { 36, 48,  0x1000, 12 },
 	[VM_MODE_P36V48_16K]	= { 36, 48,  0x4000, 14 },
 	[VM_MODE_P36V48_64K]	= { 36, 48, 0x10000, 16 },
+	[VM_MODE_P47V47_16K]	= { 47, 47,  0x4000, 14 },
 	[VM_MODE_P36V47_16K]	= { 36, 47,  0x4000, 14 },
 };
 _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
@@ -276,7 +287,6 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
 
 	vm->mode = shape.mode;
 	vm->type = shape.type;
-	vm->subtype = shape.subtype;
 
 	vm->pa_bits = vm_guest_mode_params[vm->mode].pa_bits;
 	vm->va_bits = vm_guest_mode_params[vm->mode].va_bits;
@@ -311,6 +321,7 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
 	case VM_MODE_P36V48_16K:
 		vm->pgtable_levels = 4;
 		break;
+	case VM_MODE_P47V47_16K:
 	case VM_MODE_P36V47_16K:
 		vm->pgtable_levels = 3;
 		break;
@@ -404,6 +415,38 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode,
 	return vm_adjust_num_guest_pages(mode, nr_pages);
 }
 
+void kvm_set_files_rlimit(uint32_t nr_vcpus)
+{
+	/*
+	 * Each vCPU will open two file descriptors: the vCPU itself and the
+	 * vCPU's binary stats file descriptor.  Add an arbitrary amount of
+	 * buffer for all other files a test may open.
+	 */
+	int nr_fds_wanted = nr_vcpus * 2 + 100;
+	struct rlimit rl;
+
+	/*
+	 * Check that we're allowed to open nr_fds_wanted file descriptors and
+	 * try raising the limits if needed.
+	 */
+	TEST_ASSERT(!getrlimit(RLIMIT_NOFILE, &rl), "getrlimit() failed!");
+
+	if (rl.rlim_cur < nr_fds_wanted) {
+		rl.rlim_cur = nr_fds_wanted;
+		if (rl.rlim_max < nr_fds_wanted) {
+			int old_rlim_max = rl.rlim_max;
+
+			rl.rlim_max = nr_fds_wanted;
+			__TEST_REQUIRE(setrlimit(RLIMIT_NOFILE, &rl) >= 0,
+				       "RLIMIT_NOFILE hard limit is too low (%d, wanted %d)",
+				       old_rlim_max, nr_fds_wanted);
+		} else {
+			TEST_ASSERT(!setrlimit(RLIMIT_NOFILE, &rl), "setrlimit() failed!");
+		}
+	}
+
+}
+
 struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
 			   uint64_t nr_extra_pages)
 {
@@ -413,6 +456,8 @@ struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
 	struct kvm_vm *vm;
 	int i;
 
+	kvm_set_files_rlimit(nr_runnable_vcpus);
+
 	pr_debug("%s: mode='%s' type='%d', pages='%ld'\n", __func__,
 		 vm_guest_mode_string(shape.mode), shape.type, nr_pages);
 
@@ -433,6 +478,13 @@ struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
 	slot0 = memslot2region(vm, 0);
 	ucall_init(vm, slot0->region.guest_phys_addr + slot0->region.memory_size);
 
+	if (guest_random_seed != last_guest_seed) {
+		pr_info("Random seed: 0x%x\n", guest_random_seed);
+		last_guest_seed = guest_random_seed;
+	}
+	guest_rng = new_guest_random_state(guest_random_seed);
+	sync_global_to_guest(vm, guest_rng);
+
 	kvm_arch_vm_post_create(vm);
 
 	return vm;
@@ -648,6 +700,23 @@ userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
 	return NULL;
 }
 
+static void kvm_stats_release(struct kvm_binary_stats *stats)
+{
+	int ret;
+
+	if (stats->fd < 0)
+		return;
+
+	if (stats->desc) {
+		free(stats->desc);
+		stats->desc = NULL;
+	}
+
+	ret = close(stats->fd);
+	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
+	stats->fd = -1;
+}
+
 __weak void vcpu_arch_free(struct kvm_vcpu *vcpu)
 {
 
@@ -681,6 +750,8 @@ static void vm_vcpu_rm(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 	ret = close(vcpu->fd);
 	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
 
+	kvm_stats_release(&vcpu->stats);
+
 	list_del(&vcpu->list);
 
 	vcpu_arch_free(vcpu);
@@ -700,22 +771,19 @@ void kvm_vm_release(struct kvm_vm *vmp)
 
 	ret = close(vmp->kvm_fd);
 	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
+
+	/* Free cached stats metadata and close FD */
+	kvm_stats_release(&vmp->stats);
 }
 
 static void __vm_mem_region_delete(struct kvm_vm *vm,
-				   struct userspace_mem_region *region,
-				   bool unlink)
+				   struct userspace_mem_region *region)
 {
 	int ret;
 
