3 files changed, 117 insertions, 64 deletions
diff --git a/tools/testing/selftests/kvm/lib/arm64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c
index 7ba3aa3755f3..9d69904cb608 100644
--- a/tools/testing/selftests/kvm/lib/arm64/processor.c
+++ b/tools/testing/selftests/kvm/lib/arm64/processor.c
@@ -72,13 +72,13 @@ static uint64_t addr_pte(struct kvm_vm *vm, uint64_t pa, uint64_t attrs)
 	uint64_t pte;
 
 	if (use_lpa2_pte_format(vm)) {
-		pte = pa & GENMASK(49, vm->page_shift);
-		pte |= FIELD_GET(GENMASK(51, 50), pa) << 8;
-		attrs &= ~GENMASK(9, 8);
+		pte = pa & PTE_ADDR_MASK_LPA2(vm->page_shift);
+		pte |= FIELD_GET(GENMASK(51, 50), pa) << PTE_ADDR_51_50_LPA2_SHIFT;
+		attrs &= ~PTE_ADDR_51_50_LPA2;
 	} else {
-		pte = pa & GENMASK(47, vm->page_shift);
+		pte = pa & PTE_ADDR_MASK(vm->page_shift);
 		if (vm->page_shift == 16)
-			pte |= FIELD_GET(GENMASK(51, 48), pa) << 12;
+			pte |= FIELD_GET(GENMASK(51, 48), pa) << PTE_ADDR_51_48_SHIFT;
 	}
 	pte |= attrs;
 
@@ -90,12 +90,12 @@ static uint64_t pte_addr(struct kvm_vm *vm, uint64_t pte)
 	uint64_t pa;
 
 	if (use_lpa2_pte_format(vm)) {
-		pa = pte & GENMASK(49, vm->page_shift);
-		pa |= FIELD_GET(GENMASK(9, 8), pte) << 50;
+		pa = pte & PTE_ADDR_MASK_LPA2(vm->page_shift);
+		pa |= FIELD_GET(PTE_ADDR_51_50_LPA2, pte) << 50;
 	} else {
-		pa = pte & GENMASK(47, vm->page_shift);
+		pa = pte & PTE_ADDR_MASK(vm->page_shift);
 		if (vm->page_shift == 16)
-			pa |= FIELD_GET(GENMASK(15, 12), pte) << 48;
+			pa |= FIELD_GET(PTE_ADDR_51_48, pte) << 48;
 	}
 
 	return pa;
@@ -128,7 +128,8 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm)
 static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 			 uint64_t flags)
 {
-	uint8_t attr_idx = flags & 7;
+	uint8_t attr_idx = flags & (PTE_ATTRINDX_MASK >> PTE_ATTRINDX_SHIFT);
+	uint64_t pg_attr;
 	uint64_t *ptep;
 
 	TEST_ASSERT((vaddr % vm->page_size) == 0,
@@ -147,18 +148,21 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 
 	ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, vaddr) * 8;
 	if (!*ptep)
-		*ptep = addr_pte(vm, vm_alloc_page_table(vm), 3);
+		*ptep = addr_pte(vm, vm_alloc_page_table(vm),
+				 PGD_TYPE_TABLE | PTE_VALID);
 
 	switch (vm->pgtable_levels) {
 	case 4:
 		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8;
 		if (!*ptep)
-			*ptep = addr_pte(vm, vm_alloc_page_table(vm), 3);
+			*ptep = addr_pte(vm, vm_alloc_page_table(vm),
+					 PUD_TYPE_TABLE | PTE_VALID);
 		/* fall through */
 	case 3:
 		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8;
 		if (!*ptep)
-			*ptep = addr_pte(vm, vm_alloc_page_table(vm), 3);
+			*ptep = addr_pte(vm, vm_alloc_page_table(vm),
+					 PMD_TYPE_TABLE | PTE_VALID);
 		/* fall through */
 	case 2:
 		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8;
@@ -167,7 +171,11 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 		TEST_FAIL("Page table levels must be 2, 3, or 4");
 	}
 