-	if (unlink) {
-		rb_erase(&region->gpa_node, &vm->regions.gpa_tree);
-		rb_erase(&region->hva_node, &vm->regions.hva_tree);
-		hash_del(&region->slot_node);
-	}
-
-	region->region.memory_size = 0;
-	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
+	rb_erase(&region->gpa_node, &vm->regions.gpa_tree);
+	rb_erase(&region->hva_node, &vm->regions.hva_tree);
+	hash_del(&region->slot_node);
 
 	sparsebit_free(&region->unused_phy_pages);
 	sparsebit_free(&region->protected_phy_pages);
@@ -745,15 +813,9 @@ void kvm_vm_free(struct kvm_vm *vmp)
 	if (vmp == NULL)
 		return;
 
-	/* Free cached stats metadata and close FD */
-	if (vmp->stats_fd) {
-		free(vmp->stats_desc);
-		close(vmp->stats_fd);
-	}
-
 	/* Free userspace_mem_regions. */
 	hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node)
-		__vm_mem_region_delete(vmp, region, false);
+		__vm_mem_region_delete(vmp, region);
 
 	/* Free sparsebit arrays. */
 	sparsebit_free(&vmp->vpages_valid);
@@ -785,76 +847,6 @@ int kvm_memfd_alloc(size_t size, bool hugepages)
 	return fd;
 }
 
-/*
- * Memory Compare, host virtual to guest virtual
- *
- * Input Args:
- *   hva - Starting host virtual address
- *   vm - Virtual Machine
- *   gva - Starting guest virtual address
- *   len - number of bytes to compare
- *
- * Output Args: None
- *
- * Input/Output Args: None
- *
- * Return:
- *   Returns 0 if the bytes starting at hva for a length of len
- *   are equal the guest virtual bytes starting at gva.  Returns
- *   a value < 0, if bytes at hva are less than those at gva.
- *   Otherwise a value > 0 is returned.
- *
- * Compares the bytes starting at the host virtual address hva, for
- * a length of len, to the guest bytes starting at the guest virtual
- * address given by gva.
- */
-int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len)
-{
-	size_t amt;
-
-	/*
-	 * Compare a batch of bytes until either a match is found
-	 * or all the bytes have been compared.
-	 */
-	for (uintptr_t offset = 0; offset < len; offset += amt) {
-		uintptr_t ptr1 = (uintptr_t)hva + offset;
-
-		/*
-		 * Determine host address for guest virtual address
-		 * at offset.
-		 */
-		uintptr_t ptr2 = (uintptr_t)addr_gva2hva(vm, gva + offset);
-
-		/*
-		 * Determine amount to compare on this pass.
-		 * Don't allow the comparsion to cross a page boundary.
-		 */
-		amt = len - offset;
-		if ((ptr1 >> vm->page_shift) != ((ptr1 + amt) >> vm->page_shift))
-			amt = vm->page_size - (ptr1 % vm->page_size);
-		if ((ptr2 >> vm->page_shift) != ((ptr2 + amt) >> vm->page_shift))
-			amt = vm->page_size - (ptr2 % vm->page_size);
-
-		assert((ptr1 >> vm->page_shift) == ((ptr1 + amt - 1) >> vm->page_shift));
-		assert((ptr2 >> vm->page_shift) == ((ptr2 + amt - 1) >> vm->page_shift));
-
-		/*
-		 * Perform the comparison.  If there is a difference
-		 * return that result to the caller, otherwise need
-		 * to continue on looking for a mismatch.
-		 */
-		int ret = memcmp((void *)ptr1, (void *)ptr2, amt);
-		if (ret != 0)
-			return ret;
-	}
-
-	/*
-	 * No mismatch found.  Let the caller know the two memory
-	 * areas are equal.
-	 */
-	return 0;
-}
-
 static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree,
 					       struct userspace_mem_region *region)
 {
@@ -930,6 +922,10 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 		    errno, strerror(errno));
 }
 
+#define TEST_REQUIRE_SET_USER_MEMORY_REGION2()			\
+	__TEST_REQUIRE(kvm_has_cap(KVM_CAP_USER_MEMORY2),	\
+		       "KVM selftests now require KVM_SET_USER_MEMORY_REGION2 (introduced in v6.8)")
+
 int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 				 uint64_t gpa, uint64_t size, void *hva,
 				 uint32_t guest_memfd, uint64_t guest_memfd_offset)
@@ -944,6 +940,8 @@ int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flag
 		.guest_memfd_offset = guest_memfd_offset,
 	};
 
+	TEST_REQUIRE_SET_USER_MEMORY_REGION2();
+
 	return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION2, &region);
 }
 
@@ -970,6 +968,8 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 	size_t mem_size = npages * vm->page_size;
 	size_t alignment;
 
+	TEST_REQUIRE_SET_USER_MEMORY_REGION2();
+
 	TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages,
 		"Number of guest pages is not compatible with the host. "
 		"Try npages=%d", vm_adjust_num_guest_pages(vm->mode, npages));
@@ -1253,7 +1253,12 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa)
  */
 void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot)
 {
-	__vm_mem_region_delete(vm, memslot2region(vm, slot), true);
+	struct userspace_mem_region *region = memslot2region(vm, slot);
+
+	region->region.memory_size = 0;
+	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
+
+	__vm_mem_region_delete(vm, region);
 }
 
 void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size,
@@ -1340,6 +1345,11 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 	TEST_ASSERT(vcpu->run != MAP_FAILED,
 		    __KVM_SYSCALL_ERROR("mmap()", (int)(unsigned long)MAP_FAILED));
 
+	if (kvm_has_cap(KVM_CAP_BINARY_STATS_FD))
+		vcpu->stats.fd = vcpu_get_stats_fd(vcpu);
+	else
+		vcpu->stats.fd = -1;
+
 	/* Add to linked-list of VCPUs. */
 	list_add(&vcpu->list, &vm->vcpus);
 
@@ -1702,7 +1712,8 @@ int _vcpu_run(struct kvm_vcpu *vcpu)
 		rc = __vcpu_run(vcpu);
 	} while (rc == -1 && errno == EINTR);
 
-	assert_on_unhandled_exception(vcpu);
+	if (!rc)
+		assert_on_unhandled_exception(vcpu);
 
 	return rc;
 }
@@ -2011,9 +2022,8 @@ static struct exit_reason {
 	KVM_EXIT_STRING(RISCV_SBI),
 	KVM_EXIT_STRING(RISCV_CSR),
 	KVM_EXIT_STRING(NOTIFY),
-#ifdef KVM_EXIT_MEMORY_NOT_PRESENT
-	KVM_EXIT_STRING(MEMORY_NOT_PRESENT),
-#endif
+	KVM_EXIT_STRING(LOONGARCH_IOCSR),
+	KVM_EXIT_STRING(MEMORY_FAULT),
 };
 
 /*
@@ -2251,46 +2261,31 @@ void read_stat_data(int stats_fd, struct kvm_stats_header *header,
 		    desc->name, size, ret);
 }
 
-/*
- * Read the data of the named stat
- *
- * Input Args:
- *   vm - the VM for which the stat should be read
- *   stat_name - the name of the stat to read
- *   max_elements - the maximum number of 8-byte values to read into data
- *
- * Output Args:
- *   data - the buffer into which stat data should be read
- *
- * Read the data values of a specified stat from the binary stats interface.
- */
-void __vm_get_stat(struct kvm_vm *vm, const char *stat_name, uint64_t *data,
-		   size_t max_elements)
+void kvm_get_stat(struct kvm_binary_stats *stats, const char *name,
+		  uint64_t *data, size_t max_elements)
 {
 	struct kvm_stats_desc *desc;
 	size_t size_desc;
 	int i;
 
-	if (!vm->stats_fd) {
-		vm->stats_fd = vm_get_stats_fd(vm);
-		read_stats_header(vm->stats_fd, &vm->stats_header);
-		vm->stats_desc = read_stats_descriptors(vm->stats_fd,
-							&vm->stats_header);
+	if (!stats->desc) {
+		read_stats_header(stats->fd, &stats->header);
+		stats->desc = read_stats_descriptors(stats->fd, &stats->header);
 	}
 
-	size_desc = get_stats_descriptor_size(&vm->stats_header);
+	size_desc = get_stats_descriptor_size(&stats->header);
 
-	for (i = 0; i < vm->stats_header.num_desc; ++i) {
-		desc = (void *)vm->stats_desc + (i * size_desc);
+	for (i = 0; i < stats->header.num_desc; ++i) {
+		desc = (void *)stats->desc + (i * size_desc);
 
-		if (strcmp(desc->name, stat_name))
+		if (strcmp(desc->name, name))
 			continue;
 
-		read_stat_data(vm->stats_fd, &vm->stats_header, desc,
-			       data, max_elements);
-
-		break;
+		read_stat_data(stats->fd, &stats->header, desc, data, max_elements);
+		return;
 	}
+
+	TEST_FAIL("Unable to find stat '%s'", name);
 }
 
 __weak void kvm_arch_vm_post_create(struct kvm_vm *vm)
@@ -2306,6 +2301,9 @@ void __attribute((constructor)) kvm_selftest_init(void)
 	/* Tell stdout not to buffer its content. */
 	setbuf(stdout, NULL);
 
+	guest_random_seed = last_guest_seed = random();
+	pr_info("Random seed: 0x%x\n", guest_random_seed);
+
 	kvm_selftest_arch_init();
 }