-	*ptep = addr_pte(vm, paddr, (attr_idx << 2) | (1 << 10) | 3);  /* AF */
+	pg_attr = PTE_AF | PTE_ATTRINDX(attr_idx) | PTE_TYPE_PAGE | PTE_VALID;
+	if (!use_lpa2_pte_format(vm))
+		pg_attr |= PTE_SHARED;
+
+	*ptep = addr_pte(vm, paddr, pg_attr);
 }
 
 void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
@@ -293,20 +301,20 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 	case VM_MODE_P48V48_64K:
 	case VM_MODE_P40V48_64K:
 	case VM_MODE_P36V48_64K:
-		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
+		tcr_el1 |= TCR_TG0_64K;
 		break;
 	case VM_MODE_P52V48_16K:
 	case VM_MODE_P48V48_16K:
 	case VM_MODE_P40V48_16K:
 	case VM_MODE_P36V48_16K:
 	case VM_MODE_P36V47_16K:
-		tcr_el1 |= 2ul << 14; /* TG0 = 16KB */
+		tcr_el1 |= TCR_TG0_16K;
 		break;
 	case VM_MODE_P52V48_4K:
 	case VM_MODE_P48V48_4K:
 	case VM_MODE_P40V48_4K:
 	case VM_MODE_P36V48_4K:
-		tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
+		tcr_el1 |= TCR_TG0_4K;
 		break;
 	default:
 		TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
@@ -319,35 +327,35 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 	case VM_MODE_P52V48_4K:
 	case VM_MODE_P52V48_16K:
 	case VM_MODE_P52V48_64K:
-		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+		tcr_el1 |= TCR_IPS_52_BITS;
 		ttbr0_el1 |= FIELD_GET(GENMASK(51, 48), vm->pgd) << 2;
 		break;
 	case VM_MODE_P48V48_4K:
 	case VM_MODE_P48V48_16K:
 	case VM_MODE_P48V48_64K:
-		tcr_el1 |= 5ul << 32; /* IPS = 48 bits */
+		tcr_el1 |= TCR_IPS_48_BITS;
 		break;
 	case VM_MODE_P40V48_4K:
 	case VM_MODE_P40V48_16K:
 	case VM_MODE_P40V48_64K:
-		tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
+		tcr_el1 |= TCR_IPS_40_BITS;
 		break;
 	case VM_MODE_P36V48_4K:
 	case VM_MODE_P36V48_16K:
 	case VM_MODE_P36V48_64K:
 	case VM_MODE_P36V47_16K:
-		tcr_el1 |= 1ul << 32; /* IPS = 36 bits */
+		tcr_el1 |= TCR_IPS_36_BITS;
 		break;
 	default:
 		TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
 	}
 
-	sctlr_el1 |= (1 << 0) | (1 << 2) | (1 << 12) /* M | C | I */;
-	/* TCR_EL1 |= IRGN0:WBWA | ORGN0:WBWA | SH0:Inner-Shareable */;
-	tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12);
-	tcr_el1 |= (64 - vm->va_bits) /* T0SZ */;
+	sctlr_el1 |= SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_I;
+
+	tcr_el1 |= TCR_IRGN0_WBWA | TCR_ORGN0_WBWA | TCR_SH0_INNER;
+	tcr_el1 |= TCR_T0SZ(vm->va_bits);
 	if (use_lpa2_pte_format(vm))
-		tcr_el1 |= (1ul << 59) /* DS */;
+		tcr_el1 |= TCR_DS;
 
 	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1);
 	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 33fefeb3ca44..815bc45dd8dc 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -12,6 +12,7 @@
 #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>
@@ -196,6 +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)
@@ -406,6 +412,38 @@ 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)
 {
@@ -415,6 +453,8 @@ 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);
 
@@ -657,6 +697,23 @@ 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)
 {
 
@@ -690,6 +747,8 @@ 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);
@@ -709,6 +768,9 @@ 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,
@@ -748,12 +810,6 @@ 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);
@@ -1286,6 +1342,11 @@ 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);
 
@@ -1958,9 +2019,8 @@ 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),
 };
 
 /*
@@ -2198,46 +2258,31 @@ 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)
diff --git a/tools/testing/selftests/kvm/lib/userfaultfd_util.c b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
index 7c9de8414462..5bde176cedd5 100644
--- a/tools/testing/selftests/kvm/lib/userfaultfd_util.c
+++ b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
@@ -114,7 +114,7 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
 
 	PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n",
 		       is_minor ? "MINOR" : "MISSING",
-		       is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY");
+		       is_minor ? "UFFDIO_CONTINUE" : "UFFDIO_COPY");
 
 	uffd_desc = malloc(sizeof(struct uffd_desc));
 	TEST_ASSERT(uffd_desc, "Failed to malloc uffd descriptor");